diff --git a/.gitattributes b/.gitattributes index be3044ea44e35525e0f52a23f82a06ac901650a1..f949c576298050ab208248c16797e9610e716ae8 100644 --- a/.gitattributes +++ b/.gitattributes @@ -2089,3 +2089,12 @@ Qwen2-7B-Instruct_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_ Qwen2-7B-Instruct_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-225-sd-10000/checkpoint-72/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2-7B-Instruct_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-225-sd-10000/checkpoint-9/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2-7B-Instruct_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-225-sd-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/tokenizer.json filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/tokenizer.json filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/tokenizer.json filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/tokenizer.json filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/tokenizer.json filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/tokenizer.json filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/tokenizer.json filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/tokenizer.json filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/README.md b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/README.md new file mode 100644 index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/README.md @@ -0,0 +1,202 @@ +--- +base_model: meta-llama/Meta-Llama-3-8B-Instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.13.1 \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..406c5a08dc4a2a33b52c62a482f98c217c417215 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "v_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe2885e2d79cf1d80cd0233413a15280e49aa853 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb322e791bb91edfa9f435335176fce66675400951366ecb3580e7f184b2e398 +size 109069176 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/README.md b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/README.md new file mode 100644 index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/README.md @@ -0,0 +1,202 @@ +--- +base_model: meta-llama/Meta-Llama-3-8B-Instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.13.1 \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..406c5a08dc4a2a33b52c62a482f98c217c417215 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "v_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d15e5c07de39160ecc212348a8c6040ae0bf5f2a --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0370d7b9368c6e4a44ec9a062b8e3941eb056a3ca1e9c162ce6e31a06ef002ce +size 109069176 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/optimizer.pt b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..c196065cc545eb6af809e0f1d7f16852626fb10f --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5022f748161d196f77aea55c08c5e004671a01eb1415c4334dc3875a4e0beb56 +size 55532666 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/rng_state.pth b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..702238377ec93f202caa49be95c6c7085cded70f --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c224adca03133cd86fc326156d5695c4816aff27f44c8391b4ceb4d8d12aec3 +size 14244 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/scheduler.pt b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..0cfb0dde074da7c9b5c0114ac93c75327d40f73b --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3516b80b38c53efbd35ab603c99be317d10840879de9946e95b7122762d87858 +size 1064 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393 +size 17209961 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|eot_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/trainer_state.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..ba90d99f2f4d238d4e3664f6b3e67e4a768f67c6 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/trainer_state.json @@ -0,0 +1,1009 @@ +{ + "best_metric": 1.205152153968811, + "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911", + "epoch": 2.9989023051591657, + "eval_steps": 10, + "global_step": 1366, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.021953896816684963, + "grad_norm": 0.6144012212753296, + "learning_rate": 0.0002, + "loss": 1.9887, + "step": 10 + }, + { + "epoch": 0.043907793633369926, + "grad_norm": 0.5587220788002014, + "learning_rate": 0.0002, + "loss": 1.6882, + "step": 20 + }, + { + "epoch": 0.06586169045005488, + "grad_norm": 0.43262454867362976, + "learning_rate": 0.0002, + "loss": 1.399, + "step": 30 + }, + { + "epoch": 0.08781558726673985, + "grad_norm": 0.4783053994178772, + "learning_rate": 0.0002, + "loss": 1.4675, + "step": 40 + }, + { + "epoch": 0.10976948408342481, + "grad_norm": 0.44338956475257874, + "learning_rate": 0.0002, + "loss": 1.1771, + "step": 50 + }, + { + "epoch": 0.13172338090010977, + "grad_norm": 0.7255092263221741, + "learning_rate": 0.0002, + "loss": 1.3706, + "step": 60 + }, + { + "epoch": 0.15367727771679474, + "grad_norm": 0.46073833107948303, + "learning_rate": 0.0002, + "loss": 1.2601, + "step": 70 + }, + { + "epoch": 0.1756311745334797, + "grad_norm": 0.6698123216629028, + "learning_rate": 0.0002, + "loss": 1.3049, + "step": 80 + }, + { + "epoch": 0.19758507135016465, + "grad_norm": 0.4190150201320648, + "learning_rate": 0.0002, + "loss": 1.2975, + "step": 90 + }, + { + "epoch": 0.21953896816684962, + "grad_norm": 0.4110015034675598, + "learning_rate": 0.0002, + "loss": 1.2797, + "step": 100 + }, + { + "epoch": 0.2414928649835346, + "grad_norm": 0.33374306559562683, + "learning_rate": 0.0002, + "loss": 1.2896, + "step": 110 + }, + { + "epoch": 0.26344676180021953, + "grad_norm": 0.3061307370662689, + "learning_rate": 0.0002, + "loss": 1.2268, + "step": 120 + }, + { + "epoch": 0.2854006586169045, + "grad_norm": 0.4386885166168213, + "learning_rate": 0.0002, + "loss": 1.376, + "step": 130 + }, + { + "epoch": 0.30735455543358947, + "grad_norm": 0.40116462111473083, + "learning_rate": 0.0002, + "loss": 1.1814, + "step": 140 + }, + { + "epoch": 0.32930845225027444, + "grad_norm": 0.5887949466705322, + "learning_rate": 0.0002, + "loss": 1.2592, + "step": 150 + }, + { + "epoch": 0.3512623490669594, + "grad_norm": 0.3401573896408081, + "learning_rate": 0.0002, + "loss": 1.2372, + "step": 160 + }, + { + "epoch": 0.3732162458836443, + "grad_norm": 0.3288364112377167, + "learning_rate": 0.0002, + "loss": 1.1901, + "step": 170 + }, + { + "epoch": 0.3951701427003293, + "grad_norm": 0.4853297472000122, + "learning_rate": 0.0002, + "loss": 1.2335, + "step": 180 + }, + { + "epoch": 0.41712403951701427, + "grad_norm": 2.6253697872161865, + "learning_rate": 0.0002, + "loss": 1.227, + "step": 190 + }, + { + "epoch": 0.43907793633369924, + "grad_norm": 0.5598543286323547, + "learning_rate": 0.0002, + "loss": 1.2673, + "step": 200 + }, + { + "epoch": 0.4610318331503842, + "grad_norm": 0.4046548902988434, + "learning_rate": 0.0002, + "loss": 1.3459, + "step": 210 + }, + { + "epoch": 0.4829857299670692, + "grad_norm": 0.3686952590942383, + "learning_rate": 0.0002, + "loss": 1.265, + "step": 220 + }, + { + "epoch": 0.5049396267837541, + "grad_norm": 0.42458799481391907, + "learning_rate": 0.0002, + "loss": 1.1364, + "step": 230 + }, + { + "epoch": 0.5268935236004391, + "grad_norm": 0.5839895009994507, + "learning_rate": 0.0002, + "loss": 1.2094, + "step": 240 + }, + { + "epoch": 0.5488474204171241, + "grad_norm": 0.408288836479187, + "learning_rate": 0.0002, + "loss": 1.2073, + "step": 250 + }, + { + "epoch": 0.570801317233809, + "grad_norm": 0.45887550711631775, + "learning_rate": 0.0002, + "loss": 1.3121, + "step": 260 + }, + { + "epoch": 0.5927552140504939, + "grad_norm": 0.5440235733985901, + "learning_rate": 0.0002, + "loss": 1.2257, + "step": 270 + }, + { + "epoch": 0.6147091108671789, + "grad_norm": 0.3725181519985199, + "learning_rate": 0.0002, + "loss": 1.1003, + "step": 280 + }, + { + "epoch": 0.6366630076838639, + "grad_norm": 0.4309018850326538, + "learning_rate": 0.0002, + "loss": 1.1538, + "step": 290 + }, + { + "epoch": 0.6586169045005489, + "grad_norm": 0.31488674879074097, + "learning_rate": 0.0002, + "loss": 1.2097, + "step": 300 + }, + { + "epoch": 0.6805708013172338, + "grad_norm": 0.34194841980934143, + "learning_rate": 0.0002, + "loss": 1.1689, + "step": 310 + }, + { + "epoch": 0.7025246981339188, + "grad_norm": 0.3407684862613678, + "learning_rate": 0.0002, + "loss": 1.2579, + "step": 320 + }, + { + "epoch": 0.7244785949506037, + "grad_norm": 0.2985728085041046, + "learning_rate": 0.0002, + "loss": 1.1144, + "step": 330 + }, + { + "epoch": 0.7464324917672887, + "grad_norm": 0.42316871881484985, + "learning_rate": 0.0002, + "loss": 1.2056, + "step": 340 + }, + { + "epoch": 0.7683863885839737, + "grad_norm": 0.3124258816242218, + "learning_rate": 0.0002, + "loss": 1.1753, + "step": 350 + }, + { + "epoch": 0.7903402854006586, + "grad_norm": 0.7727567553520203, + "learning_rate": 0.0002, + "loss": 1.2547, + "step": 360 + }, + { + "epoch": 0.8122941822173436, + "grad_norm": 0.363765686750412, + "learning_rate": 0.0002, + "loss": 1.124, + "step": 370 + }, + { + "epoch": 0.8342480790340285, + "grad_norm": 0.35582536458969116, + "learning_rate": 0.0002, + "loss": 1.1302, + "step": 380 + }, + { + "epoch": 0.8562019758507134, + "grad_norm": 0.31982025504112244, + "learning_rate": 0.0002, + "loss": 1.1787, + "step": 390 + }, + { + "epoch": 0.8781558726673985, + "grad_norm": 0.34978964924812317, + "learning_rate": 0.0002, + "loss": 1.2056, + "step": 400 + }, + { + "epoch": 0.9001097694840834, + "grad_norm": 0.8346716165542603, + "learning_rate": 0.0002, + "loss": 1.3577, + "step": 410 + }, + { + "epoch": 0.9220636663007684, + "grad_norm": 0.31984028220176697, + "learning_rate": 0.0002, + "loss": 1.1029, + "step": 420 + }, + { + "epoch": 0.9440175631174533, + "grad_norm": 0.32078951597213745, + "learning_rate": 0.0002, + "loss": 1.0967, + "step": 430 + }, + { + "epoch": 0.9659714599341384, + "grad_norm": 0.3417500853538513, + "learning_rate": 0.0002, + "loss": 1.0936, + "step": 440 + }, + { + "epoch": 0.9879253567508233, + "grad_norm": 0.42359477281570435, + "learning_rate": 0.0002, + "loss": 1.3412, + "step": 450 + }, + { + "epoch": 0.9989023051591658, + "eval_loss": 1.2201528549194336, + "eval_runtime": 87.152, + "eval_samples_per_second": 4.945, + "eval_steps_per_second": 0.62, + "step": 455 + }, + { + "epoch": 1.0098792535675083, + "grad_norm": 0.37914523482322693, + "learning_rate": 0.0002, + "loss": 1.1909, + "step": 460 + }, + { + "epoch": 1.031833150384193, + "grad_norm": 0.43655872344970703, + "learning_rate": 0.0002, + "loss": 1.0948, + "step": 470 + }, + { + "epoch": 1.0537870472008781, + "grad_norm": 0.3673796057701111, + "learning_rate": 0.0002, + "loss": 1.0873, + "step": 480 + }, + { + "epoch": 1.0757409440175631, + "grad_norm": 0.37673917412757874, + "learning_rate": 0.0002, + "loss": 1.0483, + "step": 490 + }, + { + "epoch": 1.0976948408342482, + "grad_norm": 0.2893829345703125, + "learning_rate": 0.0002, + "loss": 1.0799, + "step": 500 + }, + { + "epoch": 1.119648737650933, + "grad_norm": 0.5551970601081848, + "learning_rate": 0.0002, + "loss": 1.1847, + "step": 510 + }, + { + "epoch": 1.141602634467618, + "grad_norm": 0.442104309797287, + "learning_rate": 0.0002, + "loss": 1.0885, + "step": 520 + }, + { + "epoch": 1.163556531284303, + "grad_norm": 0.4035094976425171, + "learning_rate": 0.0002, + "loss": 1.1766, + "step": 530 + }, + { + "epoch": 1.1855104281009878, + "grad_norm": 0.47009000182151794, + "learning_rate": 0.0002, + "loss": 1.0282, + "step": 540 + }, + { + "epoch": 1.2074643249176729, + "grad_norm": 0.4118749797344208, + "learning_rate": 0.0002, + "loss": 1.2625, + "step": 550 + }, + { + "epoch": 1.2294182217343579, + "grad_norm": 0.35173165798187256, + "learning_rate": 0.0002, + "loss": 1.0988, + "step": 560 + }, + { + "epoch": 1.2513721185510427, + "grad_norm": 0.7024672031402588, + "learning_rate": 0.0002, + "loss": 1.0498, + "step": 570 + }, + { + "epoch": 1.2733260153677277, + "grad_norm": 0.42657527327537537, + "learning_rate": 0.0002, + "loss": 1.1339, + "step": 580 + }, + { + "epoch": 1.2952799121844127, + "grad_norm": 0.3815029561519623, + "learning_rate": 0.0002, + "loss": 1.0545, + "step": 590 + }, + { + "epoch": 1.3172338090010978, + "grad_norm": 0.7031055688858032, + "learning_rate": 0.0002, + "loss": 1.1528, + "step": 600 + }, + { + "epoch": 1.3391877058177828, + "grad_norm": 0.393911212682724, + "learning_rate": 0.0002, + "loss": 1.1347, + "step": 610 + }, + { + "epoch": 1.3611416026344676, + "grad_norm": 0.5077702403068542, + "learning_rate": 0.0002, + "loss": 1.1901, + "step": 620 + }, + { + "epoch": 1.3830954994511526, + "grad_norm": 2.330033302307129, + "learning_rate": 0.0002, + "loss": 1.1251, + "step": 630 + }, + { + "epoch": 1.4050493962678376, + "grad_norm": 0.35322949290275574, + "learning_rate": 0.0002, + "loss": 1.0477, + "step": 640 + }, + { + "epoch": 1.4270032930845225, + "grad_norm": 0.44401052594184875, + "learning_rate": 0.0002, + "loss": 1.14, + "step": 650 + }, + { + "epoch": 1.4489571899012075, + "grad_norm": 0.35945481061935425, + "learning_rate": 0.0002, + "loss": 1.0318, + "step": 660 + }, + { + "epoch": 1.4709110867178925, + "grad_norm": 0.3058856129646301, + "learning_rate": 0.0002, + "loss": 1.1988, + "step": 670 + }, + { + "epoch": 1.4928649835345773, + "grad_norm": 0.7067602872848511, + "learning_rate": 0.0002, + "loss": 1.1545, + "step": 680 + }, + { + "epoch": 1.5148188803512623, + "grad_norm": 0.4219357371330261, + "learning_rate": 0.0002, + "loss": 1.0925, + "step": 690 + }, + { + "epoch": 1.5367727771679474, + "grad_norm": 0.5970841646194458, + "learning_rate": 0.0002, + "loss": 1.1622, + "step": 700 + }, + { + "epoch": 1.5587266739846322, + "grad_norm": 0.4381934404373169, + "learning_rate": 0.0002, + "loss": 1.0803, + "step": 710 + }, + { + "epoch": 1.5806805708013172, + "grad_norm": 0.4101450443267822, + "learning_rate": 0.0002, + "loss": 1.0961, + "step": 720 + }, + { + "epoch": 1.6026344676180022, + "grad_norm": 0.3657490015029907, + "learning_rate": 0.0002, + "loss": 1.0474, + "step": 730 + }, + { + "epoch": 1.624588364434687, + "grad_norm": 0.36240628361701965, + "learning_rate": 0.0002, + "loss": 1.0936, + "step": 740 + }, + { + "epoch": 1.6465422612513723, + "grad_norm": 0.4103568494319916, + "learning_rate": 0.0002, + "loss": 1.0489, + "step": 750 + }, + { + "epoch": 1.668496158068057, + "grad_norm": 0.3138505816459656, + "learning_rate": 0.0002, + "loss": 1.0919, + "step": 760 + }, + { + "epoch": 1.690450054884742, + "grad_norm": 0.41215717792510986, + "learning_rate": 0.0002, + "loss": 1.2308, + "step": 770 + }, + { + "epoch": 1.7124039517014271, + "grad_norm": 0.4589519202709198, + "learning_rate": 0.0002, + "loss": 1.1659, + "step": 780 + }, + { + "epoch": 1.734357848518112, + "grad_norm": 0.4049508571624756, + "learning_rate": 0.0002, + "loss": 1.0913, + "step": 790 + }, + { + "epoch": 1.756311745334797, + "grad_norm": 0.48557212948799133, + "learning_rate": 0.0002, + "loss": 1.1329, + "step": 800 + }, + { + "epoch": 1.778265642151482, + "grad_norm": 0.5331754088401794, + "learning_rate": 0.0002, + "loss": 1.0729, + "step": 810 + }, + { + "epoch": 1.8002195389681668, + "grad_norm": 0.3853185772895813, + "learning_rate": 0.0002, + "loss": 1.1452, + "step": 820 + }, + { + "epoch": 1.8221734357848518, + "grad_norm": 0.424062579870224, + "learning_rate": 0.0002, + "loss": 1.1061, + "step": 830 + }, + { + "epoch": 1.8441273326015368, + "grad_norm": 0.3418445289134979, + "learning_rate": 0.0002, + "loss": 1.1104, + "step": 840 + }, + { + "epoch": 1.8660812294182216, + "grad_norm": 0.4045565128326416, + "learning_rate": 0.0002, + "loss": 1.0546, + "step": 850 + }, + { + "epoch": 1.8880351262349067, + "grad_norm": 0.42155781388282776, + "learning_rate": 0.0002, + "loss": 1.1608, + "step": 860 + }, + { + "epoch": 1.9099890230515917, + "grad_norm": 0.40554770827293396, + "learning_rate": 0.0002, + "loss": 1.0628, + "step": 870 + }, + { + "epoch": 1.9319429198682765, + "grad_norm": 0.42644748091697693, + "learning_rate": 0.0002, + "loss": 1.1609, + "step": 880 + }, + { + "epoch": 1.9538968166849617, + "grad_norm": 0.45260652899742126, + "learning_rate": 0.0002, + "loss": 1.1132, + "step": 890 + }, + { + "epoch": 1.9758507135016465, + "grad_norm": 0.4114069938659668, + "learning_rate": 0.0002, + "loss": 1.048, + "step": 900 + }, + { + "epoch": 1.9978046103183313, + "grad_norm": 0.375802218914032, + "learning_rate": 0.0002, + "loss": 1.1941, + "step": 910 + }, + { + "epoch": 2.0, + "eval_loss": 1.205152153968811, + "eval_runtime": 86.8795, + "eval_samples_per_second": 4.961, + "eval_steps_per_second": 0.622, + "step": 911 + }, + { + "epoch": 2.0197585071350166, + "grad_norm": 0.47718703746795654, + "learning_rate": 0.0002, + "loss": 1.0897, + "step": 920 + }, + { + "epoch": 2.0417124039517014, + "grad_norm": 0.45628082752227783, + "learning_rate": 0.0002, + "loss": 1.0329, + "step": 930 + }, + { + "epoch": 2.063666300768386, + "grad_norm": 0.5933247804641724, + "learning_rate": 0.0002, + "loss": 1.0538, + "step": 940 + }, + { + "epoch": 2.0856201975850714, + "grad_norm": 0.5355812907218933, + "learning_rate": 0.0002, + "loss": 1.0152, + "step": 950 + }, + { + "epoch": 2.1075740944017562, + "grad_norm": 0.5860010385513306, + "learning_rate": 0.0002, + "loss": 1.0726, + "step": 960 + }, + { + "epoch": 2.129527991218441, + "grad_norm": 0.7471673488616943, + "learning_rate": 0.0002, + "loss": 1.025, + "step": 970 + }, + { + "epoch": 2.1514818880351263, + "grad_norm": 2.0918211936950684, + "learning_rate": 0.0002, + "loss": 1.0247, + "step": 980 + }, + { + "epoch": 2.173435784851811, + "grad_norm": 0.4021058678627014, + "learning_rate": 0.0002, + "loss": 0.8947, + "step": 990 + }, + { + "epoch": 2.1953896816684964, + "grad_norm": 0.564975380897522, + "learning_rate": 0.0002, + "loss": 0.8875, + "step": 1000 + }, + { + "epoch": 2.217343578485181, + "grad_norm": 0.46260079741477966, + "learning_rate": 0.0002, + "loss": 1.0264, + "step": 1010 + }, + { + "epoch": 2.239297475301866, + "grad_norm": 0.4791034460067749, + "learning_rate": 0.0002, + "loss": 0.9265, + "step": 1020 + }, + { + "epoch": 2.261251372118551, + "grad_norm": 0.5272043943405151, + "learning_rate": 0.0002, + "loss": 0.8869, + "step": 1030 + }, + { + "epoch": 2.283205268935236, + "grad_norm": 0.5221094489097595, + "learning_rate": 0.0002, + "loss": 1.0007, + "step": 1040 + }, + { + "epoch": 2.305159165751921, + "grad_norm": 0.558032751083374, + "learning_rate": 0.0002, + "loss": 0.9472, + "step": 1050 + }, + { + "epoch": 2.327113062568606, + "grad_norm": 0.5905590653419495, + "learning_rate": 0.0002, + "loss": 0.9617, + "step": 1060 + }, + { + "epoch": 2.349066959385291, + "grad_norm": 0.5308699607849121, + "learning_rate": 0.0002, + "loss": 0.9592, + "step": 1070 + }, + { + "epoch": 2.3710208562019757, + "grad_norm": 0.6375027894973755, + "learning_rate": 0.0002, + "loss": 1.0646, + "step": 1080 + }, + { + "epoch": 2.392974753018661, + "grad_norm": 0.7439115643501282, + "learning_rate": 0.0002, + "loss": 1.0354, + "step": 1090 + }, + { + "epoch": 2.4149286498353457, + "grad_norm": 0.41945117712020874, + "learning_rate": 0.0002, + "loss": 1.0212, + "step": 1100 + }, + { + "epoch": 2.436882546652031, + "grad_norm": 0.4891968369483948, + "learning_rate": 0.0002, + "loss": 0.9609, + "step": 1110 + }, + { + "epoch": 2.4588364434687158, + "grad_norm": 0.4686794579029083, + "learning_rate": 0.0002, + "loss": 0.9829, + "step": 1120 + }, + { + "epoch": 2.4807903402854006, + "grad_norm": 0.5204509496688843, + "learning_rate": 0.0002, + "loss": 0.8919, + "step": 1130 + }, + { + "epoch": 2.5027442371020854, + "grad_norm": 0.6779005527496338, + "learning_rate": 0.0002, + "loss": 0.8983, + "step": 1140 + }, + { + "epoch": 2.5246981339187706, + "grad_norm": 0.682621955871582, + "learning_rate": 0.0002, + "loss": 0.9733, + "step": 1150 + }, + { + "epoch": 2.5466520307354554, + "grad_norm": 0.5744376182556152, + "learning_rate": 0.0002, + "loss": 1.051, + "step": 1160 + }, + { + "epoch": 2.5686059275521407, + "grad_norm": 0.49954667687416077, + "learning_rate": 0.0002, + "loss": 0.8764, + "step": 1170 + }, + { + "epoch": 2.5905598243688255, + "grad_norm": 0.4761793315410614, + "learning_rate": 0.0002, + "loss": 0.9896, + "step": 1180 + }, + { + "epoch": 2.6125137211855103, + "grad_norm": 0.548299252986908, + "learning_rate": 0.0002, + "loss": 0.8593, + "step": 1190 + }, + { + "epoch": 2.6344676180021955, + "grad_norm": 0.5771360993385315, + "learning_rate": 0.0002, + "loss": 1.0017, + "step": 1200 + }, + { + "epoch": 2.6564215148188803, + "grad_norm": 0.5543120503425598, + "learning_rate": 0.0002, + "loss": 0.9858, + "step": 1210 + }, + { + "epoch": 2.6783754116355656, + "grad_norm": 0.7564870715141296, + "learning_rate": 0.0002, + "loss": 0.9565, + "step": 1220 + }, + { + "epoch": 2.7003293084522504, + "grad_norm": 0.8222362399101257, + "learning_rate": 0.0002, + "loss": 0.9753, + "step": 1230 + }, + { + "epoch": 2.722283205268935, + "grad_norm": 0.6894469857215881, + "learning_rate": 0.0002, + "loss": 1.0079, + "step": 1240 + }, + { + "epoch": 2.74423710208562, + "grad_norm": 0.6121546030044556, + "learning_rate": 0.0002, + "loss": 1.0106, + "step": 1250 + }, + { + "epoch": 2.7661909989023052, + "grad_norm": 0.521809995174408, + "learning_rate": 0.0002, + "loss": 0.9801, + "step": 1260 + }, + { + "epoch": 2.78814489571899, + "grad_norm": 0.766968309879303, + "learning_rate": 0.0002, + "loss": 1.0196, + "step": 1270 + }, + { + "epoch": 2.8100987925356753, + "grad_norm": 0.522331714630127, + "learning_rate": 0.0002, + "loss": 0.976, + "step": 1280 + }, + { + "epoch": 2.83205268935236, + "grad_norm": 0.42923519015312195, + "learning_rate": 0.0002, + "loss": 0.8866, + "step": 1290 + }, + { + "epoch": 2.854006586169045, + "grad_norm": 0.47810837626457214, + "learning_rate": 0.0002, + "loss": 0.9049, + "step": 1300 + }, + { + "epoch": 2.8759604829857297, + "grad_norm": 1.0958846807479858, + "learning_rate": 0.0002, + "loss": 1.0291, + "step": 1310 + }, + { + "epoch": 2.897914379802415, + "grad_norm": 0.4755791127681732, + "learning_rate": 0.0002, + "loss": 0.8724, + "step": 1320 + }, + { + "epoch": 2.9198682766190998, + "grad_norm": 0.5575157403945923, + "learning_rate": 0.0002, + "loss": 0.9317, + "step": 1330 + }, + { + "epoch": 2.941822173435785, + "grad_norm": 0.5938076376914978, + "learning_rate": 0.0002, + "loss": 1.0131, + "step": 1340 + }, + { + "epoch": 2.96377607025247, + "grad_norm": 0.5751763582229614, + "learning_rate": 0.0002, + "loss": 0.9857, + "step": 1350 + }, + { + "epoch": 2.9857299670691546, + "grad_norm": 0.5590175986289978, + "learning_rate": 0.0002, + "loss": 1.0212, + "step": 1360 + }, + { + "epoch": 2.9989023051591657, + "eval_loss": 1.2402944564819336, + "eval_runtime": 88.822, + "eval_samples_per_second": 4.852, + "eval_steps_per_second": 0.608, + "step": 1366 + } + ], + "logging_steps": 10, + "max_steps": 3640, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 6.323856028257485e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f75755c7cf71aeb05b76db2632173f96f74e8f7 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf90ce7dd53cc68edd44d14e30ca84a5d7431a5b99d4697b17af4b2f7ec0abab +size 5624 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/README.md b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/README.md new file mode 100644 index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/README.md @@ -0,0 +1,202 @@ +--- +base_model: meta-llama/Meta-Llama-3-8B-Instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.13.1 \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..406c5a08dc4a2a33b52c62a482f98c217c417215 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "v_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..53eb8476a223a2bdc8229ca7f27db83c3253b0cb --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdd662729c18e2ae17e0532c2a10a7225f6b690ab2f68160a3899a37c72638bf +size 109069176 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/optimizer.pt b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..8ca3e82a30deedfe383bfc8f56380377bbe5fb54 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba4d6429e46fa1c59b2fcd4f3e7db7d2b39e1180a8368b7edf9f299b36574979 +size 55532666 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/rng_state.pth b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..6402763e937fc0caa8165e993a633fd551894756 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28426692871cf5cf6b3fcbb7954b695d1a7612f76ad200ab9263813cf45e86d7 +size 14244 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/scheduler.pt b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5a43516f7eec93992d1996fee34bab2042aaca7b --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49576c0a7c5058f8291777ab40a303a807766b0e9604129e7e31f02391844f52 +size 1064 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393 +size 17209961 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|eot_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/trainer_state.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..a58975814028a6edadc84d972964cbdf8a8693b8 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/trainer_state.json @@ -0,0 +1,1339 @@ +{ + "best_metric": 1.205152153968811, + "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911", + "epoch": 4.0, + "eval_steps": 10, + "global_step": 1822, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.021953896816684963, + "grad_norm": 0.6144012212753296, + "learning_rate": 0.0002, + "loss": 1.9887, + "step": 10 + }, + { + "epoch": 0.043907793633369926, + "grad_norm": 0.5587220788002014, + "learning_rate": 0.0002, + "loss": 1.6882, + "step": 20 + }, + { + "epoch": 0.06586169045005488, + "grad_norm": 0.43262454867362976, + "learning_rate": 0.0002, + "loss": 1.399, + "step": 30 + }, + { + "epoch": 0.08781558726673985, + "grad_norm": 0.4783053994178772, + "learning_rate": 0.0002, + "loss": 1.4675, + "step": 40 + }, + { + "epoch": 0.10976948408342481, + "grad_norm": 0.44338956475257874, + "learning_rate": 0.0002, + "loss": 1.1771, + "step": 50 + }, + { + "epoch": 0.13172338090010977, + "grad_norm": 0.7255092263221741, + "learning_rate": 0.0002, + "loss": 1.3706, + "step": 60 + }, + { + "epoch": 0.15367727771679474, + "grad_norm": 0.46073833107948303, + "learning_rate": 0.0002, + "loss": 1.2601, + "step": 70 + }, + { + "epoch": 0.1756311745334797, + "grad_norm": 0.6698123216629028, + "learning_rate": 0.0002, + "loss": 1.3049, + "step": 80 + }, + { + "epoch": 0.19758507135016465, + "grad_norm": 0.4190150201320648, + "learning_rate": 0.0002, + "loss": 1.2975, + "step": 90 + }, + { + "epoch": 0.21953896816684962, + "grad_norm": 0.4110015034675598, + "learning_rate": 0.0002, + "loss": 1.2797, + "step": 100 + }, + { + "epoch": 0.2414928649835346, + "grad_norm": 0.33374306559562683, + "learning_rate": 0.0002, + "loss": 1.2896, + "step": 110 + }, + { + "epoch": 0.26344676180021953, + "grad_norm": 0.3061307370662689, + "learning_rate": 0.0002, + "loss": 1.2268, + "step": 120 + }, + { + "epoch": 0.2854006586169045, + "grad_norm": 0.4386885166168213, + "learning_rate": 0.0002, + "loss": 1.376, + "step": 130 + }, + { + "epoch": 0.30735455543358947, + "grad_norm": 0.40116462111473083, + "learning_rate": 0.0002, + "loss": 1.1814, + "step": 140 + }, + { + "epoch": 0.32930845225027444, + "grad_norm": 0.5887949466705322, + "learning_rate": 0.0002, + "loss": 1.2592, + "step": 150 + }, + { + "epoch": 0.3512623490669594, + "grad_norm": 0.3401573896408081, + "learning_rate": 0.0002, + "loss": 1.2372, + "step": 160 + }, + { + "epoch": 0.3732162458836443, + "grad_norm": 0.3288364112377167, + "learning_rate": 0.0002, + "loss": 1.1901, + "step": 170 + }, + { + "epoch": 0.3951701427003293, + "grad_norm": 0.4853297472000122, + "learning_rate": 0.0002, + "loss": 1.2335, + "step": 180 + }, + { + "epoch": 0.41712403951701427, + "grad_norm": 2.6253697872161865, + "learning_rate": 0.0002, + "loss": 1.227, + "step": 190 + }, + { + "epoch": 0.43907793633369924, + "grad_norm": 0.5598543286323547, + "learning_rate": 0.0002, + "loss": 1.2673, + "step": 200 + }, + { + "epoch": 0.4610318331503842, + "grad_norm": 0.4046548902988434, + "learning_rate": 0.0002, + "loss": 1.3459, + "step": 210 + }, + { + "epoch": 0.4829857299670692, + "grad_norm": 0.3686952590942383, + "learning_rate": 0.0002, + "loss": 1.265, + "step": 220 + }, + { + "epoch": 0.5049396267837541, + "grad_norm": 0.42458799481391907, + "learning_rate": 0.0002, + "loss": 1.1364, + "step": 230 + }, + { + "epoch": 0.5268935236004391, + "grad_norm": 0.5839895009994507, + "learning_rate": 0.0002, + "loss": 1.2094, + "step": 240 + }, + { + "epoch": 0.5488474204171241, + "grad_norm": 0.408288836479187, + "learning_rate": 0.0002, + "loss": 1.2073, + "step": 250 + }, + { + "epoch": 0.570801317233809, + "grad_norm": 0.45887550711631775, + "learning_rate": 0.0002, + "loss": 1.3121, + "step": 260 + }, + { + "epoch": 0.5927552140504939, + "grad_norm": 0.5440235733985901, + "learning_rate": 0.0002, + "loss": 1.2257, + "step": 270 + }, + { + "epoch": 0.6147091108671789, + "grad_norm": 0.3725181519985199, + "learning_rate": 0.0002, + "loss": 1.1003, + "step": 280 + }, + { + "epoch": 0.6366630076838639, + "grad_norm": 0.4309018850326538, + "learning_rate": 0.0002, + "loss": 1.1538, + "step": 290 + }, + { + "epoch": 0.6586169045005489, + "grad_norm": 0.31488674879074097, + "learning_rate": 0.0002, + "loss": 1.2097, + "step": 300 + }, + { + "epoch": 0.6805708013172338, + "grad_norm": 0.34194841980934143, + "learning_rate": 0.0002, + "loss": 1.1689, + "step": 310 + }, + { + "epoch": 0.7025246981339188, + "grad_norm": 0.3407684862613678, + "learning_rate": 0.0002, + "loss": 1.2579, + "step": 320 + }, + { + "epoch": 0.7244785949506037, + "grad_norm": 0.2985728085041046, + "learning_rate": 0.0002, + "loss": 1.1144, + "step": 330 + }, + { + "epoch": 0.7464324917672887, + "grad_norm": 0.42316871881484985, + "learning_rate": 0.0002, + "loss": 1.2056, + "step": 340 + }, + { + "epoch": 0.7683863885839737, + "grad_norm": 0.3124258816242218, + "learning_rate": 0.0002, + "loss": 1.1753, + "step": 350 + }, + { + "epoch": 0.7903402854006586, + "grad_norm": 0.7727567553520203, + "learning_rate": 0.0002, + "loss": 1.2547, + "step": 360 + }, + { + "epoch": 0.8122941822173436, + "grad_norm": 0.363765686750412, + "learning_rate": 0.0002, + "loss": 1.124, + "step": 370 + }, + { + "epoch": 0.8342480790340285, + "grad_norm": 0.35582536458969116, + "learning_rate": 0.0002, + "loss": 1.1302, + "step": 380 + }, + { + "epoch": 0.8562019758507134, + "grad_norm": 0.31982025504112244, + "learning_rate": 0.0002, + "loss": 1.1787, + "step": 390 + }, + { + "epoch": 0.8781558726673985, + "grad_norm": 0.34978964924812317, + "learning_rate": 0.0002, + "loss": 1.2056, + "step": 400 + }, + { + "epoch": 0.9001097694840834, + "grad_norm": 0.8346716165542603, + "learning_rate": 0.0002, + "loss": 1.3577, + "step": 410 + }, + { + "epoch": 0.9220636663007684, + "grad_norm": 0.31984028220176697, + "learning_rate": 0.0002, + "loss": 1.1029, + "step": 420 + }, + { + "epoch": 0.9440175631174533, + "grad_norm": 0.32078951597213745, + "learning_rate": 0.0002, + "loss": 1.0967, + "step": 430 + }, + { + "epoch": 0.9659714599341384, + "grad_norm": 0.3417500853538513, + "learning_rate": 0.0002, + "loss": 1.0936, + "step": 440 + }, + { + "epoch": 0.9879253567508233, + "grad_norm": 0.42359477281570435, + "learning_rate": 0.0002, + "loss": 1.3412, + "step": 450 + }, + { + "epoch": 0.9989023051591658, + "eval_loss": 1.2201528549194336, + "eval_runtime": 87.152, + "eval_samples_per_second": 4.945, + "eval_steps_per_second": 0.62, + "step": 455 + }, + { + "epoch": 1.0098792535675083, + "grad_norm": 0.37914523482322693, + "learning_rate": 0.0002, + "loss": 1.1909, + "step": 460 + }, + { + "epoch": 1.031833150384193, + "grad_norm": 0.43655872344970703, + "learning_rate": 0.0002, + "loss": 1.0948, + "step": 470 + }, + { + "epoch": 1.0537870472008781, + "grad_norm": 0.3673796057701111, + "learning_rate": 0.0002, + "loss": 1.0873, + "step": 480 + }, + { + "epoch": 1.0757409440175631, + "grad_norm": 0.37673917412757874, + "learning_rate": 0.0002, + "loss": 1.0483, + "step": 490 + }, + { + "epoch": 1.0976948408342482, + "grad_norm": 0.2893829345703125, + "learning_rate": 0.0002, + "loss": 1.0799, + "step": 500 + }, + { + "epoch": 1.119648737650933, + "grad_norm": 0.5551970601081848, + "learning_rate": 0.0002, + "loss": 1.1847, + "step": 510 + }, + { + "epoch": 1.141602634467618, + "grad_norm": 0.442104309797287, + "learning_rate": 0.0002, + "loss": 1.0885, + "step": 520 + }, + { + "epoch": 1.163556531284303, + "grad_norm": 0.4035094976425171, + "learning_rate": 0.0002, + "loss": 1.1766, + "step": 530 + }, + { + "epoch": 1.1855104281009878, + "grad_norm": 0.47009000182151794, + "learning_rate": 0.0002, + "loss": 1.0282, + "step": 540 + }, + { + "epoch": 1.2074643249176729, + "grad_norm": 0.4118749797344208, + "learning_rate": 0.0002, + "loss": 1.2625, + "step": 550 + }, + { + "epoch": 1.2294182217343579, + "grad_norm": 0.35173165798187256, + "learning_rate": 0.0002, + "loss": 1.0988, + "step": 560 + }, + { + "epoch": 1.2513721185510427, + "grad_norm": 0.7024672031402588, + "learning_rate": 0.0002, + "loss": 1.0498, + "step": 570 + }, + { + "epoch": 1.2733260153677277, + "grad_norm": 0.42657527327537537, + "learning_rate": 0.0002, + "loss": 1.1339, + "step": 580 + }, + { + "epoch": 1.2952799121844127, + "grad_norm": 0.3815029561519623, + "learning_rate": 0.0002, + "loss": 1.0545, + "step": 590 + }, + { + "epoch": 1.3172338090010978, + "grad_norm": 0.7031055688858032, + "learning_rate": 0.0002, + "loss": 1.1528, + "step": 600 + }, + { + "epoch": 1.3391877058177828, + "grad_norm": 0.393911212682724, + "learning_rate": 0.0002, + "loss": 1.1347, + "step": 610 + }, + { + "epoch": 1.3611416026344676, + "grad_norm": 0.5077702403068542, + "learning_rate": 0.0002, + "loss": 1.1901, + "step": 620 + }, + { + "epoch": 1.3830954994511526, + "grad_norm": 2.330033302307129, + "learning_rate": 0.0002, + "loss": 1.1251, + "step": 630 + }, + { + "epoch": 1.4050493962678376, + "grad_norm": 0.35322949290275574, + "learning_rate": 0.0002, + "loss": 1.0477, + "step": 640 + }, + { + "epoch": 1.4270032930845225, + "grad_norm": 0.44401052594184875, + "learning_rate": 0.0002, + "loss": 1.14, + "step": 650 + }, + { + "epoch": 1.4489571899012075, + "grad_norm": 0.35945481061935425, + "learning_rate": 0.0002, + "loss": 1.0318, + "step": 660 + }, + { + "epoch": 1.4709110867178925, + "grad_norm": 0.3058856129646301, + "learning_rate": 0.0002, + "loss": 1.1988, + "step": 670 + }, + { + "epoch": 1.4928649835345773, + "grad_norm": 0.7067602872848511, + "learning_rate": 0.0002, + "loss": 1.1545, + "step": 680 + }, + { + "epoch": 1.5148188803512623, + "grad_norm": 0.4219357371330261, + "learning_rate": 0.0002, + "loss": 1.0925, + "step": 690 + }, + { + "epoch": 1.5367727771679474, + "grad_norm": 0.5970841646194458, + "learning_rate": 0.0002, + "loss": 1.1622, + "step": 700 + }, + { + "epoch": 1.5587266739846322, + "grad_norm": 0.4381934404373169, + "learning_rate": 0.0002, + "loss": 1.0803, + "step": 710 + }, + { + "epoch": 1.5806805708013172, + "grad_norm": 0.4101450443267822, + "learning_rate": 0.0002, + "loss": 1.0961, + "step": 720 + }, + { + "epoch": 1.6026344676180022, + "grad_norm": 0.3657490015029907, + "learning_rate": 0.0002, + "loss": 1.0474, + "step": 730 + }, + { + "epoch": 1.624588364434687, + "grad_norm": 0.36240628361701965, + "learning_rate": 0.0002, + "loss": 1.0936, + "step": 740 + }, + { + "epoch": 1.6465422612513723, + "grad_norm": 0.4103568494319916, + "learning_rate": 0.0002, + "loss": 1.0489, + "step": 750 + }, + { + "epoch": 1.668496158068057, + "grad_norm": 0.3138505816459656, + "learning_rate": 0.0002, + "loss": 1.0919, + "step": 760 + }, + { + "epoch": 1.690450054884742, + "grad_norm": 0.41215717792510986, + "learning_rate": 0.0002, + "loss": 1.2308, + "step": 770 + }, + { + "epoch": 1.7124039517014271, + "grad_norm": 0.4589519202709198, + "learning_rate": 0.0002, + "loss": 1.1659, + "step": 780 + }, + { + "epoch": 1.734357848518112, + "grad_norm": 0.4049508571624756, + "learning_rate": 0.0002, + "loss": 1.0913, + "step": 790 + }, + { + "epoch": 1.756311745334797, + "grad_norm": 0.48557212948799133, + "learning_rate": 0.0002, + "loss": 1.1329, + "step": 800 + }, + { + "epoch": 1.778265642151482, + "grad_norm": 0.5331754088401794, + "learning_rate": 0.0002, + "loss": 1.0729, + "step": 810 + }, + { + "epoch": 1.8002195389681668, + "grad_norm": 0.3853185772895813, + "learning_rate": 0.0002, + "loss": 1.1452, + "step": 820 + }, + { + "epoch": 1.8221734357848518, + "grad_norm": 0.424062579870224, + "learning_rate": 0.0002, + "loss": 1.1061, + "step": 830 + }, + { + "epoch": 1.8441273326015368, + "grad_norm": 0.3418445289134979, + "learning_rate": 0.0002, + "loss": 1.1104, + "step": 840 + }, + { + "epoch": 1.8660812294182216, + "grad_norm": 0.4045565128326416, + "learning_rate": 0.0002, + "loss": 1.0546, + "step": 850 + }, + { + "epoch": 1.8880351262349067, + "grad_norm": 0.42155781388282776, + "learning_rate": 0.0002, + "loss": 1.1608, + "step": 860 + }, + { + "epoch": 1.9099890230515917, + "grad_norm": 0.40554770827293396, + "learning_rate": 0.0002, + "loss": 1.0628, + "step": 870 + }, + { + "epoch": 1.9319429198682765, + "grad_norm": 0.42644748091697693, + "learning_rate": 0.0002, + "loss": 1.1609, + "step": 880 + }, + { + "epoch": 1.9538968166849617, + "grad_norm": 0.45260652899742126, + "learning_rate": 0.0002, + "loss": 1.1132, + "step": 890 + }, + { + "epoch": 1.9758507135016465, + "grad_norm": 0.4114069938659668, + "learning_rate": 0.0002, + "loss": 1.048, + "step": 900 + }, + { + "epoch": 1.9978046103183313, + "grad_norm": 0.375802218914032, + "learning_rate": 0.0002, + "loss": 1.1941, + "step": 910 + }, + { + "epoch": 2.0, + "eval_loss": 1.205152153968811, + "eval_runtime": 86.8795, + "eval_samples_per_second": 4.961, + "eval_steps_per_second": 0.622, + "step": 911 + }, + { + "epoch": 2.0197585071350166, + "grad_norm": 0.47718703746795654, + "learning_rate": 0.0002, + "loss": 1.0897, + "step": 920 + }, + { + "epoch": 2.0417124039517014, + "grad_norm": 0.45628082752227783, + "learning_rate": 0.0002, + "loss": 1.0329, + "step": 930 + }, + { + "epoch": 2.063666300768386, + "grad_norm": 0.5933247804641724, + "learning_rate": 0.0002, + "loss": 1.0538, + "step": 940 + }, + { + "epoch": 2.0856201975850714, + "grad_norm": 0.5355812907218933, + "learning_rate": 0.0002, + "loss": 1.0152, + "step": 950 + }, + { + "epoch": 2.1075740944017562, + "grad_norm": 0.5860010385513306, + "learning_rate": 0.0002, + "loss": 1.0726, + "step": 960 + }, + { + "epoch": 2.129527991218441, + "grad_norm": 0.7471673488616943, + "learning_rate": 0.0002, + "loss": 1.025, + "step": 970 + }, + { + "epoch": 2.1514818880351263, + "grad_norm": 2.0918211936950684, + "learning_rate": 0.0002, + "loss": 1.0247, + "step": 980 + }, + { + "epoch": 2.173435784851811, + "grad_norm": 0.4021058678627014, + "learning_rate": 0.0002, + "loss": 0.8947, + "step": 990 + }, + { + "epoch": 2.1953896816684964, + "grad_norm": 0.564975380897522, + "learning_rate": 0.0002, + "loss": 0.8875, + "step": 1000 + }, + { + "epoch": 2.217343578485181, + "grad_norm": 0.46260079741477966, + "learning_rate": 0.0002, + "loss": 1.0264, + "step": 1010 + }, + { + "epoch": 2.239297475301866, + "grad_norm": 0.4791034460067749, + "learning_rate": 0.0002, + "loss": 0.9265, + "step": 1020 + }, + { + "epoch": 2.261251372118551, + "grad_norm": 0.5272043943405151, + "learning_rate": 0.0002, + "loss": 0.8869, + "step": 1030 + }, + { + "epoch": 2.283205268935236, + "grad_norm": 0.5221094489097595, + "learning_rate": 0.0002, + "loss": 1.0007, + "step": 1040 + }, + { + "epoch": 2.305159165751921, + "grad_norm": 0.558032751083374, + "learning_rate": 0.0002, + "loss": 0.9472, + "step": 1050 + }, + { + "epoch": 2.327113062568606, + "grad_norm": 0.5905590653419495, + "learning_rate": 0.0002, + "loss": 0.9617, + "step": 1060 + }, + { + "epoch": 2.349066959385291, + "grad_norm": 0.5308699607849121, + "learning_rate": 0.0002, + "loss": 0.9592, + "step": 1070 + }, + { + "epoch": 2.3710208562019757, + "grad_norm": 0.6375027894973755, + "learning_rate": 0.0002, + "loss": 1.0646, + "step": 1080 + }, + { + "epoch": 2.392974753018661, + "grad_norm": 0.7439115643501282, + "learning_rate": 0.0002, + "loss": 1.0354, + "step": 1090 + }, + { + "epoch": 2.4149286498353457, + "grad_norm": 0.41945117712020874, + "learning_rate": 0.0002, + "loss": 1.0212, + "step": 1100 + }, + { + "epoch": 2.436882546652031, + "grad_norm": 0.4891968369483948, + "learning_rate": 0.0002, + "loss": 0.9609, + "step": 1110 + }, + { + "epoch": 2.4588364434687158, + "grad_norm": 0.4686794579029083, + "learning_rate": 0.0002, + "loss": 0.9829, + "step": 1120 + }, + { + "epoch": 2.4807903402854006, + "grad_norm": 0.5204509496688843, + "learning_rate": 0.0002, + "loss": 0.8919, + "step": 1130 + }, + { + "epoch": 2.5027442371020854, + "grad_norm": 0.6779005527496338, + "learning_rate": 0.0002, + "loss": 0.8983, + "step": 1140 + }, + { + "epoch": 2.5246981339187706, + "grad_norm": 0.682621955871582, + "learning_rate": 0.0002, + "loss": 0.9733, + "step": 1150 + }, + { + "epoch": 2.5466520307354554, + "grad_norm": 0.5744376182556152, + "learning_rate": 0.0002, + "loss": 1.051, + "step": 1160 + }, + { + "epoch": 2.5686059275521407, + "grad_norm": 0.49954667687416077, + "learning_rate": 0.0002, + "loss": 0.8764, + "step": 1170 + }, + { + "epoch": 2.5905598243688255, + "grad_norm": 0.4761793315410614, + "learning_rate": 0.0002, + "loss": 0.9896, + "step": 1180 + }, + { + "epoch": 2.6125137211855103, + "grad_norm": 0.548299252986908, + "learning_rate": 0.0002, + "loss": 0.8593, + "step": 1190 + }, + { + "epoch": 2.6344676180021955, + "grad_norm": 0.5771360993385315, + "learning_rate": 0.0002, + "loss": 1.0017, + "step": 1200 + }, + { + "epoch": 2.6564215148188803, + "grad_norm": 0.5543120503425598, + "learning_rate": 0.0002, + "loss": 0.9858, + "step": 1210 + }, + { + "epoch": 2.6783754116355656, + "grad_norm": 0.7564870715141296, + "learning_rate": 0.0002, + "loss": 0.9565, + "step": 1220 + }, + { + "epoch": 2.7003293084522504, + "grad_norm": 0.8222362399101257, + "learning_rate": 0.0002, + "loss": 0.9753, + "step": 1230 + }, + { + "epoch": 2.722283205268935, + "grad_norm": 0.6894469857215881, + "learning_rate": 0.0002, + "loss": 1.0079, + "step": 1240 + }, + { + "epoch": 2.74423710208562, + "grad_norm": 0.6121546030044556, + "learning_rate": 0.0002, + "loss": 1.0106, + "step": 1250 + }, + { + "epoch": 2.7661909989023052, + "grad_norm": 0.521809995174408, + "learning_rate": 0.0002, + "loss": 0.9801, + "step": 1260 + }, + { + "epoch": 2.78814489571899, + "grad_norm": 0.766968309879303, + "learning_rate": 0.0002, + "loss": 1.0196, + "step": 1270 + }, + { + "epoch": 2.8100987925356753, + "grad_norm": 0.522331714630127, + "learning_rate": 0.0002, + "loss": 0.976, + "step": 1280 + }, + { + "epoch": 2.83205268935236, + "grad_norm": 0.42923519015312195, + "learning_rate": 0.0002, + "loss": 0.8866, + "step": 1290 + }, + { + "epoch": 2.854006586169045, + "grad_norm": 0.47810837626457214, + "learning_rate": 0.0002, + "loss": 0.9049, + "step": 1300 + }, + { + "epoch": 2.8759604829857297, + "grad_norm": 1.0958846807479858, + "learning_rate": 0.0002, + "loss": 1.0291, + "step": 1310 + }, + { + "epoch": 2.897914379802415, + "grad_norm": 0.4755791127681732, + "learning_rate": 0.0002, + "loss": 0.8724, + "step": 1320 + }, + { + "epoch": 2.9198682766190998, + "grad_norm": 0.5575157403945923, + "learning_rate": 0.0002, + "loss": 0.9317, + "step": 1330 + }, + { + "epoch": 2.941822173435785, + "grad_norm": 0.5938076376914978, + "learning_rate": 0.0002, + "loss": 1.0131, + "step": 1340 + }, + { + "epoch": 2.96377607025247, + "grad_norm": 0.5751763582229614, + "learning_rate": 0.0002, + "loss": 0.9857, + "step": 1350 + }, + { + "epoch": 2.9857299670691546, + "grad_norm": 0.5590175986289978, + "learning_rate": 0.0002, + "loss": 1.0212, + "step": 1360 + }, + { + "epoch": 2.9989023051591657, + "eval_loss": 1.2402944564819336, + "eval_runtime": 88.822, + "eval_samples_per_second": 4.852, + "eval_steps_per_second": 0.608, + "step": 1366 + }, + { + "epoch": 3.00768386388584, + "grad_norm": 0.463539719581604, + "learning_rate": 0.0002, + "loss": 0.844, + "step": 1370 + }, + { + "epoch": 3.0296377607025247, + "grad_norm": 0.6667885780334473, + "learning_rate": 0.0002, + "loss": 0.8955, + "step": 1380 + }, + { + "epoch": 3.0515916575192095, + "grad_norm": 0.5849342942237854, + "learning_rate": 0.0002, + "loss": 0.8765, + "step": 1390 + }, + { + "epoch": 3.0735455543358947, + "grad_norm": 0.5571770668029785, + "learning_rate": 0.0002, + "loss": 0.7808, + "step": 1400 + }, + { + "epoch": 3.0954994511525795, + "grad_norm": 0.5761234164237976, + "learning_rate": 0.0002, + "loss": 0.7448, + "step": 1410 + }, + { + "epoch": 3.1174533479692643, + "grad_norm": 0.7277371883392334, + "learning_rate": 0.0002, + "loss": 0.7854, + "step": 1420 + }, + { + "epoch": 3.1394072447859496, + "grad_norm": 0.5190334320068359, + "learning_rate": 0.0002, + "loss": 0.817, + "step": 1430 + }, + { + "epoch": 3.1613611416026344, + "grad_norm": 0.632939875125885, + "learning_rate": 0.0002, + "loss": 0.7548, + "step": 1440 + }, + { + "epoch": 3.1833150384193196, + "grad_norm": 0.7229540944099426, + "learning_rate": 0.0002, + "loss": 0.8447, + "step": 1450 + }, + { + "epoch": 3.2052689352360044, + "grad_norm": 0.7584632039070129, + "learning_rate": 0.0002, + "loss": 0.8595, + "step": 1460 + }, + { + "epoch": 3.2272228320526892, + "grad_norm": 0.6546088457107544, + "learning_rate": 0.0002, + "loss": 0.7456, + "step": 1470 + }, + { + "epoch": 3.2491767288693745, + "grad_norm": 0.8116684556007385, + "learning_rate": 0.0002, + "loss": 0.8531, + "step": 1480 + }, + { + "epoch": 3.2711306256860593, + "grad_norm": 0.6206557750701904, + "learning_rate": 0.0002, + "loss": 0.9272, + "step": 1490 + }, + { + "epoch": 3.293084522502744, + "grad_norm": 0.5393369197845459, + "learning_rate": 0.0002, + "loss": 0.7972, + "step": 1500 + }, + { + "epoch": 3.3150384193194293, + "grad_norm": 0.7006453275680542, + "learning_rate": 0.0002, + "loss": 0.7614, + "step": 1510 + }, + { + "epoch": 3.336992316136114, + "grad_norm": 0.95253986120224, + "learning_rate": 0.0002, + "loss": 0.7358, + "step": 1520 + }, + { + "epoch": 3.358946212952799, + "grad_norm": 0.8138132095336914, + "learning_rate": 0.0002, + "loss": 0.8131, + "step": 1530 + }, + { + "epoch": 3.380900109769484, + "grad_norm": 0.7974302172660828, + "learning_rate": 0.0002, + "loss": 0.7738, + "step": 1540 + }, + { + "epoch": 3.402854006586169, + "grad_norm": 0.6694685220718384, + "learning_rate": 0.0002, + "loss": 0.8161, + "step": 1550 + }, + { + "epoch": 3.4248079034028542, + "grad_norm": 0.908634603023529, + "learning_rate": 0.0002, + "loss": 0.8503, + "step": 1560 + }, + { + "epoch": 3.446761800219539, + "grad_norm": 0.5625193119049072, + "learning_rate": 0.0002, + "loss": 0.7609, + "step": 1570 + }, + { + "epoch": 3.468715697036224, + "grad_norm": 0.779325544834137, + "learning_rate": 0.0002, + "loss": 0.7658, + "step": 1580 + }, + { + "epoch": 3.4906695938529086, + "grad_norm": 0.7133058905601501, + "learning_rate": 0.0002, + "loss": 0.7485, + "step": 1590 + }, + { + "epoch": 3.512623490669594, + "grad_norm": 0.6741108298301697, + "learning_rate": 0.0002, + "loss": 0.8847, + "step": 1600 + }, + { + "epoch": 3.5345773874862787, + "grad_norm": 0.696982204914093, + "learning_rate": 0.0002, + "loss": 0.7838, + "step": 1610 + }, + { + "epoch": 3.556531284302964, + "grad_norm": 0.7946001291275024, + "learning_rate": 0.0002, + "loss": 0.7195, + "step": 1620 + }, + { + "epoch": 3.5784851811196488, + "grad_norm": 0.6313548684120178, + "learning_rate": 0.0002, + "loss": 0.7772, + "step": 1630 + }, + { + "epoch": 3.6004390779363336, + "grad_norm": 0.9246852397918701, + "learning_rate": 0.0002, + "loss": 0.8267, + "step": 1640 + }, + { + "epoch": 3.622392974753019, + "grad_norm": 0.6615420579910278, + "learning_rate": 0.0002, + "loss": 0.779, + "step": 1650 + }, + { + "epoch": 3.6443468715697036, + "grad_norm": 1.5050125122070312, + "learning_rate": 0.0002, + "loss": 0.883, + "step": 1660 + }, + { + "epoch": 3.666300768386389, + "grad_norm": 0.5023762583732605, + "learning_rate": 0.0002, + "loss": 0.7763, + "step": 1670 + }, + { + "epoch": 3.6882546652030737, + "grad_norm": 0.6289586424827576, + "learning_rate": 0.0002, + "loss": 0.8173, + "step": 1680 + }, + { + "epoch": 3.7102085620197585, + "grad_norm": 1.050397515296936, + "learning_rate": 0.0002, + "loss": 0.9028, + "step": 1690 + }, + { + "epoch": 3.7321624588364433, + "grad_norm": 0.6785626411437988, + "learning_rate": 0.0002, + "loss": 0.7747, + "step": 1700 + }, + { + "epoch": 3.7541163556531285, + "grad_norm": 0.7565035223960876, + "learning_rate": 0.0002, + "loss": 0.9215, + "step": 1710 + }, + { + "epoch": 3.7760702524698133, + "grad_norm": 0.7775155901908875, + "learning_rate": 0.0002, + "loss": 0.7913, + "step": 1720 + }, + { + "epoch": 3.7980241492864986, + "grad_norm": 0.765260636806488, + "learning_rate": 0.0002, + "loss": 0.8081, + "step": 1730 + }, + { + "epoch": 3.8199780461031834, + "grad_norm": 0.7982407808303833, + "learning_rate": 0.0002, + "loss": 0.9231, + "step": 1740 + }, + { + "epoch": 3.841931942919868, + "grad_norm": 0.7431730628013611, + "learning_rate": 0.0002, + "loss": 0.7755, + "step": 1750 + }, + { + "epoch": 3.863885839736553, + "grad_norm": 0.9758927226066589, + "learning_rate": 0.0002, + "loss": 0.9236, + "step": 1760 + }, + { + "epoch": 3.885839736553238, + "grad_norm": 0.8014697432518005, + "learning_rate": 0.0002, + "loss": 0.9118, + "step": 1770 + }, + { + "epoch": 3.907793633369923, + "grad_norm": 0.7212756276130676, + "learning_rate": 0.0002, + "loss": 0.7503, + "step": 1780 + }, + { + "epoch": 3.9297475301866083, + "grad_norm": 0.584318220615387, + "learning_rate": 0.0002, + "loss": 0.7978, + "step": 1790 + }, + { + "epoch": 3.951701427003293, + "grad_norm": 0.7612535953521729, + "learning_rate": 0.0002, + "loss": 0.7894, + "step": 1800 + }, + { + "epoch": 3.973655323819978, + "grad_norm": 0.735103189945221, + "learning_rate": 0.0002, + "loss": 0.8589, + "step": 1810 + }, + { + "epoch": 3.995609220636663, + "grad_norm": 0.9074980020523071, + "learning_rate": 0.0002, + "loss": 0.8192, + "step": 1820 + }, + { + "epoch": 4.0, + "eval_loss": 1.279890537261963, + "eval_runtime": 88.8969, + "eval_samples_per_second": 4.848, + "eval_steps_per_second": 0.607, + "step": 1822 + } + ], + "logging_steps": 10, + "max_steps": 3640, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 8.431808037676646e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f75755c7cf71aeb05b76db2632173f96f74e8f7 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf90ce7dd53cc68edd44d14e30ca84a5d7431a5b99d4697b17af4b2f7ec0abab +size 5624 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/README.md b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/README.md new file mode 100644 index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/README.md @@ -0,0 +1,202 @@ +--- +base_model: meta-llama/Meta-Llama-3-8B-Instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.13.1 \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..406c5a08dc4a2a33b52c62a482f98c217c417215 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "v_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..58a8f9d5116e9e367a609d86119965b4f992222c --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c96d3d7a842c87fa06a3879c84ca1bcf04cd5da6f344179383bdd42e7dd2a2dd +size 109069176 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/optimizer.pt b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..25f555f58fe50dafa449ae0c8b9c6b725fd46336 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d31faef2a2b0b29f8764f5175c794426c1984ff47fb280c987b9c09f638affe +size 55532666 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/rng_state.pth b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..50c2109db972a96721ea9ba73d0f233faf48a9b2 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28e15845f1efe266490b2686e71d5c1a896220db3dab076ec5da4eb620926599 +size 14244 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/scheduler.pt b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..7ae236f35a39725a2b2ea5612e3ec4817be66801 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc6cb40028b40235e27b0cac0a4339b75f0d188d520221f5823c28cfacfd1224 +size 1064 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393 +size 17209961 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|eot_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/trainer_state.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..788b209678fce8b56b67e06433a09967f9b1f06d --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/trainer_state.json @@ -0,0 +1,1662 @@ +{ + "best_metric": 1.205152153968811, + "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911", + "epoch": 4.998902305159166, + "eval_steps": 10, + "global_step": 2277, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.021953896816684963, + "grad_norm": 0.6144012212753296, + "learning_rate": 0.0002, + "loss": 1.9887, + "step": 10 + }, + { + "epoch": 0.043907793633369926, + "grad_norm": 0.5587220788002014, + "learning_rate": 0.0002, + "loss": 1.6882, + "step": 20 + }, + { + "epoch": 0.06586169045005488, + "grad_norm": 0.43262454867362976, + "learning_rate": 0.0002, + "loss": 1.399, + "step": 30 + }, + { + "epoch": 0.08781558726673985, + "grad_norm": 0.4783053994178772, + "learning_rate": 0.0002, + "loss": 1.4675, + "step": 40 + }, + { + "epoch": 0.10976948408342481, + "grad_norm": 0.44338956475257874, + "learning_rate": 0.0002, + "loss": 1.1771, + "step": 50 + }, + { + "epoch": 0.13172338090010977, + "grad_norm": 0.7255092263221741, + "learning_rate": 0.0002, + "loss": 1.3706, + "step": 60 + }, + { + "epoch": 0.15367727771679474, + "grad_norm": 0.46073833107948303, + "learning_rate": 0.0002, + "loss": 1.2601, + "step": 70 + }, + { + "epoch": 0.1756311745334797, + "grad_norm": 0.6698123216629028, + "learning_rate": 0.0002, + "loss": 1.3049, + "step": 80 + }, + { + "epoch": 0.19758507135016465, + "grad_norm": 0.4190150201320648, + "learning_rate": 0.0002, + "loss": 1.2975, + "step": 90 + }, + { + "epoch": 0.21953896816684962, + "grad_norm": 0.4110015034675598, + "learning_rate": 0.0002, + "loss": 1.2797, + "step": 100 + }, + { + "epoch": 0.2414928649835346, + "grad_norm": 0.33374306559562683, + "learning_rate": 0.0002, + "loss": 1.2896, + "step": 110 + }, + { + "epoch": 0.26344676180021953, + "grad_norm": 0.3061307370662689, + "learning_rate": 0.0002, + "loss": 1.2268, + "step": 120 + }, + { + "epoch": 0.2854006586169045, + "grad_norm": 0.4386885166168213, + "learning_rate": 0.0002, + "loss": 1.376, + "step": 130 + }, + { + "epoch": 0.30735455543358947, + "grad_norm": 0.40116462111473083, + "learning_rate": 0.0002, + "loss": 1.1814, + "step": 140 + }, + { + "epoch": 0.32930845225027444, + "grad_norm": 0.5887949466705322, + "learning_rate": 0.0002, + "loss": 1.2592, + "step": 150 + }, + { + "epoch": 0.3512623490669594, + "grad_norm": 0.3401573896408081, + "learning_rate": 0.0002, + "loss": 1.2372, + "step": 160 + }, + { + "epoch": 0.3732162458836443, + "grad_norm": 0.3288364112377167, + "learning_rate": 0.0002, + "loss": 1.1901, + "step": 170 + }, + { + "epoch": 0.3951701427003293, + "grad_norm": 0.4853297472000122, + "learning_rate": 0.0002, + "loss": 1.2335, + "step": 180 + }, + { + "epoch": 0.41712403951701427, + "grad_norm": 2.6253697872161865, + "learning_rate": 0.0002, + "loss": 1.227, + "step": 190 + }, + { + "epoch": 0.43907793633369924, + "grad_norm": 0.5598543286323547, + "learning_rate": 0.0002, + "loss": 1.2673, + "step": 200 + }, + { + "epoch": 0.4610318331503842, + "grad_norm": 0.4046548902988434, + "learning_rate": 0.0002, + "loss": 1.3459, + "step": 210 + }, + { + "epoch": 0.4829857299670692, + "grad_norm": 0.3686952590942383, + "learning_rate": 0.0002, + "loss": 1.265, + "step": 220 + }, + { + "epoch": 0.5049396267837541, + "grad_norm": 0.42458799481391907, + "learning_rate": 0.0002, + "loss": 1.1364, + "step": 230 + }, + { + "epoch": 0.5268935236004391, + "grad_norm": 0.5839895009994507, + "learning_rate": 0.0002, + "loss": 1.2094, + "step": 240 + }, + { + "epoch": 0.5488474204171241, + "grad_norm": 0.408288836479187, + "learning_rate": 0.0002, + "loss": 1.2073, + "step": 250 + }, + { + "epoch": 0.570801317233809, + "grad_norm": 0.45887550711631775, + "learning_rate": 0.0002, + "loss": 1.3121, + "step": 260 + }, + { + "epoch": 0.5927552140504939, + "grad_norm": 0.5440235733985901, + "learning_rate": 0.0002, + "loss": 1.2257, + "step": 270 + }, + { + "epoch": 0.6147091108671789, + "grad_norm": 0.3725181519985199, + "learning_rate": 0.0002, + "loss": 1.1003, + "step": 280 + }, + { + "epoch": 0.6366630076838639, + "grad_norm": 0.4309018850326538, + "learning_rate": 0.0002, + "loss": 1.1538, + "step": 290 + }, + { + "epoch": 0.6586169045005489, + "grad_norm": 0.31488674879074097, + "learning_rate": 0.0002, + "loss": 1.2097, + "step": 300 + }, + { + "epoch": 0.6805708013172338, + "grad_norm": 0.34194841980934143, + "learning_rate": 0.0002, + "loss": 1.1689, + "step": 310 + }, + { + "epoch": 0.7025246981339188, + "grad_norm": 0.3407684862613678, + "learning_rate": 0.0002, + "loss": 1.2579, + "step": 320 + }, + { + "epoch": 0.7244785949506037, + "grad_norm": 0.2985728085041046, + "learning_rate": 0.0002, + "loss": 1.1144, + "step": 330 + }, + { + "epoch": 0.7464324917672887, + "grad_norm": 0.42316871881484985, + "learning_rate": 0.0002, + "loss": 1.2056, + "step": 340 + }, + { + "epoch": 0.7683863885839737, + "grad_norm": 0.3124258816242218, + "learning_rate": 0.0002, + "loss": 1.1753, + "step": 350 + }, + { + "epoch": 0.7903402854006586, + "grad_norm": 0.7727567553520203, + "learning_rate": 0.0002, + "loss": 1.2547, + "step": 360 + }, + { + "epoch": 0.8122941822173436, + "grad_norm": 0.363765686750412, + "learning_rate": 0.0002, + "loss": 1.124, + "step": 370 + }, + { + "epoch": 0.8342480790340285, + "grad_norm": 0.35582536458969116, + "learning_rate": 0.0002, + "loss": 1.1302, + "step": 380 + }, + { + "epoch": 0.8562019758507134, + "grad_norm": 0.31982025504112244, + "learning_rate": 0.0002, + "loss": 1.1787, + "step": 390 + }, + { + "epoch": 0.8781558726673985, + "grad_norm": 0.34978964924812317, + "learning_rate": 0.0002, + "loss": 1.2056, + "step": 400 + }, + { + "epoch": 0.9001097694840834, + "grad_norm": 0.8346716165542603, + "learning_rate": 0.0002, + "loss": 1.3577, + "step": 410 + }, + { + "epoch": 0.9220636663007684, + "grad_norm": 0.31984028220176697, + "learning_rate": 0.0002, + "loss": 1.1029, + "step": 420 + }, + { + "epoch": 0.9440175631174533, + "grad_norm": 0.32078951597213745, + "learning_rate": 0.0002, + "loss": 1.0967, + "step": 430 + }, + { + "epoch": 0.9659714599341384, + "grad_norm": 0.3417500853538513, + "learning_rate": 0.0002, + "loss": 1.0936, + "step": 440 + }, + { + "epoch": 0.9879253567508233, + "grad_norm": 0.42359477281570435, + "learning_rate": 0.0002, + "loss": 1.3412, + "step": 450 + }, + { + "epoch": 0.9989023051591658, + "eval_loss": 1.2201528549194336, + "eval_runtime": 87.152, + "eval_samples_per_second": 4.945, + "eval_steps_per_second": 0.62, + "step": 455 + }, + { + "epoch": 1.0098792535675083, + "grad_norm": 0.37914523482322693, + "learning_rate": 0.0002, + "loss": 1.1909, + "step": 460 + }, + { + "epoch": 1.031833150384193, + "grad_norm": 0.43655872344970703, + "learning_rate": 0.0002, + "loss": 1.0948, + "step": 470 + }, + { + "epoch": 1.0537870472008781, + "grad_norm": 0.3673796057701111, + "learning_rate": 0.0002, + "loss": 1.0873, + "step": 480 + }, + { + "epoch": 1.0757409440175631, + "grad_norm": 0.37673917412757874, + "learning_rate": 0.0002, + "loss": 1.0483, + "step": 490 + }, + { + "epoch": 1.0976948408342482, + "grad_norm": 0.2893829345703125, + "learning_rate": 0.0002, + "loss": 1.0799, + "step": 500 + }, + { + "epoch": 1.119648737650933, + "grad_norm": 0.5551970601081848, + "learning_rate": 0.0002, + "loss": 1.1847, + "step": 510 + }, + { + "epoch": 1.141602634467618, + "grad_norm": 0.442104309797287, + "learning_rate": 0.0002, + "loss": 1.0885, + "step": 520 + }, + { + "epoch": 1.163556531284303, + "grad_norm": 0.4035094976425171, + "learning_rate": 0.0002, + "loss": 1.1766, + "step": 530 + }, + { + "epoch": 1.1855104281009878, + "grad_norm": 0.47009000182151794, + "learning_rate": 0.0002, + "loss": 1.0282, + "step": 540 + }, + { + "epoch": 1.2074643249176729, + "grad_norm": 0.4118749797344208, + "learning_rate": 0.0002, + "loss": 1.2625, + "step": 550 + }, + { + "epoch": 1.2294182217343579, + "grad_norm": 0.35173165798187256, + "learning_rate": 0.0002, + "loss": 1.0988, + "step": 560 + }, + { + "epoch": 1.2513721185510427, + "grad_norm": 0.7024672031402588, + "learning_rate": 0.0002, + "loss": 1.0498, + "step": 570 + }, + { + "epoch": 1.2733260153677277, + "grad_norm": 0.42657527327537537, + "learning_rate": 0.0002, + "loss": 1.1339, + "step": 580 + }, + { + "epoch": 1.2952799121844127, + "grad_norm": 0.3815029561519623, + "learning_rate": 0.0002, + "loss": 1.0545, + "step": 590 + }, + { + "epoch": 1.3172338090010978, + "grad_norm": 0.7031055688858032, + "learning_rate": 0.0002, + "loss": 1.1528, + "step": 600 + }, + { + "epoch": 1.3391877058177828, + "grad_norm": 0.393911212682724, + "learning_rate": 0.0002, + "loss": 1.1347, + "step": 610 + }, + { + "epoch": 1.3611416026344676, + "grad_norm": 0.5077702403068542, + "learning_rate": 0.0002, + "loss": 1.1901, + "step": 620 + }, + { + "epoch": 1.3830954994511526, + "grad_norm": 2.330033302307129, + "learning_rate": 0.0002, + "loss": 1.1251, + "step": 630 + }, + { + "epoch": 1.4050493962678376, + "grad_norm": 0.35322949290275574, + "learning_rate": 0.0002, + "loss": 1.0477, + "step": 640 + }, + { + "epoch": 1.4270032930845225, + "grad_norm": 0.44401052594184875, + "learning_rate": 0.0002, + "loss": 1.14, + "step": 650 + }, + { + "epoch": 1.4489571899012075, + "grad_norm": 0.35945481061935425, + "learning_rate": 0.0002, + "loss": 1.0318, + "step": 660 + }, + { + "epoch": 1.4709110867178925, + "grad_norm": 0.3058856129646301, + "learning_rate": 0.0002, + "loss": 1.1988, + "step": 670 + }, + { + "epoch": 1.4928649835345773, + "grad_norm": 0.7067602872848511, + "learning_rate": 0.0002, + "loss": 1.1545, + "step": 680 + }, + { + "epoch": 1.5148188803512623, + "grad_norm": 0.4219357371330261, + "learning_rate": 0.0002, + "loss": 1.0925, + "step": 690 + }, + { + "epoch": 1.5367727771679474, + "grad_norm": 0.5970841646194458, + "learning_rate": 0.0002, + "loss": 1.1622, + "step": 700 + }, + { + "epoch": 1.5587266739846322, + "grad_norm": 0.4381934404373169, + "learning_rate": 0.0002, + "loss": 1.0803, + "step": 710 + }, + { + "epoch": 1.5806805708013172, + "grad_norm": 0.4101450443267822, + "learning_rate": 0.0002, + "loss": 1.0961, + "step": 720 + }, + { + "epoch": 1.6026344676180022, + "grad_norm": 0.3657490015029907, + "learning_rate": 0.0002, + "loss": 1.0474, + "step": 730 + }, + { + "epoch": 1.624588364434687, + "grad_norm": 0.36240628361701965, + "learning_rate": 0.0002, + "loss": 1.0936, + "step": 740 + }, + { + "epoch": 1.6465422612513723, + "grad_norm": 0.4103568494319916, + "learning_rate": 0.0002, + "loss": 1.0489, + "step": 750 + }, + { + "epoch": 1.668496158068057, + "grad_norm": 0.3138505816459656, + "learning_rate": 0.0002, + "loss": 1.0919, + "step": 760 + }, + { + "epoch": 1.690450054884742, + "grad_norm": 0.41215717792510986, + "learning_rate": 0.0002, + "loss": 1.2308, + "step": 770 + }, + { + "epoch": 1.7124039517014271, + "grad_norm": 0.4589519202709198, + "learning_rate": 0.0002, + "loss": 1.1659, + "step": 780 + }, + { + "epoch": 1.734357848518112, + "grad_norm": 0.4049508571624756, + "learning_rate": 0.0002, + "loss": 1.0913, + "step": 790 + }, + { + "epoch": 1.756311745334797, + "grad_norm": 0.48557212948799133, + "learning_rate": 0.0002, + "loss": 1.1329, + "step": 800 + }, + { + "epoch": 1.778265642151482, + "grad_norm": 0.5331754088401794, + "learning_rate": 0.0002, + "loss": 1.0729, + "step": 810 + }, + { + "epoch": 1.8002195389681668, + "grad_norm": 0.3853185772895813, + "learning_rate": 0.0002, + "loss": 1.1452, + "step": 820 + }, + { + "epoch": 1.8221734357848518, + "grad_norm": 0.424062579870224, + "learning_rate": 0.0002, + "loss": 1.1061, + "step": 830 + }, + { + "epoch": 1.8441273326015368, + "grad_norm": 0.3418445289134979, + "learning_rate": 0.0002, + "loss": 1.1104, + "step": 840 + }, + { + "epoch": 1.8660812294182216, + "grad_norm": 0.4045565128326416, + "learning_rate": 0.0002, + "loss": 1.0546, + "step": 850 + }, + { + "epoch": 1.8880351262349067, + "grad_norm": 0.42155781388282776, + "learning_rate": 0.0002, + "loss": 1.1608, + "step": 860 + }, + { + "epoch": 1.9099890230515917, + "grad_norm": 0.40554770827293396, + "learning_rate": 0.0002, + "loss": 1.0628, + "step": 870 + }, + { + "epoch": 1.9319429198682765, + "grad_norm": 0.42644748091697693, + "learning_rate": 0.0002, + "loss": 1.1609, + "step": 880 + }, + { + "epoch": 1.9538968166849617, + "grad_norm": 0.45260652899742126, + "learning_rate": 0.0002, + "loss": 1.1132, + "step": 890 + }, + { + "epoch": 1.9758507135016465, + "grad_norm": 0.4114069938659668, + "learning_rate": 0.0002, + "loss": 1.048, + "step": 900 + }, + { + "epoch": 1.9978046103183313, + "grad_norm": 0.375802218914032, + "learning_rate": 0.0002, + "loss": 1.1941, + "step": 910 + }, + { + "epoch": 2.0, + "eval_loss": 1.205152153968811, + "eval_runtime": 86.8795, + "eval_samples_per_second": 4.961, + "eval_steps_per_second": 0.622, + "step": 911 + }, + { + "epoch": 2.0197585071350166, + "grad_norm": 0.47718703746795654, + "learning_rate": 0.0002, + "loss": 1.0897, + "step": 920 + }, + { + "epoch": 2.0417124039517014, + "grad_norm": 0.45628082752227783, + "learning_rate": 0.0002, + "loss": 1.0329, + "step": 930 + }, + { + "epoch": 2.063666300768386, + "grad_norm": 0.5933247804641724, + "learning_rate": 0.0002, + "loss": 1.0538, + "step": 940 + }, + { + "epoch": 2.0856201975850714, + "grad_norm": 0.5355812907218933, + "learning_rate": 0.0002, + "loss": 1.0152, + "step": 950 + }, + { + "epoch": 2.1075740944017562, + "grad_norm": 0.5860010385513306, + "learning_rate": 0.0002, + "loss": 1.0726, + "step": 960 + }, + { + "epoch": 2.129527991218441, + "grad_norm": 0.7471673488616943, + "learning_rate": 0.0002, + "loss": 1.025, + "step": 970 + }, + { + "epoch": 2.1514818880351263, + "grad_norm": 2.0918211936950684, + "learning_rate": 0.0002, + "loss": 1.0247, + "step": 980 + }, + { + "epoch": 2.173435784851811, + "grad_norm": 0.4021058678627014, + "learning_rate": 0.0002, + "loss": 0.8947, + "step": 990 + }, + { + "epoch": 2.1953896816684964, + "grad_norm": 0.564975380897522, + "learning_rate": 0.0002, + "loss": 0.8875, + "step": 1000 + }, + { + "epoch": 2.217343578485181, + "grad_norm": 0.46260079741477966, + "learning_rate": 0.0002, + "loss": 1.0264, + "step": 1010 + }, + { + "epoch": 2.239297475301866, + "grad_norm": 0.4791034460067749, + "learning_rate": 0.0002, + "loss": 0.9265, + "step": 1020 + }, + { + "epoch": 2.261251372118551, + "grad_norm": 0.5272043943405151, + "learning_rate": 0.0002, + "loss": 0.8869, + "step": 1030 + }, + { + "epoch": 2.283205268935236, + "grad_norm": 0.5221094489097595, + "learning_rate": 0.0002, + "loss": 1.0007, + "step": 1040 + }, + { + "epoch": 2.305159165751921, + "grad_norm": 0.558032751083374, + "learning_rate": 0.0002, + "loss": 0.9472, + "step": 1050 + }, + { + "epoch": 2.327113062568606, + "grad_norm": 0.5905590653419495, + "learning_rate": 0.0002, + "loss": 0.9617, + "step": 1060 + }, + { + "epoch": 2.349066959385291, + "grad_norm": 0.5308699607849121, + "learning_rate": 0.0002, + "loss": 0.9592, + "step": 1070 + }, + { + "epoch": 2.3710208562019757, + "grad_norm": 0.6375027894973755, + "learning_rate": 0.0002, + "loss": 1.0646, + "step": 1080 + }, + { + "epoch": 2.392974753018661, + "grad_norm": 0.7439115643501282, + "learning_rate": 0.0002, + "loss": 1.0354, + "step": 1090 + }, + { + "epoch": 2.4149286498353457, + "grad_norm": 0.41945117712020874, + "learning_rate": 0.0002, + "loss": 1.0212, + "step": 1100 + }, + { + "epoch": 2.436882546652031, + "grad_norm": 0.4891968369483948, + "learning_rate": 0.0002, + "loss": 0.9609, + "step": 1110 + }, + { + "epoch": 2.4588364434687158, + "grad_norm": 0.4686794579029083, + "learning_rate": 0.0002, + "loss": 0.9829, + "step": 1120 + }, + { + "epoch": 2.4807903402854006, + "grad_norm": 0.5204509496688843, + "learning_rate": 0.0002, + "loss": 0.8919, + "step": 1130 + }, + { + "epoch": 2.5027442371020854, + "grad_norm": 0.6779005527496338, + "learning_rate": 0.0002, + "loss": 0.8983, + "step": 1140 + }, + { + "epoch": 2.5246981339187706, + "grad_norm": 0.682621955871582, + "learning_rate": 0.0002, + "loss": 0.9733, + "step": 1150 + }, + { + "epoch": 2.5466520307354554, + "grad_norm": 0.5744376182556152, + "learning_rate": 0.0002, + "loss": 1.051, + "step": 1160 + }, + { + "epoch": 2.5686059275521407, + "grad_norm": 0.49954667687416077, + "learning_rate": 0.0002, + "loss": 0.8764, + "step": 1170 + }, + { + "epoch": 2.5905598243688255, + "grad_norm": 0.4761793315410614, + "learning_rate": 0.0002, + "loss": 0.9896, + "step": 1180 + }, + { + "epoch": 2.6125137211855103, + "grad_norm": 0.548299252986908, + "learning_rate": 0.0002, + "loss": 0.8593, + "step": 1190 + }, + { + "epoch": 2.6344676180021955, + "grad_norm": 0.5771360993385315, + "learning_rate": 0.0002, + "loss": 1.0017, + "step": 1200 + }, + { + "epoch": 2.6564215148188803, + "grad_norm": 0.5543120503425598, + "learning_rate": 0.0002, + "loss": 0.9858, + "step": 1210 + }, + { + "epoch": 2.6783754116355656, + "grad_norm": 0.7564870715141296, + "learning_rate": 0.0002, + "loss": 0.9565, + "step": 1220 + }, + { + "epoch": 2.7003293084522504, + "grad_norm": 0.8222362399101257, + "learning_rate": 0.0002, + "loss": 0.9753, + "step": 1230 + }, + { + "epoch": 2.722283205268935, + "grad_norm": 0.6894469857215881, + "learning_rate": 0.0002, + "loss": 1.0079, + "step": 1240 + }, + { + "epoch": 2.74423710208562, + "grad_norm": 0.6121546030044556, + "learning_rate": 0.0002, + "loss": 1.0106, + "step": 1250 + }, + { + "epoch": 2.7661909989023052, + "grad_norm": 0.521809995174408, + "learning_rate": 0.0002, + "loss": 0.9801, + "step": 1260 + }, + { + "epoch": 2.78814489571899, + "grad_norm": 0.766968309879303, + "learning_rate": 0.0002, + "loss": 1.0196, + "step": 1270 + }, + { + "epoch": 2.8100987925356753, + "grad_norm": 0.522331714630127, + "learning_rate": 0.0002, + "loss": 0.976, + "step": 1280 + }, + { + "epoch": 2.83205268935236, + "grad_norm": 0.42923519015312195, + "learning_rate": 0.0002, + "loss": 0.8866, + "step": 1290 + }, + { + "epoch": 2.854006586169045, + "grad_norm": 0.47810837626457214, + "learning_rate": 0.0002, + "loss": 0.9049, + "step": 1300 + }, + { + "epoch": 2.8759604829857297, + "grad_norm": 1.0958846807479858, + "learning_rate": 0.0002, + "loss": 1.0291, + "step": 1310 + }, + { + "epoch": 2.897914379802415, + "grad_norm": 0.4755791127681732, + "learning_rate": 0.0002, + "loss": 0.8724, + "step": 1320 + }, + { + "epoch": 2.9198682766190998, + "grad_norm": 0.5575157403945923, + "learning_rate": 0.0002, + "loss": 0.9317, + "step": 1330 + }, + { + "epoch": 2.941822173435785, + "grad_norm": 0.5938076376914978, + "learning_rate": 0.0002, + "loss": 1.0131, + "step": 1340 + }, + { + "epoch": 2.96377607025247, + "grad_norm": 0.5751763582229614, + "learning_rate": 0.0002, + "loss": 0.9857, + "step": 1350 + }, + { + "epoch": 2.9857299670691546, + "grad_norm": 0.5590175986289978, + "learning_rate": 0.0002, + "loss": 1.0212, + "step": 1360 + }, + { + "epoch": 2.9989023051591657, + "eval_loss": 1.2402944564819336, + "eval_runtime": 88.822, + "eval_samples_per_second": 4.852, + "eval_steps_per_second": 0.608, + "step": 1366 + }, + { + "epoch": 3.00768386388584, + "grad_norm": 0.463539719581604, + "learning_rate": 0.0002, + "loss": 0.844, + "step": 1370 + }, + { + "epoch": 3.0296377607025247, + "grad_norm": 0.6667885780334473, + "learning_rate": 0.0002, + "loss": 0.8955, + "step": 1380 + }, + { + "epoch": 3.0515916575192095, + "grad_norm": 0.5849342942237854, + "learning_rate": 0.0002, + "loss": 0.8765, + "step": 1390 + }, + { + "epoch": 3.0735455543358947, + "grad_norm": 0.5571770668029785, + "learning_rate": 0.0002, + "loss": 0.7808, + "step": 1400 + }, + { + "epoch": 3.0954994511525795, + "grad_norm": 0.5761234164237976, + "learning_rate": 0.0002, + "loss": 0.7448, + "step": 1410 + }, + { + "epoch": 3.1174533479692643, + "grad_norm": 0.7277371883392334, + "learning_rate": 0.0002, + "loss": 0.7854, + "step": 1420 + }, + { + "epoch": 3.1394072447859496, + "grad_norm": 0.5190334320068359, + "learning_rate": 0.0002, + "loss": 0.817, + "step": 1430 + }, + { + "epoch": 3.1613611416026344, + "grad_norm": 0.632939875125885, + "learning_rate": 0.0002, + "loss": 0.7548, + "step": 1440 + }, + { + "epoch": 3.1833150384193196, + "grad_norm": 0.7229540944099426, + "learning_rate": 0.0002, + "loss": 0.8447, + "step": 1450 + }, + { + "epoch": 3.2052689352360044, + "grad_norm": 0.7584632039070129, + "learning_rate": 0.0002, + "loss": 0.8595, + "step": 1460 + }, + { + "epoch": 3.2272228320526892, + "grad_norm": 0.6546088457107544, + "learning_rate": 0.0002, + "loss": 0.7456, + "step": 1470 + }, + { + "epoch": 3.2491767288693745, + "grad_norm": 0.8116684556007385, + "learning_rate": 0.0002, + "loss": 0.8531, + "step": 1480 + }, + { + "epoch": 3.2711306256860593, + "grad_norm": 0.6206557750701904, + "learning_rate": 0.0002, + "loss": 0.9272, + "step": 1490 + }, + { + "epoch": 3.293084522502744, + "grad_norm": 0.5393369197845459, + "learning_rate": 0.0002, + "loss": 0.7972, + "step": 1500 + }, + { + "epoch": 3.3150384193194293, + "grad_norm": 0.7006453275680542, + "learning_rate": 0.0002, + "loss": 0.7614, + "step": 1510 + }, + { + "epoch": 3.336992316136114, + "grad_norm": 0.95253986120224, + "learning_rate": 0.0002, + "loss": 0.7358, + "step": 1520 + }, + { + "epoch": 3.358946212952799, + "grad_norm": 0.8138132095336914, + "learning_rate": 0.0002, + "loss": 0.8131, + "step": 1530 + }, + { + "epoch": 3.380900109769484, + "grad_norm": 0.7974302172660828, + "learning_rate": 0.0002, + "loss": 0.7738, + "step": 1540 + }, + { + "epoch": 3.402854006586169, + "grad_norm": 0.6694685220718384, + "learning_rate": 0.0002, + "loss": 0.8161, + "step": 1550 + }, + { + "epoch": 3.4248079034028542, + "grad_norm": 0.908634603023529, + "learning_rate": 0.0002, + "loss": 0.8503, + "step": 1560 + }, + { + "epoch": 3.446761800219539, + "grad_norm": 0.5625193119049072, + "learning_rate": 0.0002, + "loss": 0.7609, + "step": 1570 + }, + { + "epoch": 3.468715697036224, + "grad_norm": 0.779325544834137, + "learning_rate": 0.0002, + "loss": 0.7658, + "step": 1580 + }, + { + "epoch": 3.4906695938529086, + "grad_norm": 0.7133058905601501, + "learning_rate": 0.0002, + "loss": 0.7485, + "step": 1590 + }, + { + "epoch": 3.512623490669594, + "grad_norm": 0.6741108298301697, + "learning_rate": 0.0002, + "loss": 0.8847, + "step": 1600 + }, + { + "epoch": 3.5345773874862787, + "grad_norm": 0.696982204914093, + "learning_rate": 0.0002, + "loss": 0.7838, + "step": 1610 + }, + { + "epoch": 3.556531284302964, + "grad_norm": 0.7946001291275024, + "learning_rate": 0.0002, + "loss": 0.7195, + "step": 1620 + }, + { + "epoch": 3.5784851811196488, + "grad_norm": 0.6313548684120178, + "learning_rate": 0.0002, + "loss": 0.7772, + "step": 1630 + }, + { + "epoch": 3.6004390779363336, + "grad_norm": 0.9246852397918701, + "learning_rate": 0.0002, + "loss": 0.8267, + "step": 1640 + }, + { + "epoch": 3.622392974753019, + "grad_norm": 0.6615420579910278, + "learning_rate": 0.0002, + "loss": 0.779, + "step": 1650 + }, + { + "epoch": 3.6443468715697036, + "grad_norm": 1.5050125122070312, + "learning_rate": 0.0002, + "loss": 0.883, + "step": 1660 + }, + { + "epoch": 3.666300768386389, + "grad_norm": 0.5023762583732605, + "learning_rate": 0.0002, + "loss": 0.7763, + "step": 1670 + }, + { + "epoch": 3.6882546652030737, + "grad_norm": 0.6289586424827576, + "learning_rate": 0.0002, + "loss": 0.8173, + "step": 1680 + }, + { + "epoch": 3.7102085620197585, + "grad_norm": 1.050397515296936, + "learning_rate": 0.0002, + "loss": 0.9028, + "step": 1690 + }, + { + "epoch": 3.7321624588364433, + "grad_norm": 0.6785626411437988, + "learning_rate": 0.0002, + "loss": 0.7747, + "step": 1700 + }, + { + "epoch": 3.7541163556531285, + "grad_norm": 0.7565035223960876, + "learning_rate": 0.0002, + "loss": 0.9215, + "step": 1710 + }, + { + "epoch": 3.7760702524698133, + "grad_norm": 0.7775155901908875, + "learning_rate": 0.0002, + "loss": 0.7913, + "step": 1720 + }, + { + "epoch": 3.7980241492864986, + "grad_norm": 0.765260636806488, + "learning_rate": 0.0002, + "loss": 0.8081, + "step": 1730 + }, + { + "epoch": 3.8199780461031834, + "grad_norm": 0.7982407808303833, + "learning_rate": 0.0002, + "loss": 0.9231, + "step": 1740 + }, + { + "epoch": 3.841931942919868, + "grad_norm": 0.7431730628013611, + "learning_rate": 0.0002, + "loss": 0.7755, + "step": 1750 + }, + { + "epoch": 3.863885839736553, + "grad_norm": 0.9758927226066589, + "learning_rate": 0.0002, + "loss": 0.9236, + "step": 1760 + }, + { + "epoch": 3.885839736553238, + "grad_norm": 0.8014697432518005, + "learning_rate": 0.0002, + "loss": 0.9118, + "step": 1770 + }, + { + "epoch": 3.907793633369923, + "grad_norm": 0.7212756276130676, + "learning_rate": 0.0002, + "loss": 0.7503, + "step": 1780 + }, + { + "epoch": 3.9297475301866083, + "grad_norm": 0.584318220615387, + "learning_rate": 0.0002, + "loss": 0.7978, + "step": 1790 + }, + { + "epoch": 3.951701427003293, + "grad_norm": 0.7612535953521729, + "learning_rate": 0.0002, + "loss": 0.7894, + "step": 1800 + }, + { + "epoch": 3.973655323819978, + "grad_norm": 0.735103189945221, + "learning_rate": 0.0002, + "loss": 0.8589, + "step": 1810 + }, + { + "epoch": 3.995609220636663, + "grad_norm": 0.9074980020523071, + "learning_rate": 0.0002, + "loss": 0.8192, + "step": 1820 + }, + { + "epoch": 4.0, + "eval_loss": 1.279890537261963, + "eval_runtime": 88.8969, + "eval_samples_per_second": 4.848, + "eval_steps_per_second": 0.607, + "step": 1822 + }, + { + "epoch": 4.017563117453348, + "grad_norm": 0.9290254712104797, + "learning_rate": 0.0002, + "loss": 0.7312, + "step": 1830 + }, + { + "epoch": 4.039517014270033, + "grad_norm": 0.723889946937561, + "learning_rate": 0.0002, + "loss": 0.6896, + "step": 1840 + }, + { + "epoch": 4.061470911086718, + "grad_norm": 0.5906972289085388, + "learning_rate": 0.0002, + "loss": 0.632, + "step": 1850 + }, + { + "epoch": 4.083424807903403, + "grad_norm": 0.8078910708427429, + "learning_rate": 0.0002, + "loss": 0.6594, + "step": 1860 + }, + { + "epoch": 4.105378704720088, + "grad_norm": 1.0101137161254883, + "learning_rate": 0.0002, + "loss": 0.6242, + "step": 1870 + }, + { + "epoch": 4.127332601536772, + "grad_norm": 0.8710281848907471, + "learning_rate": 0.0002, + "loss": 0.7259, + "step": 1880 + }, + { + "epoch": 4.149286498353458, + "grad_norm": 0.9604734778404236, + "learning_rate": 0.0002, + "loss": 0.6993, + "step": 1890 + }, + { + "epoch": 4.171240395170143, + "grad_norm": 0.9829702377319336, + "learning_rate": 0.0002, + "loss": 0.6706, + "step": 1900 + }, + { + "epoch": 4.193194291986828, + "grad_norm": 0.6572765707969666, + "learning_rate": 0.0002, + "loss": 0.7013, + "step": 1910 + }, + { + "epoch": 4.2151481888035125, + "grad_norm": 0.8459188938140869, + "learning_rate": 0.0002, + "loss": 0.5539, + "step": 1920 + }, + { + "epoch": 4.237102085620197, + "grad_norm": 0.8321021795272827, + "learning_rate": 0.0002, + "loss": 0.6235, + "step": 1930 + }, + { + "epoch": 4.259055982436882, + "grad_norm": 0.8611727356910706, + "learning_rate": 0.0002, + "loss": 0.6442, + "step": 1940 + }, + { + "epoch": 4.281009879253568, + "grad_norm": 0.8490208387374878, + "learning_rate": 0.0002, + "loss": 0.6852, + "step": 1950 + }, + { + "epoch": 4.302963776070253, + "grad_norm": 0.9628722667694092, + "learning_rate": 0.0002, + "loss": 0.6175, + "step": 1960 + }, + { + "epoch": 4.324917672886937, + "grad_norm": 0.9632807374000549, + "learning_rate": 0.0002, + "loss": 0.5982, + "step": 1970 + }, + { + "epoch": 4.346871569703622, + "grad_norm": 0.7023298740386963, + "learning_rate": 0.0002, + "loss": 0.6138, + "step": 1980 + }, + { + "epoch": 4.368825466520307, + "grad_norm": 0.7912909388542175, + "learning_rate": 0.0002, + "loss": 0.6012, + "step": 1990 + }, + { + "epoch": 4.390779363336993, + "grad_norm": 1.1463429927825928, + "learning_rate": 0.0002, + "loss": 0.6767, + "step": 2000 + }, + { + "epoch": 4.4127332601536775, + "grad_norm": 1.1780626773834229, + "learning_rate": 0.0002, + "loss": 0.6607, + "step": 2010 + }, + { + "epoch": 4.434687156970362, + "grad_norm": 0.9349206686019897, + "learning_rate": 0.0002, + "loss": 0.6746, + "step": 2020 + }, + { + "epoch": 4.456641053787047, + "grad_norm": 0.7816639542579651, + "learning_rate": 0.0002, + "loss": 0.7087, + "step": 2030 + }, + { + "epoch": 4.478594950603732, + "grad_norm": 0.7005311250686646, + "learning_rate": 0.0002, + "loss": 0.6222, + "step": 2040 + }, + { + "epoch": 4.500548847420417, + "grad_norm": 0.7746558785438538, + "learning_rate": 0.0002, + "loss": 0.6608, + "step": 2050 + }, + { + "epoch": 4.522502744237102, + "grad_norm": 0.8261151313781738, + "learning_rate": 0.0002, + "loss": 0.6305, + "step": 2060 + }, + { + "epoch": 4.544456641053787, + "grad_norm": 1.0917805433273315, + "learning_rate": 0.0002, + "loss": 0.6502, + "step": 2070 + }, + { + "epoch": 4.566410537870472, + "grad_norm": 1.1570647954940796, + "learning_rate": 0.0002, + "loss": 0.6798, + "step": 2080 + }, + { + "epoch": 4.588364434687157, + "grad_norm": 0.9936433434486389, + "learning_rate": 0.0002, + "loss": 0.6296, + "step": 2090 + }, + { + "epoch": 4.610318331503842, + "grad_norm": 0.8574427366256714, + "learning_rate": 0.0002, + "loss": 0.5936, + "step": 2100 + }, + { + "epoch": 4.632272228320527, + "grad_norm": 0.7630168795585632, + "learning_rate": 0.0002, + "loss": 0.6529, + "step": 2110 + }, + { + "epoch": 4.654226125137212, + "grad_norm": 0.8146462440490723, + "learning_rate": 0.0002, + "loss": 0.5935, + "step": 2120 + }, + { + "epoch": 4.676180021953897, + "grad_norm": 0.7090407609939575, + "learning_rate": 0.0002, + "loss": 0.7102, + "step": 2130 + }, + { + "epoch": 4.698133918770582, + "grad_norm": 0.8278160095214844, + "learning_rate": 0.0002, + "loss": 0.6575, + "step": 2140 + }, + { + "epoch": 4.7200878155872665, + "grad_norm": 0.9415683746337891, + "learning_rate": 0.0002, + "loss": 0.664, + "step": 2150 + }, + { + "epoch": 4.742041712403951, + "grad_norm": 1.0056205987930298, + "learning_rate": 0.0002, + "loss": 0.7283, + "step": 2160 + }, + { + "epoch": 4.763995609220637, + "grad_norm": 0.768304705619812, + "learning_rate": 0.0002, + "loss": 0.6845, + "step": 2170 + }, + { + "epoch": 4.785949506037322, + "grad_norm": 1.0604112148284912, + "learning_rate": 0.0002, + "loss": 0.6922, + "step": 2180 + }, + { + "epoch": 4.807903402854007, + "grad_norm": 1.132864236831665, + "learning_rate": 0.0002, + "loss": 0.7092, + "step": 2190 + }, + { + "epoch": 4.829857299670691, + "grad_norm": 0.7543689608573914, + "learning_rate": 0.0002, + "loss": 0.6936, + "step": 2200 + }, + { + "epoch": 4.851811196487376, + "grad_norm": 0.8047362565994263, + "learning_rate": 0.0002, + "loss": 0.6921, + "step": 2210 + }, + { + "epoch": 4.873765093304062, + "grad_norm": 1.135778546333313, + "learning_rate": 0.0002, + "loss": 0.6753, + "step": 2220 + }, + { + "epoch": 4.895718990120747, + "grad_norm": 0.9068503379821777, + "learning_rate": 0.0002, + "loss": 0.6443, + "step": 2230 + }, + { + "epoch": 4.9176728869374315, + "grad_norm": 1.822325587272644, + "learning_rate": 0.0002, + "loss": 0.7419, + "step": 2240 + }, + { + "epoch": 4.939626783754116, + "grad_norm": 1.1124998331069946, + "learning_rate": 0.0002, + "loss": 0.6436, + "step": 2250 + }, + { + "epoch": 4.961580680570801, + "grad_norm": 0.818484365940094, + "learning_rate": 0.0002, + "loss": 0.7423, + "step": 2260 + }, + { + "epoch": 4.983534577387486, + "grad_norm": 1.0057194232940674, + "learning_rate": 0.0002, + "loss": 0.6872, + "step": 2270 + }, + { + "epoch": 4.998902305159166, + "eval_loss": 1.4120490550994873, + "eval_runtime": 87.5617, + "eval_samples_per_second": 4.922, + "eval_steps_per_second": 0.617, + "step": 2277 + } + ], + "logging_steps": 10, + "max_steps": 3640, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.0539760047095808e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f75755c7cf71aeb05b76db2632173f96f74e8f7 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf90ce7dd53cc68edd44d14e30ca84a5d7431a5b99d4697b17af4b2f7ec0abab +size 5624 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/README.md b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/README.md new file mode 100644 index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/README.md @@ -0,0 +1,202 @@ +--- +base_model: meta-llama/Meta-Llama-3-8B-Instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.13.1 \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..406c5a08dc4a2a33b52c62a482f98c217c417215 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "v_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8bb219ac5da6a931f5ae269e6647f204d01b0737 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:667c6b4ac631a3df51962f967def2173f4f013fddf97a06dda77a5b8b45e00ea +size 109069176 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/optimizer.pt b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..ba7659727cc377418e824a870cfa25847a778483 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f960eb6a99562ea0e9bd182ec9a173484345481d091a1a4369799782144d5793 +size 55532666 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/rng_state.pth b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..9f4a93e3a3fb3b393ba4fd92658d7c77acafef61 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4510bdee8ebac6ee997ff7dd13f372e8fdf526e7ba9626c7c8dd9aaff07746d5 +size 14244 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/scheduler.pt b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d92c37045ff57c619fe398f344c1086e690ed62 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:945550866d1df72da91321b3e6aeb168119fb3964ab6ca020def3cdd749b589e +size 1064 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393 +size 17209961 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|eot_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/trainer_state.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..fdbb8e274e8d14ce270256613461cac128b84952 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/trainer_state.json @@ -0,0 +1,1992 @@ +{ + "best_metric": 1.205152153968811, + "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911", + "epoch": 6.0, + "eval_steps": 10, + "global_step": 2733, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.021953896816684963, + "grad_norm": 0.6144012212753296, + "learning_rate": 0.0002, + "loss": 1.9887, + "step": 10 + }, + { + "epoch": 0.043907793633369926, + "grad_norm": 0.5587220788002014, + "learning_rate": 0.0002, + "loss": 1.6882, + "step": 20 + }, + { + "epoch": 0.06586169045005488, + "grad_norm": 0.43262454867362976, + "learning_rate": 0.0002, + "loss": 1.399, + "step": 30 + }, + { + "epoch": 0.08781558726673985, + "grad_norm": 0.4783053994178772, + "learning_rate": 0.0002, + "loss": 1.4675, + "step": 40 + }, + { + "epoch": 0.10976948408342481, + "grad_norm": 0.44338956475257874, + "learning_rate": 0.0002, + "loss": 1.1771, + "step": 50 + }, + { + "epoch": 0.13172338090010977, + "grad_norm": 0.7255092263221741, + "learning_rate": 0.0002, + "loss": 1.3706, + "step": 60 + }, + { + "epoch": 0.15367727771679474, + "grad_norm": 0.46073833107948303, + "learning_rate": 0.0002, + "loss": 1.2601, + "step": 70 + }, + { + "epoch": 0.1756311745334797, + "grad_norm": 0.6698123216629028, + "learning_rate": 0.0002, + "loss": 1.3049, + "step": 80 + }, + { + "epoch": 0.19758507135016465, + "grad_norm": 0.4190150201320648, + "learning_rate": 0.0002, + "loss": 1.2975, + "step": 90 + }, + { + "epoch": 0.21953896816684962, + "grad_norm": 0.4110015034675598, + "learning_rate": 0.0002, + "loss": 1.2797, + "step": 100 + }, + { + "epoch": 0.2414928649835346, + "grad_norm": 0.33374306559562683, + "learning_rate": 0.0002, + "loss": 1.2896, + "step": 110 + }, + { + "epoch": 0.26344676180021953, + "grad_norm": 0.3061307370662689, + "learning_rate": 0.0002, + "loss": 1.2268, + "step": 120 + }, + { + "epoch": 0.2854006586169045, + "grad_norm": 0.4386885166168213, + "learning_rate": 0.0002, + "loss": 1.376, + "step": 130 + }, + { + "epoch": 0.30735455543358947, + "grad_norm": 0.40116462111473083, + "learning_rate": 0.0002, + "loss": 1.1814, + "step": 140 + }, + { + "epoch": 0.32930845225027444, + "grad_norm": 0.5887949466705322, + "learning_rate": 0.0002, + "loss": 1.2592, + "step": 150 + }, + { + "epoch": 0.3512623490669594, + "grad_norm": 0.3401573896408081, + "learning_rate": 0.0002, + "loss": 1.2372, + "step": 160 + }, + { + "epoch": 0.3732162458836443, + "grad_norm": 0.3288364112377167, + "learning_rate": 0.0002, + "loss": 1.1901, + "step": 170 + }, + { + "epoch": 0.3951701427003293, + "grad_norm": 0.4853297472000122, + "learning_rate": 0.0002, + "loss": 1.2335, + "step": 180 + }, + { + "epoch": 0.41712403951701427, + "grad_norm": 2.6253697872161865, + "learning_rate": 0.0002, + "loss": 1.227, + "step": 190 + }, + { + "epoch": 0.43907793633369924, + "grad_norm": 0.5598543286323547, + "learning_rate": 0.0002, + "loss": 1.2673, + "step": 200 + }, + { + "epoch": 0.4610318331503842, + "grad_norm": 0.4046548902988434, + "learning_rate": 0.0002, + "loss": 1.3459, + "step": 210 + }, + { + "epoch": 0.4829857299670692, + "grad_norm": 0.3686952590942383, + "learning_rate": 0.0002, + "loss": 1.265, + "step": 220 + }, + { + "epoch": 0.5049396267837541, + "grad_norm": 0.42458799481391907, + "learning_rate": 0.0002, + "loss": 1.1364, + "step": 230 + }, + { + "epoch": 0.5268935236004391, + "grad_norm": 0.5839895009994507, + "learning_rate": 0.0002, + "loss": 1.2094, + "step": 240 + }, + { + "epoch": 0.5488474204171241, + "grad_norm": 0.408288836479187, + "learning_rate": 0.0002, + "loss": 1.2073, + "step": 250 + }, + { + "epoch": 0.570801317233809, + "grad_norm": 0.45887550711631775, + "learning_rate": 0.0002, + "loss": 1.3121, + "step": 260 + }, + { + "epoch": 0.5927552140504939, + "grad_norm": 0.5440235733985901, + "learning_rate": 0.0002, + "loss": 1.2257, + "step": 270 + }, + { + "epoch": 0.6147091108671789, + "grad_norm": 0.3725181519985199, + "learning_rate": 0.0002, + "loss": 1.1003, + "step": 280 + }, + { + "epoch": 0.6366630076838639, + "grad_norm": 0.4309018850326538, + "learning_rate": 0.0002, + "loss": 1.1538, + "step": 290 + }, + { + "epoch": 0.6586169045005489, + "grad_norm": 0.31488674879074097, + "learning_rate": 0.0002, + "loss": 1.2097, + "step": 300 + }, + { + "epoch": 0.6805708013172338, + "grad_norm": 0.34194841980934143, + "learning_rate": 0.0002, + "loss": 1.1689, + "step": 310 + }, + { + "epoch": 0.7025246981339188, + "grad_norm": 0.3407684862613678, + "learning_rate": 0.0002, + "loss": 1.2579, + "step": 320 + }, + { + "epoch": 0.7244785949506037, + "grad_norm": 0.2985728085041046, + "learning_rate": 0.0002, + "loss": 1.1144, + "step": 330 + }, + { + "epoch": 0.7464324917672887, + "grad_norm": 0.42316871881484985, + "learning_rate": 0.0002, + "loss": 1.2056, + "step": 340 + }, + { + "epoch": 0.7683863885839737, + "grad_norm": 0.3124258816242218, + "learning_rate": 0.0002, + "loss": 1.1753, + "step": 350 + }, + { + "epoch": 0.7903402854006586, + "grad_norm": 0.7727567553520203, + "learning_rate": 0.0002, + "loss": 1.2547, + "step": 360 + }, + { + "epoch": 0.8122941822173436, + "grad_norm": 0.363765686750412, + "learning_rate": 0.0002, + "loss": 1.124, + "step": 370 + }, + { + "epoch": 0.8342480790340285, + "grad_norm": 0.35582536458969116, + "learning_rate": 0.0002, + "loss": 1.1302, + "step": 380 + }, + { + "epoch": 0.8562019758507134, + "grad_norm": 0.31982025504112244, + "learning_rate": 0.0002, + "loss": 1.1787, + "step": 390 + }, + { + "epoch": 0.8781558726673985, + "grad_norm": 0.34978964924812317, + "learning_rate": 0.0002, + "loss": 1.2056, + "step": 400 + }, + { + "epoch": 0.9001097694840834, + "grad_norm": 0.8346716165542603, + "learning_rate": 0.0002, + "loss": 1.3577, + "step": 410 + }, + { + "epoch": 0.9220636663007684, + "grad_norm": 0.31984028220176697, + "learning_rate": 0.0002, + "loss": 1.1029, + "step": 420 + }, + { + "epoch": 0.9440175631174533, + "grad_norm": 0.32078951597213745, + "learning_rate": 0.0002, + "loss": 1.0967, + "step": 430 + }, + { + "epoch": 0.9659714599341384, + "grad_norm": 0.3417500853538513, + "learning_rate": 0.0002, + "loss": 1.0936, + "step": 440 + }, + { + "epoch": 0.9879253567508233, + "grad_norm": 0.42359477281570435, + "learning_rate": 0.0002, + "loss": 1.3412, + "step": 450 + }, + { + "epoch": 0.9989023051591658, + "eval_loss": 1.2201528549194336, + "eval_runtime": 87.152, + "eval_samples_per_second": 4.945, + "eval_steps_per_second": 0.62, + "step": 455 + }, + { + "epoch": 1.0098792535675083, + "grad_norm": 0.37914523482322693, + "learning_rate": 0.0002, + "loss": 1.1909, + "step": 460 + }, + { + "epoch": 1.031833150384193, + "grad_norm": 0.43655872344970703, + "learning_rate": 0.0002, + "loss": 1.0948, + "step": 470 + }, + { + "epoch": 1.0537870472008781, + "grad_norm": 0.3673796057701111, + "learning_rate": 0.0002, + "loss": 1.0873, + "step": 480 + }, + { + "epoch": 1.0757409440175631, + "grad_norm": 0.37673917412757874, + "learning_rate": 0.0002, + "loss": 1.0483, + "step": 490 + }, + { + "epoch": 1.0976948408342482, + "grad_norm": 0.2893829345703125, + "learning_rate": 0.0002, + "loss": 1.0799, + "step": 500 + }, + { + "epoch": 1.119648737650933, + "grad_norm": 0.5551970601081848, + "learning_rate": 0.0002, + "loss": 1.1847, + "step": 510 + }, + { + "epoch": 1.141602634467618, + "grad_norm": 0.442104309797287, + "learning_rate": 0.0002, + "loss": 1.0885, + "step": 520 + }, + { + "epoch": 1.163556531284303, + "grad_norm": 0.4035094976425171, + "learning_rate": 0.0002, + "loss": 1.1766, + "step": 530 + }, + { + "epoch": 1.1855104281009878, + "grad_norm": 0.47009000182151794, + "learning_rate": 0.0002, + "loss": 1.0282, + "step": 540 + }, + { + "epoch": 1.2074643249176729, + "grad_norm": 0.4118749797344208, + "learning_rate": 0.0002, + "loss": 1.2625, + "step": 550 + }, + { + "epoch": 1.2294182217343579, + "grad_norm": 0.35173165798187256, + "learning_rate": 0.0002, + "loss": 1.0988, + "step": 560 + }, + { + "epoch": 1.2513721185510427, + "grad_norm": 0.7024672031402588, + "learning_rate": 0.0002, + "loss": 1.0498, + "step": 570 + }, + { + "epoch": 1.2733260153677277, + "grad_norm": 0.42657527327537537, + "learning_rate": 0.0002, + "loss": 1.1339, + "step": 580 + }, + { + "epoch": 1.2952799121844127, + "grad_norm": 0.3815029561519623, + "learning_rate": 0.0002, + "loss": 1.0545, + "step": 590 + }, + { + "epoch": 1.3172338090010978, + "grad_norm": 0.7031055688858032, + "learning_rate": 0.0002, + "loss": 1.1528, + "step": 600 + }, + { + "epoch": 1.3391877058177828, + "grad_norm": 0.393911212682724, + "learning_rate": 0.0002, + "loss": 1.1347, + "step": 610 + }, + { + "epoch": 1.3611416026344676, + "grad_norm": 0.5077702403068542, + "learning_rate": 0.0002, + "loss": 1.1901, + "step": 620 + }, + { + "epoch": 1.3830954994511526, + "grad_norm": 2.330033302307129, + "learning_rate": 0.0002, + "loss": 1.1251, + "step": 630 + }, + { + "epoch": 1.4050493962678376, + "grad_norm": 0.35322949290275574, + "learning_rate": 0.0002, + "loss": 1.0477, + "step": 640 + }, + { + "epoch": 1.4270032930845225, + "grad_norm": 0.44401052594184875, + "learning_rate": 0.0002, + "loss": 1.14, + "step": 650 + }, + { + "epoch": 1.4489571899012075, + "grad_norm": 0.35945481061935425, + "learning_rate": 0.0002, + "loss": 1.0318, + "step": 660 + }, + { + "epoch": 1.4709110867178925, + "grad_norm": 0.3058856129646301, + "learning_rate": 0.0002, + "loss": 1.1988, + "step": 670 + }, + { + "epoch": 1.4928649835345773, + "grad_norm": 0.7067602872848511, + "learning_rate": 0.0002, + "loss": 1.1545, + "step": 680 + }, + { + "epoch": 1.5148188803512623, + "grad_norm": 0.4219357371330261, + "learning_rate": 0.0002, + "loss": 1.0925, + "step": 690 + }, + { + "epoch": 1.5367727771679474, + "grad_norm": 0.5970841646194458, + "learning_rate": 0.0002, + "loss": 1.1622, + "step": 700 + }, + { + "epoch": 1.5587266739846322, + "grad_norm": 0.4381934404373169, + "learning_rate": 0.0002, + "loss": 1.0803, + "step": 710 + }, + { + "epoch": 1.5806805708013172, + "grad_norm": 0.4101450443267822, + "learning_rate": 0.0002, + "loss": 1.0961, + "step": 720 + }, + { + "epoch": 1.6026344676180022, + "grad_norm": 0.3657490015029907, + "learning_rate": 0.0002, + "loss": 1.0474, + "step": 730 + }, + { + "epoch": 1.624588364434687, + "grad_norm": 0.36240628361701965, + "learning_rate": 0.0002, + "loss": 1.0936, + "step": 740 + }, + { + "epoch": 1.6465422612513723, + "grad_norm": 0.4103568494319916, + "learning_rate": 0.0002, + "loss": 1.0489, + "step": 750 + }, + { + "epoch": 1.668496158068057, + "grad_norm": 0.3138505816459656, + "learning_rate": 0.0002, + "loss": 1.0919, + "step": 760 + }, + { + "epoch": 1.690450054884742, + "grad_norm": 0.41215717792510986, + "learning_rate": 0.0002, + "loss": 1.2308, + "step": 770 + }, + { + "epoch": 1.7124039517014271, + "grad_norm": 0.4589519202709198, + "learning_rate": 0.0002, + "loss": 1.1659, + "step": 780 + }, + { + "epoch": 1.734357848518112, + "grad_norm": 0.4049508571624756, + "learning_rate": 0.0002, + "loss": 1.0913, + "step": 790 + }, + { + "epoch": 1.756311745334797, + "grad_norm": 0.48557212948799133, + "learning_rate": 0.0002, + "loss": 1.1329, + "step": 800 + }, + { + "epoch": 1.778265642151482, + "grad_norm": 0.5331754088401794, + "learning_rate": 0.0002, + "loss": 1.0729, + "step": 810 + }, + { + "epoch": 1.8002195389681668, + "grad_norm": 0.3853185772895813, + "learning_rate": 0.0002, + "loss": 1.1452, + "step": 820 + }, + { + "epoch": 1.8221734357848518, + "grad_norm": 0.424062579870224, + "learning_rate": 0.0002, + "loss": 1.1061, + "step": 830 + }, + { + "epoch": 1.8441273326015368, + "grad_norm": 0.3418445289134979, + "learning_rate": 0.0002, + "loss": 1.1104, + "step": 840 + }, + { + "epoch": 1.8660812294182216, + "grad_norm": 0.4045565128326416, + "learning_rate": 0.0002, + "loss": 1.0546, + "step": 850 + }, + { + "epoch": 1.8880351262349067, + "grad_norm": 0.42155781388282776, + "learning_rate": 0.0002, + "loss": 1.1608, + "step": 860 + }, + { + "epoch": 1.9099890230515917, + "grad_norm": 0.40554770827293396, + "learning_rate": 0.0002, + "loss": 1.0628, + "step": 870 + }, + { + "epoch": 1.9319429198682765, + "grad_norm": 0.42644748091697693, + "learning_rate": 0.0002, + "loss": 1.1609, + "step": 880 + }, + { + "epoch": 1.9538968166849617, + "grad_norm": 0.45260652899742126, + "learning_rate": 0.0002, + "loss": 1.1132, + "step": 890 + }, + { + "epoch": 1.9758507135016465, + "grad_norm": 0.4114069938659668, + "learning_rate": 0.0002, + "loss": 1.048, + "step": 900 + }, + { + "epoch": 1.9978046103183313, + "grad_norm": 0.375802218914032, + "learning_rate": 0.0002, + "loss": 1.1941, + "step": 910 + }, + { + "epoch": 2.0, + "eval_loss": 1.205152153968811, + "eval_runtime": 86.8795, + "eval_samples_per_second": 4.961, + "eval_steps_per_second": 0.622, + "step": 911 + }, + { + "epoch": 2.0197585071350166, + "grad_norm": 0.47718703746795654, + "learning_rate": 0.0002, + "loss": 1.0897, + "step": 920 + }, + { + "epoch": 2.0417124039517014, + "grad_norm": 0.45628082752227783, + "learning_rate": 0.0002, + "loss": 1.0329, + "step": 930 + }, + { + "epoch": 2.063666300768386, + "grad_norm": 0.5933247804641724, + "learning_rate": 0.0002, + "loss": 1.0538, + "step": 940 + }, + { + "epoch": 2.0856201975850714, + "grad_norm": 0.5355812907218933, + "learning_rate": 0.0002, + "loss": 1.0152, + "step": 950 + }, + { + "epoch": 2.1075740944017562, + "grad_norm": 0.5860010385513306, + "learning_rate": 0.0002, + "loss": 1.0726, + "step": 960 + }, + { + "epoch": 2.129527991218441, + "grad_norm": 0.7471673488616943, + "learning_rate": 0.0002, + "loss": 1.025, + "step": 970 + }, + { + "epoch": 2.1514818880351263, + "grad_norm": 2.0918211936950684, + "learning_rate": 0.0002, + "loss": 1.0247, + "step": 980 + }, + { + "epoch": 2.173435784851811, + "grad_norm": 0.4021058678627014, + "learning_rate": 0.0002, + "loss": 0.8947, + "step": 990 + }, + { + "epoch": 2.1953896816684964, + "grad_norm": 0.564975380897522, + "learning_rate": 0.0002, + "loss": 0.8875, + "step": 1000 + }, + { + "epoch": 2.217343578485181, + "grad_norm": 0.46260079741477966, + "learning_rate": 0.0002, + "loss": 1.0264, + "step": 1010 + }, + { + "epoch": 2.239297475301866, + "grad_norm": 0.4791034460067749, + "learning_rate": 0.0002, + "loss": 0.9265, + "step": 1020 + }, + { + "epoch": 2.261251372118551, + "grad_norm": 0.5272043943405151, + "learning_rate": 0.0002, + "loss": 0.8869, + "step": 1030 + }, + { + "epoch": 2.283205268935236, + "grad_norm": 0.5221094489097595, + "learning_rate": 0.0002, + "loss": 1.0007, + "step": 1040 + }, + { + "epoch": 2.305159165751921, + "grad_norm": 0.558032751083374, + "learning_rate": 0.0002, + "loss": 0.9472, + "step": 1050 + }, + { + "epoch": 2.327113062568606, + "grad_norm": 0.5905590653419495, + "learning_rate": 0.0002, + "loss": 0.9617, + "step": 1060 + }, + { + "epoch": 2.349066959385291, + "grad_norm": 0.5308699607849121, + "learning_rate": 0.0002, + "loss": 0.9592, + "step": 1070 + }, + { + "epoch": 2.3710208562019757, + "grad_norm": 0.6375027894973755, + "learning_rate": 0.0002, + "loss": 1.0646, + "step": 1080 + }, + { + "epoch": 2.392974753018661, + "grad_norm": 0.7439115643501282, + "learning_rate": 0.0002, + "loss": 1.0354, + "step": 1090 + }, + { + "epoch": 2.4149286498353457, + "grad_norm": 0.41945117712020874, + "learning_rate": 0.0002, + "loss": 1.0212, + "step": 1100 + }, + { + "epoch": 2.436882546652031, + "grad_norm": 0.4891968369483948, + "learning_rate": 0.0002, + "loss": 0.9609, + "step": 1110 + }, + { + "epoch": 2.4588364434687158, + "grad_norm": 0.4686794579029083, + "learning_rate": 0.0002, + "loss": 0.9829, + "step": 1120 + }, + { + "epoch": 2.4807903402854006, + "grad_norm": 0.5204509496688843, + "learning_rate": 0.0002, + "loss": 0.8919, + "step": 1130 + }, + { + "epoch": 2.5027442371020854, + "grad_norm": 0.6779005527496338, + "learning_rate": 0.0002, + "loss": 0.8983, + "step": 1140 + }, + { + "epoch": 2.5246981339187706, + "grad_norm": 0.682621955871582, + "learning_rate": 0.0002, + "loss": 0.9733, + "step": 1150 + }, + { + "epoch": 2.5466520307354554, + "grad_norm": 0.5744376182556152, + "learning_rate": 0.0002, + "loss": 1.051, + "step": 1160 + }, + { + "epoch": 2.5686059275521407, + "grad_norm": 0.49954667687416077, + "learning_rate": 0.0002, + "loss": 0.8764, + "step": 1170 + }, + { + "epoch": 2.5905598243688255, + "grad_norm": 0.4761793315410614, + "learning_rate": 0.0002, + "loss": 0.9896, + "step": 1180 + }, + { + "epoch": 2.6125137211855103, + "grad_norm": 0.548299252986908, + "learning_rate": 0.0002, + "loss": 0.8593, + "step": 1190 + }, + { + "epoch": 2.6344676180021955, + "grad_norm": 0.5771360993385315, + "learning_rate": 0.0002, + "loss": 1.0017, + "step": 1200 + }, + { + "epoch": 2.6564215148188803, + "grad_norm": 0.5543120503425598, + "learning_rate": 0.0002, + "loss": 0.9858, + "step": 1210 + }, + { + "epoch": 2.6783754116355656, + "grad_norm": 0.7564870715141296, + "learning_rate": 0.0002, + "loss": 0.9565, + "step": 1220 + }, + { + "epoch": 2.7003293084522504, + "grad_norm": 0.8222362399101257, + "learning_rate": 0.0002, + "loss": 0.9753, + "step": 1230 + }, + { + "epoch": 2.722283205268935, + "grad_norm": 0.6894469857215881, + "learning_rate": 0.0002, + "loss": 1.0079, + "step": 1240 + }, + { + "epoch": 2.74423710208562, + "grad_norm": 0.6121546030044556, + "learning_rate": 0.0002, + "loss": 1.0106, + "step": 1250 + }, + { + "epoch": 2.7661909989023052, + "grad_norm": 0.521809995174408, + "learning_rate": 0.0002, + "loss": 0.9801, + "step": 1260 + }, + { + "epoch": 2.78814489571899, + "grad_norm": 0.766968309879303, + "learning_rate": 0.0002, + "loss": 1.0196, + "step": 1270 + }, + { + "epoch": 2.8100987925356753, + "grad_norm": 0.522331714630127, + "learning_rate": 0.0002, + "loss": 0.976, + "step": 1280 + }, + { + "epoch": 2.83205268935236, + "grad_norm": 0.42923519015312195, + "learning_rate": 0.0002, + "loss": 0.8866, + "step": 1290 + }, + { + "epoch": 2.854006586169045, + "grad_norm": 0.47810837626457214, + "learning_rate": 0.0002, + "loss": 0.9049, + "step": 1300 + }, + { + "epoch": 2.8759604829857297, + "grad_norm": 1.0958846807479858, + "learning_rate": 0.0002, + "loss": 1.0291, + "step": 1310 + }, + { + "epoch": 2.897914379802415, + "grad_norm": 0.4755791127681732, + "learning_rate": 0.0002, + "loss": 0.8724, + "step": 1320 + }, + { + "epoch": 2.9198682766190998, + "grad_norm": 0.5575157403945923, + "learning_rate": 0.0002, + "loss": 0.9317, + "step": 1330 + }, + { + "epoch": 2.941822173435785, + "grad_norm": 0.5938076376914978, + "learning_rate": 0.0002, + "loss": 1.0131, + "step": 1340 + }, + { + "epoch": 2.96377607025247, + "grad_norm": 0.5751763582229614, + "learning_rate": 0.0002, + "loss": 0.9857, + "step": 1350 + }, + { + "epoch": 2.9857299670691546, + "grad_norm": 0.5590175986289978, + "learning_rate": 0.0002, + "loss": 1.0212, + "step": 1360 + }, + { + "epoch": 2.9989023051591657, + "eval_loss": 1.2402944564819336, + "eval_runtime": 88.822, + "eval_samples_per_second": 4.852, + "eval_steps_per_second": 0.608, + "step": 1366 + }, + { + "epoch": 3.00768386388584, + "grad_norm": 0.463539719581604, + "learning_rate": 0.0002, + "loss": 0.844, + "step": 1370 + }, + { + "epoch": 3.0296377607025247, + "grad_norm": 0.6667885780334473, + "learning_rate": 0.0002, + "loss": 0.8955, + "step": 1380 + }, + { + "epoch": 3.0515916575192095, + "grad_norm": 0.5849342942237854, + "learning_rate": 0.0002, + "loss": 0.8765, + "step": 1390 + }, + { + "epoch": 3.0735455543358947, + "grad_norm": 0.5571770668029785, + "learning_rate": 0.0002, + "loss": 0.7808, + "step": 1400 + }, + { + "epoch": 3.0954994511525795, + "grad_norm": 0.5761234164237976, + "learning_rate": 0.0002, + "loss": 0.7448, + "step": 1410 + }, + { + "epoch": 3.1174533479692643, + "grad_norm": 0.7277371883392334, + "learning_rate": 0.0002, + "loss": 0.7854, + "step": 1420 + }, + { + "epoch": 3.1394072447859496, + "grad_norm": 0.5190334320068359, + "learning_rate": 0.0002, + "loss": 0.817, + "step": 1430 + }, + { + "epoch": 3.1613611416026344, + "grad_norm": 0.632939875125885, + "learning_rate": 0.0002, + "loss": 0.7548, + "step": 1440 + }, + { + "epoch": 3.1833150384193196, + "grad_norm": 0.7229540944099426, + "learning_rate": 0.0002, + "loss": 0.8447, + "step": 1450 + }, + { + "epoch": 3.2052689352360044, + "grad_norm": 0.7584632039070129, + "learning_rate": 0.0002, + "loss": 0.8595, + "step": 1460 + }, + { + "epoch": 3.2272228320526892, + "grad_norm": 0.6546088457107544, + "learning_rate": 0.0002, + "loss": 0.7456, + "step": 1470 + }, + { + "epoch": 3.2491767288693745, + "grad_norm": 0.8116684556007385, + "learning_rate": 0.0002, + "loss": 0.8531, + "step": 1480 + }, + { + "epoch": 3.2711306256860593, + "grad_norm": 0.6206557750701904, + "learning_rate": 0.0002, + "loss": 0.9272, + "step": 1490 + }, + { + "epoch": 3.293084522502744, + "grad_norm": 0.5393369197845459, + "learning_rate": 0.0002, + "loss": 0.7972, + "step": 1500 + }, + { + "epoch": 3.3150384193194293, + "grad_norm": 0.7006453275680542, + "learning_rate": 0.0002, + "loss": 0.7614, + "step": 1510 + }, + { + "epoch": 3.336992316136114, + "grad_norm": 0.95253986120224, + "learning_rate": 0.0002, + "loss": 0.7358, + "step": 1520 + }, + { + "epoch": 3.358946212952799, + "grad_norm": 0.8138132095336914, + "learning_rate": 0.0002, + "loss": 0.8131, + "step": 1530 + }, + { + "epoch": 3.380900109769484, + "grad_norm": 0.7974302172660828, + "learning_rate": 0.0002, + "loss": 0.7738, + "step": 1540 + }, + { + "epoch": 3.402854006586169, + "grad_norm": 0.6694685220718384, + "learning_rate": 0.0002, + "loss": 0.8161, + "step": 1550 + }, + { + "epoch": 3.4248079034028542, + "grad_norm": 0.908634603023529, + "learning_rate": 0.0002, + "loss": 0.8503, + "step": 1560 + }, + { + "epoch": 3.446761800219539, + "grad_norm": 0.5625193119049072, + "learning_rate": 0.0002, + "loss": 0.7609, + "step": 1570 + }, + { + "epoch": 3.468715697036224, + "grad_norm": 0.779325544834137, + "learning_rate": 0.0002, + "loss": 0.7658, + "step": 1580 + }, + { + "epoch": 3.4906695938529086, + "grad_norm": 0.7133058905601501, + "learning_rate": 0.0002, + "loss": 0.7485, + "step": 1590 + }, + { + "epoch": 3.512623490669594, + "grad_norm": 0.6741108298301697, + "learning_rate": 0.0002, + "loss": 0.8847, + "step": 1600 + }, + { + "epoch": 3.5345773874862787, + "grad_norm": 0.696982204914093, + "learning_rate": 0.0002, + "loss": 0.7838, + "step": 1610 + }, + { + "epoch": 3.556531284302964, + "grad_norm": 0.7946001291275024, + "learning_rate": 0.0002, + "loss": 0.7195, + "step": 1620 + }, + { + "epoch": 3.5784851811196488, + "grad_norm": 0.6313548684120178, + "learning_rate": 0.0002, + "loss": 0.7772, + "step": 1630 + }, + { + "epoch": 3.6004390779363336, + "grad_norm": 0.9246852397918701, + "learning_rate": 0.0002, + "loss": 0.8267, + "step": 1640 + }, + { + "epoch": 3.622392974753019, + "grad_norm": 0.6615420579910278, + "learning_rate": 0.0002, + "loss": 0.779, + "step": 1650 + }, + { + "epoch": 3.6443468715697036, + "grad_norm": 1.5050125122070312, + "learning_rate": 0.0002, + "loss": 0.883, + "step": 1660 + }, + { + "epoch": 3.666300768386389, + "grad_norm": 0.5023762583732605, + "learning_rate": 0.0002, + "loss": 0.7763, + "step": 1670 + }, + { + "epoch": 3.6882546652030737, + "grad_norm": 0.6289586424827576, + "learning_rate": 0.0002, + "loss": 0.8173, + "step": 1680 + }, + { + "epoch": 3.7102085620197585, + "grad_norm": 1.050397515296936, + "learning_rate": 0.0002, + "loss": 0.9028, + "step": 1690 + }, + { + "epoch": 3.7321624588364433, + "grad_norm": 0.6785626411437988, + "learning_rate": 0.0002, + "loss": 0.7747, + "step": 1700 + }, + { + "epoch": 3.7541163556531285, + "grad_norm": 0.7565035223960876, + "learning_rate": 0.0002, + "loss": 0.9215, + "step": 1710 + }, + { + "epoch": 3.7760702524698133, + "grad_norm": 0.7775155901908875, + "learning_rate": 0.0002, + "loss": 0.7913, + "step": 1720 + }, + { + "epoch": 3.7980241492864986, + "grad_norm": 0.765260636806488, + "learning_rate": 0.0002, + "loss": 0.8081, + "step": 1730 + }, + { + "epoch": 3.8199780461031834, + "grad_norm": 0.7982407808303833, + "learning_rate": 0.0002, + "loss": 0.9231, + "step": 1740 + }, + { + "epoch": 3.841931942919868, + "grad_norm": 0.7431730628013611, + "learning_rate": 0.0002, + "loss": 0.7755, + "step": 1750 + }, + { + "epoch": 3.863885839736553, + "grad_norm": 0.9758927226066589, + "learning_rate": 0.0002, + "loss": 0.9236, + "step": 1760 + }, + { + "epoch": 3.885839736553238, + "grad_norm": 0.8014697432518005, + "learning_rate": 0.0002, + "loss": 0.9118, + "step": 1770 + }, + { + "epoch": 3.907793633369923, + "grad_norm": 0.7212756276130676, + "learning_rate": 0.0002, + "loss": 0.7503, + "step": 1780 + }, + { + "epoch": 3.9297475301866083, + "grad_norm": 0.584318220615387, + "learning_rate": 0.0002, + "loss": 0.7978, + "step": 1790 + }, + { + "epoch": 3.951701427003293, + "grad_norm": 0.7612535953521729, + "learning_rate": 0.0002, + "loss": 0.7894, + "step": 1800 + }, + { + "epoch": 3.973655323819978, + "grad_norm": 0.735103189945221, + "learning_rate": 0.0002, + "loss": 0.8589, + "step": 1810 + }, + { + "epoch": 3.995609220636663, + "grad_norm": 0.9074980020523071, + "learning_rate": 0.0002, + "loss": 0.8192, + "step": 1820 + }, + { + "epoch": 4.0, + "eval_loss": 1.279890537261963, + "eval_runtime": 88.8969, + "eval_samples_per_second": 4.848, + "eval_steps_per_second": 0.607, + "step": 1822 + }, + { + "epoch": 4.017563117453348, + "grad_norm": 0.9290254712104797, + "learning_rate": 0.0002, + "loss": 0.7312, + "step": 1830 + }, + { + "epoch": 4.039517014270033, + "grad_norm": 0.723889946937561, + "learning_rate": 0.0002, + "loss": 0.6896, + "step": 1840 + }, + { + "epoch": 4.061470911086718, + "grad_norm": 0.5906972289085388, + "learning_rate": 0.0002, + "loss": 0.632, + "step": 1850 + }, + { + "epoch": 4.083424807903403, + "grad_norm": 0.8078910708427429, + "learning_rate": 0.0002, + "loss": 0.6594, + "step": 1860 + }, + { + "epoch": 4.105378704720088, + "grad_norm": 1.0101137161254883, + "learning_rate": 0.0002, + "loss": 0.6242, + "step": 1870 + }, + { + "epoch": 4.127332601536772, + "grad_norm": 0.8710281848907471, + "learning_rate": 0.0002, + "loss": 0.7259, + "step": 1880 + }, + { + "epoch": 4.149286498353458, + "grad_norm": 0.9604734778404236, + "learning_rate": 0.0002, + "loss": 0.6993, + "step": 1890 + }, + { + "epoch": 4.171240395170143, + "grad_norm": 0.9829702377319336, + "learning_rate": 0.0002, + "loss": 0.6706, + "step": 1900 + }, + { + "epoch": 4.193194291986828, + "grad_norm": 0.6572765707969666, + "learning_rate": 0.0002, + "loss": 0.7013, + "step": 1910 + }, + { + "epoch": 4.2151481888035125, + "grad_norm": 0.8459188938140869, + "learning_rate": 0.0002, + "loss": 0.5539, + "step": 1920 + }, + { + "epoch": 4.237102085620197, + "grad_norm": 0.8321021795272827, + "learning_rate": 0.0002, + "loss": 0.6235, + "step": 1930 + }, + { + "epoch": 4.259055982436882, + "grad_norm": 0.8611727356910706, + "learning_rate": 0.0002, + "loss": 0.6442, + "step": 1940 + }, + { + "epoch": 4.281009879253568, + "grad_norm": 0.8490208387374878, + "learning_rate": 0.0002, + "loss": 0.6852, + "step": 1950 + }, + { + "epoch": 4.302963776070253, + "grad_norm": 0.9628722667694092, + "learning_rate": 0.0002, + "loss": 0.6175, + "step": 1960 + }, + { + "epoch": 4.324917672886937, + "grad_norm": 0.9632807374000549, + "learning_rate": 0.0002, + "loss": 0.5982, + "step": 1970 + }, + { + "epoch": 4.346871569703622, + "grad_norm": 0.7023298740386963, + "learning_rate": 0.0002, + "loss": 0.6138, + "step": 1980 + }, + { + "epoch": 4.368825466520307, + "grad_norm": 0.7912909388542175, + "learning_rate": 0.0002, + "loss": 0.6012, + "step": 1990 + }, + { + "epoch": 4.390779363336993, + "grad_norm": 1.1463429927825928, + "learning_rate": 0.0002, + "loss": 0.6767, + "step": 2000 + }, + { + "epoch": 4.4127332601536775, + "grad_norm": 1.1780626773834229, + "learning_rate": 0.0002, + "loss": 0.6607, + "step": 2010 + }, + { + "epoch": 4.434687156970362, + "grad_norm": 0.9349206686019897, + "learning_rate": 0.0002, + "loss": 0.6746, + "step": 2020 + }, + { + "epoch": 4.456641053787047, + "grad_norm": 0.7816639542579651, + "learning_rate": 0.0002, + "loss": 0.7087, + "step": 2030 + }, + { + "epoch": 4.478594950603732, + "grad_norm": 0.7005311250686646, + "learning_rate": 0.0002, + "loss": 0.6222, + "step": 2040 + }, + { + "epoch": 4.500548847420417, + "grad_norm": 0.7746558785438538, + "learning_rate": 0.0002, + "loss": 0.6608, + "step": 2050 + }, + { + "epoch": 4.522502744237102, + "grad_norm": 0.8261151313781738, + "learning_rate": 0.0002, + "loss": 0.6305, + "step": 2060 + }, + { + "epoch": 4.544456641053787, + "grad_norm": 1.0917805433273315, + "learning_rate": 0.0002, + "loss": 0.6502, + "step": 2070 + }, + { + "epoch": 4.566410537870472, + "grad_norm": 1.1570647954940796, + "learning_rate": 0.0002, + "loss": 0.6798, + "step": 2080 + }, + { + "epoch": 4.588364434687157, + "grad_norm": 0.9936433434486389, + "learning_rate": 0.0002, + "loss": 0.6296, + "step": 2090 + }, + { + "epoch": 4.610318331503842, + "grad_norm": 0.8574427366256714, + "learning_rate": 0.0002, + "loss": 0.5936, + "step": 2100 + }, + { + "epoch": 4.632272228320527, + "grad_norm": 0.7630168795585632, + "learning_rate": 0.0002, + "loss": 0.6529, + "step": 2110 + }, + { + "epoch": 4.654226125137212, + "grad_norm": 0.8146462440490723, + "learning_rate": 0.0002, + "loss": 0.5935, + "step": 2120 + }, + { + "epoch": 4.676180021953897, + "grad_norm": 0.7090407609939575, + "learning_rate": 0.0002, + "loss": 0.7102, + "step": 2130 + }, + { + "epoch": 4.698133918770582, + "grad_norm": 0.8278160095214844, + "learning_rate": 0.0002, + "loss": 0.6575, + "step": 2140 + }, + { + "epoch": 4.7200878155872665, + "grad_norm": 0.9415683746337891, + "learning_rate": 0.0002, + "loss": 0.664, + "step": 2150 + }, + { + "epoch": 4.742041712403951, + "grad_norm": 1.0056205987930298, + "learning_rate": 0.0002, + "loss": 0.7283, + "step": 2160 + }, + { + "epoch": 4.763995609220637, + "grad_norm": 0.768304705619812, + "learning_rate": 0.0002, + "loss": 0.6845, + "step": 2170 + }, + { + "epoch": 4.785949506037322, + "grad_norm": 1.0604112148284912, + "learning_rate": 0.0002, + "loss": 0.6922, + "step": 2180 + }, + { + "epoch": 4.807903402854007, + "grad_norm": 1.132864236831665, + "learning_rate": 0.0002, + "loss": 0.7092, + "step": 2190 + }, + { + "epoch": 4.829857299670691, + "grad_norm": 0.7543689608573914, + "learning_rate": 0.0002, + "loss": 0.6936, + "step": 2200 + }, + { + "epoch": 4.851811196487376, + "grad_norm": 0.8047362565994263, + "learning_rate": 0.0002, + "loss": 0.6921, + "step": 2210 + }, + { + "epoch": 4.873765093304062, + "grad_norm": 1.135778546333313, + "learning_rate": 0.0002, + "loss": 0.6753, + "step": 2220 + }, + { + "epoch": 4.895718990120747, + "grad_norm": 0.9068503379821777, + "learning_rate": 0.0002, + "loss": 0.6443, + "step": 2230 + }, + { + "epoch": 4.9176728869374315, + "grad_norm": 1.822325587272644, + "learning_rate": 0.0002, + "loss": 0.7419, + "step": 2240 + }, + { + "epoch": 4.939626783754116, + "grad_norm": 1.1124998331069946, + "learning_rate": 0.0002, + "loss": 0.6436, + "step": 2250 + }, + { + "epoch": 4.961580680570801, + "grad_norm": 0.818484365940094, + "learning_rate": 0.0002, + "loss": 0.7423, + "step": 2260 + }, + { + "epoch": 4.983534577387486, + "grad_norm": 1.0057194232940674, + "learning_rate": 0.0002, + "loss": 0.6872, + "step": 2270 + }, + { + "epoch": 4.998902305159166, + "eval_loss": 1.4120490550994873, + "eval_runtime": 87.5617, + "eval_samples_per_second": 4.922, + "eval_steps_per_second": 0.617, + "step": 2277 + }, + { + "epoch": 5.005488474204172, + "grad_norm": 0.8211547136306763, + "learning_rate": 0.0002, + "loss": 0.5451, + "step": 2280 + }, + { + "epoch": 5.0274423710208564, + "grad_norm": 1.1704130172729492, + "learning_rate": 0.0002, + "loss": 0.4965, + "step": 2290 + }, + { + "epoch": 5.049396267837541, + "grad_norm": 1.033539891242981, + "learning_rate": 0.0002, + "loss": 0.4827, + "step": 2300 + }, + { + "epoch": 5.071350164654226, + "grad_norm": 0.8830313682556152, + "learning_rate": 0.0002, + "loss": 0.447, + "step": 2310 + }, + { + "epoch": 5.093304061470911, + "grad_norm": 1.160437822341919, + "learning_rate": 0.0002, + "loss": 0.5502, + "step": 2320 + }, + { + "epoch": 5.115257958287596, + "grad_norm": 0.919956386089325, + "learning_rate": 0.0002, + "loss": 0.5123, + "step": 2330 + }, + { + "epoch": 5.137211855104281, + "grad_norm": 1.0099905729293823, + "learning_rate": 0.0002, + "loss": 0.4784, + "step": 2340 + }, + { + "epoch": 5.159165751920966, + "grad_norm": 1.1484816074371338, + "learning_rate": 0.0002, + "loss": 0.5109, + "step": 2350 + }, + { + "epoch": 5.181119648737651, + "grad_norm": 1.0373470783233643, + "learning_rate": 0.0002, + "loss": 0.5222, + "step": 2360 + }, + { + "epoch": 5.203073545554336, + "grad_norm": 1.0824922323226929, + "learning_rate": 0.0002, + "loss": 0.5366, + "step": 2370 + }, + { + "epoch": 5.225027442371021, + "grad_norm": 1.3817942142486572, + "learning_rate": 0.0002, + "loss": 0.5592, + "step": 2380 + }, + { + "epoch": 5.246981339187705, + "grad_norm": 1.197035551071167, + "learning_rate": 0.0002, + "loss": 0.504, + "step": 2390 + }, + { + "epoch": 5.268935236004391, + "grad_norm": 1.098778486251831, + "learning_rate": 0.0002, + "loss": 0.5326, + "step": 2400 + }, + { + "epoch": 5.290889132821076, + "grad_norm": 0.9713385105133057, + "learning_rate": 0.0002, + "loss": 0.5039, + "step": 2410 + }, + { + "epoch": 5.312843029637761, + "grad_norm": 1.321574330329895, + "learning_rate": 0.0002, + "loss": 0.5735, + "step": 2420 + }, + { + "epoch": 5.3347969264544455, + "grad_norm": 0.9402496218681335, + "learning_rate": 0.0002, + "loss": 0.4777, + "step": 2430 + }, + { + "epoch": 5.35675082327113, + "grad_norm": 0.8644852042198181, + "learning_rate": 0.0002, + "loss": 0.5604, + "step": 2440 + }, + { + "epoch": 5.378704720087816, + "grad_norm": 1.060290813446045, + "learning_rate": 0.0002, + "loss": 0.5324, + "step": 2450 + }, + { + "epoch": 5.400658616904501, + "grad_norm": 1.0725265741348267, + "learning_rate": 0.0002, + "loss": 0.5366, + "step": 2460 + }, + { + "epoch": 5.422612513721186, + "grad_norm": 0.9409431219100952, + "learning_rate": 0.0002, + "loss": 0.5469, + "step": 2470 + }, + { + "epoch": 5.44456641053787, + "grad_norm": 1.1108187437057495, + "learning_rate": 0.0002, + "loss": 0.5186, + "step": 2480 + }, + { + "epoch": 5.466520307354555, + "grad_norm": 1.0210821628570557, + "learning_rate": 0.0002, + "loss": 0.5312, + "step": 2490 + }, + { + "epoch": 5.48847420417124, + "grad_norm": 1.110597014427185, + "learning_rate": 0.0002, + "loss": 0.5016, + "step": 2500 + }, + { + "epoch": 5.510428100987926, + "grad_norm": 1.2534265518188477, + "learning_rate": 0.0002, + "loss": 0.511, + "step": 2510 + }, + { + "epoch": 5.5323819978046105, + "grad_norm": 1.3389744758605957, + "learning_rate": 0.0002, + "loss": 0.6062, + "step": 2520 + }, + { + "epoch": 5.554335894621295, + "grad_norm": 0.9520368576049805, + "learning_rate": 0.0002, + "loss": 0.4653, + "step": 2530 + }, + { + "epoch": 5.57628979143798, + "grad_norm": 1.4737157821655273, + "learning_rate": 0.0002, + "loss": 0.4746, + "step": 2540 + }, + { + "epoch": 5.598243688254665, + "grad_norm": 1.4143685102462769, + "learning_rate": 0.0002, + "loss": 0.5432, + "step": 2550 + }, + { + "epoch": 5.620197585071351, + "grad_norm": 1.3573999404907227, + "learning_rate": 0.0002, + "loss": 0.4722, + "step": 2560 + }, + { + "epoch": 5.642151481888035, + "grad_norm": 0.8475444316864014, + "learning_rate": 0.0002, + "loss": 0.5063, + "step": 2570 + }, + { + "epoch": 5.66410537870472, + "grad_norm": 1.2670329809188843, + "learning_rate": 0.0002, + "loss": 0.4911, + "step": 2580 + }, + { + "epoch": 5.686059275521405, + "grad_norm": 0.9688172936439514, + "learning_rate": 0.0002, + "loss": 0.5137, + "step": 2590 + }, + { + "epoch": 5.70801317233809, + "grad_norm": 1.3652743101119995, + "learning_rate": 0.0002, + "loss": 0.5116, + "step": 2600 + }, + { + "epoch": 5.729967069154775, + "grad_norm": 1.1475377082824707, + "learning_rate": 0.0002, + "loss": 0.5661, + "step": 2610 + }, + { + "epoch": 5.75192096597146, + "grad_norm": 1.3105946779251099, + "learning_rate": 0.0002, + "loss": 0.567, + "step": 2620 + }, + { + "epoch": 5.773874862788145, + "grad_norm": 0.920238196849823, + "learning_rate": 0.0002, + "loss": 0.4964, + "step": 2630 + }, + { + "epoch": 5.79582875960483, + "grad_norm": 1.0981792211532593, + "learning_rate": 0.0002, + "loss": 0.5473, + "step": 2640 + }, + { + "epoch": 5.817782656421515, + "grad_norm": 1.0734144449234009, + "learning_rate": 0.0002, + "loss": 0.5132, + "step": 2650 + }, + { + "epoch": 5.8397365532381995, + "grad_norm": 1.0541702508926392, + "learning_rate": 0.0002, + "loss": 0.5404, + "step": 2660 + }, + { + "epoch": 5.861690450054885, + "grad_norm": 1.0913143157958984, + "learning_rate": 0.0002, + "loss": 0.5056, + "step": 2670 + }, + { + "epoch": 5.88364434687157, + "grad_norm": 1.0431408882141113, + "learning_rate": 0.0002, + "loss": 0.5425, + "step": 2680 + }, + { + "epoch": 5.905598243688255, + "grad_norm": 1.3515729904174805, + "learning_rate": 0.0002, + "loss": 0.5398, + "step": 2690 + }, + { + "epoch": 5.92755214050494, + "grad_norm": 1.3153903484344482, + "learning_rate": 0.0002, + "loss": 0.5936, + "step": 2700 + }, + { + "epoch": 5.949506037321624, + "grad_norm": 1.024109125137329, + "learning_rate": 0.0002, + "loss": 0.5643, + "step": 2710 + }, + { + "epoch": 5.971459934138309, + "grad_norm": 1.0308483839035034, + "learning_rate": 0.0002, + "loss": 0.5143, + "step": 2720 + }, + { + "epoch": 5.993413830954994, + "grad_norm": 0.8329401016235352, + "learning_rate": 0.0002, + "loss": 0.4835, + "step": 2730 + }, + { + "epoch": 6.0, + "eval_loss": 1.510581612586975, + "eval_runtime": 89.0047, + "eval_samples_per_second": 4.842, + "eval_steps_per_second": 0.607, + "step": 2733 + } + ], + "logging_steps": 10, + "max_steps": 3640, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.264771205651497e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f75755c7cf71aeb05b76db2632173f96f74e8f7 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf90ce7dd53cc68edd44d14e30ca84a5d7431a5b99d4697b17af4b2f7ec0abab +size 5624 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/README.md b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/README.md new file mode 100644 index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/README.md @@ -0,0 +1,202 @@ +--- +base_model: meta-llama/Meta-Llama-3-8B-Instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.13.1 \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..406c5a08dc4a2a33b52c62a482f98c217c417215 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "v_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c1bc2f7db80ca96e9cb5944bee4b3f6fb7ae1559 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3bdd1709fc00f332adfdf9177607689dbacc6a97a1a7544db88c2b3b0ad963b +size 109069176 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/optimizer.pt b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..bec07d5a91bd37e057ce1138e060cb4d0249af6a --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6135d055622ad65d74dd6a8203eb81fe31af1e78e099007c7a580a1f014b0775 +size 55532666 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/rng_state.pth b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..36e2f773b720ac626ab8a0f220a891722c8d8e25 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd88f055587d30dc0eca808987761abeb4f79dbd85ead77c4ae9eddff60f6497 +size 14244 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/scheduler.pt b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..14ac3e297d334cf471359f30dca03131ea0a7b62 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:963f330eae9682a38829ee0476279ed27221f622ebd1bb13e09f8de509794e4a +size 1064 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393 +size 17209961 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|eot_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/trainer_state.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..ef7d21d4a2099bca3c5eb7e5b4d527fbb8c7fc25 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/trainer_state.json @@ -0,0 +1,2315 @@ +{ + "best_metric": 1.205152153968811, + "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911", + "epoch": 6.998902305159166, + "eval_steps": 10, + "global_step": 3188, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.021953896816684963, + "grad_norm": 0.6144012212753296, + "learning_rate": 0.0002, + "loss": 1.9887, + "step": 10 + }, + { + "epoch": 0.043907793633369926, + "grad_norm": 0.5587220788002014, + "learning_rate": 0.0002, + "loss": 1.6882, + "step": 20 + }, + { + "epoch": 0.06586169045005488, + "grad_norm": 0.43262454867362976, + "learning_rate": 0.0002, + "loss": 1.399, + "step": 30 + }, + { + "epoch": 0.08781558726673985, + "grad_norm": 0.4783053994178772, + "learning_rate": 0.0002, + "loss": 1.4675, + "step": 40 + }, + { + "epoch": 0.10976948408342481, + "grad_norm": 0.44338956475257874, + "learning_rate": 0.0002, + "loss": 1.1771, + "step": 50 + }, + { + "epoch": 0.13172338090010977, + "grad_norm": 0.7255092263221741, + "learning_rate": 0.0002, + "loss": 1.3706, + "step": 60 + }, + { + "epoch": 0.15367727771679474, + "grad_norm": 0.46073833107948303, + "learning_rate": 0.0002, + "loss": 1.2601, + "step": 70 + }, + { + "epoch": 0.1756311745334797, + "grad_norm": 0.6698123216629028, + "learning_rate": 0.0002, + "loss": 1.3049, + "step": 80 + }, + { + "epoch": 0.19758507135016465, + "grad_norm": 0.4190150201320648, + "learning_rate": 0.0002, + "loss": 1.2975, + "step": 90 + }, + { + "epoch": 0.21953896816684962, + "grad_norm": 0.4110015034675598, + "learning_rate": 0.0002, + "loss": 1.2797, + "step": 100 + }, + { + "epoch": 0.2414928649835346, + "grad_norm": 0.33374306559562683, + "learning_rate": 0.0002, + "loss": 1.2896, + "step": 110 + }, + { + "epoch": 0.26344676180021953, + "grad_norm": 0.3061307370662689, + "learning_rate": 0.0002, + "loss": 1.2268, + "step": 120 + }, + { + "epoch": 0.2854006586169045, + "grad_norm": 0.4386885166168213, + "learning_rate": 0.0002, + "loss": 1.376, + "step": 130 + }, + { + "epoch": 0.30735455543358947, + "grad_norm": 0.40116462111473083, + "learning_rate": 0.0002, + "loss": 1.1814, + "step": 140 + }, + { + "epoch": 0.32930845225027444, + "grad_norm": 0.5887949466705322, + "learning_rate": 0.0002, + "loss": 1.2592, + "step": 150 + }, + { + "epoch": 0.3512623490669594, + "grad_norm": 0.3401573896408081, + "learning_rate": 0.0002, + "loss": 1.2372, + "step": 160 + }, + { + "epoch": 0.3732162458836443, + "grad_norm": 0.3288364112377167, + "learning_rate": 0.0002, + "loss": 1.1901, + "step": 170 + }, + { + "epoch": 0.3951701427003293, + "grad_norm": 0.4853297472000122, + "learning_rate": 0.0002, + "loss": 1.2335, + "step": 180 + }, + { + "epoch": 0.41712403951701427, + "grad_norm": 2.6253697872161865, + "learning_rate": 0.0002, + "loss": 1.227, + "step": 190 + }, + { + "epoch": 0.43907793633369924, + "grad_norm": 0.5598543286323547, + "learning_rate": 0.0002, + "loss": 1.2673, + "step": 200 + }, + { + "epoch": 0.4610318331503842, + "grad_norm": 0.4046548902988434, + "learning_rate": 0.0002, + "loss": 1.3459, + "step": 210 + }, + { + "epoch": 0.4829857299670692, + "grad_norm": 0.3686952590942383, + "learning_rate": 0.0002, + "loss": 1.265, + "step": 220 + }, + { + "epoch": 0.5049396267837541, + "grad_norm": 0.42458799481391907, + "learning_rate": 0.0002, + "loss": 1.1364, + "step": 230 + }, + { + "epoch": 0.5268935236004391, + "grad_norm": 0.5839895009994507, + "learning_rate": 0.0002, + "loss": 1.2094, + "step": 240 + }, + { + "epoch": 0.5488474204171241, + "grad_norm": 0.408288836479187, + "learning_rate": 0.0002, + "loss": 1.2073, + "step": 250 + }, + { + "epoch": 0.570801317233809, + "grad_norm": 0.45887550711631775, + "learning_rate": 0.0002, + "loss": 1.3121, + "step": 260 + }, + { + "epoch": 0.5927552140504939, + "grad_norm": 0.5440235733985901, + "learning_rate": 0.0002, + "loss": 1.2257, + "step": 270 + }, + { + "epoch": 0.6147091108671789, + "grad_norm": 0.3725181519985199, + "learning_rate": 0.0002, + "loss": 1.1003, + "step": 280 + }, + { + "epoch": 0.6366630076838639, + "grad_norm": 0.4309018850326538, + "learning_rate": 0.0002, + "loss": 1.1538, + "step": 290 + }, + { + "epoch": 0.6586169045005489, + "grad_norm": 0.31488674879074097, + "learning_rate": 0.0002, + "loss": 1.2097, + "step": 300 + }, + { + "epoch": 0.6805708013172338, + "grad_norm": 0.34194841980934143, + "learning_rate": 0.0002, + "loss": 1.1689, + "step": 310 + }, + { + "epoch": 0.7025246981339188, + "grad_norm": 0.3407684862613678, + "learning_rate": 0.0002, + "loss": 1.2579, + "step": 320 + }, + { + "epoch": 0.7244785949506037, + "grad_norm": 0.2985728085041046, + "learning_rate": 0.0002, + "loss": 1.1144, + "step": 330 + }, + { + "epoch": 0.7464324917672887, + "grad_norm": 0.42316871881484985, + "learning_rate": 0.0002, + "loss": 1.2056, + "step": 340 + }, + { + "epoch": 0.7683863885839737, + "grad_norm": 0.3124258816242218, + "learning_rate": 0.0002, + "loss": 1.1753, + "step": 350 + }, + { + "epoch": 0.7903402854006586, + "grad_norm": 0.7727567553520203, + "learning_rate": 0.0002, + "loss": 1.2547, + "step": 360 + }, + { + "epoch": 0.8122941822173436, + "grad_norm": 0.363765686750412, + "learning_rate": 0.0002, + "loss": 1.124, + "step": 370 + }, + { + "epoch": 0.8342480790340285, + "grad_norm": 0.35582536458969116, + "learning_rate": 0.0002, + "loss": 1.1302, + "step": 380 + }, + { + "epoch": 0.8562019758507134, + "grad_norm": 0.31982025504112244, + "learning_rate": 0.0002, + "loss": 1.1787, + "step": 390 + }, + { + "epoch": 0.8781558726673985, + "grad_norm": 0.34978964924812317, + "learning_rate": 0.0002, + "loss": 1.2056, + "step": 400 + }, + { + "epoch": 0.9001097694840834, + "grad_norm": 0.8346716165542603, + "learning_rate": 0.0002, + "loss": 1.3577, + "step": 410 + }, + { + "epoch": 0.9220636663007684, + "grad_norm": 0.31984028220176697, + "learning_rate": 0.0002, + "loss": 1.1029, + "step": 420 + }, + { + "epoch": 0.9440175631174533, + "grad_norm": 0.32078951597213745, + "learning_rate": 0.0002, + "loss": 1.0967, + "step": 430 + }, + { + "epoch": 0.9659714599341384, + "grad_norm": 0.3417500853538513, + "learning_rate": 0.0002, + "loss": 1.0936, + "step": 440 + }, + { + "epoch": 0.9879253567508233, + "grad_norm": 0.42359477281570435, + "learning_rate": 0.0002, + "loss": 1.3412, + "step": 450 + }, + { + "epoch": 0.9989023051591658, + "eval_loss": 1.2201528549194336, + "eval_runtime": 87.152, + "eval_samples_per_second": 4.945, + "eval_steps_per_second": 0.62, + "step": 455 + }, + { + "epoch": 1.0098792535675083, + "grad_norm": 0.37914523482322693, + "learning_rate": 0.0002, + "loss": 1.1909, + "step": 460 + }, + { + "epoch": 1.031833150384193, + "grad_norm": 0.43655872344970703, + "learning_rate": 0.0002, + "loss": 1.0948, + "step": 470 + }, + { + "epoch": 1.0537870472008781, + "grad_norm": 0.3673796057701111, + "learning_rate": 0.0002, + "loss": 1.0873, + "step": 480 + }, + { + "epoch": 1.0757409440175631, + "grad_norm": 0.37673917412757874, + "learning_rate": 0.0002, + "loss": 1.0483, + "step": 490 + }, + { + "epoch": 1.0976948408342482, + "grad_norm": 0.2893829345703125, + "learning_rate": 0.0002, + "loss": 1.0799, + "step": 500 + }, + { + "epoch": 1.119648737650933, + "grad_norm": 0.5551970601081848, + "learning_rate": 0.0002, + "loss": 1.1847, + "step": 510 + }, + { + "epoch": 1.141602634467618, + "grad_norm": 0.442104309797287, + "learning_rate": 0.0002, + "loss": 1.0885, + "step": 520 + }, + { + "epoch": 1.163556531284303, + "grad_norm": 0.4035094976425171, + "learning_rate": 0.0002, + "loss": 1.1766, + "step": 530 + }, + { + "epoch": 1.1855104281009878, + "grad_norm": 0.47009000182151794, + "learning_rate": 0.0002, + "loss": 1.0282, + "step": 540 + }, + { + "epoch": 1.2074643249176729, + "grad_norm": 0.4118749797344208, + "learning_rate": 0.0002, + "loss": 1.2625, + "step": 550 + }, + { + "epoch": 1.2294182217343579, + "grad_norm": 0.35173165798187256, + "learning_rate": 0.0002, + "loss": 1.0988, + "step": 560 + }, + { + "epoch": 1.2513721185510427, + "grad_norm": 0.7024672031402588, + "learning_rate": 0.0002, + "loss": 1.0498, + "step": 570 + }, + { + "epoch": 1.2733260153677277, + "grad_norm": 0.42657527327537537, + "learning_rate": 0.0002, + "loss": 1.1339, + "step": 580 + }, + { + "epoch": 1.2952799121844127, + "grad_norm": 0.3815029561519623, + "learning_rate": 0.0002, + "loss": 1.0545, + "step": 590 + }, + { + "epoch": 1.3172338090010978, + "grad_norm": 0.7031055688858032, + "learning_rate": 0.0002, + "loss": 1.1528, + "step": 600 + }, + { + "epoch": 1.3391877058177828, + "grad_norm": 0.393911212682724, + "learning_rate": 0.0002, + "loss": 1.1347, + "step": 610 + }, + { + "epoch": 1.3611416026344676, + "grad_norm": 0.5077702403068542, + "learning_rate": 0.0002, + "loss": 1.1901, + "step": 620 + }, + { + "epoch": 1.3830954994511526, + "grad_norm": 2.330033302307129, + "learning_rate": 0.0002, + "loss": 1.1251, + "step": 630 + }, + { + "epoch": 1.4050493962678376, + "grad_norm": 0.35322949290275574, + "learning_rate": 0.0002, + "loss": 1.0477, + "step": 640 + }, + { + "epoch": 1.4270032930845225, + "grad_norm": 0.44401052594184875, + "learning_rate": 0.0002, + "loss": 1.14, + "step": 650 + }, + { + "epoch": 1.4489571899012075, + "grad_norm": 0.35945481061935425, + "learning_rate": 0.0002, + "loss": 1.0318, + "step": 660 + }, + { + "epoch": 1.4709110867178925, + "grad_norm": 0.3058856129646301, + "learning_rate": 0.0002, + "loss": 1.1988, + "step": 670 + }, + { + "epoch": 1.4928649835345773, + "grad_norm": 0.7067602872848511, + "learning_rate": 0.0002, + "loss": 1.1545, + "step": 680 + }, + { + "epoch": 1.5148188803512623, + "grad_norm": 0.4219357371330261, + "learning_rate": 0.0002, + "loss": 1.0925, + "step": 690 + }, + { + "epoch": 1.5367727771679474, + "grad_norm": 0.5970841646194458, + "learning_rate": 0.0002, + "loss": 1.1622, + "step": 700 + }, + { + "epoch": 1.5587266739846322, + "grad_norm": 0.4381934404373169, + "learning_rate": 0.0002, + "loss": 1.0803, + "step": 710 + }, + { + "epoch": 1.5806805708013172, + "grad_norm": 0.4101450443267822, + "learning_rate": 0.0002, + "loss": 1.0961, + "step": 720 + }, + { + "epoch": 1.6026344676180022, + "grad_norm": 0.3657490015029907, + "learning_rate": 0.0002, + "loss": 1.0474, + "step": 730 + }, + { + "epoch": 1.624588364434687, + "grad_norm": 0.36240628361701965, + "learning_rate": 0.0002, + "loss": 1.0936, + "step": 740 + }, + { + "epoch": 1.6465422612513723, + "grad_norm": 0.4103568494319916, + "learning_rate": 0.0002, + "loss": 1.0489, + "step": 750 + }, + { + "epoch": 1.668496158068057, + "grad_norm": 0.3138505816459656, + "learning_rate": 0.0002, + "loss": 1.0919, + "step": 760 + }, + { + "epoch": 1.690450054884742, + "grad_norm": 0.41215717792510986, + "learning_rate": 0.0002, + "loss": 1.2308, + "step": 770 + }, + { + "epoch": 1.7124039517014271, + "grad_norm": 0.4589519202709198, + "learning_rate": 0.0002, + "loss": 1.1659, + "step": 780 + }, + { + "epoch": 1.734357848518112, + "grad_norm": 0.4049508571624756, + "learning_rate": 0.0002, + "loss": 1.0913, + "step": 790 + }, + { + "epoch": 1.756311745334797, + "grad_norm": 0.48557212948799133, + "learning_rate": 0.0002, + "loss": 1.1329, + "step": 800 + }, + { + "epoch": 1.778265642151482, + "grad_norm": 0.5331754088401794, + "learning_rate": 0.0002, + "loss": 1.0729, + "step": 810 + }, + { + "epoch": 1.8002195389681668, + "grad_norm": 0.3853185772895813, + "learning_rate": 0.0002, + "loss": 1.1452, + "step": 820 + }, + { + "epoch": 1.8221734357848518, + "grad_norm": 0.424062579870224, + "learning_rate": 0.0002, + "loss": 1.1061, + "step": 830 + }, + { + "epoch": 1.8441273326015368, + "grad_norm": 0.3418445289134979, + "learning_rate": 0.0002, + "loss": 1.1104, + "step": 840 + }, + { + "epoch": 1.8660812294182216, + "grad_norm": 0.4045565128326416, + "learning_rate": 0.0002, + "loss": 1.0546, + "step": 850 + }, + { + "epoch": 1.8880351262349067, + "grad_norm": 0.42155781388282776, + "learning_rate": 0.0002, + "loss": 1.1608, + "step": 860 + }, + { + "epoch": 1.9099890230515917, + "grad_norm": 0.40554770827293396, + "learning_rate": 0.0002, + "loss": 1.0628, + "step": 870 + }, + { + "epoch": 1.9319429198682765, + "grad_norm": 0.42644748091697693, + "learning_rate": 0.0002, + "loss": 1.1609, + "step": 880 + }, + { + "epoch": 1.9538968166849617, + "grad_norm": 0.45260652899742126, + "learning_rate": 0.0002, + "loss": 1.1132, + "step": 890 + }, + { + "epoch": 1.9758507135016465, + "grad_norm": 0.4114069938659668, + "learning_rate": 0.0002, + "loss": 1.048, + "step": 900 + }, + { + "epoch": 1.9978046103183313, + "grad_norm": 0.375802218914032, + "learning_rate": 0.0002, + "loss": 1.1941, + "step": 910 + }, + { + "epoch": 2.0, + "eval_loss": 1.205152153968811, + "eval_runtime": 86.8795, + "eval_samples_per_second": 4.961, + "eval_steps_per_second": 0.622, + "step": 911 + }, + { + "epoch": 2.0197585071350166, + "grad_norm": 0.47718703746795654, + "learning_rate": 0.0002, + "loss": 1.0897, + "step": 920 + }, + { + "epoch": 2.0417124039517014, + "grad_norm": 0.45628082752227783, + "learning_rate": 0.0002, + "loss": 1.0329, + "step": 930 + }, + { + "epoch": 2.063666300768386, + "grad_norm": 0.5933247804641724, + "learning_rate": 0.0002, + "loss": 1.0538, + "step": 940 + }, + { + "epoch": 2.0856201975850714, + "grad_norm": 0.5355812907218933, + "learning_rate": 0.0002, + "loss": 1.0152, + "step": 950 + }, + { + "epoch": 2.1075740944017562, + "grad_norm": 0.5860010385513306, + "learning_rate": 0.0002, + "loss": 1.0726, + "step": 960 + }, + { + "epoch": 2.129527991218441, + "grad_norm": 0.7471673488616943, + "learning_rate": 0.0002, + "loss": 1.025, + "step": 970 + }, + { + "epoch": 2.1514818880351263, + "grad_norm": 2.0918211936950684, + "learning_rate": 0.0002, + "loss": 1.0247, + "step": 980 + }, + { + "epoch": 2.173435784851811, + "grad_norm": 0.4021058678627014, + "learning_rate": 0.0002, + "loss": 0.8947, + "step": 990 + }, + { + "epoch": 2.1953896816684964, + "grad_norm": 0.564975380897522, + "learning_rate": 0.0002, + "loss": 0.8875, + "step": 1000 + }, + { + "epoch": 2.217343578485181, + "grad_norm": 0.46260079741477966, + "learning_rate": 0.0002, + "loss": 1.0264, + "step": 1010 + }, + { + "epoch": 2.239297475301866, + "grad_norm": 0.4791034460067749, + "learning_rate": 0.0002, + "loss": 0.9265, + "step": 1020 + }, + { + "epoch": 2.261251372118551, + "grad_norm": 0.5272043943405151, + "learning_rate": 0.0002, + "loss": 0.8869, + "step": 1030 + }, + { + "epoch": 2.283205268935236, + "grad_norm": 0.5221094489097595, + "learning_rate": 0.0002, + "loss": 1.0007, + "step": 1040 + }, + { + "epoch": 2.305159165751921, + "grad_norm": 0.558032751083374, + "learning_rate": 0.0002, + "loss": 0.9472, + "step": 1050 + }, + { + "epoch": 2.327113062568606, + "grad_norm": 0.5905590653419495, + "learning_rate": 0.0002, + "loss": 0.9617, + "step": 1060 + }, + { + "epoch": 2.349066959385291, + "grad_norm": 0.5308699607849121, + "learning_rate": 0.0002, + "loss": 0.9592, + "step": 1070 + }, + { + "epoch": 2.3710208562019757, + "grad_norm": 0.6375027894973755, + "learning_rate": 0.0002, + "loss": 1.0646, + "step": 1080 + }, + { + "epoch": 2.392974753018661, + "grad_norm": 0.7439115643501282, + "learning_rate": 0.0002, + "loss": 1.0354, + "step": 1090 + }, + { + "epoch": 2.4149286498353457, + "grad_norm": 0.41945117712020874, + "learning_rate": 0.0002, + "loss": 1.0212, + "step": 1100 + }, + { + "epoch": 2.436882546652031, + "grad_norm": 0.4891968369483948, + "learning_rate": 0.0002, + "loss": 0.9609, + "step": 1110 + }, + { + "epoch": 2.4588364434687158, + "grad_norm": 0.4686794579029083, + "learning_rate": 0.0002, + "loss": 0.9829, + "step": 1120 + }, + { + "epoch": 2.4807903402854006, + "grad_norm": 0.5204509496688843, + "learning_rate": 0.0002, + "loss": 0.8919, + "step": 1130 + }, + { + "epoch": 2.5027442371020854, + "grad_norm": 0.6779005527496338, + "learning_rate": 0.0002, + "loss": 0.8983, + "step": 1140 + }, + { + "epoch": 2.5246981339187706, + "grad_norm": 0.682621955871582, + "learning_rate": 0.0002, + "loss": 0.9733, + "step": 1150 + }, + { + "epoch": 2.5466520307354554, + "grad_norm": 0.5744376182556152, + "learning_rate": 0.0002, + "loss": 1.051, + "step": 1160 + }, + { + "epoch": 2.5686059275521407, + "grad_norm": 0.49954667687416077, + "learning_rate": 0.0002, + "loss": 0.8764, + "step": 1170 + }, + { + "epoch": 2.5905598243688255, + "grad_norm": 0.4761793315410614, + "learning_rate": 0.0002, + "loss": 0.9896, + "step": 1180 + }, + { + "epoch": 2.6125137211855103, + "grad_norm": 0.548299252986908, + "learning_rate": 0.0002, + "loss": 0.8593, + "step": 1190 + }, + { + "epoch": 2.6344676180021955, + "grad_norm": 0.5771360993385315, + "learning_rate": 0.0002, + "loss": 1.0017, + "step": 1200 + }, + { + "epoch": 2.6564215148188803, + "grad_norm": 0.5543120503425598, + "learning_rate": 0.0002, + "loss": 0.9858, + "step": 1210 + }, + { + "epoch": 2.6783754116355656, + "grad_norm": 0.7564870715141296, + "learning_rate": 0.0002, + "loss": 0.9565, + "step": 1220 + }, + { + "epoch": 2.7003293084522504, + "grad_norm": 0.8222362399101257, + "learning_rate": 0.0002, + "loss": 0.9753, + "step": 1230 + }, + { + "epoch": 2.722283205268935, + "grad_norm": 0.6894469857215881, + "learning_rate": 0.0002, + "loss": 1.0079, + "step": 1240 + }, + { + "epoch": 2.74423710208562, + "grad_norm": 0.6121546030044556, + "learning_rate": 0.0002, + "loss": 1.0106, + "step": 1250 + }, + { + "epoch": 2.7661909989023052, + "grad_norm": 0.521809995174408, + "learning_rate": 0.0002, + "loss": 0.9801, + "step": 1260 + }, + { + "epoch": 2.78814489571899, + "grad_norm": 0.766968309879303, + "learning_rate": 0.0002, + "loss": 1.0196, + "step": 1270 + }, + { + "epoch": 2.8100987925356753, + "grad_norm": 0.522331714630127, + "learning_rate": 0.0002, + "loss": 0.976, + "step": 1280 + }, + { + "epoch": 2.83205268935236, + "grad_norm": 0.42923519015312195, + "learning_rate": 0.0002, + "loss": 0.8866, + "step": 1290 + }, + { + "epoch": 2.854006586169045, + "grad_norm": 0.47810837626457214, + "learning_rate": 0.0002, + "loss": 0.9049, + "step": 1300 + }, + { + "epoch": 2.8759604829857297, + "grad_norm": 1.0958846807479858, + "learning_rate": 0.0002, + "loss": 1.0291, + "step": 1310 + }, + { + "epoch": 2.897914379802415, + "grad_norm": 0.4755791127681732, + "learning_rate": 0.0002, + "loss": 0.8724, + "step": 1320 + }, + { + "epoch": 2.9198682766190998, + "grad_norm": 0.5575157403945923, + "learning_rate": 0.0002, + "loss": 0.9317, + "step": 1330 + }, + { + "epoch": 2.941822173435785, + "grad_norm": 0.5938076376914978, + "learning_rate": 0.0002, + "loss": 1.0131, + "step": 1340 + }, + { + "epoch": 2.96377607025247, + "grad_norm": 0.5751763582229614, + "learning_rate": 0.0002, + "loss": 0.9857, + "step": 1350 + }, + { + "epoch": 2.9857299670691546, + "grad_norm": 0.5590175986289978, + "learning_rate": 0.0002, + "loss": 1.0212, + "step": 1360 + }, + { + "epoch": 2.9989023051591657, + "eval_loss": 1.2402944564819336, + "eval_runtime": 88.822, + "eval_samples_per_second": 4.852, + "eval_steps_per_second": 0.608, + "step": 1366 + }, + { + "epoch": 3.00768386388584, + "grad_norm": 0.463539719581604, + "learning_rate": 0.0002, + "loss": 0.844, + "step": 1370 + }, + { + "epoch": 3.0296377607025247, + "grad_norm": 0.6667885780334473, + "learning_rate": 0.0002, + "loss": 0.8955, + "step": 1380 + }, + { + "epoch": 3.0515916575192095, + "grad_norm": 0.5849342942237854, + "learning_rate": 0.0002, + "loss": 0.8765, + "step": 1390 + }, + { + "epoch": 3.0735455543358947, + "grad_norm": 0.5571770668029785, + "learning_rate": 0.0002, + "loss": 0.7808, + "step": 1400 + }, + { + "epoch": 3.0954994511525795, + "grad_norm": 0.5761234164237976, + "learning_rate": 0.0002, + "loss": 0.7448, + "step": 1410 + }, + { + "epoch": 3.1174533479692643, + "grad_norm": 0.7277371883392334, + "learning_rate": 0.0002, + "loss": 0.7854, + "step": 1420 + }, + { + "epoch": 3.1394072447859496, + "grad_norm": 0.5190334320068359, + "learning_rate": 0.0002, + "loss": 0.817, + "step": 1430 + }, + { + "epoch": 3.1613611416026344, + "grad_norm": 0.632939875125885, + "learning_rate": 0.0002, + "loss": 0.7548, + "step": 1440 + }, + { + "epoch": 3.1833150384193196, + "grad_norm": 0.7229540944099426, + "learning_rate": 0.0002, + "loss": 0.8447, + "step": 1450 + }, + { + "epoch": 3.2052689352360044, + "grad_norm": 0.7584632039070129, + "learning_rate": 0.0002, + "loss": 0.8595, + "step": 1460 + }, + { + "epoch": 3.2272228320526892, + "grad_norm": 0.6546088457107544, + "learning_rate": 0.0002, + "loss": 0.7456, + "step": 1470 + }, + { + "epoch": 3.2491767288693745, + "grad_norm": 0.8116684556007385, + "learning_rate": 0.0002, + "loss": 0.8531, + "step": 1480 + }, + { + "epoch": 3.2711306256860593, + "grad_norm": 0.6206557750701904, + "learning_rate": 0.0002, + "loss": 0.9272, + "step": 1490 + }, + { + "epoch": 3.293084522502744, + "grad_norm": 0.5393369197845459, + "learning_rate": 0.0002, + "loss": 0.7972, + "step": 1500 + }, + { + "epoch": 3.3150384193194293, + "grad_norm": 0.7006453275680542, + "learning_rate": 0.0002, + "loss": 0.7614, + "step": 1510 + }, + { + "epoch": 3.336992316136114, + "grad_norm": 0.95253986120224, + "learning_rate": 0.0002, + "loss": 0.7358, + "step": 1520 + }, + { + "epoch": 3.358946212952799, + "grad_norm": 0.8138132095336914, + "learning_rate": 0.0002, + "loss": 0.8131, + "step": 1530 + }, + { + "epoch": 3.380900109769484, + "grad_norm": 0.7974302172660828, + "learning_rate": 0.0002, + "loss": 0.7738, + "step": 1540 + }, + { + "epoch": 3.402854006586169, + "grad_norm": 0.6694685220718384, + "learning_rate": 0.0002, + "loss": 0.8161, + "step": 1550 + }, + { + "epoch": 3.4248079034028542, + "grad_norm": 0.908634603023529, + "learning_rate": 0.0002, + "loss": 0.8503, + "step": 1560 + }, + { + "epoch": 3.446761800219539, + "grad_norm": 0.5625193119049072, + "learning_rate": 0.0002, + "loss": 0.7609, + "step": 1570 + }, + { + "epoch": 3.468715697036224, + "grad_norm": 0.779325544834137, + "learning_rate": 0.0002, + "loss": 0.7658, + "step": 1580 + }, + { + "epoch": 3.4906695938529086, + "grad_norm": 0.7133058905601501, + "learning_rate": 0.0002, + "loss": 0.7485, + "step": 1590 + }, + { + "epoch": 3.512623490669594, + "grad_norm": 0.6741108298301697, + "learning_rate": 0.0002, + "loss": 0.8847, + "step": 1600 + }, + { + "epoch": 3.5345773874862787, + "grad_norm": 0.696982204914093, + "learning_rate": 0.0002, + "loss": 0.7838, + "step": 1610 + }, + { + "epoch": 3.556531284302964, + "grad_norm": 0.7946001291275024, + "learning_rate": 0.0002, + "loss": 0.7195, + "step": 1620 + }, + { + "epoch": 3.5784851811196488, + "grad_norm": 0.6313548684120178, + "learning_rate": 0.0002, + "loss": 0.7772, + "step": 1630 + }, + { + "epoch": 3.6004390779363336, + "grad_norm": 0.9246852397918701, + "learning_rate": 0.0002, + "loss": 0.8267, + "step": 1640 + }, + { + "epoch": 3.622392974753019, + "grad_norm": 0.6615420579910278, + "learning_rate": 0.0002, + "loss": 0.779, + "step": 1650 + }, + { + "epoch": 3.6443468715697036, + "grad_norm": 1.5050125122070312, + "learning_rate": 0.0002, + "loss": 0.883, + "step": 1660 + }, + { + "epoch": 3.666300768386389, + "grad_norm": 0.5023762583732605, + "learning_rate": 0.0002, + "loss": 0.7763, + "step": 1670 + }, + { + "epoch": 3.6882546652030737, + "grad_norm": 0.6289586424827576, + "learning_rate": 0.0002, + "loss": 0.8173, + "step": 1680 + }, + { + "epoch": 3.7102085620197585, + "grad_norm": 1.050397515296936, + "learning_rate": 0.0002, + "loss": 0.9028, + "step": 1690 + }, + { + "epoch": 3.7321624588364433, + "grad_norm": 0.6785626411437988, + "learning_rate": 0.0002, + "loss": 0.7747, + "step": 1700 + }, + { + "epoch": 3.7541163556531285, + "grad_norm": 0.7565035223960876, + "learning_rate": 0.0002, + "loss": 0.9215, + "step": 1710 + }, + { + "epoch": 3.7760702524698133, + "grad_norm": 0.7775155901908875, + "learning_rate": 0.0002, + "loss": 0.7913, + "step": 1720 + }, + { + "epoch": 3.7980241492864986, + "grad_norm": 0.765260636806488, + "learning_rate": 0.0002, + "loss": 0.8081, + "step": 1730 + }, + { + "epoch": 3.8199780461031834, + "grad_norm": 0.7982407808303833, + "learning_rate": 0.0002, + "loss": 0.9231, + "step": 1740 + }, + { + "epoch": 3.841931942919868, + "grad_norm": 0.7431730628013611, + "learning_rate": 0.0002, + "loss": 0.7755, + "step": 1750 + }, + { + "epoch": 3.863885839736553, + "grad_norm": 0.9758927226066589, + "learning_rate": 0.0002, + "loss": 0.9236, + "step": 1760 + }, + { + "epoch": 3.885839736553238, + "grad_norm": 0.8014697432518005, + "learning_rate": 0.0002, + "loss": 0.9118, + "step": 1770 + }, + { + "epoch": 3.907793633369923, + "grad_norm": 0.7212756276130676, + "learning_rate": 0.0002, + "loss": 0.7503, + "step": 1780 + }, + { + "epoch": 3.9297475301866083, + "grad_norm": 0.584318220615387, + "learning_rate": 0.0002, + "loss": 0.7978, + "step": 1790 + }, + { + "epoch": 3.951701427003293, + "grad_norm": 0.7612535953521729, + "learning_rate": 0.0002, + "loss": 0.7894, + "step": 1800 + }, + { + "epoch": 3.973655323819978, + "grad_norm": 0.735103189945221, + "learning_rate": 0.0002, + "loss": 0.8589, + "step": 1810 + }, + { + "epoch": 3.995609220636663, + "grad_norm": 0.9074980020523071, + "learning_rate": 0.0002, + "loss": 0.8192, + "step": 1820 + }, + { + "epoch": 4.0, + "eval_loss": 1.279890537261963, + "eval_runtime": 88.8969, + "eval_samples_per_second": 4.848, + "eval_steps_per_second": 0.607, + "step": 1822 + }, + { + "epoch": 4.017563117453348, + "grad_norm": 0.9290254712104797, + "learning_rate": 0.0002, + "loss": 0.7312, + "step": 1830 + }, + { + "epoch": 4.039517014270033, + "grad_norm": 0.723889946937561, + "learning_rate": 0.0002, + "loss": 0.6896, + "step": 1840 + }, + { + "epoch": 4.061470911086718, + "grad_norm": 0.5906972289085388, + "learning_rate": 0.0002, + "loss": 0.632, + "step": 1850 + }, + { + "epoch": 4.083424807903403, + "grad_norm": 0.8078910708427429, + "learning_rate": 0.0002, + "loss": 0.6594, + "step": 1860 + }, + { + "epoch": 4.105378704720088, + "grad_norm": 1.0101137161254883, + "learning_rate": 0.0002, + "loss": 0.6242, + "step": 1870 + }, + { + "epoch": 4.127332601536772, + "grad_norm": 0.8710281848907471, + "learning_rate": 0.0002, + "loss": 0.7259, + "step": 1880 + }, + { + "epoch": 4.149286498353458, + "grad_norm": 0.9604734778404236, + "learning_rate": 0.0002, + "loss": 0.6993, + "step": 1890 + }, + { + "epoch": 4.171240395170143, + "grad_norm": 0.9829702377319336, + "learning_rate": 0.0002, + "loss": 0.6706, + "step": 1900 + }, + { + "epoch": 4.193194291986828, + "grad_norm": 0.6572765707969666, + "learning_rate": 0.0002, + "loss": 0.7013, + "step": 1910 + }, + { + "epoch": 4.2151481888035125, + "grad_norm": 0.8459188938140869, + "learning_rate": 0.0002, + "loss": 0.5539, + "step": 1920 + }, + { + "epoch": 4.237102085620197, + "grad_norm": 0.8321021795272827, + "learning_rate": 0.0002, + "loss": 0.6235, + "step": 1930 + }, + { + "epoch": 4.259055982436882, + "grad_norm": 0.8611727356910706, + "learning_rate": 0.0002, + "loss": 0.6442, + "step": 1940 + }, + { + "epoch": 4.281009879253568, + "grad_norm": 0.8490208387374878, + "learning_rate": 0.0002, + "loss": 0.6852, + "step": 1950 + }, + { + "epoch": 4.302963776070253, + "grad_norm": 0.9628722667694092, + "learning_rate": 0.0002, + "loss": 0.6175, + "step": 1960 + }, + { + "epoch": 4.324917672886937, + "grad_norm": 0.9632807374000549, + "learning_rate": 0.0002, + "loss": 0.5982, + "step": 1970 + }, + { + "epoch": 4.346871569703622, + "grad_norm": 0.7023298740386963, + "learning_rate": 0.0002, + "loss": 0.6138, + "step": 1980 + }, + { + "epoch": 4.368825466520307, + "grad_norm": 0.7912909388542175, + "learning_rate": 0.0002, + "loss": 0.6012, + "step": 1990 + }, + { + "epoch": 4.390779363336993, + "grad_norm": 1.1463429927825928, + "learning_rate": 0.0002, + "loss": 0.6767, + "step": 2000 + }, + { + "epoch": 4.4127332601536775, + "grad_norm": 1.1780626773834229, + "learning_rate": 0.0002, + "loss": 0.6607, + "step": 2010 + }, + { + "epoch": 4.434687156970362, + "grad_norm": 0.9349206686019897, + "learning_rate": 0.0002, + "loss": 0.6746, + "step": 2020 + }, + { + "epoch": 4.456641053787047, + "grad_norm": 0.7816639542579651, + "learning_rate": 0.0002, + "loss": 0.7087, + "step": 2030 + }, + { + "epoch": 4.478594950603732, + "grad_norm": 0.7005311250686646, + "learning_rate": 0.0002, + "loss": 0.6222, + "step": 2040 + }, + { + "epoch": 4.500548847420417, + "grad_norm": 0.7746558785438538, + "learning_rate": 0.0002, + "loss": 0.6608, + "step": 2050 + }, + { + "epoch": 4.522502744237102, + "grad_norm": 0.8261151313781738, + "learning_rate": 0.0002, + "loss": 0.6305, + "step": 2060 + }, + { + "epoch": 4.544456641053787, + "grad_norm": 1.0917805433273315, + "learning_rate": 0.0002, + "loss": 0.6502, + "step": 2070 + }, + { + "epoch": 4.566410537870472, + "grad_norm": 1.1570647954940796, + "learning_rate": 0.0002, + "loss": 0.6798, + "step": 2080 + }, + { + "epoch": 4.588364434687157, + "grad_norm": 0.9936433434486389, + "learning_rate": 0.0002, + "loss": 0.6296, + "step": 2090 + }, + { + "epoch": 4.610318331503842, + "grad_norm": 0.8574427366256714, + "learning_rate": 0.0002, + "loss": 0.5936, + "step": 2100 + }, + { + "epoch": 4.632272228320527, + "grad_norm": 0.7630168795585632, + "learning_rate": 0.0002, + "loss": 0.6529, + "step": 2110 + }, + { + "epoch": 4.654226125137212, + "grad_norm": 0.8146462440490723, + "learning_rate": 0.0002, + "loss": 0.5935, + "step": 2120 + }, + { + "epoch": 4.676180021953897, + "grad_norm": 0.7090407609939575, + "learning_rate": 0.0002, + "loss": 0.7102, + "step": 2130 + }, + { + "epoch": 4.698133918770582, + "grad_norm": 0.8278160095214844, + "learning_rate": 0.0002, + "loss": 0.6575, + "step": 2140 + }, + { + "epoch": 4.7200878155872665, + "grad_norm": 0.9415683746337891, + "learning_rate": 0.0002, + "loss": 0.664, + "step": 2150 + }, + { + "epoch": 4.742041712403951, + "grad_norm": 1.0056205987930298, + "learning_rate": 0.0002, + "loss": 0.7283, + "step": 2160 + }, + { + "epoch": 4.763995609220637, + "grad_norm": 0.768304705619812, + "learning_rate": 0.0002, + "loss": 0.6845, + "step": 2170 + }, + { + "epoch": 4.785949506037322, + "grad_norm": 1.0604112148284912, + "learning_rate": 0.0002, + "loss": 0.6922, + "step": 2180 + }, + { + "epoch": 4.807903402854007, + "grad_norm": 1.132864236831665, + "learning_rate": 0.0002, + "loss": 0.7092, + "step": 2190 + }, + { + "epoch": 4.829857299670691, + "grad_norm": 0.7543689608573914, + "learning_rate": 0.0002, + "loss": 0.6936, + "step": 2200 + }, + { + "epoch": 4.851811196487376, + "grad_norm": 0.8047362565994263, + "learning_rate": 0.0002, + "loss": 0.6921, + "step": 2210 + }, + { + "epoch": 4.873765093304062, + "grad_norm": 1.135778546333313, + "learning_rate": 0.0002, + "loss": 0.6753, + "step": 2220 + }, + { + "epoch": 4.895718990120747, + "grad_norm": 0.9068503379821777, + "learning_rate": 0.0002, + "loss": 0.6443, + "step": 2230 + }, + { + "epoch": 4.9176728869374315, + "grad_norm": 1.822325587272644, + "learning_rate": 0.0002, + "loss": 0.7419, + "step": 2240 + }, + { + "epoch": 4.939626783754116, + "grad_norm": 1.1124998331069946, + "learning_rate": 0.0002, + "loss": 0.6436, + "step": 2250 + }, + { + "epoch": 4.961580680570801, + "grad_norm": 0.818484365940094, + "learning_rate": 0.0002, + "loss": 0.7423, + "step": 2260 + }, + { + "epoch": 4.983534577387486, + "grad_norm": 1.0057194232940674, + "learning_rate": 0.0002, + "loss": 0.6872, + "step": 2270 + }, + { + "epoch": 4.998902305159166, + "eval_loss": 1.4120490550994873, + "eval_runtime": 87.5617, + "eval_samples_per_second": 4.922, + "eval_steps_per_second": 0.617, + "step": 2277 + }, + { + "epoch": 5.005488474204172, + "grad_norm": 0.8211547136306763, + "learning_rate": 0.0002, + "loss": 0.5451, + "step": 2280 + }, + { + "epoch": 5.0274423710208564, + "grad_norm": 1.1704130172729492, + "learning_rate": 0.0002, + "loss": 0.4965, + "step": 2290 + }, + { + "epoch": 5.049396267837541, + "grad_norm": 1.033539891242981, + "learning_rate": 0.0002, + "loss": 0.4827, + "step": 2300 + }, + { + "epoch": 5.071350164654226, + "grad_norm": 0.8830313682556152, + "learning_rate": 0.0002, + "loss": 0.447, + "step": 2310 + }, + { + "epoch": 5.093304061470911, + "grad_norm": 1.160437822341919, + "learning_rate": 0.0002, + "loss": 0.5502, + "step": 2320 + }, + { + "epoch": 5.115257958287596, + "grad_norm": 0.919956386089325, + "learning_rate": 0.0002, + "loss": 0.5123, + "step": 2330 + }, + { + "epoch": 5.137211855104281, + "grad_norm": 1.0099905729293823, + "learning_rate": 0.0002, + "loss": 0.4784, + "step": 2340 + }, + { + "epoch": 5.159165751920966, + "grad_norm": 1.1484816074371338, + "learning_rate": 0.0002, + "loss": 0.5109, + "step": 2350 + }, + { + "epoch": 5.181119648737651, + "grad_norm": 1.0373470783233643, + "learning_rate": 0.0002, + "loss": 0.5222, + "step": 2360 + }, + { + "epoch": 5.203073545554336, + "grad_norm": 1.0824922323226929, + "learning_rate": 0.0002, + "loss": 0.5366, + "step": 2370 + }, + { + "epoch": 5.225027442371021, + "grad_norm": 1.3817942142486572, + "learning_rate": 0.0002, + "loss": 0.5592, + "step": 2380 + }, + { + "epoch": 5.246981339187705, + "grad_norm": 1.197035551071167, + "learning_rate": 0.0002, + "loss": 0.504, + "step": 2390 + }, + { + "epoch": 5.268935236004391, + "grad_norm": 1.098778486251831, + "learning_rate": 0.0002, + "loss": 0.5326, + "step": 2400 + }, + { + "epoch": 5.290889132821076, + "grad_norm": 0.9713385105133057, + "learning_rate": 0.0002, + "loss": 0.5039, + "step": 2410 + }, + { + "epoch": 5.312843029637761, + "grad_norm": 1.321574330329895, + "learning_rate": 0.0002, + "loss": 0.5735, + "step": 2420 + }, + { + "epoch": 5.3347969264544455, + "grad_norm": 0.9402496218681335, + "learning_rate": 0.0002, + "loss": 0.4777, + "step": 2430 + }, + { + "epoch": 5.35675082327113, + "grad_norm": 0.8644852042198181, + "learning_rate": 0.0002, + "loss": 0.5604, + "step": 2440 + }, + { + "epoch": 5.378704720087816, + "grad_norm": 1.060290813446045, + "learning_rate": 0.0002, + "loss": 0.5324, + "step": 2450 + }, + { + "epoch": 5.400658616904501, + "grad_norm": 1.0725265741348267, + "learning_rate": 0.0002, + "loss": 0.5366, + "step": 2460 + }, + { + "epoch": 5.422612513721186, + "grad_norm": 0.9409431219100952, + "learning_rate": 0.0002, + "loss": 0.5469, + "step": 2470 + }, + { + "epoch": 5.44456641053787, + "grad_norm": 1.1108187437057495, + "learning_rate": 0.0002, + "loss": 0.5186, + "step": 2480 + }, + { + "epoch": 5.466520307354555, + "grad_norm": 1.0210821628570557, + "learning_rate": 0.0002, + "loss": 0.5312, + "step": 2490 + }, + { + "epoch": 5.48847420417124, + "grad_norm": 1.110597014427185, + "learning_rate": 0.0002, + "loss": 0.5016, + "step": 2500 + }, + { + "epoch": 5.510428100987926, + "grad_norm": 1.2534265518188477, + "learning_rate": 0.0002, + "loss": 0.511, + "step": 2510 + }, + { + "epoch": 5.5323819978046105, + "grad_norm": 1.3389744758605957, + "learning_rate": 0.0002, + "loss": 0.6062, + "step": 2520 + }, + { + "epoch": 5.554335894621295, + "grad_norm": 0.9520368576049805, + "learning_rate": 0.0002, + "loss": 0.4653, + "step": 2530 + }, + { + "epoch": 5.57628979143798, + "grad_norm": 1.4737157821655273, + "learning_rate": 0.0002, + "loss": 0.4746, + "step": 2540 + }, + { + "epoch": 5.598243688254665, + "grad_norm": 1.4143685102462769, + "learning_rate": 0.0002, + "loss": 0.5432, + "step": 2550 + }, + { + "epoch": 5.620197585071351, + "grad_norm": 1.3573999404907227, + "learning_rate": 0.0002, + "loss": 0.4722, + "step": 2560 + }, + { + "epoch": 5.642151481888035, + "grad_norm": 0.8475444316864014, + "learning_rate": 0.0002, + "loss": 0.5063, + "step": 2570 + }, + { + "epoch": 5.66410537870472, + "grad_norm": 1.2670329809188843, + "learning_rate": 0.0002, + "loss": 0.4911, + "step": 2580 + }, + { + "epoch": 5.686059275521405, + "grad_norm": 0.9688172936439514, + "learning_rate": 0.0002, + "loss": 0.5137, + "step": 2590 + }, + { + "epoch": 5.70801317233809, + "grad_norm": 1.3652743101119995, + "learning_rate": 0.0002, + "loss": 0.5116, + "step": 2600 + }, + { + "epoch": 5.729967069154775, + "grad_norm": 1.1475377082824707, + "learning_rate": 0.0002, + "loss": 0.5661, + "step": 2610 + }, + { + "epoch": 5.75192096597146, + "grad_norm": 1.3105946779251099, + "learning_rate": 0.0002, + "loss": 0.567, + "step": 2620 + }, + { + "epoch": 5.773874862788145, + "grad_norm": 0.920238196849823, + "learning_rate": 0.0002, + "loss": 0.4964, + "step": 2630 + }, + { + "epoch": 5.79582875960483, + "grad_norm": 1.0981792211532593, + "learning_rate": 0.0002, + "loss": 0.5473, + "step": 2640 + }, + { + "epoch": 5.817782656421515, + "grad_norm": 1.0734144449234009, + "learning_rate": 0.0002, + "loss": 0.5132, + "step": 2650 + }, + { + "epoch": 5.8397365532381995, + "grad_norm": 1.0541702508926392, + "learning_rate": 0.0002, + "loss": 0.5404, + "step": 2660 + }, + { + "epoch": 5.861690450054885, + "grad_norm": 1.0913143157958984, + "learning_rate": 0.0002, + "loss": 0.5056, + "step": 2670 + }, + { + "epoch": 5.88364434687157, + "grad_norm": 1.0431408882141113, + "learning_rate": 0.0002, + "loss": 0.5425, + "step": 2680 + }, + { + "epoch": 5.905598243688255, + "grad_norm": 1.3515729904174805, + "learning_rate": 0.0002, + "loss": 0.5398, + "step": 2690 + }, + { + "epoch": 5.92755214050494, + "grad_norm": 1.3153903484344482, + "learning_rate": 0.0002, + "loss": 0.5936, + "step": 2700 + }, + { + "epoch": 5.949506037321624, + "grad_norm": 1.024109125137329, + "learning_rate": 0.0002, + "loss": 0.5643, + "step": 2710 + }, + { + "epoch": 5.971459934138309, + "grad_norm": 1.0308483839035034, + "learning_rate": 0.0002, + "loss": 0.5143, + "step": 2720 + }, + { + "epoch": 5.993413830954994, + "grad_norm": 0.8329401016235352, + "learning_rate": 0.0002, + "loss": 0.4835, + "step": 2730 + }, + { + "epoch": 6.0, + "eval_loss": 1.510581612586975, + "eval_runtime": 89.0047, + "eval_samples_per_second": 4.842, + "eval_steps_per_second": 0.607, + "step": 2733 + }, + { + "epoch": 6.01536772777168, + "grad_norm": 1.1903921365737915, + "learning_rate": 0.0002, + "loss": 0.4282, + "step": 2740 + }, + { + "epoch": 6.0373216245883645, + "grad_norm": 1.0170859098434448, + "learning_rate": 0.0002, + "loss": 0.3844, + "step": 2750 + }, + { + "epoch": 6.059275521405049, + "grad_norm": 1.269655704498291, + "learning_rate": 0.0002, + "loss": 0.4116, + "step": 2760 + }, + { + "epoch": 6.081229418221734, + "grad_norm": 1.1271249055862427, + "learning_rate": 0.0002, + "loss": 0.381, + "step": 2770 + }, + { + "epoch": 6.103183315038419, + "grad_norm": 1.0269793272018433, + "learning_rate": 0.0002, + "loss": 0.391, + "step": 2780 + }, + { + "epoch": 6.125137211855105, + "grad_norm": 1.1622686386108398, + "learning_rate": 0.0002, + "loss": 0.3896, + "step": 2790 + }, + { + "epoch": 6.147091108671789, + "grad_norm": 1.3457845449447632, + "learning_rate": 0.0002, + "loss": 0.3907, + "step": 2800 + }, + { + "epoch": 6.169045005488474, + "grad_norm": 1.008620262145996, + "learning_rate": 0.0002, + "loss": 0.3447, + "step": 2810 + }, + { + "epoch": 6.190998902305159, + "grad_norm": 0.9964058995246887, + "learning_rate": 0.0002, + "loss": 0.3437, + "step": 2820 + }, + { + "epoch": 6.212952799121844, + "grad_norm": 1.265552043914795, + "learning_rate": 0.0002, + "loss": 0.4073, + "step": 2830 + }, + { + "epoch": 6.234906695938529, + "grad_norm": 1.0481451749801636, + "learning_rate": 0.0002, + "loss": 0.4199, + "step": 2840 + }, + { + "epoch": 6.256860592755214, + "grad_norm": 1.3813395500183105, + "learning_rate": 0.0002, + "loss": 0.4243, + "step": 2850 + }, + { + "epoch": 6.278814489571899, + "grad_norm": 1.1307486295700073, + "learning_rate": 0.0002, + "loss": 0.4039, + "step": 2860 + }, + { + "epoch": 6.300768386388584, + "grad_norm": 1.122252106666565, + "learning_rate": 0.0002, + "loss": 0.3665, + "step": 2870 + }, + { + "epoch": 6.322722283205269, + "grad_norm": 0.9570856094360352, + "learning_rate": 0.0002, + "loss": 0.4377, + "step": 2880 + }, + { + "epoch": 6.3446761800219535, + "grad_norm": 1.429248332977295, + "learning_rate": 0.0002, + "loss": 0.3762, + "step": 2890 + }, + { + "epoch": 6.366630076838639, + "grad_norm": 1.228832483291626, + "learning_rate": 0.0002, + "loss": 0.3746, + "step": 2900 + }, + { + "epoch": 6.388583973655324, + "grad_norm": 0.9634972810745239, + "learning_rate": 0.0002, + "loss": 0.3714, + "step": 2910 + }, + { + "epoch": 6.410537870472009, + "grad_norm": 1.392120599746704, + "learning_rate": 0.0002, + "loss": 0.3856, + "step": 2920 + }, + { + "epoch": 6.432491767288694, + "grad_norm": 1.0452295541763306, + "learning_rate": 0.0002, + "loss": 0.4395, + "step": 2930 + }, + { + "epoch": 6.4544456641053785, + "grad_norm": 0.9953978657722473, + "learning_rate": 0.0002, + "loss": 0.4559, + "step": 2940 + }, + { + "epoch": 6.476399560922063, + "grad_norm": 1.090386986732483, + "learning_rate": 0.0002, + "loss": 0.4108, + "step": 2950 + }, + { + "epoch": 6.498353457738749, + "grad_norm": 1.2177232503890991, + "learning_rate": 0.0002, + "loss": 0.4059, + "step": 2960 + }, + { + "epoch": 6.520307354555434, + "grad_norm": 0.8435868620872498, + "learning_rate": 0.0002, + "loss": 0.4403, + "step": 2970 + }, + { + "epoch": 6.542261251372119, + "grad_norm": 1.0110384225845337, + "learning_rate": 0.0002, + "loss": 0.4143, + "step": 2980 + }, + { + "epoch": 6.564215148188803, + "grad_norm": 0.8551704287528992, + "learning_rate": 0.0002, + "loss": 0.4396, + "step": 2990 + }, + { + "epoch": 6.586169045005488, + "grad_norm": 1.2663729190826416, + "learning_rate": 0.0002, + "loss": 0.3908, + "step": 3000 + }, + { + "epoch": 6.608122941822174, + "grad_norm": 1.2262762784957886, + "learning_rate": 0.0002, + "loss": 0.3927, + "step": 3010 + }, + { + "epoch": 6.630076838638859, + "grad_norm": 1.3794647455215454, + "learning_rate": 0.0002, + "loss": 0.4183, + "step": 3020 + }, + { + "epoch": 6.6520307354555435, + "grad_norm": 0.9994757175445557, + "learning_rate": 0.0002, + "loss": 0.3903, + "step": 3030 + }, + { + "epoch": 6.673984632272228, + "grad_norm": 1.067501187324524, + "learning_rate": 0.0002, + "loss": 0.4083, + "step": 3040 + }, + { + "epoch": 6.695938529088913, + "grad_norm": 1.1194695234298706, + "learning_rate": 0.0002, + "loss": 0.4551, + "step": 3050 + }, + { + "epoch": 6.717892425905598, + "grad_norm": 1.572695255279541, + "learning_rate": 0.0002, + "loss": 0.4276, + "step": 3060 + }, + { + "epoch": 6.739846322722284, + "grad_norm": 1.063094139099121, + "learning_rate": 0.0002, + "loss": 0.3681, + "step": 3070 + }, + { + "epoch": 6.761800219538968, + "grad_norm": 1.2257463932037354, + "learning_rate": 0.0002, + "loss": 0.3656, + "step": 3080 + }, + { + "epoch": 6.783754116355653, + "grad_norm": 1.259731411933899, + "learning_rate": 0.0002, + "loss": 0.4504, + "step": 3090 + }, + { + "epoch": 6.805708013172338, + "grad_norm": 1.3234009742736816, + "learning_rate": 0.0002, + "loss": 0.4067, + "step": 3100 + }, + { + "epoch": 6.827661909989023, + "grad_norm": 1.4324477910995483, + "learning_rate": 0.0002, + "loss": 0.4913, + "step": 3110 + }, + { + "epoch": 6.8496158068057085, + "grad_norm": 1.4183896780014038, + "learning_rate": 0.0002, + "loss": 0.4408, + "step": 3120 + }, + { + "epoch": 6.871569703622393, + "grad_norm": 1.1369833946228027, + "learning_rate": 0.0002, + "loss": 0.4517, + "step": 3130 + }, + { + "epoch": 6.893523600439078, + "grad_norm": 1.2804654836654663, + "learning_rate": 0.0002, + "loss": 0.458, + "step": 3140 + }, + { + "epoch": 6.915477497255763, + "grad_norm": 1.535305380821228, + "learning_rate": 0.0002, + "loss": 0.4616, + "step": 3150 + }, + { + "epoch": 6.937431394072448, + "grad_norm": 1.2820420265197754, + "learning_rate": 0.0002, + "loss": 0.4178, + "step": 3160 + }, + { + "epoch": 6.9593852908891325, + "grad_norm": 1.1014128923416138, + "learning_rate": 0.0002, + "loss": 0.442, + "step": 3170 + }, + { + "epoch": 6.981339187705817, + "grad_norm": 0.9979909658432007, + "learning_rate": 0.0002, + "loss": 0.4379, + "step": 3180 + }, + { + "epoch": 6.998902305159166, + "eval_loss": 1.6552348136901855, + "eval_runtime": 88.8609, + "eval_samples_per_second": 4.85, + "eval_steps_per_second": 0.608, + "step": 3188 + } + ], + "logging_steps": 10, + "max_steps": 3640, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.475566406593413e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f75755c7cf71aeb05b76db2632173f96f74e8f7 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf90ce7dd53cc68edd44d14e30ca84a5d7431a5b99d4697b17af4b2f7ec0abab +size 5624 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/README.md b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/README.md new file mode 100644 index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/README.md @@ -0,0 +1,202 @@ +--- +base_model: meta-llama/Meta-Llama-3-8B-Instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.13.1 \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..406c5a08dc4a2a33b52c62a482f98c217c417215 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "v_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..02002595b1b96c88329343db6509ceb731872990 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ac0fc8e1c67ea27a709565bb5f83137e77415b684608aced3c9d4c6e0a469d1 +size 109069176 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/optimizer.pt b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..91d990153508f37567f6b4b964e4261136b88e59 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bcaf97dd9672de5a01249b71e6371cdaaba9174dda328ee8fd47d54c9eae838 +size 55532666 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/rng_state.pth b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..8c520d6839a9c59e1734d7f6941a38975a09a21e --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd0edfc81ffac99ca4be7be07bdf809b56dd301410ac19638c1862d47d935b26 +size 14244 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/scheduler.pt b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..f9cfc5587cb67fc8260a99b4993f873a67621966 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e57f07ef3bd784649891931742469967191a4b09f737552cd8be028ac6ade9ec +size 1064 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393 +size 17209961 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|eot_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/trainer_state.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..600189815ed2035ed35421aa809982242ae61343 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/trainer_state.json @@ -0,0 +1,2645 @@ +{ + "best_metric": 1.205152153968811, + "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911", + "epoch": 7.991218441273326, + "eval_steps": 10, + "global_step": 3640, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.021953896816684963, + "grad_norm": 0.6144012212753296, + "learning_rate": 0.0002, + "loss": 1.9887, + "step": 10 + }, + { + "epoch": 0.043907793633369926, + "grad_norm": 0.5587220788002014, + "learning_rate": 0.0002, + "loss": 1.6882, + "step": 20 + }, + { + "epoch": 0.06586169045005488, + "grad_norm": 0.43262454867362976, + "learning_rate": 0.0002, + "loss": 1.399, + "step": 30 + }, + { + "epoch": 0.08781558726673985, + "grad_norm": 0.4783053994178772, + "learning_rate": 0.0002, + "loss": 1.4675, + "step": 40 + }, + { + "epoch": 0.10976948408342481, + "grad_norm": 0.44338956475257874, + "learning_rate": 0.0002, + "loss": 1.1771, + "step": 50 + }, + { + "epoch": 0.13172338090010977, + "grad_norm": 0.7255092263221741, + "learning_rate": 0.0002, + "loss": 1.3706, + "step": 60 + }, + { + "epoch": 0.15367727771679474, + "grad_norm": 0.46073833107948303, + "learning_rate": 0.0002, + "loss": 1.2601, + "step": 70 + }, + { + "epoch": 0.1756311745334797, + "grad_norm": 0.6698123216629028, + "learning_rate": 0.0002, + "loss": 1.3049, + "step": 80 + }, + { + "epoch": 0.19758507135016465, + "grad_norm": 0.4190150201320648, + "learning_rate": 0.0002, + "loss": 1.2975, + "step": 90 + }, + { + "epoch": 0.21953896816684962, + "grad_norm": 0.4110015034675598, + "learning_rate": 0.0002, + "loss": 1.2797, + "step": 100 + }, + { + "epoch": 0.2414928649835346, + "grad_norm": 0.33374306559562683, + "learning_rate": 0.0002, + "loss": 1.2896, + "step": 110 + }, + { + "epoch": 0.26344676180021953, + "grad_norm": 0.3061307370662689, + "learning_rate": 0.0002, + "loss": 1.2268, + "step": 120 + }, + { + "epoch": 0.2854006586169045, + "grad_norm": 0.4386885166168213, + "learning_rate": 0.0002, + "loss": 1.376, + "step": 130 + }, + { + "epoch": 0.30735455543358947, + "grad_norm": 0.40116462111473083, + "learning_rate": 0.0002, + "loss": 1.1814, + "step": 140 + }, + { + "epoch": 0.32930845225027444, + "grad_norm": 0.5887949466705322, + "learning_rate": 0.0002, + "loss": 1.2592, + "step": 150 + }, + { + "epoch": 0.3512623490669594, + "grad_norm": 0.3401573896408081, + "learning_rate": 0.0002, + "loss": 1.2372, + "step": 160 + }, + { + "epoch": 0.3732162458836443, + "grad_norm": 0.3288364112377167, + "learning_rate": 0.0002, + "loss": 1.1901, + "step": 170 + }, + { + "epoch": 0.3951701427003293, + "grad_norm": 0.4853297472000122, + "learning_rate": 0.0002, + "loss": 1.2335, + "step": 180 + }, + { + "epoch": 0.41712403951701427, + "grad_norm": 2.6253697872161865, + "learning_rate": 0.0002, + "loss": 1.227, + "step": 190 + }, + { + "epoch": 0.43907793633369924, + "grad_norm": 0.5598543286323547, + "learning_rate": 0.0002, + "loss": 1.2673, + "step": 200 + }, + { + "epoch": 0.4610318331503842, + "grad_norm": 0.4046548902988434, + "learning_rate": 0.0002, + "loss": 1.3459, + "step": 210 + }, + { + "epoch": 0.4829857299670692, + "grad_norm": 0.3686952590942383, + "learning_rate": 0.0002, + "loss": 1.265, + "step": 220 + }, + { + "epoch": 0.5049396267837541, + "grad_norm": 0.42458799481391907, + "learning_rate": 0.0002, + "loss": 1.1364, + "step": 230 + }, + { + "epoch": 0.5268935236004391, + "grad_norm": 0.5839895009994507, + "learning_rate": 0.0002, + "loss": 1.2094, + "step": 240 + }, + { + "epoch": 0.5488474204171241, + "grad_norm": 0.408288836479187, + "learning_rate": 0.0002, + "loss": 1.2073, + "step": 250 + }, + { + "epoch": 0.570801317233809, + "grad_norm": 0.45887550711631775, + "learning_rate": 0.0002, + "loss": 1.3121, + "step": 260 + }, + { + "epoch": 0.5927552140504939, + "grad_norm": 0.5440235733985901, + "learning_rate": 0.0002, + "loss": 1.2257, + "step": 270 + }, + { + "epoch": 0.6147091108671789, + "grad_norm": 0.3725181519985199, + "learning_rate": 0.0002, + "loss": 1.1003, + "step": 280 + }, + { + "epoch": 0.6366630076838639, + "grad_norm": 0.4309018850326538, + "learning_rate": 0.0002, + "loss": 1.1538, + "step": 290 + }, + { + "epoch": 0.6586169045005489, + "grad_norm": 0.31488674879074097, + "learning_rate": 0.0002, + "loss": 1.2097, + "step": 300 + }, + { + "epoch": 0.6805708013172338, + "grad_norm": 0.34194841980934143, + "learning_rate": 0.0002, + "loss": 1.1689, + "step": 310 + }, + { + "epoch": 0.7025246981339188, + "grad_norm": 0.3407684862613678, + "learning_rate": 0.0002, + "loss": 1.2579, + "step": 320 + }, + { + "epoch": 0.7244785949506037, + "grad_norm": 0.2985728085041046, + "learning_rate": 0.0002, + "loss": 1.1144, + "step": 330 + }, + { + "epoch": 0.7464324917672887, + "grad_norm": 0.42316871881484985, + "learning_rate": 0.0002, + "loss": 1.2056, + "step": 340 + }, + { + "epoch": 0.7683863885839737, + "grad_norm": 0.3124258816242218, + "learning_rate": 0.0002, + "loss": 1.1753, + "step": 350 + }, + { + "epoch": 0.7903402854006586, + "grad_norm": 0.7727567553520203, + "learning_rate": 0.0002, + "loss": 1.2547, + "step": 360 + }, + { + "epoch": 0.8122941822173436, + "grad_norm": 0.363765686750412, + "learning_rate": 0.0002, + "loss": 1.124, + "step": 370 + }, + { + "epoch": 0.8342480790340285, + "grad_norm": 0.35582536458969116, + "learning_rate": 0.0002, + "loss": 1.1302, + "step": 380 + }, + { + "epoch": 0.8562019758507134, + "grad_norm": 0.31982025504112244, + "learning_rate": 0.0002, + "loss": 1.1787, + "step": 390 + }, + { + "epoch": 0.8781558726673985, + "grad_norm": 0.34978964924812317, + "learning_rate": 0.0002, + "loss": 1.2056, + "step": 400 + }, + { + "epoch": 0.9001097694840834, + "grad_norm": 0.8346716165542603, + "learning_rate": 0.0002, + "loss": 1.3577, + "step": 410 + }, + { + "epoch": 0.9220636663007684, + "grad_norm": 0.31984028220176697, + "learning_rate": 0.0002, + "loss": 1.1029, + "step": 420 + }, + { + "epoch": 0.9440175631174533, + "grad_norm": 0.32078951597213745, + "learning_rate": 0.0002, + "loss": 1.0967, + "step": 430 + }, + { + "epoch": 0.9659714599341384, + "grad_norm": 0.3417500853538513, + "learning_rate": 0.0002, + "loss": 1.0936, + "step": 440 + }, + { + "epoch": 0.9879253567508233, + "grad_norm": 0.42359477281570435, + "learning_rate": 0.0002, + "loss": 1.3412, + "step": 450 + }, + { + "epoch": 0.9989023051591658, + "eval_loss": 1.2201528549194336, + "eval_runtime": 87.152, + "eval_samples_per_second": 4.945, + "eval_steps_per_second": 0.62, + "step": 455 + }, + { + "epoch": 1.0098792535675083, + "grad_norm": 0.37914523482322693, + "learning_rate": 0.0002, + "loss": 1.1909, + "step": 460 + }, + { + "epoch": 1.031833150384193, + "grad_norm": 0.43655872344970703, + "learning_rate": 0.0002, + "loss": 1.0948, + "step": 470 + }, + { + "epoch": 1.0537870472008781, + "grad_norm": 0.3673796057701111, + "learning_rate": 0.0002, + "loss": 1.0873, + "step": 480 + }, + { + "epoch": 1.0757409440175631, + "grad_norm": 0.37673917412757874, + "learning_rate": 0.0002, + "loss": 1.0483, + "step": 490 + }, + { + "epoch": 1.0976948408342482, + "grad_norm": 0.2893829345703125, + "learning_rate": 0.0002, + "loss": 1.0799, + "step": 500 + }, + { + "epoch": 1.119648737650933, + "grad_norm": 0.5551970601081848, + "learning_rate": 0.0002, + "loss": 1.1847, + "step": 510 + }, + { + "epoch": 1.141602634467618, + "grad_norm": 0.442104309797287, + "learning_rate": 0.0002, + "loss": 1.0885, + "step": 520 + }, + { + "epoch": 1.163556531284303, + "grad_norm": 0.4035094976425171, + "learning_rate": 0.0002, + "loss": 1.1766, + "step": 530 + }, + { + "epoch": 1.1855104281009878, + "grad_norm": 0.47009000182151794, + "learning_rate": 0.0002, + "loss": 1.0282, + "step": 540 + }, + { + "epoch": 1.2074643249176729, + "grad_norm": 0.4118749797344208, + "learning_rate": 0.0002, + "loss": 1.2625, + "step": 550 + }, + { + "epoch": 1.2294182217343579, + "grad_norm": 0.35173165798187256, + "learning_rate": 0.0002, + "loss": 1.0988, + "step": 560 + }, + { + "epoch": 1.2513721185510427, + "grad_norm": 0.7024672031402588, + "learning_rate": 0.0002, + "loss": 1.0498, + "step": 570 + }, + { + "epoch": 1.2733260153677277, + "grad_norm": 0.42657527327537537, + "learning_rate": 0.0002, + "loss": 1.1339, + "step": 580 + }, + { + "epoch": 1.2952799121844127, + "grad_norm": 0.3815029561519623, + "learning_rate": 0.0002, + "loss": 1.0545, + "step": 590 + }, + { + "epoch": 1.3172338090010978, + "grad_norm": 0.7031055688858032, + "learning_rate": 0.0002, + "loss": 1.1528, + "step": 600 + }, + { + "epoch": 1.3391877058177828, + "grad_norm": 0.393911212682724, + "learning_rate": 0.0002, + "loss": 1.1347, + "step": 610 + }, + { + "epoch": 1.3611416026344676, + "grad_norm": 0.5077702403068542, + "learning_rate": 0.0002, + "loss": 1.1901, + "step": 620 + }, + { + "epoch": 1.3830954994511526, + "grad_norm": 2.330033302307129, + "learning_rate": 0.0002, + "loss": 1.1251, + "step": 630 + }, + { + "epoch": 1.4050493962678376, + "grad_norm": 0.35322949290275574, + "learning_rate": 0.0002, + "loss": 1.0477, + "step": 640 + }, + { + "epoch": 1.4270032930845225, + "grad_norm": 0.44401052594184875, + "learning_rate": 0.0002, + "loss": 1.14, + "step": 650 + }, + { + "epoch": 1.4489571899012075, + "grad_norm": 0.35945481061935425, + "learning_rate": 0.0002, + "loss": 1.0318, + "step": 660 + }, + { + "epoch": 1.4709110867178925, + "grad_norm": 0.3058856129646301, + "learning_rate": 0.0002, + "loss": 1.1988, + "step": 670 + }, + { + "epoch": 1.4928649835345773, + "grad_norm": 0.7067602872848511, + "learning_rate": 0.0002, + "loss": 1.1545, + "step": 680 + }, + { + "epoch": 1.5148188803512623, + "grad_norm": 0.4219357371330261, + "learning_rate": 0.0002, + "loss": 1.0925, + "step": 690 + }, + { + "epoch": 1.5367727771679474, + "grad_norm": 0.5970841646194458, + "learning_rate": 0.0002, + "loss": 1.1622, + "step": 700 + }, + { + "epoch": 1.5587266739846322, + "grad_norm": 0.4381934404373169, + "learning_rate": 0.0002, + "loss": 1.0803, + "step": 710 + }, + { + "epoch": 1.5806805708013172, + "grad_norm": 0.4101450443267822, + "learning_rate": 0.0002, + "loss": 1.0961, + "step": 720 + }, + { + "epoch": 1.6026344676180022, + "grad_norm": 0.3657490015029907, + "learning_rate": 0.0002, + "loss": 1.0474, + "step": 730 + }, + { + "epoch": 1.624588364434687, + "grad_norm": 0.36240628361701965, + "learning_rate": 0.0002, + "loss": 1.0936, + "step": 740 + }, + { + "epoch": 1.6465422612513723, + "grad_norm": 0.4103568494319916, + "learning_rate": 0.0002, + "loss": 1.0489, + "step": 750 + }, + { + "epoch": 1.668496158068057, + "grad_norm": 0.3138505816459656, + "learning_rate": 0.0002, + "loss": 1.0919, + "step": 760 + }, + { + "epoch": 1.690450054884742, + "grad_norm": 0.41215717792510986, + "learning_rate": 0.0002, + "loss": 1.2308, + "step": 770 + }, + { + "epoch": 1.7124039517014271, + "grad_norm": 0.4589519202709198, + "learning_rate": 0.0002, + "loss": 1.1659, + "step": 780 + }, + { + "epoch": 1.734357848518112, + "grad_norm": 0.4049508571624756, + "learning_rate": 0.0002, + "loss": 1.0913, + "step": 790 + }, + { + "epoch": 1.756311745334797, + "grad_norm": 0.48557212948799133, + "learning_rate": 0.0002, + "loss": 1.1329, + "step": 800 + }, + { + "epoch": 1.778265642151482, + "grad_norm": 0.5331754088401794, + "learning_rate": 0.0002, + "loss": 1.0729, + "step": 810 + }, + { + "epoch": 1.8002195389681668, + "grad_norm": 0.3853185772895813, + "learning_rate": 0.0002, + "loss": 1.1452, + "step": 820 + }, + { + "epoch": 1.8221734357848518, + "grad_norm": 0.424062579870224, + "learning_rate": 0.0002, + "loss": 1.1061, + "step": 830 + }, + { + "epoch": 1.8441273326015368, + "grad_norm": 0.3418445289134979, + "learning_rate": 0.0002, + "loss": 1.1104, + "step": 840 + }, + { + "epoch": 1.8660812294182216, + "grad_norm": 0.4045565128326416, + "learning_rate": 0.0002, + "loss": 1.0546, + "step": 850 + }, + { + "epoch": 1.8880351262349067, + "grad_norm": 0.42155781388282776, + "learning_rate": 0.0002, + "loss": 1.1608, + "step": 860 + }, + { + "epoch": 1.9099890230515917, + "grad_norm": 0.40554770827293396, + "learning_rate": 0.0002, + "loss": 1.0628, + "step": 870 + }, + { + "epoch": 1.9319429198682765, + "grad_norm": 0.42644748091697693, + "learning_rate": 0.0002, + "loss": 1.1609, + "step": 880 + }, + { + "epoch": 1.9538968166849617, + "grad_norm": 0.45260652899742126, + "learning_rate": 0.0002, + "loss": 1.1132, + "step": 890 + }, + { + "epoch": 1.9758507135016465, + "grad_norm": 0.4114069938659668, + "learning_rate": 0.0002, + "loss": 1.048, + "step": 900 + }, + { + "epoch": 1.9978046103183313, + "grad_norm": 0.375802218914032, + "learning_rate": 0.0002, + "loss": 1.1941, + "step": 910 + }, + { + "epoch": 2.0, + "eval_loss": 1.205152153968811, + "eval_runtime": 86.8795, + "eval_samples_per_second": 4.961, + "eval_steps_per_second": 0.622, + "step": 911 + }, + { + "epoch": 2.0197585071350166, + "grad_norm": 0.47718703746795654, + "learning_rate": 0.0002, + "loss": 1.0897, + "step": 920 + }, + { + "epoch": 2.0417124039517014, + "grad_norm": 0.45628082752227783, + "learning_rate": 0.0002, + "loss": 1.0329, + "step": 930 + }, + { + "epoch": 2.063666300768386, + "grad_norm": 0.5933247804641724, + "learning_rate": 0.0002, + "loss": 1.0538, + "step": 940 + }, + { + "epoch": 2.0856201975850714, + "grad_norm": 0.5355812907218933, + "learning_rate": 0.0002, + "loss": 1.0152, + "step": 950 + }, + { + "epoch": 2.1075740944017562, + "grad_norm": 0.5860010385513306, + "learning_rate": 0.0002, + "loss": 1.0726, + "step": 960 + }, + { + "epoch": 2.129527991218441, + "grad_norm": 0.7471673488616943, + "learning_rate": 0.0002, + "loss": 1.025, + "step": 970 + }, + { + "epoch": 2.1514818880351263, + "grad_norm": 2.0918211936950684, + "learning_rate": 0.0002, + "loss": 1.0247, + "step": 980 + }, + { + "epoch": 2.173435784851811, + "grad_norm": 0.4021058678627014, + "learning_rate": 0.0002, + "loss": 0.8947, + "step": 990 + }, + { + "epoch": 2.1953896816684964, + "grad_norm": 0.564975380897522, + "learning_rate": 0.0002, + "loss": 0.8875, + "step": 1000 + }, + { + "epoch": 2.217343578485181, + "grad_norm": 0.46260079741477966, + "learning_rate": 0.0002, + "loss": 1.0264, + "step": 1010 + }, + { + "epoch": 2.239297475301866, + "grad_norm": 0.4791034460067749, + "learning_rate": 0.0002, + "loss": 0.9265, + "step": 1020 + }, + { + "epoch": 2.261251372118551, + "grad_norm": 0.5272043943405151, + "learning_rate": 0.0002, + "loss": 0.8869, + "step": 1030 + }, + { + "epoch": 2.283205268935236, + "grad_norm": 0.5221094489097595, + "learning_rate": 0.0002, + "loss": 1.0007, + "step": 1040 + }, + { + "epoch": 2.305159165751921, + "grad_norm": 0.558032751083374, + "learning_rate": 0.0002, + "loss": 0.9472, + "step": 1050 + }, + { + "epoch": 2.327113062568606, + "grad_norm": 0.5905590653419495, + "learning_rate": 0.0002, + "loss": 0.9617, + "step": 1060 + }, + { + "epoch": 2.349066959385291, + "grad_norm": 0.5308699607849121, + "learning_rate": 0.0002, + "loss": 0.9592, + "step": 1070 + }, + { + "epoch": 2.3710208562019757, + "grad_norm": 0.6375027894973755, + "learning_rate": 0.0002, + "loss": 1.0646, + "step": 1080 + }, + { + "epoch": 2.392974753018661, + "grad_norm": 0.7439115643501282, + "learning_rate": 0.0002, + "loss": 1.0354, + "step": 1090 + }, + { + "epoch": 2.4149286498353457, + "grad_norm": 0.41945117712020874, + "learning_rate": 0.0002, + "loss": 1.0212, + "step": 1100 + }, + { + "epoch": 2.436882546652031, + "grad_norm": 0.4891968369483948, + "learning_rate": 0.0002, + "loss": 0.9609, + "step": 1110 + }, + { + "epoch": 2.4588364434687158, + "grad_norm": 0.4686794579029083, + "learning_rate": 0.0002, + "loss": 0.9829, + "step": 1120 + }, + { + "epoch": 2.4807903402854006, + "grad_norm": 0.5204509496688843, + "learning_rate": 0.0002, + "loss": 0.8919, + "step": 1130 + }, + { + "epoch": 2.5027442371020854, + "grad_norm": 0.6779005527496338, + "learning_rate": 0.0002, + "loss": 0.8983, + "step": 1140 + }, + { + "epoch": 2.5246981339187706, + "grad_norm": 0.682621955871582, + "learning_rate": 0.0002, + "loss": 0.9733, + "step": 1150 + }, + { + "epoch": 2.5466520307354554, + "grad_norm": 0.5744376182556152, + "learning_rate": 0.0002, + "loss": 1.051, + "step": 1160 + }, + { + "epoch": 2.5686059275521407, + "grad_norm": 0.49954667687416077, + "learning_rate": 0.0002, + "loss": 0.8764, + "step": 1170 + }, + { + "epoch": 2.5905598243688255, + "grad_norm": 0.4761793315410614, + "learning_rate": 0.0002, + "loss": 0.9896, + "step": 1180 + }, + { + "epoch": 2.6125137211855103, + "grad_norm": 0.548299252986908, + "learning_rate": 0.0002, + "loss": 0.8593, + "step": 1190 + }, + { + "epoch": 2.6344676180021955, + "grad_norm": 0.5771360993385315, + "learning_rate": 0.0002, + "loss": 1.0017, + "step": 1200 + }, + { + "epoch": 2.6564215148188803, + "grad_norm": 0.5543120503425598, + "learning_rate": 0.0002, + "loss": 0.9858, + "step": 1210 + }, + { + "epoch": 2.6783754116355656, + "grad_norm": 0.7564870715141296, + "learning_rate": 0.0002, + "loss": 0.9565, + "step": 1220 + }, + { + "epoch": 2.7003293084522504, + "grad_norm": 0.8222362399101257, + "learning_rate": 0.0002, + "loss": 0.9753, + "step": 1230 + }, + { + "epoch": 2.722283205268935, + "grad_norm": 0.6894469857215881, + "learning_rate": 0.0002, + "loss": 1.0079, + "step": 1240 + }, + { + "epoch": 2.74423710208562, + "grad_norm": 0.6121546030044556, + "learning_rate": 0.0002, + "loss": 1.0106, + "step": 1250 + }, + { + "epoch": 2.7661909989023052, + "grad_norm": 0.521809995174408, + "learning_rate": 0.0002, + "loss": 0.9801, + "step": 1260 + }, + { + "epoch": 2.78814489571899, + "grad_norm": 0.766968309879303, + "learning_rate": 0.0002, + "loss": 1.0196, + "step": 1270 + }, + { + "epoch": 2.8100987925356753, + "grad_norm": 0.522331714630127, + "learning_rate": 0.0002, + "loss": 0.976, + "step": 1280 + }, + { + "epoch": 2.83205268935236, + "grad_norm": 0.42923519015312195, + "learning_rate": 0.0002, + "loss": 0.8866, + "step": 1290 + }, + { + "epoch": 2.854006586169045, + "grad_norm": 0.47810837626457214, + "learning_rate": 0.0002, + "loss": 0.9049, + "step": 1300 + }, + { + "epoch": 2.8759604829857297, + "grad_norm": 1.0958846807479858, + "learning_rate": 0.0002, + "loss": 1.0291, + "step": 1310 + }, + { + "epoch": 2.897914379802415, + "grad_norm": 0.4755791127681732, + "learning_rate": 0.0002, + "loss": 0.8724, + "step": 1320 + }, + { + "epoch": 2.9198682766190998, + "grad_norm": 0.5575157403945923, + "learning_rate": 0.0002, + "loss": 0.9317, + "step": 1330 + }, + { + "epoch": 2.941822173435785, + "grad_norm": 0.5938076376914978, + "learning_rate": 0.0002, + "loss": 1.0131, + "step": 1340 + }, + { + "epoch": 2.96377607025247, + "grad_norm": 0.5751763582229614, + "learning_rate": 0.0002, + "loss": 0.9857, + "step": 1350 + }, + { + "epoch": 2.9857299670691546, + "grad_norm": 0.5590175986289978, + "learning_rate": 0.0002, + "loss": 1.0212, + "step": 1360 + }, + { + "epoch": 2.9989023051591657, + "eval_loss": 1.2402944564819336, + "eval_runtime": 88.822, + "eval_samples_per_second": 4.852, + "eval_steps_per_second": 0.608, + "step": 1366 + }, + { + "epoch": 3.00768386388584, + "grad_norm": 0.463539719581604, + "learning_rate": 0.0002, + "loss": 0.844, + "step": 1370 + }, + { + "epoch": 3.0296377607025247, + "grad_norm": 0.6667885780334473, + "learning_rate": 0.0002, + "loss": 0.8955, + "step": 1380 + }, + { + "epoch": 3.0515916575192095, + "grad_norm": 0.5849342942237854, + "learning_rate": 0.0002, + "loss": 0.8765, + "step": 1390 + }, + { + "epoch": 3.0735455543358947, + "grad_norm": 0.5571770668029785, + "learning_rate": 0.0002, + "loss": 0.7808, + "step": 1400 + }, + { + "epoch": 3.0954994511525795, + "grad_norm": 0.5761234164237976, + "learning_rate": 0.0002, + "loss": 0.7448, + "step": 1410 + }, + { + "epoch": 3.1174533479692643, + "grad_norm": 0.7277371883392334, + "learning_rate": 0.0002, + "loss": 0.7854, + "step": 1420 + }, + { + "epoch": 3.1394072447859496, + "grad_norm": 0.5190334320068359, + "learning_rate": 0.0002, + "loss": 0.817, + "step": 1430 + }, + { + "epoch": 3.1613611416026344, + "grad_norm": 0.632939875125885, + "learning_rate": 0.0002, + "loss": 0.7548, + "step": 1440 + }, + { + "epoch": 3.1833150384193196, + "grad_norm": 0.7229540944099426, + "learning_rate": 0.0002, + "loss": 0.8447, + "step": 1450 + }, + { + "epoch": 3.2052689352360044, + "grad_norm": 0.7584632039070129, + "learning_rate": 0.0002, + "loss": 0.8595, + "step": 1460 + }, + { + "epoch": 3.2272228320526892, + "grad_norm": 0.6546088457107544, + "learning_rate": 0.0002, + "loss": 0.7456, + "step": 1470 + }, + { + "epoch": 3.2491767288693745, + "grad_norm": 0.8116684556007385, + "learning_rate": 0.0002, + "loss": 0.8531, + "step": 1480 + }, + { + "epoch": 3.2711306256860593, + "grad_norm": 0.6206557750701904, + "learning_rate": 0.0002, + "loss": 0.9272, + "step": 1490 + }, + { + "epoch": 3.293084522502744, + "grad_norm": 0.5393369197845459, + "learning_rate": 0.0002, + "loss": 0.7972, + "step": 1500 + }, + { + "epoch": 3.3150384193194293, + "grad_norm": 0.7006453275680542, + "learning_rate": 0.0002, + "loss": 0.7614, + "step": 1510 + }, + { + "epoch": 3.336992316136114, + "grad_norm": 0.95253986120224, + "learning_rate": 0.0002, + "loss": 0.7358, + "step": 1520 + }, + { + "epoch": 3.358946212952799, + "grad_norm": 0.8138132095336914, + "learning_rate": 0.0002, + "loss": 0.8131, + "step": 1530 + }, + { + "epoch": 3.380900109769484, + "grad_norm": 0.7974302172660828, + "learning_rate": 0.0002, + "loss": 0.7738, + "step": 1540 + }, + { + "epoch": 3.402854006586169, + "grad_norm": 0.6694685220718384, + "learning_rate": 0.0002, + "loss": 0.8161, + "step": 1550 + }, + { + "epoch": 3.4248079034028542, + "grad_norm": 0.908634603023529, + "learning_rate": 0.0002, + "loss": 0.8503, + "step": 1560 + }, + { + "epoch": 3.446761800219539, + "grad_norm": 0.5625193119049072, + "learning_rate": 0.0002, + "loss": 0.7609, + "step": 1570 + }, + { + "epoch": 3.468715697036224, + "grad_norm": 0.779325544834137, + "learning_rate": 0.0002, + "loss": 0.7658, + "step": 1580 + }, + { + "epoch": 3.4906695938529086, + "grad_norm": 0.7133058905601501, + "learning_rate": 0.0002, + "loss": 0.7485, + "step": 1590 + }, + { + "epoch": 3.512623490669594, + "grad_norm": 0.6741108298301697, + "learning_rate": 0.0002, + "loss": 0.8847, + "step": 1600 + }, + { + "epoch": 3.5345773874862787, + "grad_norm": 0.696982204914093, + "learning_rate": 0.0002, + "loss": 0.7838, + "step": 1610 + }, + { + "epoch": 3.556531284302964, + "grad_norm": 0.7946001291275024, + "learning_rate": 0.0002, + "loss": 0.7195, + "step": 1620 + }, + { + "epoch": 3.5784851811196488, + "grad_norm": 0.6313548684120178, + "learning_rate": 0.0002, + "loss": 0.7772, + "step": 1630 + }, + { + "epoch": 3.6004390779363336, + "grad_norm": 0.9246852397918701, + "learning_rate": 0.0002, + "loss": 0.8267, + "step": 1640 + }, + { + "epoch": 3.622392974753019, + "grad_norm": 0.6615420579910278, + "learning_rate": 0.0002, + "loss": 0.779, + "step": 1650 + }, + { + "epoch": 3.6443468715697036, + "grad_norm": 1.5050125122070312, + "learning_rate": 0.0002, + "loss": 0.883, + "step": 1660 + }, + { + "epoch": 3.666300768386389, + "grad_norm": 0.5023762583732605, + "learning_rate": 0.0002, + "loss": 0.7763, + "step": 1670 + }, + { + "epoch": 3.6882546652030737, + "grad_norm": 0.6289586424827576, + "learning_rate": 0.0002, + "loss": 0.8173, + "step": 1680 + }, + { + "epoch": 3.7102085620197585, + "grad_norm": 1.050397515296936, + "learning_rate": 0.0002, + "loss": 0.9028, + "step": 1690 + }, + { + "epoch": 3.7321624588364433, + "grad_norm": 0.6785626411437988, + "learning_rate": 0.0002, + "loss": 0.7747, + "step": 1700 + }, + { + "epoch": 3.7541163556531285, + "grad_norm": 0.7565035223960876, + "learning_rate": 0.0002, + "loss": 0.9215, + "step": 1710 + }, + { + "epoch": 3.7760702524698133, + "grad_norm": 0.7775155901908875, + "learning_rate": 0.0002, + "loss": 0.7913, + "step": 1720 + }, + { + "epoch": 3.7980241492864986, + "grad_norm": 0.765260636806488, + "learning_rate": 0.0002, + "loss": 0.8081, + "step": 1730 + }, + { + "epoch": 3.8199780461031834, + "grad_norm": 0.7982407808303833, + "learning_rate": 0.0002, + "loss": 0.9231, + "step": 1740 + }, + { + "epoch": 3.841931942919868, + "grad_norm": 0.7431730628013611, + "learning_rate": 0.0002, + "loss": 0.7755, + "step": 1750 + }, + { + "epoch": 3.863885839736553, + "grad_norm": 0.9758927226066589, + "learning_rate": 0.0002, + "loss": 0.9236, + "step": 1760 + }, + { + "epoch": 3.885839736553238, + "grad_norm": 0.8014697432518005, + "learning_rate": 0.0002, + "loss": 0.9118, + "step": 1770 + }, + { + "epoch": 3.907793633369923, + "grad_norm": 0.7212756276130676, + "learning_rate": 0.0002, + "loss": 0.7503, + "step": 1780 + }, + { + "epoch": 3.9297475301866083, + "grad_norm": 0.584318220615387, + "learning_rate": 0.0002, + "loss": 0.7978, + "step": 1790 + }, + { + "epoch": 3.951701427003293, + "grad_norm": 0.7612535953521729, + "learning_rate": 0.0002, + "loss": 0.7894, + "step": 1800 + }, + { + "epoch": 3.973655323819978, + "grad_norm": 0.735103189945221, + "learning_rate": 0.0002, + "loss": 0.8589, + "step": 1810 + }, + { + "epoch": 3.995609220636663, + "grad_norm": 0.9074980020523071, + "learning_rate": 0.0002, + "loss": 0.8192, + "step": 1820 + }, + { + "epoch": 4.0, + "eval_loss": 1.279890537261963, + "eval_runtime": 88.8969, + "eval_samples_per_second": 4.848, + "eval_steps_per_second": 0.607, + "step": 1822 + }, + { + "epoch": 4.017563117453348, + "grad_norm": 0.9290254712104797, + "learning_rate": 0.0002, + "loss": 0.7312, + "step": 1830 + }, + { + "epoch": 4.039517014270033, + "grad_norm": 0.723889946937561, + "learning_rate": 0.0002, + "loss": 0.6896, + "step": 1840 + }, + { + "epoch": 4.061470911086718, + "grad_norm": 0.5906972289085388, + "learning_rate": 0.0002, + "loss": 0.632, + "step": 1850 + }, + { + "epoch": 4.083424807903403, + "grad_norm": 0.8078910708427429, + "learning_rate": 0.0002, + "loss": 0.6594, + "step": 1860 + }, + { + "epoch": 4.105378704720088, + "grad_norm": 1.0101137161254883, + "learning_rate": 0.0002, + "loss": 0.6242, + "step": 1870 + }, + { + "epoch": 4.127332601536772, + "grad_norm": 0.8710281848907471, + "learning_rate": 0.0002, + "loss": 0.7259, + "step": 1880 + }, + { + "epoch": 4.149286498353458, + "grad_norm": 0.9604734778404236, + "learning_rate": 0.0002, + "loss": 0.6993, + "step": 1890 + }, + { + "epoch": 4.171240395170143, + "grad_norm": 0.9829702377319336, + "learning_rate": 0.0002, + "loss": 0.6706, + "step": 1900 + }, + { + "epoch": 4.193194291986828, + "grad_norm": 0.6572765707969666, + "learning_rate": 0.0002, + "loss": 0.7013, + "step": 1910 + }, + { + "epoch": 4.2151481888035125, + "grad_norm": 0.8459188938140869, + "learning_rate": 0.0002, + "loss": 0.5539, + "step": 1920 + }, + { + "epoch": 4.237102085620197, + "grad_norm": 0.8321021795272827, + "learning_rate": 0.0002, + "loss": 0.6235, + "step": 1930 + }, + { + "epoch": 4.259055982436882, + "grad_norm": 0.8611727356910706, + "learning_rate": 0.0002, + "loss": 0.6442, + "step": 1940 + }, + { + "epoch": 4.281009879253568, + "grad_norm": 0.8490208387374878, + "learning_rate": 0.0002, + "loss": 0.6852, + "step": 1950 + }, + { + "epoch": 4.302963776070253, + "grad_norm": 0.9628722667694092, + "learning_rate": 0.0002, + "loss": 0.6175, + "step": 1960 + }, + { + "epoch": 4.324917672886937, + "grad_norm": 0.9632807374000549, + "learning_rate": 0.0002, + "loss": 0.5982, + "step": 1970 + }, + { + "epoch": 4.346871569703622, + "grad_norm": 0.7023298740386963, + "learning_rate": 0.0002, + "loss": 0.6138, + "step": 1980 + }, + { + "epoch": 4.368825466520307, + "grad_norm": 0.7912909388542175, + "learning_rate": 0.0002, + "loss": 0.6012, + "step": 1990 + }, + { + "epoch": 4.390779363336993, + "grad_norm": 1.1463429927825928, + "learning_rate": 0.0002, + "loss": 0.6767, + "step": 2000 + }, + { + "epoch": 4.4127332601536775, + "grad_norm": 1.1780626773834229, + "learning_rate": 0.0002, + "loss": 0.6607, + "step": 2010 + }, + { + "epoch": 4.434687156970362, + "grad_norm": 0.9349206686019897, + "learning_rate": 0.0002, + "loss": 0.6746, + "step": 2020 + }, + { + "epoch": 4.456641053787047, + "grad_norm": 0.7816639542579651, + "learning_rate": 0.0002, + "loss": 0.7087, + "step": 2030 + }, + { + "epoch": 4.478594950603732, + "grad_norm": 0.7005311250686646, + "learning_rate": 0.0002, + "loss": 0.6222, + "step": 2040 + }, + { + "epoch": 4.500548847420417, + "grad_norm": 0.7746558785438538, + "learning_rate": 0.0002, + "loss": 0.6608, + "step": 2050 + }, + { + "epoch": 4.522502744237102, + "grad_norm": 0.8261151313781738, + "learning_rate": 0.0002, + "loss": 0.6305, + "step": 2060 + }, + { + "epoch": 4.544456641053787, + "grad_norm": 1.0917805433273315, + "learning_rate": 0.0002, + "loss": 0.6502, + "step": 2070 + }, + { + "epoch": 4.566410537870472, + "grad_norm": 1.1570647954940796, + "learning_rate": 0.0002, + "loss": 0.6798, + "step": 2080 + }, + { + "epoch": 4.588364434687157, + "grad_norm": 0.9936433434486389, + "learning_rate": 0.0002, + "loss": 0.6296, + "step": 2090 + }, + { + "epoch": 4.610318331503842, + "grad_norm": 0.8574427366256714, + "learning_rate": 0.0002, + "loss": 0.5936, + "step": 2100 + }, + { + "epoch": 4.632272228320527, + "grad_norm": 0.7630168795585632, + "learning_rate": 0.0002, + "loss": 0.6529, + "step": 2110 + }, + { + "epoch": 4.654226125137212, + "grad_norm": 0.8146462440490723, + "learning_rate": 0.0002, + "loss": 0.5935, + "step": 2120 + }, + { + "epoch": 4.676180021953897, + "grad_norm": 0.7090407609939575, + "learning_rate": 0.0002, + "loss": 0.7102, + "step": 2130 + }, + { + "epoch": 4.698133918770582, + "grad_norm": 0.8278160095214844, + "learning_rate": 0.0002, + "loss": 0.6575, + "step": 2140 + }, + { + "epoch": 4.7200878155872665, + "grad_norm": 0.9415683746337891, + "learning_rate": 0.0002, + "loss": 0.664, + "step": 2150 + }, + { + "epoch": 4.742041712403951, + "grad_norm": 1.0056205987930298, + "learning_rate": 0.0002, + "loss": 0.7283, + "step": 2160 + }, + { + "epoch": 4.763995609220637, + "grad_norm": 0.768304705619812, + "learning_rate": 0.0002, + "loss": 0.6845, + "step": 2170 + }, + { + "epoch": 4.785949506037322, + "grad_norm": 1.0604112148284912, + "learning_rate": 0.0002, + "loss": 0.6922, + "step": 2180 + }, + { + "epoch": 4.807903402854007, + "grad_norm": 1.132864236831665, + "learning_rate": 0.0002, + "loss": 0.7092, + "step": 2190 + }, + { + "epoch": 4.829857299670691, + "grad_norm": 0.7543689608573914, + "learning_rate": 0.0002, + "loss": 0.6936, + "step": 2200 + }, + { + "epoch": 4.851811196487376, + "grad_norm": 0.8047362565994263, + "learning_rate": 0.0002, + "loss": 0.6921, + "step": 2210 + }, + { + "epoch": 4.873765093304062, + "grad_norm": 1.135778546333313, + "learning_rate": 0.0002, + "loss": 0.6753, + "step": 2220 + }, + { + "epoch": 4.895718990120747, + "grad_norm": 0.9068503379821777, + "learning_rate": 0.0002, + "loss": 0.6443, + "step": 2230 + }, + { + "epoch": 4.9176728869374315, + "grad_norm": 1.822325587272644, + "learning_rate": 0.0002, + "loss": 0.7419, + "step": 2240 + }, + { + "epoch": 4.939626783754116, + "grad_norm": 1.1124998331069946, + "learning_rate": 0.0002, + "loss": 0.6436, + "step": 2250 + }, + { + "epoch": 4.961580680570801, + "grad_norm": 0.818484365940094, + "learning_rate": 0.0002, + "loss": 0.7423, + "step": 2260 + }, + { + "epoch": 4.983534577387486, + "grad_norm": 1.0057194232940674, + "learning_rate": 0.0002, + "loss": 0.6872, + "step": 2270 + }, + { + "epoch": 4.998902305159166, + "eval_loss": 1.4120490550994873, + "eval_runtime": 87.5617, + "eval_samples_per_second": 4.922, + "eval_steps_per_second": 0.617, + "step": 2277 + }, + { + "epoch": 5.005488474204172, + "grad_norm": 0.8211547136306763, + "learning_rate": 0.0002, + "loss": 0.5451, + "step": 2280 + }, + { + "epoch": 5.0274423710208564, + "grad_norm": 1.1704130172729492, + "learning_rate": 0.0002, + "loss": 0.4965, + "step": 2290 + }, + { + "epoch": 5.049396267837541, + "grad_norm": 1.033539891242981, + "learning_rate": 0.0002, + "loss": 0.4827, + "step": 2300 + }, + { + "epoch": 5.071350164654226, + "grad_norm": 0.8830313682556152, + "learning_rate": 0.0002, + "loss": 0.447, + "step": 2310 + }, + { + "epoch": 5.093304061470911, + "grad_norm": 1.160437822341919, + "learning_rate": 0.0002, + "loss": 0.5502, + "step": 2320 + }, + { + "epoch": 5.115257958287596, + "grad_norm": 0.919956386089325, + "learning_rate": 0.0002, + "loss": 0.5123, + "step": 2330 + }, + { + "epoch": 5.137211855104281, + "grad_norm": 1.0099905729293823, + "learning_rate": 0.0002, + "loss": 0.4784, + "step": 2340 + }, + { + "epoch": 5.159165751920966, + "grad_norm": 1.1484816074371338, + "learning_rate": 0.0002, + "loss": 0.5109, + "step": 2350 + }, + { + "epoch": 5.181119648737651, + "grad_norm": 1.0373470783233643, + "learning_rate": 0.0002, + "loss": 0.5222, + "step": 2360 + }, + { + "epoch": 5.203073545554336, + "grad_norm": 1.0824922323226929, + "learning_rate": 0.0002, + "loss": 0.5366, + "step": 2370 + }, + { + "epoch": 5.225027442371021, + "grad_norm": 1.3817942142486572, + "learning_rate": 0.0002, + "loss": 0.5592, + "step": 2380 + }, + { + "epoch": 5.246981339187705, + "grad_norm": 1.197035551071167, + "learning_rate": 0.0002, + "loss": 0.504, + "step": 2390 + }, + { + "epoch": 5.268935236004391, + "grad_norm": 1.098778486251831, + "learning_rate": 0.0002, + "loss": 0.5326, + "step": 2400 + }, + { + "epoch": 5.290889132821076, + "grad_norm": 0.9713385105133057, + "learning_rate": 0.0002, + "loss": 0.5039, + "step": 2410 + }, + { + "epoch": 5.312843029637761, + "grad_norm": 1.321574330329895, + "learning_rate": 0.0002, + "loss": 0.5735, + "step": 2420 + }, + { + "epoch": 5.3347969264544455, + "grad_norm": 0.9402496218681335, + "learning_rate": 0.0002, + "loss": 0.4777, + "step": 2430 + }, + { + "epoch": 5.35675082327113, + "grad_norm": 0.8644852042198181, + "learning_rate": 0.0002, + "loss": 0.5604, + "step": 2440 + }, + { + "epoch": 5.378704720087816, + "grad_norm": 1.060290813446045, + "learning_rate": 0.0002, + "loss": 0.5324, + "step": 2450 + }, + { + "epoch": 5.400658616904501, + "grad_norm": 1.0725265741348267, + "learning_rate": 0.0002, + "loss": 0.5366, + "step": 2460 + }, + { + "epoch": 5.422612513721186, + "grad_norm": 0.9409431219100952, + "learning_rate": 0.0002, + "loss": 0.5469, + "step": 2470 + }, + { + "epoch": 5.44456641053787, + "grad_norm": 1.1108187437057495, + "learning_rate": 0.0002, + "loss": 0.5186, + "step": 2480 + }, + { + "epoch": 5.466520307354555, + "grad_norm": 1.0210821628570557, + "learning_rate": 0.0002, + "loss": 0.5312, + "step": 2490 + }, + { + "epoch": 5.48847420417124, + "grad_norm": 1.110597014427185, + "learning_rate": 0.0002, + "loss": 0.5016, + "step": 2500 + }, + { + "epoch": 5.510428100987926, + "grad_norm": 1.2534265518188477, + "learning_rate": 0.0002, + "loss": 0.511, + "step": 2510 + }, + { + "epoch": 5.5323819978046105, + "grad_norm": 1.3389744758605957, + "learning_rate": 0.0002, + "loss": 0.6062, + "step": 2520 + }, + { + "epoch": 5.554335894621295, + "grad_norm": 0.9520368576049805, + "learning_rate": 0.0002, + "loss": 0.4653, + "step": 2530 + }, + { + "epoch": 5.57628979143798, + "grad_norm": 1.4737157821655273, + "learning_rate": 0.0002, + "loss": 0.4746, + "step": 2540 + }, + { + "epoch": 5.598243688254665, + "grad_norm": 1.4143685102462769, + "learning_rate": 0.0002, + "loss": 0.5432, + "step": 2550 + }, + { + "epoch": 5.620197585071351, + "grad_norm": 1.3573999404907227, + "learning_rate": 0.0002, + "loss": 0.4722, + "step": 2560 + }, + { + "epoch": 5.642151481888035, + "grad_norm": 0.8475444316864014, + "learning_rate": 0.0002, + "loss": 0.5063, + "step": 2570 + }, + { + "epoch": 5.66410537870472, + "grad_norm": 1.2670329809188843, + "learning_rate": 0.0002, + "loss": 0.4911, + "step": 2580 + }, + { + "epoch": 5.686059275521405, + "grad_norm": 0.9688172936439514, + "learning_rate": 0.0002, + "loss": 0.5137, + "step": 2590 + }, + { + "epoch": 5.70801317233809, + "grad_norm": 1.3652743101119995, + "learning_rate": 0.0002, + "loss": 0.5116, + "step": 2600 + }, + { + "epoch": 5.729967069154775, + "grad_norm": 1.1475377082824707, + "learning_rate": 0.0002, + "loss": 0.5661, + "step": 2610 + }, + { + "epoch": 5.75192096597146, + "grad_norm": 1.3105946779251099, + "learning_rate": 0.0002, + "loss": 0.567, + "step": 2620 + }, + { + "epoch": 5.773874862788145, + "grad_norm": 0.920238196849823, + "learning_rate": 0.0002, + "loss": 0.4964, + "step": 2630 + }, + { + "epoch": 5.79582875960483, + "grad_norm": 1.0981792211532593, + "learning_rate": 0.0002, + "loss": 0.5473, + "step": 2640 + }, + { + "epoch": 5.817782656421515, + "grad_norm": 1.0734144449234009, + "learning_rate": 0.0002, + "loss": 0.5132, + "step": 2650 + }, + { + "epoch": 5.8397365532381995, + "grad_norm": 1.0541702508926392, + "learning_rate": 0.0002, + "loss": 0.5404, + "step": 2660 + }, + { + "epoch": 5.861690450054885, + "grad_norm": 1.0913143157958984, + "learning_rate": 0.0002, + "loss": 0.5056, + "step": 2670 + }, + { + "epoch": 5.88364434687157, + "grad_norm": 1.0431408882141113, + "learning_rate": 0.0002, + "loss": 0.5425, + "step": 2680 + }, + { + "epoch": 5.905598243688255, + "grad_norm": 1.3515729904174805, + "learning_rate": 0.0002, + "loss": 0.5398, + "step": 2690 + }, + { + "epoch": 5.92755214050494, + "grad_norm": 1.3153903484344482, + "learning_rate": 0.0002, + "loss": 0.5936, + "step": 2700 + }, + { + "epoch": 5.949506037321624, + "grad_norm": 1.024109125137329, + "learning_rate": 0.0002, + "loss": 0.5643, + "step": 2710 + }, + { + "epoch": 5.971459934138309, + "grad_norm": 1.0308483839035034, + "learning_rate": 0.0002, + "loss": 0.5143, + "step": 2720 + }, + { + "epoch": 5.993413830954994, + "grad_norm": 0.8329401016235352, + "learning_rate": 0.0002, + "loss": 0.4835, + "step": 2730 + }, + { + "epoch": 6.0, + "eval_loss": 1.510581612586975, + "eval_runtime": 89.0047, + "eval_samples_per_second": 4.842, + "eval_steps_per_second": 0.607, + "step": 2733 + }, + { + "epoch": 6.01536772777168, + "grad_norm": 1.1903921365737915, + "learning_rate": 0.0002, + "loss": 0.4282, + "step": 2740 + }, + { + "epoch": 6.0373216245883645, + "grad_norm": 1.0170859098434448, + "learning_rate": 0.0002, + "loss": 0.3844, + "step": 2750 + }, + { + "epoch": 6.059275521405049, + "grad_norm": 1.269655704498291, + "learning_rate": 0.0002, + "loss": 0.4116, + "step": 2760 + }, + { + "epoch": 6.081229418221734, + "grad_norm": 1.1271249055862427, + "learning_rate": 0.0002, + "loss": 0.381, + "step": 2770 + }, + { + "epoch": 6.103183315038419, + "grad_norm": 1.0269793272018433, + "learning_rate": 0.0002, + "loss": 0.391, + "step": 2780 + }, + { + "epoch": 6.125137211855105, + "grad_norm": 1.1622686386108398, + "learning_rate": 0.0002, + "loss": 0.3896, + "step": 2790 + }, + { + "epoch": 6.147091108671789, + "grad_norm": 1.3457845449447632, + "learning_rate": 0.0002, + "loss": 0.3907, + "step": 2800 + }, + { + "epoch": 6.169045005488474, + "grad_norm": 1.008620262145996, + "learning_rate": 0.0002, + "loss": 0.3447, + "step": 2810 + }, + { + "epoch": 6.190998902305159, + "grad_norm": 0.9964058995246887, + "learning_rate": 0.0002, + "loss": 0.3437, + "step": 2820 + }, + { + "epoch": 6.212952799121844, + "grad_norm": 1.265552043914795, + "learning_rate": 0.0002, + "loss": 0.4073, + "step": 2830 + }, + { + "epoch": 6.234906695938529, + "grad_norm": 1.0481451749801636, + "learning_rate": 0.0002, + "loss": 0.4199, + "step": 2840 + }, + { + "epoch": 6.256860592755214, + "grad_norm": 1.3813395500183105, + "learning_rate": 0.0002, + "loss": 0.4243, + "step": 2850 + }, + { + "epoch": 6.278814489571899, + "grad_norm": 1.1307486295700073, + "learning_rate": 0.0002, + "loss": 0.4039, + "step": 2860 + }, + { + "epoch": 6.300768386388584, + "grad_norm": 1.122252106666565, + "learning_rate": 0.0002, + "loss": 0.3665, + "step": 2870 + }, + { + "epoch": 6.322722283205269, + "grad_norm": 0.9570856094360352, + "learning_rate": 0.0002, + "loss": 0.4377, + "step": 2880 + }, + { + "epoch": 6.3446761800219535, + "grad_norm": 1.429248332977295, + "learning_rate": 0.0002, + "loss": 0.3762, + "step": 2890 + }, + { + "epoch": 6.366630076838639, + "grad_norm": 1.228832483291626, + "learning_rate": 0.0002, + "loss": 0.3746, + "step": 2900 + }, + { + "epoch": 6.388583973655324, + "grad_norm": 0.9634972810745239, + "learning_rate": 0.0002, + "loss": 0.3714, + "step": 2910 + }, + { + "epoch": 6.410537870472009, + "grad_norm": 1.392120599746704, + "learning_rate": 0.0002, + "loss": 0.3856, + "step": 2920 + }, + { + "epoch": 6.432491767288694, + "grad_norm": 1.0452295541763306, + "learning_rate": 0.0002, + "loss": 0.4395, + "step": 2930 + }, + { + "epoch": 6.4544456641053785, + "grad_norm": 0.9953978657722473, + "learning_rate": 0.0002, + "loss": 0.4559, + "step": 2940 + }, + { + "epoch": 6.476399560922063, + "grad_norm": 1.090386986732483, + "learning_rate": 0.0002, + "loss": 0.4108, + "step": 2950 + }, + { + "epoch": 6.498353457738749, + "grad_norm": 1.2177232503890991, + "learning_rate": 0.0002, + "loss": 0.4059, + "step": 2960 + }, + { + "epoch": 6.520307354555434, + "grad_norm": 0.8435868620872498, + "learning_rate": 0.0002, + "loss": 0.4403, + "step": 2970 + }, + { + "epoch": 6.542261251372119, + "grad_norm": 1.0110384225845337, + "learning_rate": 0.0002, + "loss": 0.4143, + "step": 2980 + }, + { + "epoch": 6.564215148188803, + "grad_norm": 0.8551704287528992, + "learning_rate": 0.0002, + "loss": 0.4396, + "step": 2990 + }, + { + "epoch": 6.586169045005488, + "grad_norm": 1.2663729190826416, + "learning_rate": 0.0002, + "loss": 0.3908, + "step": 3000 + }, + { + "epoch": 6.608122941822174, + "grad_norm": 1.2262762784957886, + "learning_rate": 0.0002, + "loss": 0.3927, + "step": 3010 + }, + { + "epoch": 6.630076838638859, + "grad_norm": 1.3794647455215454, + "learning_rate": 0.0002, + "loss": 0.4183, + "step": 3020 + }, + { + "epoch": 6.6520307354555435, + "grad_norm": 0.9994757175445557, + "learning_rate": 0.0002, + "loss": 0.3903, + "step": 3030 + }, + { + "epoch": 6.673984632272228, + "grad_norm": 1.067501187324524, + "learning_rate": 0.0002, + "loss": 0.4083, + "step": 3040 + }, + { + "epoch": 6.695938529088913, + "grad_norm": 1.1194695234298706, + "learning_rate": 0.0002, + "loss": 0.4551, + "step": 3050 + }, + { + "epoch": 6.717892425905598, + "grad_norm": 1.572695255279541, + "learning_rate": 0.0002, + "loss": 0.4276, + "step": 3060 + }, + { + "epoch": 6.739846322722284, + "grad_norm": 1.063094139099121, + "learning_rate": 0.0002, + "loss": 0.3681, + "step": 3070 + }, + { + "epoch": 6.761800219538968, + "grad_norm": 1.2257463932037354, + "learning_rate": 0.0002, + "loss": 0.3656, + "step": 3080 + }, + { + "epoch": 6.783754116355653, + "grad_norm": 1.259731411933899, + "learning_rate": 0.0002, + "loss": 0.4504, + "step": 3090 + }, + { + "epoch": 6.805708013172338, + "grad_norm": 1.3234009742736816, + "learning_rate": 0.0002, + "loss": 0.4067, + "step": 3100 + }, + { + "epoch": 6.827661909989023, + "grad_norm": 1.4324477910995483, + "learning_rate": 0.0002, + "loss": 0.4913, + "step": 3110 + }, + { + "epoch": 6.8496158068057085, + "grad_norm": 1.4183896780014038, + "learning_rate": 0.0002, + "loss": 0.4408, + "step": 3120 + }, + { + "epoch": 6.871569703622393, + "grad_norm": 1.1369833946228027, + "learning_rate": 0.0002, + "loss": 0.4517, + "step": 3130 + }, + { + "epoch": 6.893523600439078, + "grad_norm": 1.2804654836654663, + "learning_rate": 0.0002, + "loss": 0.458, + "step": 3140 + }, + { + "epoch": 6.915477497255763, + "grad_norm": 1.535305380821228, + "learning_rate": 0.0002, + "loss": 0.4616, + "step": 3150 + }, + { + "epoch": 6.937431394072448, + "grad_norm": 1.2820420265197754, + "learning_rate": 0.0002, + "loss": 0.4178, + "step": 3160 + }, + { + "epoch": 6.9593852908891325, + "grad_norm": 1.1014128923416138, + "learning_rate": 0.0002, + "loss": 0.442, + "step": 3170 + }, + { + "epoch": 6.981339187705817, + "grad_norm": 0.9979909658432007, + "learning_rate": 0.0002, + "loss": 0.4379, + "step": 3180 + }, + { + "epoch": 6.998902305159166, + "eval_loss": 1.6552348136901855, + "eval_runtime": 88.8609, + "eval_samples_per_second": 4.85, + "eval_steps_per_second": 0.608, + "step": 3188 + }, + { + "epoch": 7.003293084522503, + "grad_norm": 0.9172588586807251, + "learning_rate": 0.0002, + "loss": 0.3922, + "step": 3190 + }, + { + "epoch": 7.025246981339188, + "grad_norm": 1.1526820659637451, + "learning_rate": 0.0002, + "loss": 0.3028, + "step": 3200 + }, + { + "epoch": 7.047200878155873, + "grad_norm": 0.9504580497741699, + "learning_rate": 0.0002, + "loss": 0.305, + "step": 3210 + }, + { + "epoch": 7.069154774972557, + "grad_norm": 1.0364530086517334, + "learning_rate": 0.0002, + "loss": 0.321, + "step": 3220 + }, + { + "epoch": 7.091108671789242, + "grad_norm": 1.133812427520752, + "learning_rate": 0.0002, + "loss": 0.2887, + "step": 3230 + }, + { + "epoch": 7.113062568605928, + "grad_norm": 0.8940557837486267, + "learning_rate": 0.0002, + "loss": 0.2754, + "step": 3240 + }, + { + "epoch": 7.135016465422613, + "grad_norm": 1.4909859895706177, + "learning_rate": 0.0002, + "loss": 0.338, + "step": 3250 + }, + { + "epoch": 7.1569703622392975, + "grad_norm": 1.1167937517166138, + "learning_rate": 0.0002, + "loss": 0.2909, + "step": 3260 + }, + { + "epoch": 7.178924259055982, + "grad_norm": 1.1566085815429688, + "learning_rate": 0.0002, + "loss": 0.2783, + "step": 3270 + }, + { + "epoch": 7.200878155872667, + "grad_norm": 1.3751647472381592, + "learning_rate": 0.0002, + "loss": 0.2852, + "step": 3280 + }, + { + "epoch": 7.222832052689352, + "grad_norm": 1.2081550359725952, + "learning_rate": 0.0002, + "loss": 0.314, + "step": 3290 + }, + { + "epoch": 7.244785949506038, + "grad_norm": 1.1245852708816528, + "learning_rate": 0.0002, + "loss": 0.3231, + "step": 3300 + }, + { + "epoch": 7.266739846322722, + "grad_norm": 0.9021703600883484, + "learning_rate": 0.0002, + "loss": 0.3434, + "step": 3310 + }, + { + "epoch": 7.288693743139407, + "grad_norm": 1.3136515617370605, + "learning_rate": 0.0002, + "loss": 0.3416, + "step": 3320 + }, + { + "epoch": 7.310647639956092, + "grad_norm": 1.3397585153579712, + "learning_rate": 0.0002, + "loss": 0.3034, + "step": 3330 + }, + { + "epoch": 7.332601536772777, + "grad_norm": 1.0277947187423706, + "learning_rate": 0.0002, + "loss": 0.3232, + "step": 3340 + }, + { + "epoch": 7.3545554335894625, + "grad_norm": 1.3082621097564697, + "learning_rate": 0.0002, + "loss": 0.3229, + "step": 3350 + }, + { + "epoch": 7.376509330406147, + "grad_norm": 1.1663758754730225, + "learning_rate": 0.0002, + "loss": 0.3172, + "step": 3360 + }, + { + "epoch": 7.398463227222832, + "grad_norm": 0.9822199940681458, + "learning_rate": 0.0002, + "loss": 0.3161, + "step": 3370 + }, + { + "epoch": 7.420417124039517, + "grad_norm": 1.1240934133529663, + "learning_rate": 0.0002, + "loss": 0.3439, + "step": 3380 + }, + { + "epoch": 7.442371020856202, + "grad_norm": 1.110464334487915, + "learning_rate": 0.0002, + "loss": 0.3419, + "step": 3390 + }, + { + "epoch": 7.4643249176728865, + "grad_norm": 1.3189985752105713, + "learning_rate": 0.0002, + "loss": 0.3127, + "step": 3400 + }, + { + "epoch": 7.486278814489572, + "grad_norm": 1.148912787437439, + "learning_rate": 0.0002, + "loss": 0.2897, + "step": 3410 + }, + { + "epoch": 7.508232711306257, + "grad_norm": 1.8192038536071777, + "learning_rate": 0.0002, + "loss": 0.362, + "step": 3420 + }, + { + "epoch": 7.530186608122942, + "grad_norm": 1.4294136762619019, + "learning_rate": 0.0002, + "loss": 0.341, + "step": 3430 + }, + { + "epoch": 7.552140504939627, + "grad_norm": 1.2051990032196045, + "learning_rate": 0.0002, + "loss": 0.3026, + "step": 3440 + }, + { + "epoch": 7.574094401756311, + "grad_norm": 0.9924893379211426, + "learning_rate": 0.0002, + "loss": 0.3572, + "step": 3450 + }, + { + "epoch": 7.596048298572997, + "grad_norm": 1.5764961242675781, + "learning_rate": 0.0002, + "loss": 0.3335, + "step": 3460 + }, + { + "epoch": 7.618002195389682, + "grad_norm": 1.5812066793441772, + "learning_rate": 0.0002, + "loss": 0.3391, + "step": 3470 + }, + { + "epoch": 7.639956092206367, + "grad_norm": 1.091802716255188, + "learning_rate": 0.0002, + "loss": 0.3517, + "step": 3480 + }, + { + "epoch": 7.6619099890230515, + "grad_norm": 0.9630248546600342, + "learning_rate": 0.0002, + "loss": 0.3144, + "step": 3490 + }, + { + "epoch": 7.683863885839736, + "grad_norm": 1.0193588733673096, + "learning_rate": 0.0002, + "loss": 0.3262, + "step": 3500 + }, + { + "epoch": 7.705817782656421, + "grad_norm": 1.1763300895690918, + "learning_rate": 0.0002, + "loss": 0.2887, + "step": 3510 + }, + { + "epoch": 7.727771679473107, + "grad_norm": 1.0153584480285645, + "learning_rate": 0.0002, + "loss": 0.3007, + "step": 3520 + }, + { + "epoch": 7.749725576289792, + "grad_norm": 1.4637620449066162, + "learning_rate": 0.0002, + "loss": 0.4009, + "step": 3530 + }, + { + "epoch": 7.771679473106476, + "grad_norm": 1.2255295515060425, + "learning_rate": 0.0002, + "loss": 0.3164, + "step": 3540 + }, + { + "epoch": 7.793633369923161, + "grad_norm": 1.29080069065094, + "learning_rate": 0.0002, + "loss": 0.3437, + "step": 3550 + }, + { + "epoch": 7.815587266739846, + "grad_norm": 1.2556861639022827, + "learning_rate": 0.0002, + "loss": 0.3482, + "step": 3560 + }, + { + "epoch": 7.837541163556532, + "grad_norm": 1.4294195175170898, + "learning_rate": 0.0002, + "loss": 0.3396, + "step": 3570 + }, + { + "epoch": 7.8594950603732165, + "grad_norm": 1.2785801887512207, + "learning_rate": 0.0002, + "loss": 0.3682, + "step": 3580 + }, + { + "epoch": 7.881448957189901, + "grad_norm": 1.252855896949768, + "learning_rate": 0.0002, + "loss": 0.3353, + "step": 3590 + }, + { + "epoch": 7.903402854006586, + "grad_norm": 1.68595552444458, + "learning_rate": 0.0002, + "loss": 0.3251, + "step": 3600 + }, + { + "epoch": 7.925356750823271, + "grad_norm": 1.2536509037017822, + "learning_rate": 0.0002, + "loss": 0.3276, + "step": 3610 + }, + { + "epoch": 7.947310647639956, + "grad_norm": 1.4146950244903564, + "learning_rate": 0.0002, + "loss": 0.3154, + "step": 3620 + }, + { + "epoch": 7.969264544456641, + "grad_norm": 1.49301278591156, + "learning_rate": 0.0002, + "loss": 0.3299, + "step": 3630 + }, + { + "epoch": 7.991218441273326, + "grad_norm": 0.9742516279220581, + "learning_rate": 0.0002, + "loss": 0.324, + "step": 3640 + }, + { + "epoch": 7.991218441273326, + "eval_loss": 1.7275148630142212, + "eval_runtime": 88.5204, + "eval_samples_per_second": 4.869, + "eval_steps_per_second": 0.61, + "step": 3640 + } + ], + "logging_steps": 10, + "max_steps": 3640, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 1.6845104970989568e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f75755c7cf71aeb05b76db2632173f96f74e8f7 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf90ce7dd53cc68edd44d14e30ca84a5d7431a5b99d4697b17af4b2f7ec0abab +size 5624 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/README.md b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/README.md new file mode 100644 index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/README.md @@ -0,0 +1,202 @@ +--- +base_model: meta-llama/Meta-Llama-3-8B-Instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.13.1 \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..406c5a08dc4a2a33b52c62a482f98c217c417215 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "v_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..53062ed1fba60f3f9e85b364f41f0a3c58522898 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0243a9f191c8f40799850f957638382a4e782f1a408a55e8ba019922c4088ce7 +size 109069176 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/optimizer.pt b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..53e1cc7b58e7b7587c0452acde45020db1ccd6aa --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fff1441d5a4166539e108188c4a2f25c427966cd49d6a87d95646a90090c3638 +size 55532666 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/rng_state.pth b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..5ad3f0b8f237923f50235120f141f31c08d05bb8 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44cdcdc684e92022ff6e357b0f235741cde6f2fa0db3f3fadd0137b195701bd5 +size 14244 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/scheduler.pt b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..e8ed1c6aec54220a59269aac775fd3bada279338 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4681d88bffdbfae5ccd016d3d48f2942c7aa00ce836ab26e0c0d1e683c665c1 +size 1064 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393 +size 17209961 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|eot_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/trainer_state.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..b9b1d217c14a240963f4036ff71bfb619f9121f2 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/trainer_state.json @@ -0,0 +1,356 @@ +{ + "best_metric": 1.2201528549194336, + "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455", + "epoch": 0.9989023051591658, + "eval_steps": 10, + "global_step": 455, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.021953896816684963, + "grad_norm": 0.6144012212753296, + "learning_rate": 0.0002, + "loss": 1.9887, + "step": 10 + }, + { + "epoch": 0.043907793633369926, + "grad_norm": 0.5587220788002014, + "learning_rate": 0.0002, + "loss": 1.6882, + "step": 20 + }, + { + "epoch": 0.06586169045005488, + "grad_norm": 0.43262454867362976, + "learning_rate": 0.0002, + "loss": 1.399, + "step": 30 + }, + { + "epoch": 0.08781558726673985, + "grad_norm": 0.4783053994178772, + "learning_rate": 0.0002, + "loss": 1.4675, + "step": 40 + }, + { + "epoch": 0.10976948408342481, + "grad_norm": 0.44338956475257874, + "learning_rate": 0.0002, + "loss": 1.1771, + "step": 50 + }, + { + "epoch": 0.13172338090010977, + "grad_norm": 0.7255092263221741, + "learning_rate": 0.0002, + "loss": 1.3706, + "step": 60 + }, + { + "epoch": 0.15367727771679474, + "grad_norm": 0.46073833107948303, + "learning_rate": 0.0002, + "loss": 1.2601, + "step": 70 + }, + { + "epoch": 0.1756311745334797, + "grad_norm": 0.6698123216629028, + "learning_rate": 0.0002, + "loss": 1.3049, + "step": 80 + }, + { + "epoch": 0.19758507135016465, + "grad_norm": 0.4190150201320648, + "learning_rate": 0.0002, + "loss": 1.2975, + "step": 90 + }, + { + "epoch": 0.21953896816684962, + "grad_norm": 0.4110015034675598, + "learning_rate": 0.0002, + "loss": 1.2797, + "step": 100 + }, + { + "epoch": 0.2414928649835346, + "grad_norm": 0.33374306559562683, + "learning_rate": 0.0002, + "loss": 1.2896, + "step": 110 + }, + { + "epoch": 0.26344676180021953, + "grad_norm": 0.3061307370662689, + "learning_rate": 0.0002, + "loss": 1.2268, + "step": 120 + }, + { + "epoch": 0.2854006586169045, + "grad_norm": 0.4386885166168213, + "learning_rate": 0.0002, + "loss": 1.376, + "step": 130 + }, + { + "epoch": 0.30735455543358947, + "grad_norm": 0.40116462111473083, + "learning_rate": 0.0002, + "loss": 1.1814, + "step": 140 + }, + { + "epoch": 0.32930845225027444, + "grad_norm": 0.5887949466705322, + "learning_rate": 0.0002, + "loss": 1.2592, + "step": 150 + }, + { + "epoch": 0.3512623490669594, + "grad_norm": 0.3401573896408081, + "learning_rate": 0.0002, + "loss": 1.2372, + "step": 160 + }, + { + "epoch": 0.3732162458836443, + "grad_norm": 0.3288364112377167, + "learning_rate": 0.0002, + "loss": 1.1901, + "step": 170 + }, + { + "epoch": 0.3951701427003293, + "grad_norm": 0.4853297472000122, + "learning_rate": 0.0002, + "loss": 1.2335, + "step": 180 + }, + { + "epoch": 0.41712403951701427, + "grad_norm": 2.6253697872161865, + "learning_rate": 0.0002, + "loss": 1.227, + "step": 190 + }, + { + "epoch": 0.43907793633369924, + "grad_norm": 0.5598543286323547, + "learning_rate": 0.0002, + "loss": 1.2673, + "step": 200 + }, + { + "epoch": 0.4610318331503842, + "grad_norm": 0.4046548902988434, + "learning_rate": 0.0002, + "loss": 1.3459, + "step": 210 + }, + { + "epoch": 0.4829857299670692, + "grad_norm": 0.3686952590942383, + "learning_rate": 0.0002, + "loss": 1.265, + "step": 220 + }, + { + "epoch": 0.5049396267837541, + "grad_norm": 0.42458799481391907, + "learning_rate": 0.0002, + "loss": 1.1364, + "step": 230 + }, + { + "epoch": 0.5268935236004391, + "grad_norm": 0.5839895009994507, + "learning_rate": 0.0002, + "loss": 1.2094, + "step": 240 + }, + { + "epoch": 0.5488474204171241, + "grad_norm": 0.408288836479187, + "learning_rate": 0.0002, + "loss": 1.2073, + "step": 250 + }, + { + "epoch": 0.570801317233809, + "grad_norm": 0.45887550711631775, + "learning_rate": 0.0002, + "loss": 1.3121, + "step": 260 + }, + { + "epoch": 0.5927552140504939, + "grad_norm": 0.5440235733985901, + "learning_rate": 0.0002, + "loss": 1.2257, + "step": 270 + }, + { + "epoch": 0.6147091108671789, + "grad_norm": 0.3725181519985199, + "learning_rate": 0.0002, + "loss": 1.1003, + "step": 280 + }, + { + "epoch": 0.6366630076838639, + "grad_norm": 0.4309018850326538, + "learning_rate": 0.0002, + "loss": 1.1538, + "step": 290 + }, + { + "epoch": 0.6586169045005489, + "grad_norm": 0.31488674879074097, + "learning_rate": 0.0002, + "loss": 1.2097, + "step": 300 + }, + { + "epoch": 0.6805708013172338, + "grad_norm": 0.34194841980934143, + "learning_rate": 0.0002, + "loss": 1.1689, + "step": 310 + }, + { + "epoch": 0.7025246981339188, + "grad_norm": 0.3407684862613678, + "learning_rate": 0.0002, + "loss": 1.2579, + "step": 320 + }, + { + "epoch": 0.7244785949506037, + "grad_norm": 0.2985728085041046, + "learning_rate": 0.0002, + "loss": 1.1144, + "step": 330 + }, + { + "epoch": 0.7464324917672887, + "grad_norm": 0.42316871881484985, + "learning_rate": 0.0002, + "loss": 1.2056, + "step": 340 + }, + { + "epoch": 0.7683863885839737, + "grad_norm": 0.3124258816242218, + "learning_rate": 0.0002, + "loss": 1.1753, + "step": 350 + }, + { + "epoch": 0.7903402854006586, + "grad_norm": 0.7727567553520203, + "learning_rate": 0.0002, + "loss": 1.2547, + "step": 360 + }, + { + "epoch": 0.8122941822173436, + "grad_norm": 0.363765686750412, + "learning_rate": 0.0002, + "loss": 1.124, + "step": 370 + }, + { + "epoch": 0.8342480790340285, + "grad_norm": 0.35582536458969116, + "learning_rate": 0.0002, + "loss": 1.1302, + "step": 380 + }, + { + "epoch": 0.8562019758507134, + "grad_norm": 0.31982025504112244, + "learning_rate": 0.0002, + "loss": 1.1787, + "step": 390 + }, + { + "epoch": 0.8781558726673985, + "grad_norm": 0.34978964924812317, + "learning_rate": 0.0002, + "loss": 1.2056, + "step": 400 + }, + { + "epoch": 0.9001097694840834, + "grad_norm": 0.8346716165542603, + "learning_rate": 0.0002, + "loss": 1.3577, + "step": 410 + }, + { + "epoch": 0.9220636663007684, + "grad_norm": 0.31984028220176697, + "learning_rate": 0.0002, + "loss": 1.1029, + "step": 420 + }, + { + "epoch": 0.9440175631174533, + "grad_norm": 0.32078951597213745, + "learning_rate": 0.0002, + "loss": 1.0967, + "step": 430 + }, + { + "epoch": 0.9659714599341384, + "grad_norm": 0.3417500853538513, + "learning_rate": 0.0002, + "loss": 1.0936, + "step": 440 + }, + { + "epoch": 0.9879253567508233, + "grad_norm": 0.42359477281570435, + "learning_rate": 0.0002, + "loss": 1.3412, + "step": 450 + }, + { + "epoch": 0.9989023051591658, + "eval_loss": 1.2201528549194336, + "eval_runtime": 87.152, + "eval_samples_per_second": 4.945, + "eval_steps_per_second": 0.62, + "step": 455 + } + ], + "logging_steps": 10, + "max_steps": 3640, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.1079520094191616e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f75755c7cf71aeb05b76db2632173f96f74e8f7 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf90ce7dd53cc68edd44d14e30ca84a5d7431a5b99d4697b17af4b2f7ec0abab +size 5624 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/README.md b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/README.md new file mode 100644 index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/README.md @@ -0,0 +1,202 @@ +--- +base_model: meta-llama/Meta-Llama-3-8B-Instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.13.1 \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..406c5a08dc4a2a33b52c62a482f98c217c417215 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "v_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe2885e2d79cf1d80cd0233413a15280e49aa853 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb322e791bb91edfa9f435335176fce66675400951366ecb3580e7f184b2e398 +size 109069176 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/optimizer.pt b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ccf114970b3ddbd9719bc5e6d809451f00ac79b --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f254bdd51e57d4d9ac3fc49975a4b7e9538aa09592763b8fd48d7f307b32742 +size 55532666 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/rng_state.pth b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..8d2bf514191dcc9791d396bfde5fb51baebf89d8 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d4d5f482a3b704507ce16cfc0a4b08277e08582c9820006dbef35c6d0c099f5 +size 14244 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/scheduler.pt b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..00e282f1bbe437447016297c43a8aa2db8058ed5 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:102d8d07045dc1341fd48b779aaa199b082c081d268dc5051459133a52754f23 +size 1064 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393 +size 17209961 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|eot_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/trainer_state.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..2418433bcaea76f3c63e9ba157c3a732b423e967 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/trainer_state.json @@ -0,0 +1,686 @@ +{ + "best_metric": 1.205152153968811, + "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911", + "epoch": 2.0, + "eval_steps": 10, + "global_step": 911, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.021953896816684963, + "grad_norm": 0.6144012212753296, + "learning_rate": 0.0002, + "loss": 1.9887, + "step": 10 + }, + { + "epoch": 0.043907793633369926, + "grad_norm": 0.5587220788002014, + "learning_rate": 0.0002, + "loss": 1.6882, + "step": 20 + }, + { + "epoch": 0.06586169045005488, + "grad_norm": 0.43262454867362976, + "learning_rate": 0.0002, + "loss": 1.399, + "step": 30 + }, + { + "epoch": 0.08781558726673985, + "grad_norm": 0.4783053994178772, + "learning_rate": 0.0002, + "loss": 1.4675, + "step": 40 + }, + { + "epoch": 0.10976948408342481, + "grad_norm": 0.44338956475257874, + "learning_rate": 0.0002, + "loss": 1.1771, + "step": 50 + }, + { + "epoch": 0.13172338090010977, + "grad_norm": 0.7255092263221741, + "learning_rate": 0.0002, + "loss": 1.3706, + "step": 60 + }, + { + "epoch": 0.15367727771679474, + "grad_norm": 0.46073833107948303, + "learning_rate": 0.0002, + "loss": 1.2601, + "step": 70 + }, + { + "epoch": 0.1756311745334797, + "grad_norm": 0.6698123216629028, + "learning_rate": 0.0002, + "loss": 1.3049, + "step": 80 + }, + { + "epoch": 0.19758507135016465, + "grad_norm": 0.4190150201320648, + "learning_rate": 0.0002, + "loss": 1.2975, + "step": 90 + }, + { + "epoch": 0.21953896816684962, + "grad_norm": 0.4110015034675598, + "learning_rate": 0.0002, + "loss": 1.2797, + "step": 100 + }, + { + "epoch": 0.2414928649835346, + "grad_norm": 0.33374306559562683, + "learning_rate": 0.0002, + "loss": 1.2896, + "step": 110 + }, + { + "epoch": 0.26344676180021953, + "grad_norm": 0.3061307370662689, + "learning_rate": 0.0002, + "loss": 1.2268, + "step": 120 + }, + { + "epoch": 0.2854006586169045, + "grad_norm": 0.4386885166168213, + "learning_rate": 0.0002, + "loss": 1.376, + "step": 130 + }, + { + "epoch": 0.30735455543358947, + "grad_norm": 0.40116462111473083, + "learning_rate": 0.0002, + "loss": 1.1814, + "step": 140 + }, + { + "epoch": 0.32930845225027444, + "grad_norm": 0.5887949466705322, + "learning_rate": 0.0002, + "loss": 1.2592, + "step": 150 + }, + { + "epoch": 0.3512623490669594, + "grad_norm": 0.3401573896408081, + "learning_rate": 0.0002, + "loss": 1.2372, + "step": 160 + }, + { + "epoch": 0.3732162458836443, + "grad_norm": 0.3288364112377167, + "learning_rate": 0.0002, + "loss": 1.1901, + "step": 170 + }, + { + "epoch": 0.3951701427003293, + "grad_norm": 0.4853297472000122, + "learning_rate": 0.0002, + "loss": 1.2335, + "step": 180 + }, + { + "epoch": 0.41712403951701427, + "grad_norm": 2.6253697872161865, + "learning_rate": 0.0002, + "loss": 1.227, + "step": 190 + }, + { + "epoch": 0.43907793633369924, + "grad_norm": 0.5598543286323547, + "learning_rate": 0.0002, + "loss": 1.2673, + "step": 200 + }, + { + "epoch": 0.4610318331503842, + "grad_norm": 0.4046548902988434, + "learning_rate": 0.0002, + "loss": 1.3459, + "step": 210 + }, + { + "epoch": 0.4829857299670692, + "grad_norm": 0.3686952590942383, + "learning_rate": 0.0002, + "loss": 1.265, + "step": 220 + }, + { + "epoch": 0.5049396267837541, + "grad_norm": 0.42458799481391907, + "learning_rate": 0.0002, + "loss": 1.1364, + "step": 230 + }, + { + "epoch": 0.5268935236004391, + "grad_norm": 0.5839895009994507, + "learning_rate": 0.0002, + "loss": 1.2094, + "step": 240 + }, + { + "epoch": 0.5488474204171241, + "grad_norm": 0.408288836479187, + "learning_rate": 0.0002, + "loss": 1.2073, + "step": 250 + }, + { + "epoch": 0.570801317233809, + "grad_norm": 0.45887550711631775, + "learning_rate": 0.0002, + "loss": 1.3121, + "step": 260 + }, + { + "epoch": 0.5927552140504939, + "grad_norm": 0.5440235733985901, + "learning_rate": 0.0002, + "loss": 1.2257, + "step": 270 + }, + { + "epoch": 0.6147091108671789, + "grad_norm": 0.3725181519985199, + "learning_rate": 0.0002, + "loss": 1.1003, + "step": 280 + }, + { + "epoch": 0.6366630076838639, + "grad_norm": 0.4309018850326538, + "learning_rate": 0.0002, + "loss": 1.1538, + "step": 290 + }, + { + "epoch": 0.6586169045005489, + "grad_norm": 0.31488674879074097, + "learning_rate": 0.0002, + "loss": 1.2097, + "step": 300 + }, + { + "epoch": 0.6805708013172338, + "grad_norm": 0.34194841980934143, + "learning_rate": 0.0002, + "loss": 1.1689, + "step": 310 + }, + { + "epoch": 0.7025246981339188, + "grad_norm": 0.3407684862613678, + "learning_rate": 0.0002, + "loss": 1.2579, + "step": 320 + }, + { + "epoch": 0.7244785949506037, + "grad_norm": 0.2985728085041046, + "learning_rate": 0.0002, + "loss": 1.1144, + "step": 330 + }, + { + "epoch": 0.7464324917672887, + "grad_norm": 0.42316871881484985, + "learning_rate": 0.0002, + "loss": 1.2056, + "step": 340 + }, + { + "epoch": 0.7683863885839737, + "grad_norm": 0.3124258816242218, + "learning_rate": 0.0002, + "loss": 1.1753, + "step": 350 + }, + { + "epoch": 0.7903402854006586, + "grad_norm": 0.7727567553520203, + "learning_rate": 0.0002, + "loss": 1.2547, + "step": 360 + }, + { + "epoch": 0.8122941822173436, + "grad_norm": 0.363765686750412, + "learning_rate": 0.0002, + "loss": 1.124, + "step": 370 + }, + { + "epoch": 0.8342480790340285, + "grad_norm": 0.35582536458969116, + "learning_rate": 0.0002, + "loss": 1.1302, + "step": 380 + }, + { + "epoch": 0.8562019758507134, + "grad_norm": 0.31982025504112244, + "learning_rate": 0.0002, + "loss": 1.1787, + "step": 390 + }, + { + "epoch": 0.8781558726673985, + "grad_norm": 0.34978964924812317, + "learning_rate": 0.0002, + "loss": 1.2056, + "step": 400 + }, + { + "epoch": 0.9001097694840834, + "grad_norm": 0.8346716165542603, + "learning_rate": 0.0002, + "loss": 1.3577, + "step": 410 + }, + { + "epoch": 0.9220636663007684, + "grad_norm": 0.31984028220176697, + "learning_rate": 0.0002, + "loss": 1.1029, + "step": 420 + }, + { + "epoch": 0.9440175631174533, + "grad_norm": 0.32078951597213745, + "learning_rate": 0.0002, + "loss": 1.0967, + "step": 430 + }, + { + "epoch": 0.9659714599341384, + "grad_norm": 0.3417500853538513, + "learning_rate": 0.0002, + "loss": 1.0936, + "step": 440 + }, + { + "epoch": 0.9879253567508233, + "grad_norm": 0.42359477281570435, + "learning_rate": 0.0002, + "loss": 1.3412, + "step": 450 + }, + { + "epoch": 0.9989023051591658, + "eval_loss": 1.2201528549194336, + "eval_runtime": 87.152, + "eval_samples_per_second": 4.945, + "eval_steps_per_second": 0.62, + "step": 455 + }, + { + "epoch": 1.0098792535675083, + "grad_norm": 0.37914523482322693, + "learning_rate": 0.0002, + "loss": 1.1909, + "step": 460 + }, + { + "epoch": 1.031833150384193, + "grad_norm": 0.43655872344970703, + "learning_rate": 0.0002, + "loss": 1.0948, + "step": 470 + }, + { + "epoch": 1.0537870472008781, + "grad_norm": 0.3673796057701111, + "learning_rate": 0.0002, + "loss": 1.0873, + "step": 480 + }, + { + "epoch": 1.0757409440175631, + "grad_norm": 0.37673917412757874, + "learning_rate": 0.0002, + "loss": 1.0483, + "step": 490 + }, + { + "epoch": 1.0976948408342482, + "grad_norm": 0.2893829345703125, + "learning_rate": 0.0002, + "loss": 1.0799, + "step": 500 + }, + { + "epoch": 1.119648737650933, + "grad_norm": 0.5551970601081848, + "learning_rate": 0.0002, + "loss": 1.1847, + "step": 510 + }, + { + "epoch": 1.141602634467618, + "grad_norm": 0.442104309797287, + "learning_rate": 0.0002, + "loss": 1.0885, + "step": 520 + }, + { + "epoch": 1.163556531284303, + "grad_norm": 0.4035094976425171, + "learning_rate": 0.0002, + "loss": 1.1766, + "step": 530 + }, + { + "epoch": 1.1855104281009878, + "grad_norm": 0.47009000182151794, + "learning_rate": 0.0002, + "loss": 1.0282, + "step": 540 + }, + { + "epoch": 1.2074643249176729, + "grad_norm": 0.4118749797344208, + "learning_rate": 0.0002, + "loss": 1.2625, + "step": 550 + }, + { + "epoch": 1.2294182217343579, + "grad_norm": 0.35173165798187256, + "learning_rate": 0.0002, + "loss": 1.0988, + "step": 560 + }, + { + "epoch": 1.2513721185510427, + "grad_norm": 0.7024672031402588, + "learning_rate": 0.0002, + "loss": 1.0498, + "step": 570 + }, + { + "epoch": 1.2733260153677277, + "grad_norm": 0.42657527327537537, + "learning_rate": 0.0002, + "loss": 1.1339, + "step": 580 + }, + { + "epoch": 1.2952799121844127, + "grad_norm": 0.3815029561519623, + "learning_rate": 0.0002, + "loss": 1.0545, + "step": 590 + }, + { + "epoch": 1.3172338090010978, + "grad_norm": 0.7031055688858032, + "learning_rate": 0.0002, + "loss": 1.1528, + "step": 600 + }, + { + "epoch": 1.3391877058177828, + "grad_norm": 0.393911212682724, + "learning_rate": 0.0002, + "loss": 1.1347, + "step": 610 + }, + { + "epoch": 1.3611416026344676, + "grad_norm": 0.5077702403068542, + "learning_rate": 0.0002, + "loss": 1.1901, + "step": 620 + }, + { + "epoch": 1.3830954994511526, + "grad_norm": 2.330033302307129, + "learning_rate": 0.0002, + "loss": 1.1251, + "step": 630 + }, + { + "epoch": 1.4050493962678376, + "grad_norm": 0.35322949290275574, + "learning_rate": 0.0002, + "loss": 1.0477, + "step": 640 + }, + { + "epoch": 1.4270032930845225, + "grad_norm": 0.44401052594184875, + "learning_rate": 0.0002, + "loss": 1.14, + "step": 650 + }, + { + "epoch": 1.4489571899012075, + "grad_norm": 0.35945481061935425, + "learning_rate": 0.0002, + "loss": 1.0318, + "step": 660 + }, + { + "epoch": 1.4709110867178925, + "grad_norm": 0.3058856129646301, + "learning_rate": 0.0002, + "loss": 1.1988, + "step": 670 + }, + { + "epoch": 1.4928649835345773, + "grad_norm": 0.7067602872848511, + "learning_rate": 0.0002, + "loss": 1.1545, + "step": 680 + }, + { + "epoch": 1.5148188803512623, + "grad_norm": 0.4219357371330261, + "learning_rate": 0.0002, + "loss": 1.0925, + "step": 690 + }, + { + "epoch": 1.5367727771679474, + "grad_norm": 0.5970841646194458, + "learning_rate": 0.0002, + "loss": 1.1622, + "step": 700 + }, + { + "epoch": 1.5587266739846322, + "grad_norm": 0.4381934404373169, + "learning_rate": 0.0002, + "loss": 1.0803, + "step": 710 + }, + { + "epoch": 1.5806805708013172, + "grad_norm": 0.4101450443267822, + "learning_rate": 0.0002, + "loss": 1.0961, + "step": 720 + }, + { + "epoch": 1.6026344676180022, + "grad_norm": 0.3657490015029907, + "learning_rate": 0.0002, + "loss": 1.0474, + "step": 730 + }, + { + "epoch": 1.624588364434687, + "grad_norm": 0.36240628361701965, + "learning_rate": 0.0002, + "loss": 1.0936, + "step": 740 + }, + { + "epoch": 1.6465422612513723, + "grad_norm": 0.4103568494319916, + "learning_rate": 0.0002, + "loss": 1.0489, + "step": 750 + }, + { + "epoch": 1.668496158068057, + "grad_norm": 0.3138505816459656, + "learning_rate": 0.0002, + "loss": 1.0919, + "step": 760 + }, + { + "epoch": 1.690450054884742, + "grad_norm": 0.41215717792510986, + "learning_rate": 0.0002, + "loss": 1.2308, + "step": 770 + }, + { + "epoch": 1.7124039517014271, + "grad_norm": 0.4589519202709198, + "learning_rate": 0.0002, + "loss": 1.1659, + "step": 780 + }, + { + "epoch": 1.734357848518112, + "grad_norm": 0.4049508571624756, + "learning_rate": 0.0002, + "loss": 1.0913, + "step": 790 + }, + { + "epoch": 1.756311745334797, + "grad_norm": 0.48557212948799133, + "learning_rate": 0.0002, + "loss": 1.1329, + "step": 800 + }, + { + "epoch": 1.778265642151482, + "grad_norm": 0.5331754088401794, + "learning_rate": 0.0002, + "loss": 1.0729, + "step": 810 + }, + { + "epoch": 1.8002195389681668, + "grad_norm": 0.3853185772895813, + "learning_rate": 0.0002, + "loss": 1.1452, + "step": 820 + }, + { + "epoch": 1.8221734357848518, + "grad_norm": 0.424062579870224, + "learning_rate": 0.0002, + "loss": 1.1061, + "step": 830 + }, + { + "epoch": 1.8441273326015368, + "grad_norm": 0.3418445289134979, + "learning_rate": 0.0002, + "loss": 1.1104, + "step": 840 + }, + { + "epoch": 1.8660812294182216, + "grad_norm": 0.4045565128326416, + "learning_rate": 0.0002, + "loss": 1.0546, + "step": 850 + }, + { + "epoch": 1.8880351262349067, + "grad_norm": 0.42155781388282776, + "learning_rate": 0.0002, + "loss": 1.1608, + "step": 860 + }, + { + "epoch": 1.9099890230515917, + "grad_norm": 0.40554770827293396, + "learning_rate": 0.0002, + "loss": 1.0628, + "step": 870 + }, + { + "epoch": 1.9319429198682765, + "grad_norm": 0.42644748091697693, + "learning_rate": 0.0002, + "loss": 1.1609, + "step": 880 + }, + { + "epoch": 1.9538968166849617, + "grad_norm": 0.45260652899742126, + "learning_rate": 0.0002, + "loss": 1.1132, + "step": 890 + }, + { + "epoch": 1.9758507135016465, + "grad_norm": 0.4114069938659668, + "learning_rate": 0.0002, + "loss": 1.048, + "step": 900 + }, + { + "epoch": 1.9978046103183313, + "grad_norm": 0.375802218914032, + "learning_rate": 0.0002, + "loss": 1.1941, + "step": 910 + }, + { + "epoch": 2.0, + "eval_loss": 1.205152153968811, + "eval_runtime": 86.8795, + "eval_samples_per_second": 4.961, + "eval_steps_per_second": 0.622, + "step": 911 + } + ], + "logging_steps": 10, + "max_steps": 3640, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 4.215904018838323e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f75755c7cf71aeb05b76db2632173f96f74e8f7 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf90ce7dd53cc68edd44d14e30ca84a5d7431a5b99d4697b17af4b2f7ec0abab +size 5624 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393 +size 17209961 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|eot_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f75755c7cf71aeb05b76db2632173f96f74e8f7 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf90ce7dd53cc68edd44d14e30ca84a5d7431a5b99d4697b17af4b2f7ec0abab +size 5624 diff --git a/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/training_log.jsonl b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/training_log.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ef02e50b8cb47a26fb5d339ee9c79fcc460cffde --- /dev/null +++ b/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/training_log.jsonl @@ -0,0 +1,9 @@ +{"epoch": 0.9989023051591658, "step": 455, "epoch_duration": 2338.0945768356323, "total_accumulated_duration": 2338.0945768356323, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7672.4541015625}, "peak_memory_usage": {"GPU_0": 9688.99365234375}, "avg_memory_reserved": {"GPU_0": 10406.0}, "peak_memory_reserved": {"GPU_0": 10406.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 1.9885, "grad_norm": 0.6242940425872803, "learning_rate": 0.0002, "epoch": 0.021953896816684963, "step": 10}, {"loss": 1.688, "grad_norm": 0.553617000579834, "learning_rate": 0.0002, "epoch": 0.043907793633369926, "step": 20}, {"loss": 1.3994, "grad_norm": 0.4264789819717407, "learning_rate": 0.0002, "epoch": 0.06586169045005488, "step": 30}, {"loss": 1.4676, "grad_norm": 0.4773778021335602, "learning_rate": 0.0002, "epoch": 0.08781558726673985, "step": 40}, {"loss": 1.1785, "grad_norm": 0.44155699014663696, "learning_rate": 0.0002, "epoch": 0.10976948408342481, "step": 50}, {"loss": 1.3698, "grad_norm": 0.7234572768211365, "learning_rate": 0.0002, "epoch": 0.13172338090010977, "step": 60}, {"loss": 1.2603, "grad_norm": 0.4489372670650482, "learning_rate": 0.0002, "epoch": 0.15367727771679474, "step": 70}, {"loss": 1.3052, "grad_norm": 0.6880296468734741, "learning_rate": 0.0002, "epoch": 0.1756311745334797, "step": 80}, {"loss": 1.2977, "grad_norm": 0.4229933023452759, "learning_rate": 0.0002, "epoch": 0.19758507135016465, "step": 90}, {"loss": 1.2795, "grad_norm": 0.4066077172756195, "learning_rate": 0.0002, "epoch": 0.21953896816684962, "step": 100}, {"loss": 1.29, "grad_norm": 0.3334372639656067, "learning_rate": 0.0002, "epoch": 0.2414928649835346, "step": 110}, {"loss": 1.2248, "grad_norm": 0.3118804395198822, "learning_rate": 0.0002, "epoch": 0.26344676180021953, "step": 120}, {"loss": 1.3774, "grad_norm": 0.4451749622821808, "learning_rate": 0.0002, "epoch": 0.2854006586169045, "step": 130}, {"loss": 1.1809, "grad_norm": 0.3972407579421997, "learning_rate": 0.0002, "epoch": 0.30735455543358947, "step": 140}, {"loss": 1.2594, "grad_norm": 0.6912697553634644, "learning_rate": 0.0002, "epoch": 0.32930845225027444, "step": 150}, {"loss": 1.2364, "grad_norm": 0.3417494297027588, "learning_rate": 0.0002, "epoch": 0.3512623490669594, "step": 160}, {"loss": 1.1895, "grad_norm": 0.32791027426719666, "learning_rate": 0.0002, "epoch": 0.3732162458836443, "step": 170}, {"loss": 1.2333, "grad_norm": 0.7495821714401245, "learning_rate": 0.0002, "epoch": 0.3951701427003293, "step": 180}, {"loss": 1.2272, "grad_norm": 0.38368701934814453, "learning_rate": 0.0002, "epoch": 0.41712403951701427, "step": 190}, {"loss": 1.2667, "grad_norm": 0.6000299453735352, "learning_rate": 0.0002, "epoch": 0.43907793633369924, "step": 200}, {"loss": 1.3461, "grad_norm": 0.4232163429260254, "learning_rate": 0.0002, "epoch": 0.4610318331503842, "step": 210}, {"loss": 1.2647, "grad_norm": 0.38271084427833557, "learning_rate": 0.0002, "epoch": 0.4829857299670692, "step": 220}, {"loss": 1.1367, "grad_norm": 0.324641615152359, "learning_rate": 0.0002, "epoch": 0.5049396267837541, "step": 230}, {"loss": 1.2099, "grad_norm": 0.5889573097229004, "learning_rate": 0.0002, "epoch": 0.5268935236004391, "step": 240}, {"loss": 1.2094, "grad_norm": 0.41033005714416504, "learning_rate": 0.0002, "epoch": 0.5488474204171241, "step": 250}, {"loss": 1.3115, "grad_norm": 0.46177080273628235, "learning_rate": 0.0002, "epoch": 0.570801317233809, "step": 260}, {"loss": 1.2282, "grad_norm": 0.5528939962387085, "learning_rate": 0.0002, "epoch": 0.5927552140504939, "step": 270}, {"loss": 1.1015, "grad_norm": 0.37327760457992554, "learning_rate": 0.0002, "epoch": 0.6147091108671789, "step": 280}, {"loss": 1.152, "grad_norm": 0.42856472730636597, "learning_rate": 0.0002, "epoch": 0.6366630076838639, "step": 290}, {"loss": 1.2105, "grad_norm": 0.30138567090034485, "learning_rate": 0.0002, "epoch": 0.6586169045005489, "step": 300}, {"loss": 1.1698, "grad_norm": 0.3417067229747772, "learning_rate": 0.0002, "epoch": 0.6805708013172338, "step": 310}, {"loss": 1.2578, "grad_norm": 0.34105488657951355, "learning_rate": 0.0002, "epoch": 0.7025246981339188, "step": 320}, {"loss": 1.1161, "grad_norm": 0.30202463269233704, "learning_rate": 0.0002, "epoch": 0.7244785949506037, "step": 330}, {"loss": 1.2032, "grad_norm": 0.3948274254798889, "learning_rate": 0.0002, "epoch": 0.7464324917672887, "step": 340}, {"loss": 1.1741, "grad_norm": 0.31234365701675415, "learning_rate": 0.0002, "epoch": 0.7683863885839737, "step": 350}, {"loss": 1.2522, "grad_norm": 0.8667094111442566, "learning_rate": 0.0002, "epoch": 0.7903402854006586, "step": 360}, {"loss": 1.1235, "grad_norm": 0.3661728799343109, "learning_rate": 0.0002, "epoch": 0.8122941822173436, "step": 370}, {"loss": 1.1306, "grad_norm": 0.3535974323749542, "learning_rate": 0.0002, "epoch": 0.8342480790340285, "step": 380}, {"loss": 1.1793, "grad_norm": 0.3261358439922333, "learning_rate": 0.0002, "epoch": 0.8562019758507134, "step": 390}, {"loss": 1.2079, "grad_norm": 0.3555273413658142, "learning_rate": 0.0002, "epoch": 0.8781558726673985, "step": 400}, {"loss": 1.3582, "grad_norm": 0.7340273857116699, "learning_rate": 0.0002, "epoch": 0.9001097694840834, "step": 410}, {"loss": 1.1019, "grad_norm": 0.31911978125572205, "learning_rate": 0.0002, "epoch": 0.9220636663007684, "step": 420}, {"loss": 1.0954, "grad_norm": 0.32541999220848083, "learning_rate": 0.0002, "epoch": 0.9440175631174533, "step": 430}, {"loss": 1.0975, "grad_norm": 0.3326643407344818, "learning_rate": 0.0002, "epoch": 0.9659714599341384, "step": 440}, {"loss": 1.3411, "grad_norm": 0.39029696583747864, "learning_rate": 0.0002, "epoch": 0.9879253567508233, "step": 450}]} +{"epoch": 0.9989023051591658, "step": 455, "epoch_duration": 1548.3599050045013, "total_accumulated_duration": 1548.3599050045013, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7672.4541015625}, "peak_memory_usage": {"GPU_0": 9688.99365234375}, "avg_memory_reserved": {"GPU_0": 10406.0}, "peak_memory_reserved": {"GPU_0": 10406.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 1.9887, "grad_norm": 0.6144012212753296, "learning_rate": 0.0002, "epoch": 0.021953896816684963, "step": 10}, {"loss": 1.6882, "grad_norm": 0.5587220788002014, "learning_rate": 0.0002, "epoch": 0.043907793633369926, "step": 20}, {"loss": 1.399, "grad_norm": 0.43262454867362976, "learning_rate": 0.0002, "epoch": 0.06586169045005488, "step": 30}, {"loss": 1.4675, "grad_norm": 0.4783053994178772, "learning_rate": 0.0002, "epoch": 0.08781558726673985, "step": 40}, {"loss": 1.1771, "grad_norm": 0.44338956475257874, "learning_rate": 0.0002, "epoch": 0.10976948408342481, "step": 50}, {"loss": 1.3706, "grad_norm": 0.7255092263221741, "learning_rate": 0.0002, "epoch": 0.13172338090010977, "step": 60}, {"loss": 1.2601, "grad_norm": 0.46073833107948303, "learning_rate": 0.0002, "epoch": 0.15367727771679474, "step": 70}, {"loss": 1.3049, "grad_norm": 0.6698123216629028, "learning_rate": 0.0002, "epoch": 0.1756311745334797, "step": 80}, {"loss": 1.2975, "grad_norm": 0.4190150201320648, "learning_rate": 0.0002, "epoch": 0.19758507135016465, "step": 90}, {"loss": 1.2797, "grad_norm": 0.4110015034675598, "learning_rate": 0.0002, "epoch": 0.21953896816684962, "step": 100}, {"loss": 1.2896, "grad_norm": 0.33374306559562683, "learning_rate": 0.0002, "epoch": 0.2414928649835346, "step": 110}, {"loss": 1.2268, "grad_norm": 0.3061307370662689, "learning_rate": 0.0002, "epoch": 0.26344676180021953, "step": 120}, {"loss": 1.376, "grad_norm": 0.4386885166168213, "learning_rate": 0.0002, "epoch": 0.2854006586169045, "step": 130}, {"loss": 1.1814, "grad_norm": 0.40116462111473083, "learning_rate": 0.0002, "epoch": 0.30735455543358947, "step": 140}, {"loss": 1.2592, "grad_norm": 0.5887949466705322, "learning_rate": 0.0002, "epoch": 0.32930845225027444, "step": 150}, {"loss": 1.2372, "grad_norm": 0.3401573896408081, "learning_rate": 0.0002, "epoch": 0.3512623490669594, "step": 160}, {"loss": 1.1901, "grad_norm": 0.3288364112377167, "learning_rate": 0.0002, "epoch": 0.3732162458836443, "step": 170}, {"loss": 1.2335, "grad_norm": 0.4853297472000122, "learning_rate": 0.0002, "epoch": 0.3951701427003293, "step": 180}, {"loss": 1.227, "grad_norm": 2.6253697872161865, "learning_rate": 0.0002, "epoch": 0.41712403951701427, "step": 190}, {"loss": 1.2673, "grad_norm": 0.5598543286323547, "learning_rate": 0.0002, "epoch": 0.43907793633369924, "step": 200}, {"loss": 1.3459, "grad_norm": 0.4046548902988434, "learning_rate": 0.0002, "epoch": 0.4610318331503842, "step": 210}, {"loss": 1.265, "grad_norm": 0.3686952590942383, "learning_rate": 0.0002, "epoch": 0.4829857299670692, "step": 220}, {"loss": 1.1364, "grad_norm": 0.42458799481391907, "learning_rate": 0.0002, "epoch": 0.5049396267837541, "step": 230}, {"loss": 1.2094, "grad_norm": 0.5839895009994507, "learning_rate": 0.0002, "epoch": 0.5268935236004391, "step": 240}, {"loss": 1.2073, "grad_norm": 0.408288836479187, "learning_rate": 0.0002, "epoch": 0.5488474204171241, "step": 250}, {"loss": 1.3121, "grad_norm": 0.45887550711631775, "learning_rate": 0.0002, "epoch": 0.570801317233809, "step": 260}, {"loss": 1.2257, "grad_norm": 0.5440235733985901, "learning_rate": 0.0002, "epoch": 0.5927552140504939, "step": 270}, {"loss": 1.1003, "grad_norm": 0.3725181519985199, "learning_rate": 0.0002, "epoch": 0.6147091108671789, "step": 280}, {"loss": 1.1538, "grad_norm": 0.4309018850326538, "learning_rate": 0.0002, "epoch": 0.6366630076838639, "step": 290}, {"loss": 1.2097, "grad_norm": 0.31488674879074097, "learning_rate": 0.0002, "epoch": 0.6586169045005489, "step": 300}, {"loss": 1.1689, "grad_norm": 0.34194841980934143, "learning_rate": 0.0002, "epoch": 0.6805708013172338, "step": 310}, {"loss": 1.2579, "grad_norm": 0.3407684862613678, "learning_rate": 0.0002, "epoch": 0.7025246981339188, "step": 320}, {"loss": 1.1144, "grad_norm": 0.2985728085041046, "learning_rate": 0.0002, "epoch": 0.7244785949506037, "step": 330}, {"loss": 1.2056, "grad_norm": 0.42316871881484985, "learning_rate": 0.0002, "epoch": 0.7464324917672887, "step": 340}, {"loss": 1.1753, "grad_norm": 0.3124258816242218, "learning_rate": 0.0002, "epoch": 0.7683863885839737, "step": 350}, {"loss": 1.2547, "grad_norm": 0.7727567553520203, "learning_rate": 0.0002, "epoch": 0.7903402854006586, "step": 360}, {"loss": 1.124, "grad_norm": 0.363765686750412, "learning_rate": 0.0002, "epoch": 0.8122941822173436, "step": 370}, {"loss": 1.1302, "grad_norm": 0.35582536458969116, "learning_rate": 0.0002, "epoch": 0.8342480790340285, "step": 380}, {"loss": 1.1787, "grad_norm": 0.31982025504112244, "learning_rate": 0.0002, "epoch": 0.8562019758507134, "step": 390}, {"loss": 1.2056, "grad_norm": 0.34978964924812317, "learning_rate": 0.0002, "epoch": 0.8781558726673985, "step": 400}, {"loss": 1.3577, "grad_norm": 0.8346716165542603, "learning_rate": 0.0002, "epoch": 0.9001097694840834, "step": 410}, {"loss": 1.1029, "grad_norm": 0.31984028220176697, "learning_rate": 0.0002, "epoch": 0.9220636663007684, "step": 420}, {"loss": 1.0967, "grad_norm": 0.32078951597213745, "learning_rate": 0.0002, "epoch": 0.9440175631174533, "step": 430}, {"loss": 1.0936, "grad_norm": 0.3417500853538513, "learning_rate": 0.0002, "epoch": 0.9659714599341384, "step": 440}, {"loss": 1.3412, "grad_norm": 0.42359477281570435, "learning_rate": 0.0002, "epoch": 0.9879253567508233, "step": 450}]} +{"epoch": 2.0, "step": 911, "epoch_duration": 1527.257779598236, "total_accumulated_duration": 3075.6176846027374, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7568.4541015625}, "peak_memory_usage": {"GPU_0": 13792.75439453125}, "avg_memory_reserved": {"GPU_0": 17416.0}, "peak_memory_reserved": {"GPU_0": 17416.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 1.9887, "grad_norm": 0.6144012212753296, "learning_rate": 0.0002, "epoch": 0.021953896816684963, "step": 10}, {"loss": 1.6882, "grad_norm": 0.5587220788002014, "learning_rate": 0.0002, "epoch": 0.043907793633369926, "step": 20}, {"loss": 1.399, "grad_norm": 0.43262454867362976, "learning_rate": 0.0002, "epoch": 0.06586169045005488, "step": 30}, {"loss": 1.4675, "grad_norm": 0.4783053994178772, "learning_rate": 0.0002, "epoch": 0.08781558726673985, "step": 40}, {"loss": 1.1771, "grad_norm": 0.44338956475257874, "learning_rate": 0.0002, "epoch": 0.10976948408342481, "step": 50}, {"loss": 1.3706, "grad_norm": 0.7255092263221741, "learning_rate": 0.0002, "epoch": 0.13172338090010977, "step": 60}, {"loss": 1.2601, "grad_norm": 0.46073833107948303, "learning_rate": 0.0002, "epoch": 0.15367727771679474, "step": 70}, {"loss": 1.3049, "grad_norm": 0.6698123216629028, "learning_rate": 0.0002, "epoch": 0.1756311745334797, "step": 80}, {"loss": 1.2975, "grad_norm": 0.4190150201320648, "learning_rate": 0.0002, "epoch": 0.19758507135016465, "step": 90}, {"loss": 1.2797, "grad_norm": 0.4110015034675598, "learning_rate": 0.0002, "epoch": 0.21953896816684962, "step": 100}, {"loss": 1.2896, "grad_norm": 0.33374306559562683, "learning_rate": 0.0002, "epoch": 0.2414928649835346, "step": 110}, {"loss": 1.2268, "grad_norm": 0.3061307370662689, "learning_rate": 0.0002, "epoch": 0.26344676180021953, "step": 120}, {"loss": 1.376, "grad_norm": 0.4386885166168213, "learning_rate": 0.0002, "epoch": 0.2854006586169045, "step": 130}, {"loss": 1.1814, "grad_norm": 0.40116462111473083, "learning_rate": 0.0002, "epoch": 0.30735455543358947, "step": 140}, {"loss": 1.2592, "grad_norm": 0.5887949466705322, "learning_rate": 0.0002, "epoch": 0.32930845225027444, "step": 150}, {"loss": 1.2372, "grad_norm": 0.3401573896408081, "learning_rate": 0.0002, "epoch": 0.3512623490669594, "step": 160}, {"loss": 1.1901, "grad_norm": 0.3288364112377167, "learning_rate": 0.0002, "epoch": 0.3732162458836443, "step": 170}, {"loss": 1.2335, "grad_norm": 0.4853297472000122, "learning_rate": 0.0002, "epoch": 0.3951701427003293, "step": 180}, {"loss": 1.227, "grad_norm": 2.6253697872161865, "learning_rate": 0.0002, "epoch": 0.41712403951701427, "step": 190}, {"loss": 1.2673, "grad_norm": 0.5598543286323547, "learning_rate": 0.0002, "epoch": 0.43907793633369924, "step": 200}, {"loss": 1.3459, "grad_norm": 0.4046548902988434, "learning_rate": 0.0002, "epoch": 0.4610318331503842, "step": 210}, {"loss": 1.265, "grad_norm": 0.3686952590942383, "learning_rate": 0.0002, "epoch": 0.4829857299670692, "step": 220}, {"loss": 1.1364, "grad_norm": 0.42458799481391907, "learning_rate": 0.0002, "epoch": 0.5049396267837541, "step": 230}, {"loss": 1.2094, "grad_norm": 0.5839895009994507, "learning_rate": 0.0002, "epoch": 0.5268935236004391, "step": 240}, {"loss": 1.2073, "grad_norm": 0.408288836479187, "learning_rate": 0.0002, "epoch": 0.5488474204171241, "step": 250}, {"loss": 1.3121, "grad_norm": 0.45887550711631775, "learning_rate": 0.0002, "epoch": 0.570801317233809, "step": 260}, {"loss": 1.2257, "grad_norm": 0.5440235733985901, "learning_rate": 0.0002, "epoch": 0.5927552140504939, "step": 270}, {"loss": 1.1003, "grad_norm": 0.3725181519985199, "learning_rate": 0.0002, "epoch": 0.6147091108671789, "step": 280}, {"loss": 1.1538, "grad_norm": 0.4309018850326538, "learning_rate": 0.0002, "epoch": 0.6366630076838639, "step": 290}, {"loss": 1.2097, "grad_norm": 0.31488674879074097, "learning_rate": 0.0002, "epoch": 0.6586169045005489, "step": 300}, {"loss": 1.1689, "grad_norm": 0.34194841980934143, "learning_rate": 0.0002, "epoch": 0.6805708013172338, "step": 310}, {"loss": 1.2579, "grad_norm": 0.3407684862613678, "learning_rate": 0.0002, "epoch": 0.7025246981339188, "step": 320}, {"loss": 1.1144, "grad_norm": 0.2985728085041046, "learning_rate": 0.0002, "epoch": 0.7244785949506037, "step": 330}, {"loss": 1.2056, "grad_norm": 0.42316871881484985, "learning_rate": 0.0002, "epoch": 0.7464324917672887, "step": 340}, {"loss": 1.1753, "grad_norm": 0.3124258816242218, "learning_rate": 0.0002, "epoch": 0.7683863885839737, "step": 350}, {"loss": 1.2547, "grad_norm": 0.7727567553520203, "learning_rate": 0.0002, "epoch": 0.7903402854006586, "step": 360}, {"loss": 1.124, "grad_norm": 0.363765686750412, "learning_rate": 0.0002, "epoch": 0.8122941822173436, "step": 370}, {"loss": 1.1302, "grad_norm": 0.35582536458969116, "learning_rate": 0.0002, "epoch": 0.8342480790340285, "step": 380}, {"loss": 1.1787, "grad_norm": 0.31982025504112244, "learning_rate": 0.0002, "epoch": 0.8562019758507134, "step": 390}, {"loss": 1.2056, "grad_norm": 0.34978964924812317, "learning_rate": 0.0002, "epoch": 0.8781558726673985, "step": 400}, {"loss": 1.3577, "grad_norm": 0.8346716165542603, "learning_rate": 0.0002, "epoch": 0.9001097694840834, "step": 410}, {"loss": 1.1029, "grad_norm": 0.31984028220176697, "learning_rate": 0.0002, "epoch": 0.9220636663007684, "step": 420}, {"loss": 1.0967, "grad_norm": 0.32078951597213745, "learning_rate": 0.0002, "epoch": 0.9440175631174533, "step": 430}, {"loss": 1.0936, "grad_norm": 0.3417500853538513, "learning_rate": 0.0002, "epoch": 0.9659714599341384, "step": 440}, {"loss": 1.3412, "grad_norm": 0.42359477281570435, "learning_rate": 0.0002, "epoch": 0.9879253567508233, "step": 450}, {"eval_loss": 1.2201528549194336, "eval_runtime": 87.152, "eval_samples_per_second": 4.945, "eval_steps_per_second": 0.62, "epoch": 0.9989023051591658, "step": 455}, {"loss": 1.1909, "grad_norm": 0.37914523482322693, "learning_rate": 0.0002, "epoch": 1.0098792535675083, "step": 460}, {"loss": 1.0948, "grad_norm": 0.43655872344970703, "learning_rate": 0.0002, "epoch": 1.031833150384193, "step": 470}, {"loss": 1.0873, "grad_norm": 0.3673796057701111, "learning_rate": 0.0002, "epoch": 1.0537870472008781, "step": 480}, {"loss": 1.0483, "grad_norm": 0.37673917412757874, "learning_rate": 0.0002, "epoch": 1.0757409440175631, "step": 490}, {"loss": 1.0799, "grad_norm": 0.2893829345703125, "learning_rate": 0.0002, "epoch": 1.0976948408342482, "step": 500}, {"loss": 1.1847, "grad_norm": 0.5551970601081848, "learning_rate": 0.0002, "epoch": 1.119648737650933, "step": 510}, {"loss": 1.0885, "grad_norm": 0.442104309797287, "learning_rate": 0.0002, "epoch": 1.141602634467618, "step": 520}, {"loss": 1.1766, "grad_norm": 0.4035094976425171, "learning_rate": 0.0002, "epoch": 1.163556531284303, "step": 530}, {"loss": 1.0282, "grad_norm": 0.47009000182151794, "learning_rate": 0.0002, "epoch": 1.1855104281009878, "step": 540}, {"loss": 1.2625, "grad_norm": 0.4118749797344208, "learning_rate": 0.0002, "epoch": 1.2074643249176729, "step": 550}, {"loss": 1.0988, "grad_norm": 0.35173165798187256, "learning_rate": 0.0002, "epoch": 1.2294182217343579, "step": 560}, {"loss": 1.0498, "grad_norm": 0.7024672031402588, "learning_rate": 0.0002, "epoch": 1.2513721185510427, "step": 570}, {"loss": 1.1339, "grad_norm": 0.42657527327537537, "learning_rate": 0.0002, "epoch": 1.2733260153677277, "step": 580}, {"loss": 1.0545, "grad_norm": 0.3815029561519623, "learning_rate": 0.0002, "epoch": 1.2952799121844127, "step": 590}, {"loss": 1.1528, "grad_norm": 0.7031055688858032, "learning_rate": 0.0002, "epoch": 1.3172338090010978, "step": 600}, {"loss": 1.1347, "grad_norm": 0.393911212682724, "learning_rate": 0.0002, "epoch": 1.3391877058177828, "step": 610}, {"loss": 1.1901, "grad_norm": 0.5077702403068542, "learning_rate": 0.0002, "epoch": 1.3611416026344676, "step": 620}, {"loss": 1.1251, "grad_norm": 2.330033302307129, "learning_rate": 0.0002, "epoch": 1.3830954994511526, "step": 630}, {"loss": 1.0477, "grad_norm": 0.35322949290275574, "learning_rate": 0.0002, "epoch": 1.4050493962678376, "step": 640}, {"loss": 1.14, "grad_norm": 0.44401052594184875, "learning_rate": 0.0002, "epoch": 1.4270032930845225, "step": 650}, {"loss": 1.0318, "grad_norm": 0.35945481061935425, "learning_rate": 0.0002, "epoch": 1.4489571899012075, "step": 660}, {"loss": 1.1988, "grad_norm": 0.3058856129646301, "learning_rate": 0.0002, "epoch": 1.4709110867178925, "step": 670}, {"loss": 1.1545, "grad_norm": 0.7067602872848511, "learning_rate": 0.0002, "epoch": 1.4928649835345773, "step": 680}, {"loss": 1.0925, "grad_norm": 0.4219357371330261, "learning_rate": 0.0002, "epoch": 1.5148188803512623, "step": 690}, {"loss": 1.1622, "grad_norm": 0.5970841646194458, "learning_rate": 0.0002, "epoch": 1.5367727771679474, "step": 700}, {"loss": 1.0803, "grad_norm": 0.4381934404373169, "learning_rate": 0.0002, "epoch": 1.5587266739846322, "step": 710}, {"loss": 1.0961, "grad_norm": 0.4101450443267822, "learning_rate": 0.0002, "epoch": 1.5806805708013172, "step": 720}, {"loss": 1.0474, "grad_norm": 0.3657490015029907, "learning_rate": 0.0002, "epoch": 1.6026344676180022, "step": 730}, {"loss": 1.0936, "grad_norm": 0.36240628361701965, "learning_rate": 0.0002, "epoch": 1.624588364434687, "step": 740}, {"loss": 1.0489, "grad_norm": 0.4103568494319916, "learning_rate": 0.0002, "epoch": 1.6465422612513723, "step": 750}, {"loss": 1.0919, "grad_norm": 0.3138505816459656, "learning_rate": 0.0002, "epoch": 1.668496158068057, "step": 760}, {"loss": 1.2308, "grad_norm": 0.41215717792510986, "learning_rate": 0.0002, "epoch": 1.690450054884742, "step": 770}, {"loss": 1.1659, "grad_norm": 0.4589519202709198, "learning_rate": 0.0002, "epoch": 1.7124039517014271, "step": 780}, {"loss": 1.0913, "grad_norm": 0.4049508571624756, "learning_rate": 0.0002, "epoch": 1.734357848518112, "step": 790}, {"loss": 1.1329, "grad_norm": 0.48557212948799133, "learning_rate": 0.0002, "epoch": 1.756311745334797, "step": 800}, {"loss": 1.0729, "grad_norm": 0.5331754088401794, "learning_rate": 0.0002, "epoch": 1.778265642151482, "step": 810}, {"loss": 1.1452, "grad_norm": 0.3853185772895813, "learning_rate": 0.0002, "epoch": 1.8002195389681668, "step": 820}, {"loss": 1.1061, "grad_norm": 0.424062579870224, "learning_rate": 0.0002, "epoch": 1.8221734357848518, "step": 830}, {"loss": 1.1104, "grad_norm": 0.3418445289134979, "learning_rate": 0.0002, "epoch": 1.8441273326015368, "step": 840}, {"loss": 1.0546, "grad_norm": 0.4045565128326416, "learning_rate": 0.0002, "epoch": 1.8660812294182216, "step": 850}, {"loss": 1.1608, "grad_norm": 0.42155781388282776, "learning_rate": 0.0002, "epoch": 1.8880351262349067, "step": 860}, {"loss": 1.0628, "grad_norm": 0.40554770827293396, "learning_rate": 0.0002, "epoch": 1.9099890230515917, "step": 870}, {"loss": 1.1609, "grad_norm": 0.42644748091697693, "learning_rate": 0.0002, "epoch": 1.9319429198682765, "step": 880}, {"loss": 1.1132, "grad_norm": 0.45260652899742126, "learning_rate": 0.0002, "epoch": 1.9538968166849617, "step": 890}, {"loss": 1.048, "grad_norm": 0.4114069938659668, "learning_rate": 0.0002, "epoch": 1.9758507135016465, "step": 900}, {"loss": 1.1941, "grad_norm": 0.375802218914032, "learning_rate": 0.0002, "epoch": 1.9978046103183313, "step": 910}]} +{"epoch": 2.9989023051591657, "step": 1366, "epoch_duration": 1555.537448644638, "total_accumulated_duration": 4631.1551332473755, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7672.4541015625}, "peak_memory_usage": {"GPU_0": 13792.75439453125}, "avg_memory_reserved": {"GPU_0": 17416.0}, "peak_memory_reserved": {"GPU_0": 17416.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 1.9887, "grad_norm": 0.6144012212753296, "learning_rate": 0.0002, "epoch": 0.021953896816684963, "step": 10}, {"loss": 1.6882, "grad_norm": 0.5587220788002014, "learning_rate": 0.0002, "epoch": 0.043907793633369926, "step": 20}, {"loss": 1.399, "grad_norm": 0.43262454867362976, "learning_rate": 0.0002, "epoch": 0.06586169045005488, "step": 30}, {"loss": 1.4675, "grad_norm": 0.4783053994178772, "learning_rate": 0.0002, "epoch": 0.08781558726673985, "step": 40}, {"loss": 1.1771, "grad_norm": 0.44338956475257874, "learning_rate": 0.0002, "epoch": 0.10976948408342481, "step": 50}, {"loss": 1.3706, "grad_norm": 0.7255092263221741, "learning_rate": 0.0002, "epoch": 0.13172338090010977, "step": 60}, {"loss": 1.2601, "grad_norm": 0.46073833107948303, "learning_rate": 0.0002, "epoch": 0.15367727771679474, "step": 70}, {"loss": 1.3049, "grad_norm": 0.6698123216629028, "learning_rate": 0.0002, "epoch": 0.1756311745334797, "step": 80}, {"loss": 1.2975, "grad_norm": 0.4190150201320648, "learning_rate": 0.0002, "epoch": 0.19758507135016465, "step": 90}, {"loss": 1.2797, "grad_norm": 0.4110015034675598, "learning_rate": 0.0002, "epoch": 0.21953896816684962, "step": 100}, {"loss": 1.2896, "grad_norm": 0.33374306559562683, "learning_rate": 0.0002, "epoch": 0.2414928649835346, "step": 110}, {"loss": 1.2268, "grad_norm": 0.3061307370662689, "learning_rate": 0.0002, "epoch": 0.26344676180021953, "step": 120}, {"loss": 1.376, "grad_norm": 0.4386885166168213, "learning_rate": 0.0002, "epoch": 0.2854006586169045, "step": 130}, {"loss": 1.1814, "grad_norm": 0.40116462111473083, "learning_rate": 0.0002, "epoch": 0.30735455543358947, "step": 140}, {"loss": 1.2592, "grad_norm": 0.5887949466705322, "learning_rate": 0.0002, "epoch": 0.32930845225027444, "step": 150}, {"loss": 1.2372, "grad_norm": 0.3401573896408081, "learning_rate": 0.0002, "epoch": 0.3512623490669594, "step": 160}, {"loss": 1.1901, "grad_norm": 0.3288364112377167, "learning_rate": 0.0002, "epoch": 0.3732162458836443, "step": 170}, {"loss": 1.2335, "grad_norm": 0.4853297472000122, "learning_rate": 0.0002, "epoch": 0.3951701427003293, "step": 180}, {"loss": 1.227, "grad_norm": 2.6253697872161865, "learning_rate": 0.0002, "epoch": 0.41712403951701427, "step": 190}, {"loss": 1.2673, "grad_norm": 0.5598543286323547, "learning_rate": 0.0002, "epoch": 0.43907793633369924, "step": 200}, {"loss": 1.3459, "grad_norm": 0.4046548902988434, "learning_rate": 0.0002, "epoch": 0.4610318331503842, "step": 210}, {"loss": 1.265, "grad_norm": 0.3686952590942383, "learning_rate": 0.0002, "epoch": 0.4829857299670692, "step": 220}, {"loss": 1.1364, "grad_norm": 0.42458799481391907, "learning_rate": 0.0002, "epoch": 0.5049396267837541, "step": 230}, {"loss": 1.2094, "grad_norm": 0.5839895009994507, "learning_rate": 0.0002, "epoch": 0.5268935236004391, "step": 240}, {"loss": 1.2073, "grad_norm": 0.408288836479187, "learning_rate": 0.0002, "epoch": 0.5488474204171241, "step": 250}, {"loss": 1.3121, "grad_norm": 0.45887550711631775, "learning_rate": 0.0002, "epoch": 0.570801317233809, "step": 260}, {"loss": 1.2257, "grad_norm": 0.5440235733985901, "learning_rate": 0.0002, "epoch": 0.5927552140504939, "step": 270}, {"loss": 1.1003, "grad_norm": 0.3725181519985199, "learning_rate": 0.0002, "epoch": 0.6147091108671789, "step": 280}, {"loss": 1.1538, "grad_norm": 0.4309018850326538, "learning_rate": 0.0002, "epoch": 0.6366630076838639, "step": 290}, {"loss": 1.2097, "grad_norm": 0.31488674879074097, "learning_rate": 0.0002, "epoch": 0.6586169045005489, "step": 300}, {"loss": 1.1689, "grad_norm": 0.34194841980934143, "learning_rate": 0.0002, "epoch": 0.6805708013172338, "step": 310}, {"loss": 1.2579, "grad_norm": 0.3407684862613678, "learning_rate": 0.0002, "epoch": 0.7025246981339188, "step": 320}, {"loss": 1.1144, "grad_norm": 0.2985728085041046, "learning_rate": 0.0002, "epoch": 0.7244785949506037, "step": 330}, {"loss": 1.2056, "grad_norm": 0.42316871881484985, "learning_rate": 0.0002, "epoch": 0.7464324917672887, "step": 340}, {"loss": 1.1753, "grad_norm": 0.3124258816242218, "learning_rate": 0.0002, "epoch": 0.7683863885839737, "step": 350}, {"loss": 1.2547, "grad_norm": 0.7727567553520203, "learning_rate": 0.0002, "epoch": 0.7903402854006586, "step": 360}, {"loss": 1.124, "grad_norm": 0.363765686750412, "learning_rate": 0.0002, "epoch": 0.8122941822173436, "step": 370}, {"loss": 1.1302, "grad_norm": 0.35582536458969116, "learning_rate": 0.0002, "epoch": 0.8342480790340285, "step": 380}, {"loss": 1.1787, "grad_norm": 0.31982025504112244, "learning_rate": 0.0002, "epoch": 0.8562019758507134, "step": 390}, {"loss": 1.2056, "grad_norm": 0.34978964924812317, "learning_rate": 0.0002, "epoch": 0.8781558726673985, "step": 400}, {"loss": 1.3577, "grad_norm": 0.8346716165542603, "learning_rate": 0.0002, "epoch": 0.9001097694840834, "step": 410}, {"loss": 1.1029, "grad_norm": 0.31984028220176697, "learning_rate": 0.0002, "epoch": 0.9220636663007684, "step": 420}, {"loss": 1.0967, "grad_norm": 0.32078951597213745, "learning_rate": 0.0002, "epoch": 0.9440175631174533, "step": 430}, {"loss": 1.0936, "grad_norm": 0.3417500853538513, "learning_rate": 0.0002, "epoch": 0.9659714599341384, "step": 440}, {"loss": 1.3412, "grad_norm": 0.42359477281570435, "learning_rate": 0.0002, "epoch": 0.9879253567508233, "step": 450}, {"eval_loss": 1.2201528549194336, "eval_runtime": 87.152, "eval_samples_per_second": 4.945, "eval_steps_per_second": 0.62, "epoch": 0.9989023051591658, "step": 455}, {"loss": 1.1909, "grad_norm": 0.37914523482322693, "learning_rate": 0.0002, "epoch": 1.0098792535675083, "step": 460}, {"loss": 1.0948, "grad_norm": 0.43655872344970703, "learning_rate": 0.0002, "epoch": 1.031833150384193, "step": 470}, {"loss": 1.0873, "grad_norm": 0.3673796057701111, "learning_rate": 0.0002, "epoch": 1.0537870472008781, "step": 480}, {"loss": 1.0483, "grad_norm": 0.37673917412757874, "learning_rate": 0.0002, "epoch": 1.0757409440175631, "step": 490}, {"loss": 1.0799, "grad_norm": 0.2893829345703125, "learning_rate": 0.0002, "epoch": 1.0976948408342482, "step": 500}, {"loss": 1.1847, "grad_norm": 0.5551970601081848, "learning_rate": 0.0002, "epoch": 1.119648737650933, "step": 510}, {"loss": 1.0885, "grad_norm": 0.442104309797287, "learning_rate": 0.0002, "epoch": 1.141602634467618, "step": 520}, {"loss": 1.1766, "grad_norm": 0.4035094976425171, "learning_rate": 0.0002, "epoch": 1.163556531284303, "step": 530}, {"loss": 1.0282, "grad_norm": 0.47009000182151794, "learning_rate": 0.0002, "epoch": 1.1855104281009878, "step": 540}, {"loss": 1.2625, "grad_norm": 0.4118749797344208, "learning_rate": 0.0002, "epoch": 1.2074643249176729, "step": 550}, {"loss": 1.0988, "grad_norm": 0.35173165798187256, "learning_rate": 0.0002, "epoch": 1.2294182217343579, "step": 560}, {"loss": 1.0498, "grad_norm": 0.7024672031402588, "learning_rate": 0.0002, "epoch": 1.2513721185510427, "step": 570}, {"loss": 1.1339, "grad_norm": 0.42657527327537537, "learning_rate": 0.0002, "epoch": 1.2733260153677277, "step": 580}, {"loss": 1.0545, "grad_norm": 0.3815029561519623, "learning_rate": 0.0002, "epoch": 1.2952799121844127, "step": 590}, {"loss": 1.1528, "grad_norm": 0.7031055688858032, "learning_rate": 0.0002, "epoch": 1.3172338090010978, "step": 600}, {"loss": 1.1347, "grad_norm": 0.393911212682724, "learning_rate": 0.0002, "epoch": 1.3391877058177828, "step": 610}, {"loss": 1.1901, "grad_norm": 0.5077702403068542, "learning_rate": 0.0002, "epoch": 1.3611416026344676, "step": 620}, {"loss": 1.1251, "grad_norm": 2.330033302307129, "learning_rate": 0.0002, "epoch": 1.3830954994511526, "step": 630}, {"loss": 1.0477, "grad_norm": 0.35322949290275574, "learning_rate": 0.0002, "epoch": 1.4050493962678376, "step": 640}, {"loss": 1.14, "grad_norm": 0.44401052594184875, "learning_rate": 0.0002, "epoch": 1.4270032930845225, "step": 650}, {"loss": 1.0318, "grad_norm": 0.35945481061935425, "learning_rate": 0.0002, "epoch": 1.4489571899012075, "step": 660}, {"loss": 1.1988, "grad_norm": 0.3058856129646301, "learning_rate": 0.0002, "epoch": 1.4709110867178925, "step": 670}, {"loss": 1.1545, "grad_norm": 0.7067602872848511, "learning_rate": 0.0002, "epoch": 1.4928649835345773, "step": 680}, {"loss": 1.0925, "grad_norm": 0.4219357371330261, "learning_rate": 0.0002, "epoch": 1.5148188803512623, "step": 690}, {"loss": 1.1622, "grad_norm": 0.5970841646194458, "learning_rate": 0.0002, "epoch": 1.5367727771679474, "step": 700}, {"loss": 1.0803, "grad_norm": 0.4381934404373169, "learning_rate": 0.0002, "epoch": 1.5587266739846322, "step": 710}, {"loss": 1.0961, "grad_norm": 0.4101450443267822, "learning_rate": 0.0002, "epoch": 1.5806805708013172, "step": 720}, {"loss": 1.0474, "grad_norm": 0.3657490015029907, "learning_rate": 0.0002, "epoch": 1.6026344676180022, "step": 730}, {"loss": 1.0936, "grad_norm": 0.36240628361701965, "learning_rate": 0.0002, "epoch": 1.624588364434687, "step": 740}, {"loss": 1.0489, "grad_norm": 0.4103568494319916, "learning_rate": 0.0002, "epoch": 1.6465422612513723, "step": 750}, {"loss": 1.0919, "grad_norm": 0.3138505816459656, "learning_rate": 0.0002, "epoch": 1.668496158068057, "step": 760}, {"loss": 1.2308, "grad_norm": 0.41215717792510986, "learning_rate": 0.0002, "epoch": 1.690450054884742, "step": 770}, {"loss": 1.1659, "grad_norm": 0.4589519202709198, "learning_rate": 0.0002, "epoch": 1.7124039517014271, "step": 780}, {"loss": 1.0913, "grad_norm": 0.4049508571624756, "learning_rate": 0.0002, "epoch": 1.734357848518112, "step": 790}, {"loss": 1.1329, "grad_norm": 0.48557212948799133, "learning_rate": 0.0002, "epoch": 1.756311745334797, "step": 800}, {"loss": 1.0729, "grad_norm": 0.5331754088401794, "learning_rate": 0.0002, "epoch": 1.778265642151482, "step": 810}, {"loss": 1.1452, "grad_norm": 0.3853185772895813, "learning_rate": 0.0002, "epoch": 1.8002195389681668, "step": 820}, {"loss": 1.1061, "grad_norm": 0.424062579870224, "learning_rate": 0.0002, "epoch": 1.8221734357848518, "step": 830}, {"loss": 1.1104, "grad_norm": 0.3418445289134979, "learning_rate": 0.0002, "epoch": 1.8441273326015368, "step": 840}, {"loss": 1.0546, "grad_norm": 0.4045565128326416, "learning_rate": 0.0002, "epoch": 1.8660812294182216, "step": 850}, {"loss": 1.1608, "grad_norm": 0.42155781388282776, "learning_rate": 0.0002, "epoch": 1.8880351262349067, "step": 860}, {"loss": 1.0628, "grad_norm": 0.40554770827293396, "learning_rate": 0.0002, "epoch": 1.9099890230515917, "step": 870}, {"loss": 1.1609, "grad_norm": 0.42644748091697693, "learning_rate": 0.0002, "epoch": 1.9319429198682765, "step": 880}, {"loss": 1.1132, "grad_norm": 0.45260652899742126, "learning_rate": 0.0002, "epoch": 1.9538968166849617, "step": 890}, {"loss": 1.048, "grad_norm": 0.4114069938659668, "learning_rate": 0.0002, "epoch": 1.9758507135016465, "step": 900}, {"loss": 1.1941, "grad_norm": 0.375802218914032, "learning_rate": 0.0002, "epoch": 1.9978046103183313, "step": 910}, {"eval_loss": 1.205152153968811, "eval_runtime": 86.8795, "eval_samples_per_second": 4.961, "eval_steps_per_second": 0.622, "epoch": 2.0, "step": 911}, {"loss": 1.0897, "grad_norm": 0.47718703746795654, "learning_rate": 0.0002, "epoch": 2.0197585071350166, "step": 920}, {"loss": 1.0329, "grad_norm": 0.45628082752227783, "learning_rate": 0.0002, "epoch": 2.0417124039517014, "step": 930}, {"loss": 1.0538, "grad_norm": 0.5933247804641724, "learning_rate": 0.0002, "epoch": 2.063666300768386, "step": 940}, {"loss": 1.0152, "grad_norm": 0.5355812907218933, "learning_rate": 0.0002, "epoch": 2.0856201975850714, "step": 950}, {"loss": 1.0726, "grad_norm": 0.5860010385513306, "learning_rate": 0.0002, "epoch": 2.1075740944017562, "step": 960}, {"loss": 1.025, "grad_norm": 0.7471673488616943, "learning_rate": 0.0002, "epoch": 2.129527991218441, "step": 970}, {"loss": 1.0247, "grad_norm": 2.0918211936950684, "learning_rate": 0.0002, "epoch": 2.1514818880351263, "step": 980}, {"loss": 0.8947, "grad_norm": 0.4021058678627014, "learning_rate": 0.0002, "epoch": 2.173435784851811, "step": 990}, {"loss": 0.8875, "grad_norm": 0.564975380897522, "learning_rate": 0.0002, "epoch": 2.1953896816684964, "step": 1000}, {"loss": 1.0264, "grad_norm": 0.46260079741477966, "learning_rate": 0.0002, "epoch": 2.217343578485181, "step": 1010}, {"loss": 0.9265, "grad_norm": 0.4791034460067749, "learning_rate": 0.0002, "epoch": 2.239297475301866, "step": 1020}, {"loss": 0.8869, "grad_norm": 0.5272043943405151, "learning_rate": 0.0002, "epoch": 2.261251372118551, "step": 1030}, {"loss": 1.0007, "grad_norm": 0.5221094489097595, "learning_rate": 0.0002, "epoch": 2.283205268935236, "step": 1040}, {"loss": 0.9472, "grad_norm": 0.558032751083374, "learning_rate": 0.0002, "epoch": 2.305159165751921, "step": 1050}, {"loss": 0.9617, "grad_norm": 0.5905590653419495, "learning_rate": 0.0002, "epoch": 2.327113062568606, "step": 1060}, {"loss": 0.9592, "grad_norm": 0.5308699607849121, "learning_rate": 0.0002, "epoch": 2.349066959385291, "step": 1070}, {"loss": 1.0646, "grad_norm": 0.6375027894973755, "learning_rate": 0.0002, "epoch": 2.3710208562019757, "step": 1080}, {"loss": 1.0354, "grad_norm": 0.7439115643501282, "learning_rate": 0.0002, "epoch": 2.392974753018661, "step": 1090}, {"loss": 1.0212, "grad_norm": 0.41945117712020874, "learning_rate": 0.0002, "epoch": 2.4149286498353457, "step": 1100}, {"loss": 0.9609, "grad_norm": 0.4891968369483948, "learning_rate": 0.0002, "epoch": 2.436882546652031, "step": 1110}, {"loss": 0.9829, "grad_norm": 0.4686794579029083, "learning_rate": 0.0002, "epoch": 2.4588364434687158, "step": 1120}, {"loss": 0.8919, "grad_norm": 0.5204509496688843, "learning_rate": 0.0002, "epoch": 2.4807903402854006, "step": 1130}, {"loss": 0.8983, "grad_norm": 0.6779005527496338, "learning_rate": 0.0002, "epoch": 2.5027442371020854, "step": 1140}, {"loss": 0.9733, "grad_norm": 0.682621955871582, "learning_rate": 0.0002, "epoch": 2.5246981339187706, "step": 1150}, {"loss": 1.051, "grad_norm": 0.5744376182556152, "learning_rate": 0.0002, "epoch": 2.5466520307354554, "step": 1160}, {"loss": 0.8764, "grad_norm": 0.49954667687416077, "learning_rate": 0.0002, "epoch": 2.5686059275521407, "step": 1170}, {"loss": 0.9896, "grad_norm": 0.4761793315410614, "learning_rate": 0.0002, "epoch": 2.5905598243688255, "step": 1180}, {"loss": 0.8593, "grad_norm": 0.548299252986908, "learning_rate": 0.0002, "epoch": 2.6125137211855103, "step": 1190}, {"loss": 1.0017, "grad_norm": 0.5771360993385315, "learning_rate": 0.0002, "epoch": 2.6344676180021955, "step": 1200}, {"loss": 0.9858, "grad_norm": 0.5543120503425598, "learning_rate": 0.0002, "epoch": 2.6564215148188803, "step": 1210}, {"loss": 0.9565, "grad_norm": 0.7564870715141296, "learning_rate": 0.0002, "epoch": 2.6783754116355656, "step": 1220}, {"loss": 0.9753, "grad_norm": 0.8222362399101257, "learning_rate": 0.0002, "epoch": 2.7003293084522504, "step": 1230}, {"loss": 1.0079, "grad_norm": 0.6894469857215881, "learning_rate": 0.0002, "epoch": 2.722283205268935, "step": 1240}, {"loss": 1.0106, "grad_norm": 0.6121546030044556, "learning_rate": 0.0002, "epoch": 2.74423710208562, "step": 1250}, {"loss": 0.9801, "grad_norm": 0.521809995174408, "learning_rate": 0.0002, "epoch": 2.7661909989023052, "step": 1260}, {"loss": 1.0196, "grad_norm": 0.766968309879303, "learning_rate": 0.0002, "epoch": 2.78814489571899, "step": 1270}, {"loss": 0.976, "grad_norm": 0.522331714630127, "learning_rate": 0.0002, "epoch": 2.8100987925356753, "step": 1280}, {"loss": 0.8866, "grad_norm": 0.42923519015312195, "learning_rate": 0.0002, "epoch": 2.83205268935236, "step": 1290}, {"loss": 0.9049, "grad_norm": 0.47810837626457214, "learning_rate": 0.0002, "epoch": 2.854006586169045, "step": 1300}, {"loss": 1.0291, "grad_norm": 1.0958846807479858, "learning_rate": 0.0002, "epoch": 2.8759604829857297, "step": 1310}, {"loss": 0.8724, "grad_norm": 0.4755791127681732, "learning_rate": 0.0002, "epoch": 2.897914379802415, "step": 1320}, {"loss": 0.9317, "grad_norm": 0.5575157403945923, "learning_rate": 0.0002, "epoch": 2.9198682766190998, "step": 1330}, {"loss": 1.0131, "grad_norm": 0.5938076376914978, "learning_rate": 0.0002, "epoch": 2.941822173435785, "step": 1340}, {"loss": 0.9857, "grad_norm": 0.5751763582229614, "learning_rate": 0.0002, "epoch": 2.96377607025247, "step": 1350}, {"loss": 1.0212, "grad_norm": 0.5590175986289978, "learning_rate": 0.0002, "epoch": 2.9857299670691546, "step": 1360}]} +{"epoch": 4.0, "step": 1822, "epoch_duration": 1552.5083029270172, "total_accumulated_duration": 6183.663436174393, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7568.4541015625}, "peak_memory_usage": {"GPU_0": 13792.75439453125}, "avg_memory_reserved": {"GPU_0": 17416.0}, "peak_memory_reserved": {"GPU_0": 17416.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 1.9887, "grad_norm": 0.6144012212753296, "learning_rate": 0.0002, "epoch": 0.021953896816684963, "step": 10}, {"loss": 1.6882, "grad_norm": 0.5587220788002014, "learning_rate": 0.0002, "epoch": 0.043907793633369926, "step": 20}, {"loss": 1.399, "grad_norm": 0.43262454867362976, "learning_rate": 0.0002, "epoch": 0.06586169045005488, "step": 30}, {"loss": 1.4675, "grad_norm": 0.4783053994178772, "learning_rate": 0.0002, "epoch": 0.08781558726673985, "step": 40}, {"loss": 1.1771, "grad_norm": 0.44338956475257874, "learning_rate": 0.0002, "epoch": 0.10976948408342481, "step": 50}, {"loss": 1.3706, "grad_norm": 0.7255092263221741, "learning_rate": 0.0002, "epoch": 0.13172338090010977, "step": 60}, {"loss": 1.2601, "grad_norm": 0.46073833107948303, "learning_rate": 0.0002, "epoch": 0.15367727771679474, "step": 70}, {"loss": 1.3049, "grad_norm": 0.6698123216629028, "learning_rate": 0.0002, "epoch": 0.1756311745334797, "step": 80}, {"loss": 1.2975, "grad_norm": 0.4190150201320648, "learning_rate": 0.0002, "epoch": 0.19758507135016465, "step": 90}, {"loss": 1.2797, "grad_norm": 0.4110015034675598, "learning_rate": 0.0002, "epoch": 0.21953896816684962, "step": 100}, {"loss": 1.2896, "grad_norm": 0.33374306559562683, "learning_rate": 0.0002, "epoch": 0.2414928649835346, "step": 110}, {"loss": 1.2268, "grad_norm": 0.3061307370662689, "learning_rate": 0.0002, "epoch": 0.26344676180021953, "step": 120}, {"loss": 1.376, "grad_norm": 0.4386885166168213, "learning_rate": 0.0002, "epoch": 0.2854006586169045, "step": 130}, {"loss": 1.1814, "grad_norm": 0.40116462111473083, "learning_rate": 0.0002, "epoch": 0.30735455543358947, "step": 140}, {"loss": 1.2592, "grad_norm": 0.5887949466705322, "learning_rate": 0.0002, "epoch": 0.32930845225027444, "step": 150}, {"loss": 1.2372, "grad_norm": 0.3401573896408081, "learning_rate": 0.0002, "epoch": 0.3512623490669594, "step": 160}, {"loss": 1.1901, "grad_norm": 0.3288364112377167, "learning_rate": 0.0002, "epoch": 0.3732162458836443, "step": 170}, {"loss": 1.2335, "grad_norm": 0.4853297472000122, "learning_rate": 0.0002, "epoch": 0.3951701427003293, "step": 180}, {"loss": 1.227, "grad_norm": 2.6253697872161865, "learning_rate": 0.0002, "epoch": 0.41712403951701427, "step": 190}, {"loss": 1.2673, "grad_norm": 0.5598543286323547, "learning_rate": 0.0002, "epoch": 0.43907793633369924, "step": 200}, {"loss": 1.3459, "grad_norm": 0.4046548902988434, "learning_rate": 0.0002, "epoch": 0.4610318331503842, "step": 210}, {"loss": 1.265, "grad_norm": 0.3686952590942383, "learning_rate": 0.0002, "epoch": 0.4829857299670692, "step": 220}, {"loss": 1.1364, "grad_norm": 0.42458799481391907, "learning_rate": 0.0002, "epoch": 0.5049396267837541, "step": 230}, {"loss": 1.2094, "grad_norm": 0.5839895009994507, "learning_rate": 0.0002, "epoch": 0.5268935236004391, "step": 240}, {"loss": 1.2073, "grad_norm": 0.408288836479187, "learning_rate": 0.0002, "epoch": 0.5488474204171241, "step": 250}, {"loss": 1.3121, "grad_norm": 0.45887550711631775, "learning_rate": 0.0002, "epoch": 0.570801317233809, "step": 260}, {"loss": 1.2257, "grad_norm": 0.5440235733985901, "learning_rate": 0.0002, "epoch": 0.5927552140504939, "step": 270}, {"loss": 1.1003, "grad_norm": 0.3725181519985199, "learning_rate": 0.0002, "epoch": 0.6147091108671789, "step": 280}, {"loss": 1.1538, "grad_norm": 0.4309018850326538, "learning_rate": 0.0002, "epoch": 0.6366630076838639, "step": 290}, {"loss": 1.2097, "grad_norm": 0.31488674879074097, "learning_rate": 0.0002, "epoch": 0.6586169045005489, "step": 300}, {"loss": 1.1689, "grad_norm": 0.34194841980934143, "learning_rate": 0.0002, "epoch": 0.6805708013172338, "step": 310}, {"loss": 1.2579, "grad_norm": 0.3407684862613678, "learning_rate": 0.0002, "epoch": 0.7025246981339188, "step": 320}, {"loss": 1.1144, "grad_norm": 0.2985728085041046, "learning_rate": 0.0002, "epoch": 0.7244785949506037, "step": 330}, {"loss": 1.2056, "grad_norm": 0.42316871881484985, "learning_rate": 0.0002, "epoch": 0.7464324917672887, "step": 340}, {"loss": 1.1753, "grad_norm": 0.3124258816242218, "learning_rate": 0.0002, "epoch": 0.7683863885839737, "step": 350}, {"loss": 1.2547, "grad_norm": 0.7727567553520203, "learning_rate": 0.0002, "epoch": 0.7903402854006586, "step": 360}, {"loss": 1.124, "grad_norm": 0.363765686750412, "learning_rate": 0.0002, "epoch": 0.8122941822173436, "step": 370}, {"loss": 1.1302, "grad_norm": 0.35582536458969116, "learning_rate": 0.0002, "epoch": 0.8342480790340285, "step": 380}, {"loss": 1.1787, "grad_norm": 0.31982025504112244, "learning_rate": 0.0002, "epoch": 0.8562019758507134, "step": 390}, {"loss": 1.2056, "grad_norm": 0.34978964924812317, "learning_rate": 0.0002, "epoch": 0.8781558726673985, "step": 400}, {"loss": 1.3577, "grad_norm": 0.8346716165542603, "learning_rate": 0.0002, "epoch": 0.9001097694840834, "step": 410}, {"loss": 1.1029, "grad_norm": 0.31984028220176697, "learning_rate": 0.0002, "epoch": 0.9220636663007684, "step": 420}, {"loss": 1.0967, "grad_norm": 0.32078951597213745, "learning_rate": 0.0002, "epoch": 0.9440175631174533, "step": 430}, {"loss": 1.0936, "grad_norm": 0.3417500853538513, "learning_rate": 0.0002, "epoch": 0.9659714599341384, "step": 440}, {"loss": 1.3412, "grad_norm": 0.42359477281570435, "learning_rate": 0.0002, "epoch": 0.9879253567508233, "step": 450}, {"eval_loss": 1.2201528549194336, "eval_runtime": 87.152, "eval_samples_per_second": 4.945, "eval_steps_per_second": 0.62, "epoch": 0.9989023051591658, "step": 455}, {"loss": 1.1909, "grad_norm": 0.37914523482322693, "learning_rate": 0.0002, "epoch": 1.0098792535675083, "step": 460}, {"loss": 1.0948, "grad_norm": 0.43655872344970703, "learning_rate": 0.0002, "epoch": 1.031833150384193, "step": 470}, {"loss": 1.0873, "grad_norm": 0.3673796057701111, "learning_rate": 0.0002, "epoch": 1.0537870472008781, "step": 480}, {"loss": 1.0483, "grad_norm": 0.37673917412757874, "learning_rate": 0.0002, "epoch": 1.0757409440175631, "step": 490}, {"loss": 1.0799, "grad_norm": 0.2893829345703125, "learning_rate": 0.0002, "epoch": 1.0976948408342482, "step": 500}, {"loss": 1.1847, "grad_norm": 0.5551970601081848, "learning_rate": 0.0002, "epoch": 1.119648737650933, "step": 510}, {"loss": 1.0885, "grad_norm": 0.442104309797287, "learning_rate": 0.0002, "epoch": 1.141602634467618, "step": 520}, {"loss": 1.1766, "grad_norm": 0.4035094976425171, "learning_rate": 0.0002, "epoch": 1.163556531284303, "step": 530}, {"loss": 1.0282, "grad_norm": 0.47009000182151794, "learning_rate": 0.0002, "epoch": 1.1855104281009878, "step": 540}, {"loss": 1.2625, "grad_norm": 0.4118749797344208, "learning_rate": 0.0002, "epoch": 1.2074643249176729, "step": 550}, {"loss": 1.0988, "grad_norm": 0.35173165798187256, "learning_rate": 0.0002, "epoch": 1.2294182217343579, "step": 560}, {"loss": 1.0498, "grad_norm": 0.7024672031402588, "learning_rate": 0.0002, "epoch": 1.2513721185510427, "step": 570}, {"loss": 1.1339, "grad_norm": 0.42657527327537537, "learning_rate": 0.0002, "epoch": 1.2733260153677277, "step": 580}, {"loss": 1.0545, "grad_norm": 0.3815029561519623, "learning_rate": 0.0002, "epoch": 1.2952799121844127, "step": 590}, {"loss": 1.1528, "grad_norm": 0.7031055688858032, "learning_rate": 0.0002, "epoch": 1.3172338090010978, "step": 600}, {"loss": 1.1347, "grad_norm": 0.393911212682724, "learning_rate": 0.0002, "epoch": 1.3391877058177828, "step": 610}, {"loss": 1.1901, "grad_norm": 0.5077702403068542, "learning_rate": 0.0002, "epoch": 1.3611416026344676, "step": 620}, {"loss": 1.1251, "grad_norm": 2.330033302307129, "learning_rate": 0.0002, "epoch": 1.3830954994511526, "step": 630}, {"loss": 1.0477, "grad_norm": 0.35322949290275574, "learning_rate": 0.0002, "epoch": 1.4050493962678376, "step": 640}, {"loss": 1.14, "grad_norm": 0.44401052594184875, "learning_rate": 0.0002, "epoch": 1.4270032930845225, "step": 650}, {"loss": 1.0318, "grad_norm": 0.35945481061935425, "learning_rate": 0.0002, "epoch": 1.4489571899012075, "step": 660}, {"loss": 1.1988, "grad_norm": 0.3058856129646301, "learning_rate": 0.0002, "epoch": 1.4709110867178925, "step": 670}, {"loss": 1.1545, "grad_norm": 0.7067602872848511, "learning_rate": 0.0002, "epoch": 1.4928649835345773, "step": 680}, {"loss": 1.0925, "grad_norm": 0.4219357371330261, "learning_rate": 0.0002, "epoch": 1.5148188803512623, "step": 690}, {"loss": 1.1622, "grad_norm": 0.5970841646194458, "learning_rate": 0.0002, "epoch": 1.5367727771679474, "step": 700}, {"loss": 1.0803, "grad_norm": 0.4381934404373169, "learning_rate": 0.0002, "epoch": 1.5587266739846322, "step": 710}, {"loss": 1.0961, "grad_norm": 0.4101450443267822, "learning_rate": 0.0002, "epoch": 1.5806805708013172, "step": 720}, {"loss": 1.0474, "grad_norm": 0.3657490015029907, "learning_rate": 0.0002, "epoch": 1.6026344676180022, "step": 730}, {"loss": 1.0936, "grad_norm": 0.36240628361701965, "learning_rate": 0.0002, "epoch": 1.624588364434687, "step": 740}, {"loss": 1.0489, "grad_norm": 0.4103568494319916, "learning_rate": 0.0002, "epoch": 1.6465422612513723, "step": 750}, {"loss": 1.0919, "grad_norm": 0.3138505816459656, "learning_rate": 0.0002, "epoch": 1.668496158068057, "step": 760}, {"loss": 1.2308, "grad_norm": 0.41215717792510986, "learning_rate": 0.0002, "epoch": 1.690450054884742, "step": 770}, {"loss": 1.1659, "grad_norm": 0.4589519202709198, "learning_rate": 0.0002, "epoch": 1.7124039517014271, "step": 780}, {"loss": 1.0913, "grad_norm": 0.4049508571624756, "learning_rate": 0.0002, "epoch": 1.734357848518112, "step": 790}, {"loss": 1.1329, "grad_norm": 0.48557212948799133, "learning_rate": 0.0002, "epoch": 1.756311745334797, "step": 800}, {"loss": 1.0729, "grad_norm": 0.5331754088401794, "learning_rate": 0.0002, "epoch": 1.778265642151482, "step": 810}, {"loss": 1.1452, "grad_norm": 0.3853185772895813, "learning_rate": 0.0002, "epoch": 1.8002195389681668, "step": 820}, {"loss": 1.1061, "grad_norm": 0.424062579870224, "learning_rate": 0.0002, "epoch": 1.8221734357848518, "step": 830}, {"loss": 1.1104, "grad_norm": 0.3418445289134979, "learning_rate": 0.0002, "epoch": 1.8441273326015368, "step": 840}, {"loss": 1.0546, "grad_norm": 0.4045565128326416, "learning_rate": 0.0002, "epoch": 1.8660812294182216, "step": 850}, {"loss": 1.1608, "grad_norm": 0.42155781388282776, "learning_rate": 0.0002, "epoch": 1.8880351262349067, "step": 860}, {"loss": 1.0628, "grad_norm": 0.40554770827293396, "learning_rate": 0.0002, "epoch": 1.9099890230515917, "step": 870}, {"loss": 1.1609, "grad_norm": 0.42644748091697693, "learning_rate": 0.0002, "epoch": 1.9319429198682765, "step": 880}, {"loss": 1.1132, "grad_norm": 0.45260652899742126, "learning_rate": 0.0002, "epoch": 1.9538968166849617, "step": 890}, {"loss": 1.048, "grad_norm": 0.4114069938659668, "learning_rate": 0.0002, "epoch": 1.9758507135016465, "step": 900}, {"loss": 1.1941, "grad_norm": 0.375802218914032, "learning_rate": 0.0002, "epoch": 1.9978046103183313, "step": 910}, {"eval_loss": 1.205152153968811, "eval_runtime": 86.8795, "eval_samples_per_second": 4.961, "eval_steps_per_second": 0.622, "epoch": 2.0, "step": 911}, {"loss": 1.0897, "grad_norm": 0.47718703746795654, "learning_rate": 0.0002, "epoch": 2.0197585071350166, "step": 920}, {"loss": 1.0329, "grad_norm": 0.45628082752227783, "learning_rate": 0.0002, "epoch": 2.0417124039517014, "step": 930}, {"loss": 1.0538, "grad_norm": 0.5933247804641724, "learning_rate": 0.0002, "epoch": 2.063666300768386, "step": 940}, {"loss": 1.0152, "grad_norm": 0.5355812907218933, "learning_rate": 0.0002, "epoch": 2.0856201975850714, "step": 950}, {"loss": 1.0726, "grad_norm": 0.5860010385513306, "learning_rate": 0.0002, "epoch": 2.1075740944017562, "step": 960}, {"loss": 1.025, "grad_norm": 0.7471673488616943, "learning_rate": 0.0002, "epoch": 2.129527991218441, "step": 970}, {"loss": 1.0247, "grad_norm": 2.0918211936950684, "learning_rate": 0.0002, "epoch": 2.1514818880351263, "step": 980}, {"loss": 0.8947, "grad_norm": 0.4021058678627014, "learning_rate": 0.0002, "epoch": 2.173435784851811, "step": 990}, {"loss": 0.8875, "grad_norm": 0.564975380897522, "learning_rate": 0.0002, "epoch": 2.1953896816684964, "step": 1000}, {"loss": 1.0264, "grad_norm": 0.46260079741477966, "learning_rate": 0.0002, "epoch": 2.217343578485181, "step": 1010}, {"loss": 0.9265, "grad_norm": 0.4791034460067749, "learning_rate": 0.0002, "epoch": 2.239297475301866, "step": 1020}, {"loss": 0.8869, "grad_norm": 0.5272043943405151, "learning_rate": 0.0002, "epoch": 2.261251372118551, "step": 1030}, {"loss": 1.0007, "grad_norm": 0.5221094489097595, "learning_rate": 0.0002, "epoch": 2.283205268935236, "step": 1040}, {"loss": 0.9472, "grad_norm": 0.558032751083374, "learning_rate": 0.0002, "epoch": 2.305159165751921, "step": 1050}, {"loss": 0.9617, "grad_norm": 0.5905590653419495, "learning_rate": 0.0002, "epoch": 2.327113062568606, "step": 1060}, {"loss": 0.9592, "grad_norm": 0.5308699607849121, "learning_rate": 0.0002, "epoch": 2.349066959385291, "step": 1070}, {"loss": 1.0646, "grad_norm": 0.6375027894973755, "learning_rate": 0.0002, "epoch": 2.3710208562019757, "step": 1080}, {"loss": 1.0354, "grad_norm": 0.7439115643501282, "learning_rate": 0.0002, "epoch": 2.392974753018661, "step": 1090}, {"loss": 1.0212, "grad_norm": 0.41945117712020874, "learning_rate": 0.0002, "epoch": 2.4149286498353457, "step": 1100}, {"loss": 0.9609, "grad_norm": 0.4891968369483948, "learning_rate": 0.0002, "epoch": 2.436882546652031, "step": 1110}, {"loss": 0.9829, "grad_norm": 0.4686794579029083, "learning_rate": 0.0002, "epoch": 2.4588364434687158, "step": 1120}, {"loss": 0.8919, "grad_norm": 0.5204509496688843, "learning_rate": 0.0002, "epoch": 2.4807903402854006, "step": 1130}, {"loss": 0.8983, "grad_norm": 0.6779005527496338, "learning_rate": 0.0002, "epoch": 2.5027442371020854, "step": 1140}, {"loss": 0.9733, "grad_norm": 0.682621955871582, "learning_rate": 0.0002, "epoch": 2.5246981339187706, "step": 1150}, {"loss": 1.051, "grad_norm": 0.5744376182556152, "learning_rate": 0.0002, "epoch": 2.5466520307354554, "step": 1160}, {"loss": 0.8764, "grad_norm": 0.49954667687416077, "learning_rate": 0.0002, "epoch": 2.5686059275521407, "step": 1170}, {"loss": 0.9896, "grad_norm": 0.4761793315410614, "learning_rate": 0.0002, "epoch": 2.5905598243688255, "step": 1180}, {"loss": 0.8593, "grad_norm": 0.548299252986908, "learning_rate": 0.0002, "epoch": 2.6125137211855103, "step": 1190}, {"loss": 1.0017, "grad_norm": 0.5771360993385315, "learning_rate": 0.0002, "epoch": 2.6344676180021955, "step": 1200}, {"loss": 0.9858, "grad_norm": 0.5543120503425598, "learning_rate": 0.0002, "epoch": 2.6564215148188803, "step": 1210}, {"loss": 0.9565, "grad_norm": 0.7564870715141296, "learning_rate": 0.0002, "epoch": 2.6783754116355656, "step": 1220}, {"loss": 0.9753, "grad_norm": 0.8222362399101257, "learning_rate": 0.0002, "epoch": 2.7003293084522504, "step": 1230}, {"loss": 1.0079, "grad_norm": 0.6894469857215881, "learning_rate": 0.0002, "epoch": 2.722283205268935, "step": 1240}, {"loss": 1.0106, "grad_norm": 0.6121546030044556, "learning_rate": 0.0002, "epoch": 2.74423710208562, "step": 1250}, {"loss": 0.9801, "grad_norm": 0.521809995174408, "learning_rate": 0.0002, "epoch": 2.7661909989023052, "step": 1260}, {"loss": 1.0196, "grad_norm": 0.766968309879303, "learning_rate": 0.0002, "epoch": 2.78814489571899, "step": 1270}, {"loss": 0.976, "grad_norm": 0.522331714630127, "learning_rate": 0.0002, "epoch": 2.8100987925356753, "step": 1280}, {"loss": 0.8866, "grad_norm": 0.42923519015312195, "learning_rate": 0.0002, "epoch": 2.83205268935236, "step": 1290}, {"loss": 0.9049, "grad_norm": 0.47810837626457214, "learning_rate": 0.0002, "epoch": 2.854006586169045, "step": 1300}, {"loss": 1.0291, "grad_norm": 1.0958846807479858, "learning_rate": 0.0002, "epoch": 2.8759604829857297, "step": 1310}, {"loss": 0.8724, "grad_norm": 0.4755791127681732, "learning_rate": 0.0002, "epoch": 2.897914379802415, "step": 1320}, {"loss": 0.9317, "grad_norm": 0.5575157403945923, "learning_rate": 0.0002, "epoch": 2.9198682766190998, "step": 1330}, {"loss": 1.0131, "grad_norm": 0.5938076376914978, "learning_rate": 0.0002, "epoch": 2.941822173435785, "step": 1340}, {"loss": 0.9857, "grad_norm": 0.5751763582229614, "learning_rate": 0.0002, "epoch": 2.96377607025247, "step": 1350}, {"loss": 1.0212, "grad_norm": 0.5590175986289978, "learning_rate": 0.0002, "epoch": 2.9857299670691546, "step": 1360}, {"eval_loss": 1.2402944564819336, "eval_runtime": 88.822, "eval_samples_per_second": 4.852, "eval_steps_per_second": 0.608, "epoch": 2.9989023051591657, "step": 1366}, {"loss": 0.844, "grad_norm": 0.463539719581604, "learning_rate": 0.0002, "epoch": 3.00768386388584, "step": 1370}, {"loss": 0.8955, "grad_norm": 0.6667885780334473, "learning_rate": 0.0002, "epoch": 3.0296377607025247, "step": 1380}, {"loss": 0.8765, "grad_norm": 0.5849342942237854, "learning_rate": 0.0002, "epoch": 3.0515916575192095, "step": 1390}, {"loss": 0.7808, "grad_norm": 0.5571770668029785, "learning_rate": 0.0002, "epoch": 3.0735455543358947, "step": 1400}, {"loss": 0.7448, "grad_norm": 0.5761234164237976, "learning_rate": 0.0002, "epoch": 3.0954994511525795, "step": 1410}, {"loss": 0.7854, "grad_norm": 0.7277371883392334, "learning_rate": 0.0002, "epoch": 3.1174533479692643, "step": 1420}, {"loss": 0.817, "grad_norm": 0.5190334320068359, "learning_rate": 0.0002, "epoch": 3.1394072447859496, "step": 1430}, {"loss": 0.7548, "grad_norm": 0.632939875125885, "learning_rate": 0.0002, "epoch": 3.1613611416026344, "step": 1440}, {"loss": 0.8447, "grad_norm": 0.7229540944099426, "learning_rate": 0.0002, "epoch": 3.1833150384193196, "step": 1450}, {"loss": 0.8595, "grad_norm": 0.7584632039070129, "learning_rate": 0.0002, "epoch": 3.2052689352360044, "step": 1460}, {"loss": 0.7456, "grad_norm": 0.6546088457107544, "learning_rate": 0.0002, "epoch": 3.2272228320526892, "step": 1470}, {"loss": 0.8531, "grad_norm": 0.8116684556007385, "learning_rate": 0.0002, "epoch": 3.2491767288693745, "step": 1480}, {"loss": 0.9272, "grad_norm": 0.6206557750701904, "learning_rate": 0.0002, "epoch": 3.2711306256860593, "step": 1490}, {"loss": 0.7972, "grad_norm": 0.5393369197845459, "learning_rate": 0.0002, "epoch": 3.293084522502744, "step": 1500}, {"loss": 0.7614, "grad_norm": 0.7006453275680542, "learning_rate": 0.0002, "epoch": 3.3150384193194293, "step": 1510}, {"loss": 0.7358, "grad_norm": 0.95253986120224, "learning_rate": 0.0002, "epoch": 3.336992316136114, "step": 1520}, {"loss": 0.8131, "grad_norm": 0.8138132095336914, "learning_rate": 0.0002, "epoch": 3.358946212952799, "step": 1530}, {"loss": 0.7738, "grad_norm": 0.7974302172660828, "learning_rate": 0.0002, "epoch": 3.380900109769484, "step": 1540}, {"loss": 0.8161, "grad_norm": 0.6694685220718384, "learning_rate": 0.0002, "epoch": 3.402854006586169, "step": 1550}, {"loss": 0.8503, "grad_norm": 0.908634603023529, "learning_rate": 0.0002, "epoch": 3.4248079034028542, "step": 1560}, {"loss": 0.7609, "grad_norm": 0.5625193119049072, "learning_rate": 0.0002, "epoch": 3.446761800219539, "step": 1570}, {"loss": 0.7658, "grad_norm": 0.779325544834137, "learning_rate": 0.0002, "epoch": 3.468715697036224, "step": 1580}, {"loss": 0.7485, "grad_norm": 0.7133058905601501, "learning_rate": 0.0002, "epoch": 3.4906695938529086, "step": 1590}, {"loss": 0.8847, "grad_norm": 0.6741108298301697, "learning_rate": 0.0002, "epoch": 3.512623490669594, "step": 1600}, {"loss": 0.7838, "grad_norm": 0.696982204914093, "learning_rate": 0.0002, "epoch": 3.5345773874862787, "step": 1610}, {"loss": 0.7195, "grad_norm": 0.7946001291275024, "learning_rate": 0.0002, "epoch": 3.556531284302964, "step": 1620}, {"loss": 0.7772, "grad_norm": 0.6313548684120178, "learning_rate": 0.0002, "epoch": 3.5784851811196488, "step": 1630}, {"loss": 0.8267, "grad_norm": 0.9246852397918701, "learning_rate": 0.0002, "epoch": 3.6004390779363336, "step": 1640}, {"loss": 0.779, "grad_norm": 0.6615420579910278, "learning_rate": 0.0002, "epoch": 3.622392974753019, "step": 1650}, {"loss": 0.883, "grad_norm": 1.5050125122070312, "learning_rate": 0.0002, "epoch": 3.6443468715697036, "step": 1660}, {"loss": 0.7763, "grad_norm": 0.5023762583732605, "learning_rate": 0.0002, "epoch": 3.666300768386389, "step": 1670}, {"loss": 0.8173, "grad_norm": 0.6289586424827576, "learning_rate": 0.0002, "epoch": 3.6882546652030737, "step": 1680}, {"loss": 0.9028, "grad_norm": 1.050397515296936, "learning_rate": 0.0002, "epoch": 3.7102085620197585, "step": 1690}, {"loss": 0.7747, "grad_norm": 0.6785626411437988, "learning_rate": 0.0002, "epoch": 3.7321624588364433, "step": 1700}, {"loss": 0.9215, "grad_norm": 0.7565035223960876, "learning_rate": 0.0002, "epoch": 3.7541163556531285, "step": 1710}, {"loss": 0.7913, "grad_norm": 0.7775155901908875, "learning_rate": 0.0002, "epoch": 3.7760702524698133, "step": 1720}, {"loss": 0.8081, "grad_norm": 0.765260636806488, "learning_rate": 0.0002, "epoch": 3.7980241492864986, "step": 1730}, {"loss": 0.9231, "grad_norm": 0.7982407808303833, "learning_rate": 0.0002, "epoch": 3.8199780461031834, "step": 1740}, {"loss": 0.7755, "grad_norm": 0.7431730628013611, "learning_rate": 0.0002, "epoch": 3.841931942919868, "step": 1750}, {"loss": 0.9236, "grad_norm": 0.9758927226066589, "learning_rate": 0.0002, "epoch": 3.863885839736553, "step": 1760}, {"loss": 0.9118, "grad_norm": 0.8014697432518005, "learning_rate": 0.0002, "epoch": 3.885839736553238, "step": 1770}, {"loss": 0.7503, "grad_norm": 0.7212756276130676, "learning_rate": 0.0002, "epoch": 3.907793633369923, "step": 1780}, {"loss": 0.7978, "grad_norm": 0.584318220615387, "learning_rate": 0.0002, "epoch": 3.9297475301866083, "step": 1790}, {"loss": 0.7894, "grad_norm": 0.7612535953521729, "learning_rate": 0.0002, "epoch": 3.951701427003293, "step": 1800}, {"loss": 0.8589, "grad_norm": 0.735103189945221, "learning_rate": 0.0002, "epoch": 3.973655323819978, "step": 1810}, {"loss": 0.8192, "grad_norm": 0.9074980020523071, "learning_rate": 0.0002, "epoch": 3.995609220636663, "step": 1820}]} +{"epoch": 4.998902305159166, "step": 2277, "epoch_duration": 1556.8957543373108, "total_accumulated_duration": 7740.5591905117035, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7672.4541015625}, "peak_memory_usage": {"GPU_0": 13792.75439453125}, "avg_memory_reserved": {"GPU_0": 17416.0}, "peak_memory_reserved": {"GPU_0": 17416.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 1.9887, "grad_norm": 0.6144012212753296, "learning_rate": 0.0002, "epoch": 0.021953896816684963, "step": 10}, {"loss": 1.6882, "grad_norm": 0.5587220788002014, "learning_rate": 0.0002, "epoch": 0.043907793633369926, "step": 20}, {"loss": 1.399, "grad_norm": 0.43262454867362976, "learning_rate": 0.0002, "epoch": 0.06586169045005488, "step": 30}, {"loss": 1.4675, "grad_norm": 0.4783053994178772, "learning_rate": 0.0002, "epoch": 0.08781558726673985, "step": 40}, {"loss": 1.1771, "grad_norm": 0.44338956475257874, "learning_rate": 0.0002, "epoch": 0.10976948408342481, "step": 50}, {"loss": 1.3706, "grad_norm": 0.7255092263221741, "learning_rate": 0.0002, "epoch": 0.13172338090010977, "step": 60}, {"loss": 1.2601, "grad_norm": 0.46073833107948303, "learning_rate": 0.0002, "epoch": 0.15367727771679474, "step": 70}, {"loss": 1.3049, "grad_norm": 0.6698123216629028, "learning_rate": 0.0002, "epoch": 0.1756311745334797, "step": 80}, {"loss": 1.2975, "grad_norm": 0.4190150201320648, "learning_rate": 0.0002, "epoch": 0.19758507135016465, "step": 90}, {"loss": 1.2797, "grad_norm": 0.4110015034675598, "learning_rate": 0.0002, "epoch": 0.21953896816684962, "step": 100}, {"loss": 1.2896, "grad_norm": 0.33374306559562683, "learning_rate": 0.0002, "epoch": 0.2414928649835346, "step": 110}, {"loss": 1.2268, "grad_norm": 0.3061307370662689, "learning_rate": 0.0002, "epoch": 0.26344676180021953, "step": 120}, {"loss": 1.376, "grad_norm": 0.4386885166168213, "learning_rate": 0.0002, "epoch": 0.2854006586169045, "step": 130}, {"loss": 1.1814, "grad_norm": 0.40116462111473083, "learning_rate": 0.0002, "epoch": 0.30735455543358947, "step": 140}, {"loss": 1.2592, "grad_norm": 0.5887949466705322, "learning_rate": 0.0002, "epoch": 0.32930845225027444, "step": 150}, {"loss": 1.2372, "grad_norm": 0.3401573896408081, "learning_rate": 0.0002, "epoch": 0.3512623490669594, "step": 160}, {"loss": 1.1901, "grad_norm": 0.3288364112377167, "learning_rate": 0.0002, "epoch": 0.3732162458836443, "step": 170}, {"loss": 1.2335, "grad_norm": 0.4853297472000122, "learning_rate": 0.0002, "epoch": 0.3951701427003293, "step": 180}, {"loss": 1.227, "grad_norm": 2.6253697872161865, "learning_rate": 0.0002, "epoch": 0.41712403951701427, "step": 190}, {"loss": 1.2673, "grad_norm": 0.5598543286323547, "learning_rate": 0.0002, "epoch": 0.43907793633369924, "step": 200}, {"loss": 1.3459, "grad_norm": 0.4046548902988434, "learning_rate": 0.0002, "epoch": 0.4610318331503842, "step": 210}, {"loss": 1.265, "grad_norm": 0.3686952590942383, "learning_rate": 0.0002, "epoch": 0.4829857299670692, "step": 220}, {"loss": 1.1364, "grad_norm": 0.42458799481391907, "learning_rate": 0.0002, "epoch": 0.5049396267837541, "step": 230}, {"loss": 1.2094, "grad_norm": 0.5839895009994507, "learning_rate": 0.0002, "epoch": 0.5268935236004391, "step": 240}, {"loss": 1.2073, "grad_norm": 0.408288836479187, "learning_rate": 0.0002, "epoch": 0.5488474204171241, "step": 250}, {"loss": 1.3121, "grad_norm": 0.45887550711631775, "learning_rate": 0.0002, "epoch": 0.570801317233809, "step": 260}, {"loss": 1.2257, "grad_norm": 0.5440235733985901, "learning_rate": 0.0002, "epoch": 0.5927552140504939, "step": 270}, {"loss": 1.1003, "grad_norm": 0.3725181519985199, "learning_rate": 0.0002, "epoch": 0.6147091108671789, "step": 280}, {"loss": 1.1538, "grad_norm": 0.4309018850326538, "learning_rate": 0.0002, "epoch": 0.6366630076838639, "step": 290}, {"loss": 1.2097, "grad_norm": 0.31488674879074097, "learning_rate": 0.0002, "epoch": 0.6586169045005489, "step": 300}, {"loss": 1.1689, "grad_norm": 0.34194841980934143, "learning_rate": 0.0002, "epoch": 0.6805708013172338, "step": 310}, {"loss": 1.2579, "grad_norm": 0.3407684862613678, "learning_rate": 0.0002, "epoch": 0.7025246981339188, "step": 320}, {"loss": 1.1144, "grad_norm": 0.2985728085041046, "learning_rate": 0.0002, "epoch": 0.7244785949506037, "step": 330}, {"loss": 1.2056, "grad_norm": 0.42316871881484985, "learning_rate": 0.0002, "epoch": 0.7464324917672887, "step": 340}, {"loss": 1.1753, "grad_norm": 0.3124258816242218, "learning_rate": 0.0002, "epoch": 0.7683863885839737, "step": 350}, {"loss": 1.2547, "grad_norm": 0.7727567553520203, "learning_rate": 0.0002, "epoch": 0.7903402854006586, "step": 360}, {"loss": 1.124, "grad_norm": 0.363765686750412, "learning_rate": 0.0002, "epoch": 0.8122941822173436, "step": 370}, {"loss": 1.1302, "grad_norm": 0.35582536458969116, "learning_rate": 0.0002, "epoch": 0.8342480790340285, "step": 380}, {"loss": 1.1787, "grad_norm": 0.31982025504112244, "learning_rate": 0.0002, "epoch": 0.8562019758507134, "step": 390}, {"loss": 1.2056, "grad_norm": 0.34978964924812317, "learning_rate": 0.0002, "epoch": 0.8781558726673985, "step": 400}, {"loss": 1.3577, "grad_norm": 0.8346716165542603, "learning_rate": 0.0002, "epoch": 0.9001097694840834, "step": 410}, {"loss": 1.1029, "grad_norm": 0.31984028220176697, "learning_rate": 0.0002, "epoch": 0.9220636663007684, "step": 420}, {"loss": 1.0967, "grad_norm": 0.32078951597213745, "learning_rate": 0.0002, "epoch": 0.9440175631174533, "step": 430}, {"loss": 1.0936, "grad_norm": 0.3417500853538513, "learning_rate": 0.0002, "epoch": 0.9659714599341384, "step": 440}, {"loss": 1.3412, "grad_norm": 0.42359477281570435, "learning_rate": 0.0002, "epoch": 0.9879253567508233, "step": 450}, {"eval_loss": 1.2201528549194336, "eval_runtime": 87.152, "eval_samples_per_second": 4.945, "eval_steps_per_second": 0.62, "epoch": 0.9989023051591658, "step": 455}, {"loss": 1.1909, "grad_norm": 0.37914523482322693, "learning_rate": 0.0002, "epoch": 1.0098792535675083, "step": 460}, {"loss": 1.0948, "grad_norm": 0.43655872344970703, "learning_rate": 0.0002, "epoch": 1.031833150384193, "step": 470}, {"loss": 1.0873, "grad_norm": 0.3673796057701111, "learning_rate": 0.0002, "epoch": 1.0537870472008781, "step": 480}, {"loss": 1.0483, "grad_norm": 0.37673917412757874, "learning_rate": 0.0002, "epoch": 1.0757409440175631, "step": 490}, {"loss": 1.0799, "grad_norm": 0.2893829345703125, "learning_rate": 0.0002, "epoch": 1.0976948408342482, "step": 500}, {"loss": 1.1847, "grad_norm": 0.5551970601081848, "learning_rate": 0.0002, "epoch": 1.119648737650933, "step": 510}, {"loss": 1.0885, "grad_norm": 0.442104309797287, "learning_rate": 0.0002, "epoch": 1.141602634467618, "step": 520}, {"loss": 1.1766, "grad_norm": 0.4035094976425171, "learning_rate": 0.0002, "epoch": 1.163556531284303, "step": 530}, {"loss": 1.0282, "grad_norm": 0.47009000182151794, "learning_rate": 0.0002, "epoch": 1.1855104281009878, "step": 540}, {"loss": 1.2625, "grad_norm": 0.4118749797344208, "learning_rate": 0.0002, "epoch": 1.2074643249176729, "step": 550}, {"loss": 1.0988, "grad_norm": 0.35173165798187256, "learning_rate": 0.0002, "epoch": 1.2294182217343579, "step": 560}, {"loss": 1.0498, "grad_norm": 0.7024672031402588, "learning_rate": 0.0002, "epoch": 1.2513721185510427, "step": 570}, {"loss": 1.1339, "grad_norm": 0.42657527327537537, "learning_rate": 0.0002, "epoch": 1.2733260153677277, "step": 580}, {"loss": 1.0545, "grad_norm": 0.3815029561519623, "learning_rate": 0.0002, "epoch": 1.2952799121844127, "step": 590}, {"loss": 1.1528, "grad_norm": 0.7031055688858032, "learning_rate": 0.0002, "epoch": 1.3172338090010978, "step": 600}, {"loss": 1.1347, "grad_norm": 0.393911212682724, "learning_rate": 0.0002, "epoch": 1.3391877058177828, "step": 610}, {"loss": 1.1901, "grad_norm": 0.5077702403068542, "learning_rate": 0.0002, "epoch": 1.3611416026344676, "step": 620}, {"loss": 1.1251, "grad_norm": 2.330033302307129, "learning_rate": 0.0002, "epoch": 1.3830954994511526, "step": 630}, {"loss": 1.0477, "grad_norm": 0.35322949290275574, "learning_rate": 0.0002, "epoch": 1.4050493962678376, "step": 640}, {"loss": 1.14, "grad_norm": 0.44401052594184875, "learning_rate": 0.0002, "epoch": 1.4270032930845225, "step": 650}, {"loss": 1.0318, "grad_norm": 0.35945481061935425, "learning_rate": 0.0002, "epoch": 1.4489571899012075, "step": 660}, {"loss": 1.1988, "grad_norm": 0.3058856129646301, "learning_rate": 0.0002, "epoch": 1.4709110867178925, "step": 670}, {"loss": 1.1545, "grad_norm": 0.7067602872848511, "learning_rate": 0.0002, "epoch": 1.4928649835345773, "step": 680}, {"loss": 1.0925, "grad_norm": 0.4219357371330261, "learning_rate": 0.0002, "epoch": 1.5148188803512623, "step": 690}, {"loss": 1.1622, "grad_norm": 0.5970841646194458, "learning_rate": 0.0002, "epoch": 1.5367727771679474, "step": 700}, {"loss": 1.0803, "grad_norm": 0.4381934404373169, "learning_rate": 0.0002, "epoch": 1.5587266739846322, "step": 710}, {"loss": 1.0961, "grad_norm": 0.4101450443267822, "learning_rate": 0.0002, "epoch": 1.5806805708013172, "step": 720}, {"loss": 1.0474, "grad_norm": 0.3657490015029907, "learning_rate": 0.0002, "epoch": 1.6026344676180022, "step": 730}, {"loss": 1.0936, "grad_norm": 0.36240628361701965, "learning_rate": 0.0002, "epoch": 1.624588364434687, "step": 740}, {"loss": 1.0489, "grad_norm": 0.4103568494319916, "learning_rate": 0.0002, "epoch": 1.6465422612513723, "step": 750}, {"loss": 1.0919, "grad_norm": 0.3138505816459656, "learning_rate": 0.0002, "epoch": 1.668496158068057, "step": 760}, {"loss": 1.2308, "grad_norm": 0.41215717792510986, "learning_rate": 0.0002, "epoch": 1.690450054884742, "step": 770}, {"loss": 1.1659, "grad_norm": 0.4589519202709198, "learning_rate": 0.0002, "epoch": 1.7124039517014271, "step": 780}, {"loss": 1.0913, "grad_norm": 0.4049508571624756, "learning_rate": 0.0002, "epoch": 1.734357848518112, "step": 790}, {"loss": 1.1329, "grad_norm": 0.48557212948799133, "learning_rate": 0.0002, "epoch": 1.756311745334797, "step": 800}, {"loss": 1.0729, "grad_norm": 0.5331754088401794, "learning_rate": 0.0002, "epoch": 1.778265642151482, "step": 810}, {"loss": 1.1452, "grad_norm": 0.3853185772895813, "learning_rate": 0.0002, "epoch": 1.8002195389681668, "step": 820}, {"loss": 1.1061, "grad_norm": 0.424062579870224, "learning_rate": 0.0002, "epoch": 1.8221734357848518, "step": 830}, {"loss": 1.1104, "grad_norm": 0.3418445289134979, "learning_rate": 0.0002, "epoch": 1.8441273326015368, "step": 840}, {"loss": 1.0546, "grad_norm": 0.4045565128326416, "learning_rate": 0.0002, "epoch": 1.8660812294182216, "step": 850}, {"loss": 1.1608, "grad_norm": 0.42155781388282776, "learning_rate": 0.0002, "epoch": 1.8880351262349067, "step": 860}, {"loss": 1.0628, "grad_norm": 0.40554770827293396, "learning_rate": 0.0002, "epoch": 1.9099890230515917, "step": 870}, {"loss": 1.1609, "grad_norm": 0.42644748091697693, "learning_rate": 0.0002, "epoch": 1.9319429198682765, "step": 880}, {"loss": 1.1132, "grad_norm": 0.45260652899742126, "learning_rate": 0.0002, "epoch": 1.9538968166849617, "step": 890}, {"loss": 1.048, "grad_norm": 0.4114069938659668, "learning_rate": 0.0002, "epoch": 1.9758507135016465, "step": 900}, {"loss": 1.1941, "grad_norm": 0.375802218914032, "learning_rate": 0.0002, "epoch": 1.9978046103183313, "step": 910}, {"eval_loss": 1.205152153968811, "eval_runtime": 86.8795, "eval_samples_per_second": 4.961, "eval_steps_per_second": 0.622, "epoch": 2.0, "step": 911}, {"loss": 1.0897, "grad_norm": 0.47718703746795654, "learning_rate": 0.0002, "epoch": 2.0197585071350166, "step": 920}, {"loss": 1.0329, "grad_norm": 0.45628082752227783, "learning_rate": 0.0002, "epoch": 2.0417124039517014, "step": 930}, {"loss": 1.0538, "grad_norm": 0.5933247804641724, "learning_rate": 0.0002, "epoch": 2.063666300768386, "step": 940}, {"loss": 1.0152, "grad_norm": 0.5355812907218933, "learning_rate": 0.0002, "epoch": 2.0856201975850714, "step": 950}, {"loss": 1.0726, "grad_norm": 0.5860010385513306, "learning_rate": 0.0002, "epoch": 2.1075740944017562, "step": 960}, {"loss": 1.025, "grad_norm": 0.7471673488616943, "learning_rate": 0.0002, "epoch": 2.129527991218441, "step": 970}, {"loss": 1.0247, "grad_norm": 2.0918211936950684, "learning_rate": 0.0002, "epoch": 2.1514818880351263, "step": 980}, {"loss": 0.8947, "grad_norm": 0.4021058678627014, "learning_rate": 0.0002, "epoch": 2.173435784851811, "step": 990}, {"loss": 0.8875, "grad_norm": 0.564975380897522, "learning_rate": 0.0002, "epoch": 2.1953896816684964, "step": 1000}, {"loss": 1.0264, "grad_norm": 0.46260079741477966, "learning_rate": 0.0002, "epoch": 2.217343578485181, "step": 1010}, {"loss": 0.9265, "grad_norm": 0.4791034460067749, "learning_rate": 0.0002, "epoch": 2.239297475301866, "step": 1020}, {"loss": 0.8869, "grad_norm": 0.5272043943405151, "learning_rate": 0.0002, "epoch": 2.261251372118551, "step": 1030}, {"loss": 1.0007, "grad_norm": 0.5221094489097595, "learning_rate": 0.0002, "epoch": 2.283205268935236, "step": 1040}, {"loss": 0.9472, "grad_norm": 0.558032751083374, "learning_rate": 0.0002, "epoch": 2.305159165751921, "step": 1050}, {"loss": 0.9617, "grad_norm": 0.5905590653419495, "learning_rate": 0.0002, "epoch": 2.327113062568606, "step": 1060}, {"loss": 0.9592, "grad_norm": 0.5308699607849121, "learning_rate": 0.0002, "epoch": 2.349066959385291, "step": 1070}, {"loss": 1.0646, "grad_norm": 0.6375027894973755, "learning_rate": 0.0002, "epoch": 2.3710208562019757, "step": 1080}, {"loss": 1.0354, "grad_norm": 0.7439115643501282, "learning_rate": 0.0002, "epoch": 2.392974753018661, "step": 1090}, {"loss": 1.0212, "grad_norm": 0.41945117712020874, "learning_rate": 0.0002, "epoch": 2.4149286498353457, "step": 1100}, {"loss": 0.9609, "grad_norm": 0.4891968369483948, "learning_rate": 0.0002, "epoch": 2.436882546652031, "step": 1110}, {"loss": 0.9829, "grad_norm": 0.4686794579029083, "learning_rate": 0.0002, "epoch": 2.4588364434687158, "step": 1120}, {"loss": 0.8919, "grad_norm": 0.5204509496688843, "learning_rate": 0.0002, "epoch": 2.4807903402854006, "step": 1130}, {"loss": 0.8983, "grad_norm": 0.6779005527496338, "learning_rate": 0.0002, "epoch": 2.5027442371020854, "step": 1140}, {"loss": 0.9733, "grad_norm": 0.682621955871582, "learning_rate": 0.0002, "epoch": 2.5246981339187706, "step": 1150}, {"loss": 1.051, "grad_norm": 0.5744376182556152, "learning_rate": 0.0002, "epoch": 2.5466520307354554, "step": 1160}, {"loss": 0.8764, "grad_norm": 0.49954667687416077, "learning_rate": 0.0002, "epoch": 2.5686059275521407, "step": 1170}, {"loss": 0.9896, "grad_norm": 0.4761793315410614, "learning_rate": 0.0002, "epoch": 2.5905598243688255, "step": 1180}, {"loss": 0.8593, "grad_norm": 0.548299252986908, "learning_rate": 0.0002, "epoch": 2.6125137211855103, "step": 1190}, {"loss": 1.0017, "grad_norm": 0.5771360993385315, "learning_rate": 0.0002, "epoch": 2.6344676180021955, "step": 1200}, {"loss": 0.9858, "grad_norm": 0.5543120503425598, "learning_rate": 0.0002, "epoch": 2.6564215148188803, "step": 1210}, {"loss": 0.9565, "grad_norm": 0.7564870715141296, "learning_rate": 0.0002, "epoch": 2.6783754116355656, "step": 1220}, {"loss": 0.9753, "grad_norm": 0.8222362399101257, "learning_rate": 0.0002, "epoch": 2.7003293084522504, "step": 1230}, {"loss": 1.0079, "grad_norm": 0.6894469857215881, "learning_rate": 0.0002, "epoch": 2.722283205268935, "step": 1240}, {"loss": 1.0106, "grad_norm": 0.6121546030044556, "learning_rate": 0.0002, "epoch": 2.74423710208562, "step": 1250}, {"loss": 0.9801, "grad_norm": 0.521809995174408, "learning_rate": 0.0002, "epoch": 2.7661909989023052, "step": 1260}, {"loss": 1.0196, "grad_norm": 0.766968309879303, "learning_rate": 0.0002, "epoch": 2.78814489571899, "step": 1270}, {"loss": 0.976, "grad_norm": 0.522331714630127, "learning_rate": 0.0002, "epoch": 2.8100987925356753, "step": 1280}, {"loss": 0.8866, "grad_norm": 0.42923519015312195, "learning_rate": 0.0002, "epoch": 2.83205268935236, "step": 1290}, {"loss": 0.9049, "grad_norm": 0.47810837626457214, "learning_rate": 0.0002, "epoch": 2.854006586169045, "step": 1300}, {"loss": 1.0291, "grad_norm": 1.0958846807479858, "learning_rate": 0.0002, "epoch": 2.8759604829857297, "step": 1310}, {"loss": 0.8724, "grad_norm": 0.4755791127681732, "learning_rate": 0.0002, "epoch": 2.897914379802415, "step": 1320}, {"loss": 0.9317, "grad_norm": 0.5575157403945923, "learning_rate": 0.0002, "epoch": 2.9198682766190998, "step": 1330}, {"loss": 1.0131, "grad_norm": 0.5938076376914978, "learning_rate": 0.0002, "epoch": 2.941822173435785, "step": 1340}, {"loss": 0.9857, "grad_norm": 0.5751763582229614, "learning_rate": 0.0002, "epoch": 2.96377607025247, "step": 1350}, {"loss": 1.0212, "grad_norm": 0.5590175986289978, "learning_rate": 0.0002, "epoch": 2.9857299670691546, "step": 1360}, {"eval_loss": 1.2402944564819336, "eval_runtime": 88.822, "eval_samples_per_second": 4.852, "eval_steps_per_second": 0.608, "epoch": 2.9989023051591657, "step": 1366}, {"loss": 0.844, "grad_norm": 0.463539719581604, "learning_rate": 0.0002, "epoch": 3.00768386388584, "step": 1370}, {"loss": 0.8955, "grad_norm": 0.6667885780334473, "learning_rate": 0.0002, "epoch": 3.0296377607025247, "step": 1380}, {"loss": 0.8765, "grad_norm": 0.5849342942237854, "learning_rate": 0.0002, "epoch": 3.0515916575192095, "step": 1390}, {"loss": 0.7808, "grad_norm": 0.5571770668029785, "learning_rate": 0.0002, "epoch": 3.0735455543358947, "step": 1400}, {"loss": 0.7448, "grad_norm": 0.5761234164237976, "learning_rate": 0.0002, "epoch": 3.0954994511525795, "step": 1410}, {"loss": 0.7854, "grad_norm": 0.7277371883392334, "learning_rate": 0.0002, "epoch": 3.1174533479692643, "step": 1420}, {"loss": 0.817, "grad_norm": 0.5190334320068359, "learning_rate": 0.0002, "epoch": 3.1394072447859496, "step": 1430}, {"loss": 0.7548, "grad_norm": 0.632939875125885, "learning_rate": 0.0002, "epoch": 3.1613611416026344, "step": 1440}, {"loss": 0.8447, "grad_norm": 0.7229540944099426, "learning_rate": 0.0002, "epoch": 3.1833150384193196, "step": 1450}, {"loss": 0.8595, "grad_norm": 0.7584632039070129, "learning_rate": 0.0002, "epoch": 3.2052689352360044, "step": 1460}, {"loss": 0.7456, "grad_norm": 0.6546088457107544, "learning_rate": 0.0002, "epoch": 3.2272228320526892, "step": 1470}, {"loss": 0.8531, "grad_norm": 0.8116684556007385, "learning_rate": 0.0002, "epoch": 3.2491767288693745, "step": 1480}, {"loss": 0.9272, "grad_norm": 0.6206557750701904, "learning_rate": 0.0002, "epoch": 3.2711306256860593, "step": 1490}, {"loss": 0.7972, "grad_norm": 0.5393369197845459, "learning_rate": 0.0002, "epoch": 3.293084522502744, "step": 1500}, {"loss": 0.7614, "grad_norm": 0.7006453275680542, "learning_rate": 0.0002, "epoch": 3.3150384193194293, "step": 1510}, {"loss": 0.7358, "grad_norm": 0.95253986120224, "learning_rate": 0.0002, "epoch": 3.336992316136114, "step": 1520}, {"loss": 0.8131, "grad_norm": 0.8138132095336914, "learning_rate": 0.0002, "epoch": 3.358946212952799, "step": 1530}, {"loss": 0.7738, "grad_norm": 0.7974302172660828, "learning_rate": 0.0002, "epoch": 3.380900109769484, "step": 1540}, {"loss": 0.8161, "grad_norm": 0.6694685220718384, "learning_rate": 0.0002, "epoch": 3.402854006586169, "step": 1550}, {"loss": 0.8503, "grad_norm": 0.908634603023529, "learning_rate": 0.0002, "epoch": 3.4248079034028542, "step": 1560}, {"loss": 0.7609, "grad_norm": 0.5625193119049072, "learning_rate": 0.0002, "epoch": 3.446761800219539, "step": 1570}, {"loss": 0.7658, "grad_norm": 0.779325544834137, "learning_rate": 0.0002, "epoch": 3.468715697036224, "step": 1580}, {"loss": 0.7485, "grad_norm": 0.7133058905601501, "learning_rate": 0.0002, "epoch": 3.4906695938529086, "step": 1590}, {"loss": 0.8847, "grad_norm": 0.6741108298301697, "learning_rate": 0.0002, "epoch": 3.512623490669594, "step": 1600}, {"loss": 0.7838, "grad_norm": 0.696982204914093, "learning_rate": 0.0002, "epoch": 3.5345773874862787, "step": 1610}, {"loss": 0.7195, "grad_norm": 0.7946001291275024, "learning_rate": 0.0002, "epoch": 3.556531284302964, "step": 1620}, {"loss": 0.7772, "grad_norm": 0.6313548684120178, "learning_rate": 0.0002, "epoch": 3.5784851811196488, "step": 1630}, {"loss": 0.8267, "grad_norm": 0.9246852397918701, "learning_rate": 0.0002, "epoch": 3.6004390779363336, "step": 1640}, {"loss": 0.779, "grad_norm": 0.6615420579910278, "learning_rate": 0.0002, "epoch": 3.622392974753019, "step": 1650}, {"loss": 0.883, "grad_norm": 1.5050125122070312, "learning_rate": 0.0002, "epoch": 3.6443468715697036, "step": 1660}, {"loss": 0.7763, "grad_norm": 0.5023762583732605, "learning_rate": 0.0002, "epoch": 3.666300768386389, "step": 1670}, {"loss": 0.8173, "grad_norm": 0.6289586424827576, "learning_rate": 0.0002, "epoch": 3.6882546652030737, "step": 1680}, {"loss": 0.9028, "grad_norm": 1.050397515296936, "learning_rate": 0.0002, "epoch": 3.7102085620197585, "step": 1690}, {"loss": 0.7747, "grad_norm": 0.6785626411437988, "learning_rate": 0.0002, "epoch": 3.7321624588364433, "step": 1700}, {"loss": 0.9215, "grad_norm": 0.7565035223960876, "learning_rate": 0.0002, "epoch": 3.7541163556531285, "step": 1710}, {"loss": 0.7913, "grad_norm": 0.7775155901908875, "learning_rate": 0.0002, "epoch": 3.7760702524698133, "step": 1720}, {"loss": 0.8081, "grad_norm": 0.765260636806488, "learning_rate": 0.0002, "epoch": 3.7980241492864986, "step": 1730}, {"loss": 0.9231, "grad_norm": 0.7982407808303833, "learning_rate": 0.0002, "epoch": 3.8199780461031834, "step": 1740}, {"loss": 0.7755, "grad_norm": 0.7431730628013611, "learning_rate": 0.0002, "epoch": 3.841931942919868, "step": 1750}, {"loss": 0.9236, "grad_norm": 0.9758927226066589, "learning_rate": 0.0002, "epoch": 3.863885839736553, "step": 1760}, {"loss": 0.9118, "grad_norm": 0.8014697432518005, "learning_rate": 0.0002, "epoch": 3.885839736553238, "step": 1770}, {"loss": 0.7503, "grad_norm": 0.7212756276130676, "learning_rate": 0.0002, "epoch": 3.907793633369923, "step": 1780}, {"loss": 0.7978, "grad_norm": 0.584318220615387, "learning_rate": 0.0002, "epoch": 3.9297475301866083, "step": 1790}, {"loss": 0.7894, "grad_norm": 0.7612535953521729, "learning_rate": 0.0002, "epoch": 3.951701427003293, "step": 1800}, {"loss": 0.8589, "grad_norm": 0.735103189945221, "learning_rate": 0.0002, "epoch": 3.973655323819978, "step": 1810}, {"loss": 0.8192, "grad_norm": 0.9074980020523071, "learning_rate": 0.0002, "epoch": 3.995609220636663, "step": 1820}, {"eval_loss": 1.279890537261963, "eval_runtime": 88.8969, "eval_samples_per_second": 4.848, "eval_steps_per_second": 0.607, "epoch": 4.0, "step": 1822}, {"loss": 0.7312, "grad_norm": 0.9290254712104797, "learning_rate": 0.0002, "epoch": 4.017563117453348, "step": 1830}, {"loss": 0.6896, "grad_norm": 0.723889946937561, "learning_rate": 0.0002, "epoch": 4.039517014270033, "step": 1840}, {"loss": 0.632, "grad_norm": 0.5906972289085388, "learning_rate": 0.0002, "epoch": 4.061470911086718, "step": 1850}, {"loss": 0.6594, "grad_norm": 0.8078910708427429, "learning_rate": 0.0002, "epoch": 4.083424807903403, "step": 1860}, {"loss": 0.6242, "grad_norm": 1.0101137161254883, "learning_rate": 0.0002, "epoch": 4.105378704720088, "step": 1870}, {"loss": 0.7259, "grad_norm": 0.8710281848907471, "learning_rate": 0.0002, "epoch": 4.127332601536772, "step": 1880}, {"loss": 0.6993, "grad_norm": 0.9604734778404236, "learning_rate": 0.0002, "epoch": 4.149286498353458, "step": 1890}, {"loss": 0.6706, "grad_norm": 0.9829702377319336, "learning_rate": 0.0002, "epoch": 4.171240395170143, "step": 1900}, {"loss": 0.7013, "grad_norm": 0.6572765707969666, "learning_rate": 0.0002, "epoch": 4.193194291986828, "step": 1910}, {"loss": 0.5539, "grad_norm": 0.8459188938140869, "learning_rate": 0.0002, "epoch": 4.2151481888035125, "step": 1920}, {"loss": 0.6235, "grad_norm": 0.8321021795272827, "learning_rate": 0.0002, "epoch": 4.237102085620197, "step": 1930}, {"loss": 0.6442, "grad_norm": 0.8611727356910706, "learning_rate": 0.0002, "epoch": 4.259055982436882, "step": 1940}, {"loss": 0.6852, "grad_norm": 0.8490208387374878, "learning_rate": 0.0002, "epoch": 4.281009879253568, "step": 1950}, {"loss": 0.6175, "grad_norm": 0.9628722667694092, "learning_rate": 0.0002, "epoch": 4.302963776070253, "step": 1960}, {"loss": 0.5982, "grad_norm": 0.9632807374000549, "learning_rate": 0.0002, "epoch": 4.324917672886937, "step": 1970}, {"loss": 0.6138, "grad_norm": 0.7023298740386963, "learning_rate": 0.0002, "epoch": 4.346871569703622, "step": 1980}, {"loss": 0.6012, "grad_norm": 0.7912909388542175, "learning_rate": 0.0002, "epoch": 4.368825466520307, "step": 1990}, {"loss": 0.6767, "grad_norm": 1.1463429927825928, "learning_rate": 0.0002, "epoch": 4.390779363336993, "step": 2000}, {"loss": 0.6607, "grad_norm": 1.1780626773834229, "learning_rate": 0.0002, "epoch": 4.4127332601536775, "step": 2010}, {"loss": 0.6746, "grad_norm": 0.9349206686019897, "learning_rate": 0.0002, "epoch": 4.434687156970362, "step": 2020}, {"loss": 0.7087, "grad_norm": 0.7816639542579651, "learning_rate": 0.0002, "epoch": 4.456641053787047, "step": 2030}, {"loss": 0.6222, "grad_norm": 0.7005311250686646, "learning_rate": 0.0002, "epoch": 4.478594950603732, "step": 2040}, {"loss": 0.6608, "grad_norm": 0.7746558785438538, "learning_rate": 0.0002, "epoch": 4.500548847420417, "step": 2050}, {"loss": 0.6305, "grad_norm": 0.8261151313781738, "learning_rate": 0.0002, "epoch": 4.522502744237102, "step": 2060}, {"loss": 0.6502, "grad_norm": 1.0917805433273315, "learning_rate": 0.0002, "epoch": 4.544456641053787, "step": 2070}, {"loss": 0.6798, "grad_norm": 1.1570647954940796, "learning_rate": 0.0002, "epoch": 4.566410537870472, "step": 2080}, {"loss": 0.6296, "grad_norm": 0.9936433434486389, "learning_rate": 0.0002, "epoch": 4.588364434687157, "step": 2090}, {"loss": 0.5936, "grad_norm": 0.8574427366256714, "learning_rate": 0.0002, "epoch": 4.610318331503842, "step": 2100}, {"loss": 0.6529, "grad_norm": 0.7630168795585632, "learning_rate": 0.0002, "epoch": 4.632272228320527, "step": 2110}, {"loss": 0.5935, "grad_norm": 0.8146462440490723, "learning_rate": 0.0002, "epoch": 4.654226125137212, "step": 2120}, {"loss": 0.7102, "grad_norm": 0.7090407609939575, "learning_rate": 0.0002, "epoch": 4.676180021953897, "step": 2130}, {"loss": 0.6575, "grad_norm": 0.8278160095214844, "learning_rate": 0.0002, "epoch": 4.698133918770582, "step": 2140}, {"loss": 0.664, "grad_norm": 0.9415683746337891, "learning_rate": 0.0002, "epoch": 4.7200878155872665, "step": 2150}, {"loss": 0.7283, "grad_norm": 1.0056205987930298, "learning_rate": 0.0002, "epoch": 4.742041712403951, "step": 2160}, {"loss": 0.6845, "grad_norm": 0.768304705619812, "learning_rate": 0.0002, "epoch": 4.763995609220637, "step": 2170}, {"loss": 0.6922, "grad_norm": 1.0604112148284912, "learning_rate": 0.0002, "epoch": 4.785949506037322, "step": 2180}, {"loss": 0.7092, "grad_norm": 1.132864236831665, "learning_rate": 0.0002, "epoch": 4.807903402854007, "step": 2190}, {"loss": 0.6936, "grad_norm": 0.7543689608573914, "learning_rate": 0.0002, "epoch": 4.829857299670691, "step": 2200}, {"loss": 0.6921, "grad_norm": 0.8047362565994263, "learning_rate": 0.0002, "epoch": 4.851811196487376, "step": 2210}, {"loss": 0.6753, "grad_norm": 1.135778546333313, "learning_rate": 0.0002, "epoch": 4.873765093304062, "step": 2220}, {"loss": 0.6443, "grad_norm": 0.9068503379821777, "learning_rate": 0.0002, "epoch": 4.895718990120747, "step": 2230}, {"loss": 0.7419, "grad_norm": 1.822325587272644, "learning_rate": 0.0002, "epoch": 4.9176728869374315, "step": 2240}, {"loss": 0.6436, "grad_norm": 1.1124998331069946, "learning_rate": 0.0002, "epoch": 4.939626783754116, "step": 2250}, {"loss": 0.7423, "grad_norm": 0.818484365940094, "learning_rate": 0.0002, "epoch": 4.961580680570801, "step": 2260}, {"loss": 0.6872, "grad_norm": 1.0057194232940674, "learning_rate": 0.0002, "epoch": 4.983534577387486, "step": 2270}]} +{"epoch": 6.0, "step": 2733, "epoch_duration": 1568.0893988609314, "total_accumulated_duration": 9308.648589372635, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7568.4541015625}, "peak_memory_usage": {"GPU_0": 13792.75439453125}, "avg_memory_reserved": {"GPU_0": 17416.0}, "peak_memory_reserved": {"GPU_0": 17416.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 1.9887, "grad_norm": 0.6144012212753296, "learning_rate": 0.0002, "epoch": 0.021953896816684963, "step": 10}, {"loss": 1.6882, "grad_norm": 0.5587220788002014, "learning_rate": 0.0002, "epoch": 0.043907793633369926, "step": 20}, {"loss": 1.399, "grad_norm": 0.43262454867362976, "learning_rate": 0.0002, "epoch": 0.06586169045005488, "step": 30}, {"loss": 1.4675, "grad_norm": 0.4783053994178772, "learning_rate": 0.0002, "epoch": 0.08781558726673985, "step": 40}, {"loss": 1.1771, "grad_norm": 0.44338956475257874, "learning_rate": 0.0002, "epoch": 0.10976948408342481, "step": 50}, {"loss": 1.3706, "grad_norm": 0.7255092263221741, "learning_rate": 0.0002, "epoch": 0.13172338090010977, "step": 60}, {"loss": 1.2601, "grad_norm": 0.46073833107948303, "learning_rate": 0.0002, "epoch": 0.15367727771679474, "step": 70}, {"loss": 1.3049, "grad_norm": 0.6698123216629028, "learning_rate": 0.0002, "epoch": 0.1756311745334797, "step": 80}, {"loss": 1.2975, "grad_norm": 0.4190150201320648, "learning_rate": 0.0002, "epoch": 0.19758507135016465, "step": 90}, {"loss": 1.2797, "grad_norm": 0.4110015034675598, "learning_rate": 0.0002, "epoch": 0.21953896816684962, "step": 100}, {"loss": 1.2896, "grad_norm": 0.33374306559562683, "learning_rate": 0.0002, "epoch": 0.2414928649835346, "step": 110}, {"loss": 1.2268, "grad_norm": 0.3061307370662689, "learning_rate": 0.0002, "epoch": 0.26344676180021953, "step": 120}, {"loss": 1.376, "grad_norm": 0.4386885166168213, "learning_rate": 0.0002, "epoch": 0.2854006586169045, "step": 130}, {"loss": 1.1814, "grad_norm": 0.40116462111473083, "learning_rate": 0.0002, "epoch": 0.30735455543358947, "step": 140}, {"loss": 1.2592, "grad_norm": 0.5887949466705322, "learning_rate": 0.0002, "epoch": 0.32930845225027444, "step": 150}, {"loss": 1.2372, "grad_norm": 0.3401573896408081, "learning_rate": 0.0002, "epoch": 0.3512623490669594, "step": 160}, {"loss": 1.1901, "grad_norm": 0.3288364112377167, "learning_rate": 0.0002, "epoch": 0.3732162458836443, "step": 170}, {"loss": 1.2335, "grad_norm": 0.4853297472000122, "learning_rate": 0.0002, "epoch": 0.3951701427003293, "step": 180}, {"loss": 1.227, "grad_norm": 2.6253697872161865, "learning_rate": 0.0002, "epoch": 0.41712403951701427, "step": 190}, {"loss": 1.2673, "grad_norm": 0.5598543286323547, "learning_rate": 0.0002, "epoch": 0.43907793633369924, "step": 200}, {"loss": 1.3459, "grad_norm": 0.4046548902988434, "learning_rate": 0.0002, "epoch": 0.4610318331503842, "step": 210}, {"loss": 1.265, "grad_norm": 0.3686952590942383, "learning_rate": 0.0002, "epoch": 0.4829857299670692, "step": 220}, {"loss": 1.1364, "grad_norm": 0.42458799481391907, "learning_rate": 0.0002, "epoch": 0.5049396267837541, "step": 230}, {"loss": 1.2094, "grad_norm": 0.5839895009994507, "learning_rate": 0.0002, "epoch": 0.5268935236004391, "step": 240}, {"loss": 1.2073, "grad_norm": 0.408288836479187, "learning_rate": 0.0002, "epoch": 0.5488474204171241, "step": 250}, {"loss": 1.3121, "grad_norm": 0.45887550711631775, "learning_rate": 0.0002, "epoch": 0.570801317233809, "step": 260}, {"loss": 1.2257, "grad_norm": 0.5440235733985901, "learning_rate": 0.0002, "epoch": 0.5927552140504939, "step": 270}, {"loss": 1.1003, "grad_norm": 0.3725181519985199, "learning_rate": 0.0002, "epoch": 0.6147091108671789, "step": 280}, {"loss": 1.1538, "grad_norm": 0.4309018850326538, "learning_rate": 0.0002, "epoch": 0.6366630076838639, "step": 290}, {"loss": 1.2097, "grad_norm": 0.31488674879074097, "learning_rate": 0.0002, "epoch": 0.6586169045005489, "step": 300}, {"loss": 1.1689, "grad_norm": 0.34194841980934143, "learning_rate": 0.0002, "epoch": 0.6805708013172338, "step": 310}, {"loss": 1.2579, "grad_norm": 0.3407684862613678, "learning_rate": 0.0002, "epoch": 0.7025246981339188, "step": 320}, {"loss": 1.1144, "grad_norm": 0.2985728085041046, "learning_rate": 0.0002, "epoch": 0.7244785949506037, "step": 330}, {"loss": 1.2056, "grad_norm": 0.42316871881484985, "learning_rate": 0.0002, "epoch": 0.7464324917672887, "step": 340}, {"loss": 1.1753, "grad_norm": 0.3124258816242218, "learning_rate": 0.0002, "epoch": 0.7683863885839737, "step": 350}, {"loss": 1.2547, "grad_norm": 0.7727567553520203, "learning_rate": 0.0002, "epoch": 0.7903402854006586, "step": 360}, {"loss": 1.124, "grad_norm": 0.363765686750412, "learning_rate": 0.0002, "epoch": 0.8122941822173436, "step": 370}, {"loss": 1.1302, "grad_norm": 0.35582536458969116, "learning_rate": 0.0002, "epoch": 0.8342480790340285, "step": 380}, {"loss": 1.1787, "grad_norm": 0.31982025504112244, "learning_rate": 0.0002, "epoch": 0.8562019758507134, "step": 390}, {"loss": 1.2056, "grad_norm": 0.34978964924812317, "learning_rate": 0.0002, "epoch": 0.8781558726673985, "step": 400}, {"loss": 1.3577, "grad_norm": 0.8346716165542603, "learning_rate": 0.0002, "epoch": 0.9001097694840834, "step": 410}, {"loss": 1.1029, "grad_norm": 0.31984028220176697, "learning_rate": 0.0002, "epoch": 0.9220636663007684, "step": 420}, {"loss": 1.0967, "grad_norm": 0.32078951597213745, "learning_rate": 0.0002, "epoch": 0.9440175631174533, "step": 430}, {"loss": 1.0936, "grad_norm": 0.3417500853538513, "learning_rate": 0.0002, "epoch": 0.9659714599341384, "step": 440}, {"loss": 1.3412, "grad_norm": 0.42359477281570435, "learning_rate": 0.0002, "epoch": 0.9879253567508233, "step": 450}, {"eval_loss": 1.2201528549194336, "eval_runtime": 87.152, "eval_samples_per_second": 4.945, "eval_steps_per_second": 0.62, "epoch": 0.9989023051591658, "step": 455}, {"loss": 1.1909, "grad_norm": 0.37914523482322693, "learning_rate": 0.0002, "epoch": 1.0098792535675083, "step": 460}, {"loss": 1.0948, "grad_norm": 0.43655872344970703, "learning_rate": 0.0002, "epoch": 1.031833150384193, "step": 470}, {"loss": 1.0873, "grad_norm": 0.3673796057701111, "learning_rate": 0.0002, "epoch": 1.0537870472008781, "step": 480}, {"loss": 1.0483, "grad_norm": 0.37673917412757874, "learning_rate": 0.0002, "epoch": 1.0757409440175631, "step": 490}, {"loss": 1.0799, "grad_norm": 0.2893829345703125, "learning_rate": 0.0002, "epoch": 1.0976948408342482, "step": 500}, {"loss": 1.1847, "grad_norm": 0.5551970601081848, "learning_rate": 0.0002, "epoch": 1.119648737650933, "step": 510}, {"loss": 1.0885, "grad_norm": 0.442104309797287, "learning_rate": 0.0002, "epoch": 1.141602634467618, "step": 520}, {"loss": 1.1766, "grad_norm": 0.4035094976425171, "learning_rate": 0.0002, "epoch": 1.163556531284303, "step": 530}, {"loss": 1.0282, "grad_norm": 0.47009000182151794, "learning_rate": 0.0002, "epoch": 1.1855104281009878, "step": 540}, {"loss": 1.2625, "grad_norm": 0.4118749797344208, "learning_rate": 0.0002, "epoch": 1.2074643249176729, "step": 550}, {"loss": 1.0988, "grad_norm": 0.35173165798187256, "learning_rate": 0.0002, "epoch": 1.2294182217343579, "step": 560}, {"loss": 1.0498, "grad_norm": 0.7024672031402588, "learning_rate": 0.0002, "epoch": 1.2513721185510427, "step": 570}, {"loss": 1.1339, "grad_norm": 0.42657527327537537, "learning_rate": 0.0002, "epoch": 1.2733260153677277, "step": 580}, {"loss": 1.0545, "grad_norm": 0.3815029561519623, "learning_rate": 0.0002, "epoch": 1.2952799121844127, "step": 590}, {"loss": 1.1528, "grad_norm": 0.7031055688858032, "learning_rate": 0.0002, "epoch": 1.3172338090010978, "step": 600}, {"loss": 1.1347, "grad_norm": 0.393911212682724, "learning_rate": 0.0002, "epoch": 1.3391877058177828, "step": 610}, {"loss": 1.1901, "grad_norm": 0.5077702403068542, "learning_rate": 0.0002, "epoch": 1.3611416026344676, "step": 620}, {"loss": 1.1251, "grad_norm": 2.330033302307129, "learning_rate": 0.0002, "epoch": 1.3830954994511526, "step": 630}, {"loss": 1.0477, "grad_norm": 0.35322949290275574, "learning_rate": 0.0002, "epoch": 1.4050493962678376, "step": 640}, {"loss": 1.14, "grad_norm": 0.44401052594184875, "learning_rate": 0.0002, "epoch": 1.4270032930845225, "step": 650}, {"loss": 1.0318, "grad_norm": 0.35945481061935425, "learning_rate": 0.0002, "epoch": 1.4489571899012075, "step": 660}, {"loss": 1.1988, "grad_norm": 0.3058856129646301, "learning_rate": 0.0002, "epoch": 1.4709110867178925, "step": 670}, {"loss": 1.1545, "grad_norm": 0.7067602872848511, "learning_rate": 0.0002, "epoch": 1.4928649835345773, "step": 680}, {"loss": 1.0925, "grad_norm": 0.4219357371330261, "learning_rate": 0.0002, "epoch": 1.5148188803512623, "step": 690}, {"loss": 1.1622, "grad_norm": 0.5970841646194458, "learning_rate": 0.0002, "epoch": 1.5367727771679474, "step": 700}, {"loss": 1.0803, "grad_norm": 0.4381934404373169, "learning_rate": 0.0002, "epoch": 1.5587266739846322, "step": 710}, {"loss": 1.0961, "grad_norm": 0.4101450443267822, "learning_rate": 0.0002, "epoch": 1.5806805708013172, "step": 720}, {"loss": 1.0474, "grad_norm": 0.3657490015029907, "learning_rate": 0.0002, "epoch": 1.6026344676180022, "step": 730}, {"loss": 1.0936, "grad_norm": 0.36240628361701965, "learning_rate": 0.0002, "epoch": 1.624588364434687, "step": 740}, {"loss": 1.0489, "grad_norm": 0.4103568494319916, "learning_rate": 0.0002, "epoch": 1.6465422612513723, "step": 750}, {"loss": 1.0919, "grad_norm": 0.3138505816459656, "learning_rate": 0.0002, "epoch": 1.668496158068057, "step": 760}, {"loss": 1.2308, "grad_norm": 0.41215717792510986, "learning_rate": 0.0002, "epoch": 1.690450054884742, "step": 770}, {"loss": 1.1659, "grad_norm": 0.4589519202709198, "learning_rate": 0.0002, "epoch": 1.7124039517014271, "step": 780}, {"loss": 1.0913, "grad_norm": 0.4049508571624756, "learning_rate": 0.0002, "epoch": 1.734357848518112, "step": 790}, {"loss": 1.1329, "grad_norm": 0.48557212948799133, "learning_rate": 0.0002, "epoch": 1.756311745334797, "step": 800}, {"loss": 1.0729, "grad_norm": 0.5331754088401794, "learning_rate": 0.0002, "epoch": 1.778265642151482, "step": 810}, {"loss": 1.1452, "grad_norm": 0.3853185772895813, "learning_rate": 0.0002, "epoch": 1.8002195389681668, "step": 820}, {"loss": 1.1061, "grad_norm": 0.424062579870224, "learning_rate": 0.0002, "epoch": 1.8221734357848518, "step": 830}, {"loss": 1.1104, "grad_norm": 0.3418445289134979, "learning_rate": 0.0002, "epoch": 1.8441273326015368, "step": 840}, {"loss": 1.0546, "grad_norm": 0.4045565128326416, "learning_rate": 0.0002, "epoch": 1.8660812294182216, "step": 850}, {"loss": 1.1608, "grad_norm": 0.42155781388282776, "learning_rate": 0.0002, "epoch": 1.8880351262349067, "step": 860}, {"loss": 1.0628, "grad_norm": 0.40554770827293396, "learning_rate": 0.0002, "epoch": 1.9099890230515917, "step": 870}, {"loss": 1.1609, "grad_norm": 0.42644748091697693, "learning_rate": 0.0002, "epoch": 1.9319429198682765, "step": 880}, {"loss": 1.1132, "grad_norm": 0.45260652899742126, "learning_rate": 0.0002, "epoch": 1.9538968166849617, "step": 890}, {"loss": 1.048, "grad_norm": 0.4114069938659668, "learning_rate": 0.0002, "epoch": 1.9758507135016465, "step": 900}, {"loss": 1.1941, "grad_norm": 0.375802218914032, "learning_rate": 0.0002, "epoch": 1.9978046103183313, "step": 910}, {"eval_loss": 1.205152153968811, "eval_runtime": 86.8795, "eval_samples_per_second": 4.961, "eval_steps_per_second": 0.622, "epoch": 2.0, "step": 911}, {"loss": 1.0897, "grad_norm": 0.47718703746795654, "learning_rate": 0.0002, "epoch": 2.0197585071350166, "step": 920}, {"loss": 1.0329, "grad_norm": 0.45628082752227783, "learning_rate": 0.0002, "epoch": 2.0417124039517014, "step": 930}, {"loss": 1.0538, "grad_norm": 0.5933247804641724, "learning_rate": 0.0002, "epoch": 2.063666300768386, "step": 940}, {"loss": 1.0152, "grad_norm": 0.5355812907218933, "learning_rate": 0.0002, "epoch": 2.0856201975850714, "step": 950}, {"loss": 1.0726, "grad_norm": 0.5860010385513306, "learning_rate": 0.0002, "epoch": 2.1075740944017562, "step": 960}, {"loss": 1.025, "grad_norm": 0.7471673488616943, "learning_rate": 0.0002, "epoch": 2.129527991218441, "step": 970}, {"loss": 1.0247, "grad_norm": 2.0918211936950684, "learning_rate": 0.0002, "epoch": 2.1514818880351263, "step": 980}, {"loss": 0.8947, "grad_norm": 0.4021058678627014, "learning_rate": 0.0002, "epoch": 2.173435784851811, "step": 990}, {"loss": 0.8875, "grad_norm": 0.564975380897522, "learning_rate": 0.0002, "epoch": 2.1953896816684964, "step": 1000}, {"loss": 1.0264, "grad_norm": 0.46260079741477966, "learning_rate": 0.0002, "epoch": 2.217343578485181, "step": 1010}, {"loss": 0.9265, "grad_norm": 0.4791034460067749, "learning_rate": 0.0002, "epoch": 2.239297475301866, "step": 1020}, {"loss": 0.8869, "grad_norm": 0.5272043943405151, "learning_rate": 0.0002, "epoch": 2.261251372118551, "step": 1030}, {"loss": 1.0007, "grad_norm": 0.5221094489097595, "learning_rate": 0.0002, "epoch": 2.283205268935236, "step": 1040}, {"loss": 0.9472, "grad_norm": 0.558032751083374, "learning_rate": 0.0002, "epoch": 2.305159165751921, "step": 1050}, {"loss": 0.9617, "grad_norm": 0.5905590653419495, "learning_rate": 0.0002, "epoch": 2.327113062568606, "step": 1060}, {"loss": 0.9592, "grad_norm": 0.5308699607849121, "learning_rate": 0.0002, "epoch": 2.349066959385291, "step": 1070}, {"loss": 1.0646, "grad_norm": 0.6375027894973755, "learning_rate": 0.0002, "epoch": 2.3710208562019757, "step": 1080}, {"loss": 1.0354, "grad_norm": 0.7439115643501282, "learning_rate": 0.0002, "epoch": 2.392974753018661, "step": 1090}, {"loss": 1.0212, "grad_norm": 0.41945117712020874, "learning_rate": 0.0002, "epoch": 2.4149286498353457, "step": 1100}, {"loss": 0.9609, "grad_norm": 0.4891968369483948, "learning_rate": 0.0002, "epoch": 2.436882546652031, "step": 1110}, {"loss": 0.9829, "grad_norm": 0.4686794579029083, "learning_rate": 0.0002, "epoch": 2.4588364434687158, "step": 1120}, {"loss": 0.8919, "grad_norm": 0.5204509496688843, "learning_rate": 0.0002, "epoch": 2.4807903402854006, "step": 1130}, {"loss": 0.8983, "grad_norm": 0.6779005527496338, "learning_rate": 0.0002, "epoch": 2.5027442371020854, "step": 1140}, {"loss": 0.9733, "grad_norm": 0.682621955871582, "learning_rate": 0.0002, "epoch": 2.5246981339187706, "step": 1150}, {"loss": 1.051, "grad_norm": 0.5744376182556152, "learning_rate": 0.0002, "epoch": 2.5466520307354554, "step": 1160}, {"loss": 0.8764, "grad_norm": 0.49954667687416077, "learning_rate": 0.0002, "epoch": 2.5686059275521407, "step": 1170}, {"loss": 0.9896, "grad_norm": 0.4761793315410614, "learning_rate": 0.0002, "epoch": 2.5905598243688255, "step": 1180}, {"loss": 0.8593, "grad_norm": 0.548299252986908, "learning_rate": 0.0002, "epoch": 2.6125137211855103, "step": 1190}, {"loss": 1.0017, "grad_norm": 0.5771360993385315, "learning_rate": 0.0002, "epoch": 2.6344676180021955, "step": 1200}, {"loss": 0.9858, "grad_norm": 0.5543120503425598, "learning_rate": 0.0002, "epoch": 2.6564215148188803, "step": 1210}, {"loss": 0.9565, "grad_norm": 0.7564870715141296, "learning_rate": 0.0002, "epoch": 2.6783754116355656, "step": 1220}, {"loss": 0.9753, "grad_norm": 0.8222362399101257, "learning_rate": 0.0002, "epoch": 2.7003293084522504, "step": 1230}, {"loss": 1.0079, "grad_norm": 0.6894469857215881, "learning_rate": 0.0002, "epoch": 2.722283205268935, "step": 1240}, {"loss": 1.0106, "grad_norm": 0.6121546030044556, "learning_rate": 0.0002, "epoch": 2.74423710208562, "step": 1250}, {"loss": 0.9801, "grad_norm": 0.521809995174408, "learning_rate": 0.0002, "epoch": 2.7661909989023052, "step": 1260}, {"loss": 1.0196, "grad_norm": 0.766968309879303, "learning_rate": 0.0002, "epoch": 2.78814489571899, "step": 1270}, {"loss": 0.976, "grad_norm": 0.522331714630127, "learning_rate": 0.0002, "epoch": 2.8100987925356753, "step": 1280}, {"loss": 0.8866, "grad_norm": 0.42923519015312195, "learning_rate": 0.0002, "epoch": 2.83205268935236, "step": 1290}, {"loss": 0.9049, "grad_norm": 0.47810837626457214, "learning_rate": 0.0002, "epoch": 2.854006586169045, "step": 1300}, {"loss": 1.0291, "grad_norm": 1.0958846807479858, "learning_rate": 0.0002, "epoch": 2.8759604829857297, "step": 1310}, {"loss": 0.8724, "grad_norm": 0.4755791127681732, "learning_rate": 0.0002, "epoch": 2.897914379802415, "step": 1320}, {"loss": 0.9317, "grad_norm": 0.5575157403945923, "learning_rate": 0.0002, "epoch": 2.9198682766190998, "step": 1330}, {"loss": 1.0131, "grad_norm": 0.5938076376914978, "learning_rate": 0.0002, "epoch": 2.941822173435785, "step": 1340}, {"loss": 0.9857, "grad_norm": 0.5751763582229614, "learning_rate": 0.0002, "epoch": 2.96377607025247, "step": 1350}, {"loss": 1.0212, "grad_norm": 0.5590175986289978, "learning_rate": 0.0002, "epoch": 2.9857299670691546, "step": 1360}, {"eval_loss": 1.2402944564819336, "eval_runtime": 88.822, "eval_samples_per_second": 4.852, "eval_steps_per_second": 0.608, "epoch": 2.9989023051591657, "step": 1366}, {"loss": 0.844, "grad_norm": 0.463539719581604, "learning_rate": 0.0002, "epoch": 3.00768386388584, "step": 1370}, {"loss": 0.8955, "grad_norm": 0.6667885780334473, "learning_rate": 0.0002, "epoch": 3.0296377607025247, "step": 1380}, {"loss": 0.8765, "grad_norm": 0.5849342942237854, "learning_rate": 0.0002, "epoch": 3.0515916575192095, "step": 1390}, {"loss": 0.7808, "grad_norm": 0.5571770668029785, "learning_rate": 0.0002, "epoch": 3.0735455543358947, "step": 1400}, {"loss": 0.7448, "grad_norm": 0.5761234164237976, "learning_rate": 0.0002, "epoch": 3.0954994511525795, "step": 1410}, {"loss": 0.7854, "grad_norm": 0.7277371883392334, "learning_rate": 0.0002, "epoch": 3.1174533479692643, "step": 1420}, {"loss": 0.817, "grad_norm": 0.5190334320068359, "learning_rate": 0.0002, "epoch": 3.1394072447859496, "step": 1430}, {"loss": 0.7548, "grad_norm": 0.632939875125885, "learning_rate": 0.0002, "epoch": 3.1613611416026344, "step": 1440}, {"loss": 0.8447, "grad_norm": 0.7229540944099426, "learning_rate": 0.0002, "epoch": 3.1833150384193196, "step": 1450}, {"loss": 0.8595, "grad_norm": 0.7584632039070129, "learning_rate": 0.0002, "epoch": 3.2052689352360044, "step": 1460}, {"loss": 0.7456, "grad_norm": 0.6546088457107544, "learning_rate": 0.0002, "epoch": 3.2272228320526892, "step": 1470}, {"loss": 0.8531, "grad_norm": 0.8116684556007385, "learning_rate": 0.0002, "epoch": 3.2491767288693745, "step": 1480}, {"loss": 0.9272, "grad_norm": 0.6206557750701904, "learning_rate": 0.0002, "epoch": 3.2711306256860593, "step": 1490}, {"loss": 0.7972, "grad_norm": 0.5393369197845459, "learning_rate": 0.0002, "epoch": 3.293084522502744, "step": 1500}, {"loss": 0.7614, "grad_norm": 0.7006453275680542, "learning_rate": 0.0002, "epoch": 3.3150384193194293, "step": 1510}, {"loss": 0.7358, "grad_norm": 0.95253986120224, "learning_rate": 0.0002, "epoch": 3.336992316136114, "step": 1520}, {"loss": 0.8131, "grad_norm": 0.8138132095336914, "learning_rate": 0.0002, "epoch": 3.358946212952799, "step": 1530}, {"loss": 0.7738, "grad_norm": 0.7974302172660828, "learning_rate": 0.0002, "epoch": 3.380900109769484, "step": 1540}, {"loss": 0.8161, "grad_norm": 0.6694685220718384, "learning_rate": 0.0002, "epoch": 3.402854006586169, "step": 1550}, {"loss": 0.8503, "grad_norm": 0.908634603023529, "learning_rate": 0.0002, "epoch": 3.4248079034028542, "step": 1560}, {"loss": 0.7609, "grad_norm": 0.5625193119049072, "learning_rate": 0.0002, "epoch": 3.446761800219539, "step": 1570}, {"loss": 0.7658, "grad_norm": 0.779325544834137, "learning_rate": 0.0002, "epoch": 3.468715697036224, "step": 1580}, {"loss": 0.7485, "grad_norm": 0.7133058905601501, "learning_rate": 0.0002, "epoch": 3.4906695938529086, "step": 1590}, {"loss": 0.8847, "grad_norm": 0.6741108298301697, "learning_rate": 0.0002, "epoch": 3.512623490669594, "step": 1600}, {"loss": 0.7838, "grad_norm": 0.696982204914093, "learning_rate": 0.0002, "epoch": 3.5345773874862787, "step": 1610}, {"loss": 0.7195, "grad_norm": 0.7946001291275024, "learning_rate": 0.0002, "epoch": 3.556531284302964, "step": 1620}, {"loss": 0.7772, "grad_norm": 0.6313548684120178, "learning_rate": 0.0002, "epoch": 3.5784851811196488, "step": 1630}, {"loss": 0.8267, "grad_norm": 0.9246852397918701, "learning_rate": 0.0002, "epoch": 3.6004390779363336, "step": 1640}, {"loss": 0.779, "grad_norm": 0.6615420579910278, "learning_rate": 0.0002, "epoch": 3.622392974753019, "step": 1650}, {"loss": 0.883, "grad_norm": 1.5050125122070312, "learning_rate": 0.0002, "epoch": 3.6443468715697036, "step": 1660}, {"loss": 0.7763, "grad_norm": 0.5023762583732605, "learning_rate": 0.0002, "epoch": 3.666300768386389, "step": 1670}, {"loss": 0.8173, "grad_norm": 0.6289586424827576, "learning_rate": 0.0002, "epoch": 3.6882546652030737, "step": 1680}, {"loss": 0.9028, "grad_norm": 1.050397515296936, "learning_rate": 0.0002, "epoch": 3.7102085620197585, "step": 1690}, {"loss": 0.7747, "grad_norm": 0.6785626411437988, "learning_rate": 0.0002, "epoch": 3.7321624588364433, "step": 1700}, {"loss": 0.9215, "grad_norm": 0.7565035223960876, "learning_rate": 0.0002, "epoch": 3.7541163556531285, "step": 1710}, {"loss": 0.7913, "grad_norm": 0.7775155901908875, "learning_rate": 0.0002, "epoch": 3.7760702524698133, "step": 1720}, {"loss": 0.8081, "grad_norm": 0.765260636806488, "learning_rate": 0.0002, "epoch": 3.7980241492864986, "step": 1730}, {"loss": 0.9231, "grad_norm": 0.7982407808303833, "learning_rate": 0.0002, "epoch": 3.8199780461031834, "step": 1740}, {"loss": 0.7755, "grad_norm": 0.7431730628013611, "learning_rate": 0.0002, "epoch": 3.841931942919868, "step": 1750}, {"loss": 0.9236, "grad_norm": 0.9758927226066589, "learning_rate": 0.0002, "epoch": 3.863885839736553, "step": 1760}, {"loss": 0.9118, "grad_norm": 0.8014697432518005, "learning_rate": 0.0002, "epoch": 3.885839736553238, "step": 1770}, {"loss": 0.7503, "grad_norm": 0.7212756276130676, "learning_rate": 0.0002, "epoch": 3.907793633369923, "step": 1780}, {"loss": 0.7978, "grad_norm": 0.584318220615387, "learning_rate": 0.0002, "epoch": 3.9297475301866083, "step": 1790}, {"loss": 0.7894, "grad_norm": 0.7612535953521729, "learning_rate": 0.0002, "epoch": 3.951701427003293, "step": 1800}, {"loss": 0.8589, "grad_norm": 0.735103189945221, "learning_rate": 0.0002, "epoch": 3.973655323819978, "step": 1810}, {"loss": 0.8192, "grad_norm": 0.9074980020523071, "learning_rate": 0.0002, "epoch": 3.995609220636663, "step": 1820}, {"eval_loss": 1.279890537261963, "eval_runtime": 88.8969, "eval_samples_per_second": 4.848, "eval_steps_per_second": 0.607, "epoch": 4.0, "step": 1822}, {"loss": 0.7312, "grad_norm": 0.9290254712104797, "learning_rate": 0.0002, "epoch": 4.017563117453348, "step": 1830}, {"loss": 0.6896, "grad_norm": 0.723889946937561, "learning_rate": 0.0002, "epoch": 4.039517014270033, "step": 1840}, {"loss": 0.632, "grad_norm": 0.5906972289085388, "learning_rate": 0.0002, "epoch": 4.061470911086718, "step": 1850}, {"loss": 0.6594, "grad_norm": 0.8078910708427429, "learning_rate": 0.0002, "epoch": 4.083424807903403, "step": 1860}, {"loss": 0.6242, "grad_norm": 1.0101137161254883, "learning_rate": 0.0002, "epoch": 4.105378704720088, "step": 1870}, {"loss": 0.7259, "grad_norm": 0.8710281848907471, "learning_rate": 0.0002, "epoch": 4.127332601536772, "step": 1880}, {"loss": 0.6993, "grad_norm": 0.9604734778404236, "learning_rate": 0.0002, "epoch": 4.149286498353458, "step": 1890}, {"loss": 0.6706, "grad_norm": 0.9829702377319336, "learning_rate": 0.0002, "epoch": 4.171240395170143, "step": 1900}, {"loss": 0.7013, "grad_norm": 0.6572765707969666, "learning_rate": 0.0002, "epoch": 4.193194291986828, "step": 1910}, {"loss": 0.5539, "grad_norm": 0.8459188938140869, "learning_rate": 0.0002, "epoch": 4.2151481888035125, "step": 1920}, {"loss": 0.6235, "grad_norm": 0.8321021795272827, "learning_rate": 0.0002, "epoch": 4.237102085620197, "step": 1930}, {"loss": 0.6442, "grad_norm": 0.8611727356910706, "learning_rate": 0.0002, "epoch": 4.259055982436882, "step": 1940}, {"loss": 0.6852, "grad_norm": 0.8490208387374878, "learning_rate": 0.0002, "epoch": 4.281009879253568, "step": 1950}, {"loss": 0.6175, "grad_norm": 0.9628722667694092, "learning_rate": 0.0002, "epoch": 4.302963776070253, "step": 1960}, {"loss": 0.5982, "grad_norm": 0.9632807374000549, "learning_rate": 0.0002, "epoch": 4.324917672886937, "step": 1970}, {"loss": 0.6138, "grad_norm": 0.7023298740386963, "learning_rate": 0.0002, "epoch": 4.346871569703622, "step": 1980}, {"loss": 0.6012, "grad_norm": 0.7912909388542175, "learning_rate": 0.0002, "epoch": 4.368825466520307, "step": 1990}, {"loss": 0.6767, "grad_norm": 1.1463429927825928, "learning_rate": 0.0002, "epoch": 4.390779363336993, "step": 2000}, {"loss": 0.6607, "grad_norm": 1.1780626773834229, "learning_rate": 0.0002, "epoch": 4.4127332601536775, "step": 2010}, {"loss": 0.6746, "grad_norm": 0.9349206686019897, "learning_rate": 0.0002, "epoch": 4.434687156970362, "step": 2020}, {"loss": 0.7087, "grad_norm": 0.7816639542579651, "learning_rate": 0.0002, "epoch": 4.456641053787047, "step": 2030}, {"loss": 0.6222, "grad_norm": 0.7005311250686646, "learning_rate": 0.0002, "epoch": 4.478594950603732, "step": 2040}, {"loss": 0.6608, "grad_norm": 0.7746558785438538, "learning_rate": 0.0002, "epoch": 4.500548847420417, "step": 2050}, {"loss": 0.6305, "grad_norm": 0.8261151313781738, "learning_rate": 0.0002, "epoch": 4.522502744237102, "step": 2060}, {"loss": 0.6502, "grad_norm": 1.0917805433273315, "learning_rate": 0.0002, "epoch": 4.544456641053787, "step": 2070}, {"loss": 0.6798, "grad_norm": 1.1570647954940796, "learning_rate": 0.0002, "epoch": 4.566410537870472, "step": 2080}, {"loss": 0.6296, "grad_norm": 0.9936433434486389, "learning_rate": 0.0002, "epoch": 4.588364434687157, "step": 2090}, {"loss": 0.5936, "grad_norm": 0.8574427366256714, "learning_rate": 0.0002, "epoch": 4.610318331503842, "step": 2100}, {"loss": 0.6529, "grad_norm": 0.7630168795585632, "learning_rate": 0.0002, "epoch": 4.632272228320527, "step": 2110}, {"loss": 0.5935, "grad_norm": 0.8146462440490723, "learning_rate": 0.0002, "epoch": 4.654226125137212, "step": 2120}, {"loss": 0.7102, "grad_norm": 0.7090407609939575, "learning_rate": 0.0002, "epoch": 4.676180021953897, "step": 2130}, {"loss": 0.6575, "grad_norm": 0.8278160095214844, "learning_rate": 0.0002, "epoch": 4.698133918770582, "step": 2140}, {"loss": 0.664, "grad_norm": 0.9415683746337891, "learning_rate": 0.0002, "epoch": 4.7200878155872665, "step": 2150}, {"loss": 0.7283, "grad_norm": 1.0056205987930298, "learning_rate": 0.0002, "epoch": 4.742041712403951, "step": 2160}, {"loss": 0.6845, "grad_norm": 0.768304705619812, "learning_rate": 0.0002, "epoch": 4.763995609220637, "step": 2170}, {"loss": 0.6922, "grad_norm": 1.0604112148284912, "learning_rate": 0.0002, "epoch": 4.785949506037322, "step": 2180}, {"loss": 0.7092, "grad_norm": 1.132864236831665, "learning_rate": 0.0002, "epoch": 4.807903402854007, "step": 2190}, {"loss": 0.6936, "grad_norm": 0.7543689608573914, "learning_rate": 0.0002, "epoch": 4.829857299670691, "step": 2200}, {"loss": 0.6921, "grad_norm": 0.8047362565994263, "learning_rate": 0.0002, "epoch": 4.851811196487376, "step": 2210}, {"loss": 0.6753, "grad_norm": 1.135778546333313, "learning_rate": 0.0002, "epoch": 4.873765093304062, "step": 2220}, {"loss": 0.6443, "grad_norm": 0.9068503379821777, "learning_rate": 0.0002, "epoch": 4.895718990120747, "step": 2230}, {"loss": 0.7419, "grad_norm": 1.822325587272644, "learning_rate": 0.0002, "epoch": 4.9176728869374315, "step": 2240}, {"loss": 0.6436, "grad_norm": 1.1124998331069946, "learning_rate": 0.0002, "epoch": 4.939626783754116, "step": 2250}, {"loss": 0.7423, "grad_norm": 0.818484365940094, "learning_rate": 0.0002, "epoch": 4.961580680570801, "step": 2260}, {"loss": 0.6872, "grad_norm": 1.0057194232940674, "learning_rate": 0.0002, "epoch": 4.983534577387486, "step": 2270}, {"eval_loss": 1.4120490550994873, "eval_runtime": 87.5617, "eval_samples_per_second": 4.922, "eval_steps_per_second": 0.617, "epoch": 4.998902305159166, "step": 2277}, {"loss": 0.5451, "grad_norm": 0.8211547136306763, "learning_rate": 0.0002, "epoch": 5.005488474204172, "step": 2280}, {"loss": 0.4965, "grad_norm": 1.1704130172729492, "learning_rate": 0.0002, "epoch": 5.0274423710208564, "step": 2290}, {"loss": 0.4827, "grad_norm": 1.033539891242981, "learning_rate": 0.0002, "epoch": 5.049396267837541, "step": 2300}, {"loss": 0.447, "grad_norm": 0.8830313682556152, "learning_rate": 0.0002, "epoch": 5.071350164654226, "step": 2310}, {"loss": 0.5502, "grad_norm": 1.160437822341919, "learning_rate": 0.0002, "epoch": 5.093304061470911, "step": 2320}, {"loss": 0.5123, "grad_norm": 0.919956386089325, "learning_rate": 0.0002, "epoch": 5.115257958287596, "step": 2330}, {"loss": 0.4784, "grad_norm": 1.0099905729293823, "learning_rate": 0.0002, "epoch": 5.137211855104281, "step": 2340}, {"loss": 0.5109, "grad_norm": 1.1484816074371338, "learning_rate": 0.0002, "epoch": 5.159165751920966, "step": 2350}, {"loss": 0.5222, "grad_norm": 1.0373470783233643, "learning_rate": 0.0002, "epoch": 5.181119648737651, "step": 2360}, {"loss": 0.5366, "grad_norm": 1.0824922323226929, "learning_rate": 0.0002, "epoch": 5.203073545554336, "step": 2370}, {"loss": 0.5592, "grad_norm": 1.3817942142486572, "learning_rate": 0.0002, "epoch": 5.225027442371021, "step": 2380}, {"loss": 0.504, "grad_norm": 1.197035551071167, "learning_rate": 0.0002, "epoch": 5.246981339187705, "step": 2390}, {"loss": 0.5326, "grad_norm": 1.098778486251831, "learning_rate": 0.0002, "epoch": 5.268935236004391, "step": 2400}, {"loss": 0.5039, "grad_norm": 0.9713385105133057, "learning_rate": 0.0002, "epoch": 5.290889132821076, "step": 2410}, {"loss": 0.5735, "grad_norm": 1.321574330329895, "learning_rate": 0.0002, "epoch": 5.312843029637761, "step": 2420}, {"loss": 0.4777, "grad_norm": 0.9402496218681335, "learning_rate": 0.0002, "epoch": 5.3347969264544455, "step": 2430}, {"loss": 0.5604, "grad_norm": 0.8644852042198181, "learning_rate": 0.0002, "epoch": 5.35675082327113, "step": 2440}, {"loss": 0.5324, "grad_norm": 1.060290813446045, "learning_rate": 0.0002, "epoch": 5.378704720087816, "step": 2450}, {"loss": 0.5366, "grad_norm": 1.0725265741348267, "learning_rate": 0.0002, "epoch": 5.400658616904501, "step": 2460}, {"loss": 0.5469, "grad_norm": 0.9409431219100952, "learning_rate": 0.0002, "epoch": 5.422612513721186, "step": 2470}, {"loss": 0.5186, "grad_norm": 1.1108187437057495, "learning_rate": 0.0002, "epoch": 5.44456641053787, "step": 2480}, {"loss": 0.5312, "grad_norm": 1.0210821628570557, "learning_rate": 0.0002, "epoch": 5.466520307354555, "step": 2490}, {"loss": 0.5016, "grad_norm": 1.110597014427185, "learning_rate": 0.0002, "epoch": 5.48847420417124, "step": 2500}, {"loss": 0.511, "grad_norm": 1.2534265518188477, "learning_rate": 0.0002, "epoch": 5.510428100987926, "step": 2510}, {"loss": 0.6062, "grad_norm": 1.3389744758605957, "learning_rate": 0.0002, "epoch": 5.5323819978046105, "step": 2520}, {"loss": 0.4653, "grad_norm": 0.9520368576049805, "learning_rate": 0.0002, "epoch": 5.554335894621295, "step": 2530}, {"loss": 0.4746, "grad_norm": 1.4737157821655273, "learning_rate": 0.0002, "epoch": 5.57628979143798, "step": 2540}, {"loss": 0.5432, "grad_norm": 1.4143685102462769, "learning_rate": 0.0002, "epoch": 5.598243688254665, "step": 2550}, {"loss": 0.4722, "grad_norm": 1.3573999404907227, "learning_rate": 0.0002, "epoch": 5.620197585071351, "step": 2560}, {"loss": 0.5063, "grad_norm": 0.8475444316864014, "learning_rate": 0.0002, "epoch": 5.642151481888035, "step": 2570}, {"loss": 0.4911, "grad_norm": 1.2670329809188843, "learning_rate": 0.0002, "epoch": 5.66410537870472, "step": 2580}, {"loss": 0.5137, "grad_norm": 0.9688172936439514, "learning_rate": 0.0002, "epoch": 5.686059275521405, "step": 2590}, {"loss": 0.5116, "grad_norm": 1.3652743101119995, "learning_rate": 0.0002, "epoch": 5.70801317233809, "step": 2600}, {"loss": 0.5661, "grad_norm": 1.1475377082824707, "learning_rate": 0.0002, "epoch": 5.729967069154775, "step": 2610}, {"loss": 0.567, "grad_norm": 1.3105946779251099, "learning_rate": 0.0002, "epoch": 5.75192096597146, "step": 2620}, {"loss": 0.4964, "grad_norm": 0.920238196849823, "learning_rate": 0.0002, "epoch": 5.773874862788145, "step": 2630}, {"loss": 0.5473, "grad_norm": 1.0981792211532593, "learning_rate": 0.0002, "epoch": 5.79582875960483, "step": 2640}, {"loss": 0.5132, "grad_norm": 1.0734144449234009, "learning_rate": 0.0002, "epoch": 5.817782656421515, "step": 2650}, {"loss": 0.5404, "grad_norm": 1.0541702508926392, "learning_rate": 0.0002, "epoch": 5.8397365532381995, "step": 2660}, {"loss": 0.5056, "grad_norm": 1.0913143157958984, "learning_rate": 0.0002, "epoch": 5.861690450054885, "step": 2670}, {"loss": 0.5425, "grad_norm": 1.0431408882141113, "learning_rate": 0.0002, "epoch": 5.88364434687157, "step": 2680}, {"loss": 0.5398, "grad_norm": 1.3515729904174805, "learning_rate": 0.0002, "epoch": 5.905598243688255, "step": 2690}, {"loss": 0.5936, "grad_norm": 1.3153903484344482, "learning_rate": 0.0002, "epoch": 5.92755214050494, "step": 2700}, {"loss": 0.5643, "grad_norm": 1.024109125137329, "learning_rate": 0.0002, "epoch": 5.949506037321624, "step": 2710}, {"loss": 0.5143, "grad_norm": 1.0308483839035034, "learning_rate": 0.0002, "epoch": 5.971459934138309, "step": 2720}, {"loss": 0.4835, "grad_norm": 0.8329401016235352, "learning_rate": 0.0002, "epoch": 5.993413830954994, "step": 2730}]} +{"epoch": 6.998902305159166, "step": 3188, "epoch_duration": 1564.2331323623657, "total_accumulated_duration": 10872.881721735, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7672.4541015625}, "peak_memory_usage": {"GPU_0": 13792.75439453125}, "avg_memory_reserved": {"GPU_0": 17416.0}, "peak_memory_reserved": {"GPU_0": 17416.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 1.9887, "grad_norm": 0.6144012212753296, "learning_rate": 0.0002, "epoch": 0.021953896816684963, "step": 10}, {"loss": 1.6882, "grad_norm": 0.5587220788002014, "learning_rate": 0.0002, "epoch": 0.043907793633369926, "step": 20}, {"loss": 1.399, "grad_norm": 0.43262454867362976, "learning_rate": 0.0002, "epoch": 0.06586169045005488, "step": 30}, {"loss": 1.4675, "grad_norm": 0.4783053994178772, "learning_rate": 0.0002, "epoch": 0.08781558726673985, "step": 40}, {"loss": 1.1771, "grad_norm": 0.44338956475257874, "learning_rate": 0.0002, "epoch": 0.10976948408342481, "step": 50}, {"loss": 1.3706, "grad_norm": 0.7255092263221741, "learning_rate": 0.0002, "epoch": 0.13172338090010977, "step": 60}, {"loss": 1.2601, "grad_norm": 0.46073833107948303, "learning_rate": 0.0002, "epoch": 0.15367727771679474, "step": 70}, {"loss": 1.3049, "grad_norm": 0.6698123216629028, "learning_rate": 0.0002, "epoch": 0.1756311745334797, "step": 80}, {"loss": 1.2975, "grad_norm": 0.4190150201320648, "learning_rate": 0.0002, "epoch": 0.19758507135016465, "step": 90}, {"loss": 1.2797, "grad_norm": 0.4110015034675598, "learning_rate": 0.0002, "epoch": 0.21953896816684962, "step": 100}, {"loss": 1.2896, "grad_norm": 0.33374306559562683, "learning_rate": 0.0002, "epoch": 0.2414928649835346, "step": 110}, {"loss": 1.2268, "grad_norm": 0.3061307370662689, "learning_rate": 0.0002, "epoch": 0.26344676180021953, "step": 120}, {"loss": 1.376, "grad_norm": 0.4386885166168213, "learning_rate": 0.0002, "epoch": 0.2854006586169045, "step": 130}, {"loss": 1.1814, "grad_norm": 0.40116462111473083, "learning_rate": 0.0002, "epoch": 0.30735455543358947, "step": 140}, {"loss": 1.2592, "grad_norm": 0.5887949466705322, "learning_rate": 0.0002, "epoch": 0.32930845225027444, "step": 150}, {"loss": 1.2372, "grad_norm": 0.3401573896408081, "learning_rate": 0.0002, "epoch": 0.3512623490669594, "step": 160}, {"loss": 1.1901, "grad_norm": 0.3288364112377167, "learning_rate": 0.0002, "epoch": 0.3732162458836443, "step": 170}, {"loss": 1.2335, "grad_norm": 0.4853297472000122, "learning_rate": 0.0002, "epoch": 0.3951701427003293, "step": 180}, {"loss": 1.227, "grad_norm": 2.6253697872161865, "learning_rate": 0.0002, "epoch": 0.41712403951701427, "step": 190}, {"loss": 1.2673, "grad_norm": 0.5598543286323547, "learning_rate": 0.0002, "epoch": 0.43907793633369924, "step": 200}, {"loss": 1.3459, "grad_norm": 0.4046548902988434, "learning_rate": 0.0002, "epoch": 0.4610318331503842, "step": 210}, {"loss": 1.265, "grad_norm": 0.3686952590942383, "learning_rate": 0.0002, "epoch": 0.4829857299670692, "step": 220}, {"loss": 1.1364, "grad_norm": 0.42458799481391907, "learning_rate": 0.0002, "epoch": 0.5049396267837541, "step": 230}, {"loss": 1.2094, "grad_norm": 0.5839895009994507, "learning_rate": 0.0002, "epoch": 0.5268935236004391, "step": 240}, {"loss": 1.2073, "grad_norm": 0.408288836479187, "learning_rate": 0.0002, "epoch": 0.5488474204171241, "step": 250}, {"loss": 1.3121, "grad_norm": 0.45887550711631775, "learning_rate": 0.0002, "epoch": 0.570801317233809, "step": 260}, {"loss": 1.2257, "grad_norm": 0.5440235733985901, "learning_rate": 0.0002, "epoch": 0.5927552140504939, "step": 270}, {"loss": 1.1003, "grad_norm": 0.3725181519985199, "learning_rate": 0.0002, "epoch": 0.6147091108671789, "step": 280}, {"loss": 1.1538, "grad_norm": 0.4309018850326538, "learning_rate": 0.0002, "epoch": 0.6366630076838639, "step": 290}, {"loss": 1.2097, "grad_norm": 0.31488674879074097, "learning_rate": 0.0002, "epoch": 0.6586169045005489, "step": 300}, {"loss": 1.1689, "grad_norm": 0.34194841980934143, "learning_rate": 0.0002, "epoch": 0.6805708013172338, "step": 310}, {"loss": 1.2579, "grad_norm": 0.3407684862613678, "learning_rate": 0.0002, "epoch": 0.7025246981339188, "step": 320}, {"loss": 1.1144, "grad_norm": 0.2985728085041046, "learning_rate": 0.0002, "epoch": 0.7244785949506037, "step": 330}, {"loss": 1.2056, "grad_norm": 0.42316871881484985, "learning_rate": 0.0002, "epoch": 0.7464324917672887, "step": 340}, {"loss": 1.1753, "grad_norm": 0.3124258816242218, "learning_rate": 0.0002, "epoch": 0.7683863885839737, "step": 350}, {"loss": 1.2547, "grad_norm": 0.7727567553520203, "learning_rate": 0.0002, "epoch": 0.7903402854006586, "step": 360}, {"loss": 1.124, "grad_norm": 0.363765686750412, "learning_rate": 0.0002, "epoch": 0.8122941822173436, "step": 370}, {"loss": 1.1302, "grad_norm": 0.35582536458969116, "learning_rate": 0.0002, "epoch": 0.8342480790340285, "step": 380}, {"loss": 1.1787, "grad_norm": 0.31982025504112244, "learning_rate": 0.0002, "epoch": 0.8562019758507134, "step": 390}, {"loss": 1.2056, "grad_norm": 0.34978964924812317, "learning_rate": 0.0002, "epoch": 0.8781558726673985, "step": 400}, {"loss": 1.3577, "grad_norm": 0.8346716165542603, "learning_rate": 0.0002, "epoch": 0.9001097694840834, "step": 410}, {"loss": 1.1029, "grad_norm": 0.31984028220176697, "learning_rate": 0.0002, "epoch": 0.9220636663007684, "step": 420}, {"loss": 1.0967, "grad_norm": 0.32078951597213745, "learning_rate": 0.0002, "epoch": 0.9440175631174533, "step": 430}, {"loss": 1.0936, "grad_norm": 0.3417500853538513, "learning_rate": 0.0002, "epoch": 0.9659714599341384, "step": 440}, {"loss": 1.3412, "grad_norm": 0.42359477281570435, "learning_rate": 0.0002, "epoch": 0.9879253567508233, "step": 450}, {"eval_loss": 1.2201528549194336, "eval_runtime": 87.152, "eval_samples_per_second": 4.945, "eval_steps_per_second": 0.62, "epoch": 0.9989023051591658, "step": 455}, {"loss": 1.1909, "grad_norm": 0.37914523482322693, "learning_rate": 0.0002, "epoch": 1.0098792535675083, "step": 460}, {"loss": 1.0948, "grad_norm": 0.43655872344970703, "learning_rate": 0.0002, "epoch": 1.031833150384193, "step": 470}, {"loss": 1.0873, "grad_norm": 0.3673796057701111, "learning_rate": 0.0002, "epoch": 1.0537870472008781, "step": 480}, {"loss": 1.0483, "grad_norm": 0.37673917412757874, "learning_rate": 0.0002, "epoch": 1.0757409440175631, "step": 490}, {"loss": 1.0799, "grad_norm": 0.2893829345703125, "learning_rate": 0.0002, "epoch": 1.0976948408342482, "step": 500}, {"loss": 1.1847, "grad_norm": 0.5551970601081848, "learning_rate": 0.0002, "epoch": 1.119648737650933, "step": 510}, {"loss": 1.0885, "grad_norm": 0.442104309797287, "learning_rate": 0.0002, "epoch": 1.141602634467618, "step": 520}, {"loss": 1.1766, "grad_norm": 0.4035094976425171, "learning_rate": 0.0002, "epoch": 1.163556531284303, "step": 530}, {"loss": 1.0282, "grad_norm": 0.47009000182151794, "learning_rate": 0.0002, "epoch": 1.1855104281009878, "step": 540}, {"loss": 1.2625, "grad_norm": 0.4118749797344208, "learning_rate": 0.0002, "epoch": 1.2074643249176729, "step": 550}, {"loss": 1.0988, "grad_norm": 0.35173165798187256, "learning_rate": 0.0002, "epoch": 1.2294182217343579, "step": 560}, {"loss": 1.0498, "grad_norm": 0.7024672031402588, "learning_rate": 0.0002, "epoch": 1.2513721185510427, "step": 570}, {"loss": 1.1339, "grad_norm": 0.42657527327537537, "learning_rate": 0.0002, "epoch": 1.2733260153677277, "step": 580}, {"loss": 1.0545, "grad_norm": 0.3815029561519623, "learning_rate": 0.0002, "epoch": 1.2952799121844127, "step": 590}, {"loss": 1.1528, "grad_norm": 0.7031055688858032, "learning_rate": 0.0002, "epoch": 1.3172338090010978, "step": 600}, {"loss": 1.1347, "grad_norm": 0.393911212682724, "learning_rate": 0.0002, "epoch": 1.3391877058177828, "step": 610}, {"loss": 1.1901, "grad_norm": 0.5077702403068542, "learning_rate": 0.0002, "epoch": 1.3611416026344676, "step": 620}, {"loss": 1.1251, "grad_norm": 2.330033302307129, "learning_rate": 0.0002, "epoch": 1.3830954994511526, "step": 630}, {"loss": 1.0477, "grad_norm": 0.35322949290275574, "learning_rate": 0.0002, "epoch": 1.4050493962678376, "step": 640}, {"loss": 1.14, "grad_norm": 0.44401052594184875, "learning_rate": 0.0002, "epoch": 1.4270032930845225, "step": 650}, {"loss": 1.0318, "grad_norm": 0.35945481061935425, "learning_rate": 0.0002, "epoch": 1.4489571899012075, "step": 660}, {"loss": 1.1988, "grad_norm": 0.3058856129646301, "learning_rate": 0.0002, "epoch": 1.4709110867178925, "step": 670}, {"loss": 1.1545, "grad_norm": 0.7067602872848511, "learning_rate": 0.0002, "epoch": 1.4928649835345773, "step": 680}, {"loss": 1.0925, "grad_norm": 0.4219357371330261, "learning_rate": 0.0002, "epoch": 1.5148188803512623, "step": 690}, {"loss": 1.1622, "grad_norm": 0.5970841646194458, "learning_rate": 0.0002, "epoch": 1.5367727771679474, "step": 700}, {"loss": 1.0803, "grad_norm": 0.4381934404373169, "learning_rate": 0.0002, "epoch": 1.5587266739846322, "step": 710}, {"loss": 1.0961, "grad_norm": 0.4101450443267822, "learning_rate": 0.0002, "epoch": 1.5806805708013172, "step": 720}, {"loss": 1.0474, "grad_norm": 0.3657490015029907, "learning_rate": 0.0002, "epoch": 1.6026344676180022, "step": 730}, {"loss": 1.0936, "grad_norm": 0.36240628361701965, "learning_rate": 0.0002, "epoch": 1.624588364434687, "step": 740}, {"loss": 1.0489, "grad_norm": 0.4103568494319916, "learning_rate": 0.0002, "epoch": 1.6465422612513723, "step": 750}, {"loss": 1.0919, "grad_norm": 0.3138505816459656, "learning_rate": 0.0002, "epoch": 1.668496158068057, "step": 760}, {"loss": 1.2308, "grad_norm": 0.41215717792510986, "learning_rate": 0.0002, "epoch": 1.690450054884742, "step": 770}, {"loss": 1.1659, "grad_norm": 0.4589519202709198, "learning_rate": 0.0002, "epoch": 1.7124039517014271, "step": 780}, {"loss": 1.0913, "grad_norm": 0.4049508571624756, "learning_rate": 0.0002, "epoch": 1.734357848518112, "step": 790}, {"loss": 1.1329, "grad_norm": 0.48557212948799133, "learning_rate": 0.0002, "epoch": 1.756311745334797, "step": 800}, {"loss": 1.0729, "grad_norm": 0.5331754088401794, "learning_rate": 0.0002, "epoch": 1.778265642151482, "step": 810}, {"loss": 1.1452, "grad_norm": 0.3853185772895813, "learning_rate": 0.0002, "epoch": 1.8002195389681668, "step": 820}, {"loss": 1.1061, "grad_norm": 0.424062579870224, "learning_rate": 0.0002, "epoch": 1.8221734357848518, "step": 830}, {"loss": 1.1104, "grad_norm": 0.3418445289134979, "learning_rate": 0.0002, "epoch": 1.8441273326015368, "step": 840}, {"loss": 1.0546, "grad_norm": 0.4045565128326416, "learning_rate": 0.0002, "epoch": 1.8660812294182216, "step": 850}, {"loss": 1.1608, "grad_norm": 0.42155781388282776, "learning_rate": 0.0002, "epoch": 1.8880351262349067, "step": 860}, {"loss": 1.0628, "grad_norm": 0.40554770827293396, "learning_rate": 0.0002, "epoch": 1.9099890230515917, "step": 870}, {"loss": 1.1609, "grad_norm": 0.42644748091697693, "learning_rate": 0.0002, "epoch": 1.9319429198682765, "step": 880}, {"loss": 1.1132, "grad_norm": 0.45260652899742126, "learning_rate": 0.0002, "epoch": 1.9538968166849617, "step": 890}, {"loss": 1.048, "grad_norm": 0.4114069938659668, "learning_rate": 0.0002, "epoch": 1.9758507135016465, "step": 900}, {"loss": 1.1941, "grad_norm": 0.375802218914032, "learning_rate": 0.0002, "epoch": 1.9978046103183313, "step": 910}, {"eval_loss": 1.205152153968811, "eval_runtime": 86.8795, "eval_samples_per_second": 4.961, "eval_steps_per_second": 0.622, "epoch": 2.0, "step": 911}, {"loss": 1.0897, "grad_norm": 0.47718703746795654, "learning_rate": 0.0002, "epoch": 2.0197585071350166, "step": 920}, {"loss": 1.0329, "grad_norm": 0.45628082752227783, "learning_rate": 0.0002, "epoch": 2.0417124039517014, "step": 930}, {"loss": 1.0538, "grad_norm": 0.5933247804641724, "learning_rate": 0.0002, "epoch": 2.063666300768386, "step": 940}, {"loss": 1.0152, "grad_norm": 0.5355812907218933, "learning_rate": 0.0002, "epoch": 2.0856201975850714, "step": 950}, {"loss": 1.0726, "grad_norm": 0.5860010385513306, "learning_rate": 0.0002, "epoch": 2.1075740944017562, "step": 960}, {"loss": 1.025, "grad_norm": 0.7471673488616943, "learning_rate": 0.0002, "epoch": 2.129527991218441, "step": 970}, {"loss": 1.0247, "grad_norm": 2.0918211936950684, "learning_rate": 0.0002, "epoch": 2.1514818880351263, "step": 980}, {"loss": 0.8947, "grad_norm": 0.4021058678627014, "learning_rate": 0.0002, "epoch": 2.173435784851811, "step": 990}, {"loss": 0.8875, "grad_norm": 0.564975380897522, "learning_rate": 0.0002, "epoch": 2.1953896816684964, "step": 1000}, {"loss": 1.0264, "grad_norm": 0.46260079741477966, "learning_rate": 0.0002, "epoch": 2.217343578485181, "step": 1010}, {"loss": 0.9265, "grad_norm": 0.4791034460067749, "learning_rate": 0.0002, "epoch": 2.239297475301866, "step": 1020}, {"loss": 0.8869, "grad_norm": 0.5272043943405151, "learning_rate": 0.0002, "epoch": 2.261251372118551, "step": 1030}, {"loss": 1.0007, "grad_norm": 0.5221094489097595, "learning_rate": 0.0002, "epoch": 2.283205268935236, "step": 1040}, {"loss": 0.9472, "grad_norm": 0.558032751083374, "learning_rate": 0.0002, "epoch": 2.305159165751921, "step": 1050}, {"loss": 0.9617, "grad_norm": 0.5905590653419495, "learning_rate": 0.0002, "epoch": 2.327113062568606, "step": 1060}, {"loss": 0.9592, "grad_norm": 0.5308699607849121, "learning_rate": 0.0002, "epoch": 2.349066959385291, "step": 1070}, {"loss": 1.0646, "grad_norm": 0.6375027894973755, "learning_rate": 0.0002, "epoch": 2.3710208562019757, "step": 1080}, {"loss": 1.0354, "grad_norm": 0.7439115643501282, "learning_rate": 0.0002, "epoch": 2.392974753018661, "step": 1090}, {"loss": 1.0212, "grad_norm": 0.41945117712020874, "learning_rate": 0.0002, "epoch": 2.4149286498353457, "step": 1100}, {"loss": 0.9609, "grad_norm": 0.4891968369483948, "learning_rate": 0.0002, "epoch": 2.436882546652031, "step": 1110}, {"loss": 0.9829, "grad_norm": 0.4686794579029083, "learning_rate": 0.0002, "epoch": 2.4588364434687158, "step": 1120}, {"loss": 0.8919, "grad_norm": 0.5204509496688843, "learning_rate": 0.0002, "epoch": 2.4807903402854006, "step": 1130}, {"loss": 0.8983, "grad_norm": 0.6779005527496338, "learning_rate": 0.0002, "epoch": 2.5027442371020854, "step": 1140}, {"loss": 0.9733, "grad_norm": 0.682621955871582, "learning_rate": 0.0002, "epoch": 2.5246981339187706, "step": 1150}, {"loss": 1.051, "grad_norm": 0.5744376182556152, "learning_rate": 0.0002, "epoch": 2.5466520307354554, "step": 1160}, {"loss": 0.8764, "grad_norm": 0.49954667687416077, "learning_rate": 0.0002, "epoch": 2.5686059275521407, "step": 1170}, {"loss": 0.9896, "grad_norm": 0.4761793315410614, "learning_rate": 0.0002, "epoch": 2.5905598243688255, "step": 1180}, {"loss": 0.8593, "grad_norm": 0.548299252986908, "learning_rate": 0.0002, "epoch": 2.6125137211855103, "step": 1190}, {"loss": 1.0017, "grad_norm": 0.5771360993385315, "learning_rate": 0.0002, "epoch": 2.6344676180021955, "step": 1200}, {"loss": 0.9858, "grad_norm": 0.5543120503425598, "learning_rate": 0.0002, "epoch": 2.6564215148188803, "step": 1210}, {"loss": 0.9565, "grad_norm": 0.7564870715141296, "learning_rate": 0.0002, "epoch": 2.6783754116355656, "step": 1220}, {"loss": 0.9753, "grad_norm": 0.8222362399101257, "learning_rate": 0.0002, "epoch": 2.7003293084522504, "step": 1230}, {"loss": 1.0079, "grad_norm": 0.6894469857215881, "learning_rate": 0.0002, "epoch": 2.722283205268935, "step": 1240}, {"loss": 1.0106, "grad_norm": 0.6121546030044556, "learning_rate": 0.0002, "epoch": 2.74423710208562, "step": 1250}, {"loss": 0.9801, "grad_norm": 0.521809995174408, "learning_rate": 0.0002, "epoch": 2.7661909989023052, "step": 1260}, {"loss": 1.0196, "grad_norm": 0.766968309879303, "learning_rate": 0.0002, "epoch": 2.78814489571899, "step": 1270}, {"loss": 0.976, "grad_norm": 0.522331714630127, "learning_rate": 0.0002, "epoch": 2.8100987925356753, "step": 1280}, {"loss": 0.8866, "grad_norm": 0.42923519015312195, "learning_rate": 0.0002, "epoch": 2.83205268935236, "step": 1290}, {"loss": 0.9049, "grad_norm": 0.47810837626457214, "learning_rate": 0.0002, "epoch": 2.854006586169045, "step": 1300}, {"loss": 1.0291, "grad_norm": 1.0958846807479858, "learning_rate": 0.0002, "epoch": 2.8759604829857297, "step": 1310}, {"loss": 0.8724, "grad_norm": 0.4755791127681732, "learning_rate": 0.0002, "epoch": 2.897914379802415, "step": 1320}, {"loss": 0.9317, "grad_norm": 0.5575157403945923, "learning_rate": 0.0002, "epoch": 2.9198682766190998, "step": 1330}, {"loss": 1.0131, "grad_norm": 0.5938076376914978, "learning_rate": 0.0002, "epoch": 2.941822173435785, "step": 1340}, {"loss": 0.9857, "grad_norm": 0.5751763582229614, "learning_rate": 0.0002, "epoch": 2.96377607025247, "step": 1350}, {"loss": 1.0212, "grad_norm": 0.5590175986289978, "learning_rate": 0.0002, "epoch": 2.9857299670691546, "step": 1360}, {"eval_loss": 1.2402944564819336, "eval_runtime": 88.822, "eval_samples_per_second": 4.852, "eval_steps_per_second": 0.608, "epoch": 2.9989023051591657, "step": 1366}, {"loss": 0.844, "grad_norm": 0.463539719581604, "learning_rate": 0.0002, "epoch": 3.00768386388584, "step": 1370}, {"loss": 0.8955, "grad_norm": 0.6667885780334473, "learning_rate": 0.0002, "epoch": 3.0296377607025247, "step": 1380}, {"loss": 0.8765, "grad_norm": 0.5849342942237854, "learning_rate": 0.0002, "epoch": 3.0515916575192095, "step": 1390}, {"loss": 0.7808, "grad_norm": 0.5571770668029785, "learning_rate": 0.0002, "epoch": 3.0735455543358947, "step": 1400}, {"loss": 0.7448, "grad_norm": 0.5761234164237976, "learning_rate": 0.0002, "epoch": 3.0954994511525795, "step": 1410}, {"loss": 0.7854, "grad_norm": 0.7277371883392334, "learning_rate": 0.0002, "epoch": 3.1174533479692643, "step": 1420}, {"loss": 0.817, "grad_norm": 0.5190334320068359, "learning_rate": 0.0002, "epoch": 3.1394072447859496, "step": 1430}, {"loss": 0.7548, "grad_norm": 0.632939875125885, "learning_rate": 0.0002, "epoch": 3.1613611416026344, "step": 1440}, {"loss": 0.8447, "grad_norm": 0.7229540944099426, "learning_rate": 0.0002, "epoch": 3.1833150384193196, "step": 1450}, {"loss": 0.8595, "grad_norm": 0.7584632039070129, "learning_rate": 0.0002, "epoch": 3.2052689352360044, "step": 1460}, {"loss": 0.7456, "grad_norm": 0.6546088457107544, "learning_rate": 0.0002, "epoch": 3.2272228320526892, "step": 1470}, {"loss": 0.8531, "grad_norm": 0.8116684556007385, "learning_rate": 0.0002, "epoch": 3.2491767288693745, "step": 1480}, {"loss": 0.9272, "grad_norm": 0.6206557750701904, "learning_rate": 0.0002, "epoch": 3.2711306256860593, "step": 1490}, {"loss": 0.7972, "grad_norm": 0.5393369197845459, "learning_rate": 0.0002, "epoch": 3.293084522502744, "step": 1500}, {"loss": 0.7614, "grad_norm": 0.7006453275680542, "learning_rate": 0.0002, "epoch": 3.3150384193194293, "step": 1510}, {"loss": 0.7358, "grad_norm": 0.95253986120224, "learning_rate": 0.0002, "epoch": 3.336992316136114, "step": 1520}, {"loss": 0.8131, "grad_norm": 0.8138132095336914, "learning_rate": 0.0002, "epoch": 3.358946212952799, "step": 1530}, {"loss": 0.7738, "grad_norm": 0.7974302172660828, "learning_rate": 0.0002, "epoch": 3.380900109769484, "step": 1540}, {"loss": 0.8161, "grad_norm": 0.6694685220718384, "learning_rate": 0.0002, "epoch": 3.402854006586169, "step": 1550}, {"loss": 0.8503, "grad_norm": 0.908634603023529, "learning_rate": 0.0002, "epoch": 3.4248079034028542, "step": 1560}, {"loss": 0.7609, "grad_norm": 0.5625193119049072, "learning_rate": 0.0002, "epoch": 3.446761800219539, "step": 1570}, {"loss": 0.7658, "grad_norm": 0.779325544834137, "learning_rate": 0.0002, "epoch": 3.468715697036224, "step": 1580}, {"loss": 0.7485, "grad_norm": 0.7133058905601501, "learning_rate": 0.0002, "epoch": 3.4906695938529086, "step": 1590}, {"loss": 0.8847, "grad_norm": 0.6741108298301697, "learning_rate": 0.0002, "epoch": 3.512623490669594, "step": 1600}, {"loss": 0.7838, "grad_norm": 0.696982204914093, "learning_rate": 0.0002, "epoch": 3.5345773874862787, "step": 1610}, {"loss": 0.7195, "grad_norm": 0.7946001291275024, "learning_rate": 0.0002, "epoch": 3.556531284302964, "step": 1620}, {"loss": 0.7772, "grad_norm": 0.6313548684120178, "learning_rate": 0.0002, "epoch": 3.5784851811196488, "step": 1630}, {"loss": 0.8267, "grad_norm": 0.9246852397918701, "learning_rate": 0.0002, "epoch": 3.6004390779363336, "step": 1640}, {"loss": 0.779, "grad_norm": 0.6615420579910278, "learning_rate": 0.0002, "epoch": 3.622392974753019, "step": 1650}, {"loss": 0.883, "grad_norm": 1.5050125122070312, "learning_rate": 0.0002, "epoch": 3.6443468715697036, "step": 1660}, {"loss": 0.7763, "grad_norm": 0.5023762583732605, "learning_rate": 0.0002, "epoch": 3.666300768386389, "step": 1670}, {"loss": 0.8173, "grad_norm": 0.6289586424827576, "learning_rate": 0.0002, "epoch": 3.6882546652030737, "step": 1680}, {"loss": 0.9028, "grad_norm": 1.050397515296936, "learning_rate": 0.0002, "epoch": 3.7102085620197585, "step": 1690}, {"loss": 0.7747, "grad_norm": 0.6785626411437988, "learning_rate": 0.0002, "epoch": 3.7321624588364433, "step": 1700}, {"loss": 0.9215, "grad_norm": 0.7565035223960876, "learning_rate": 0.0002, "epoch": 3.7541163556531285, "step": 1710}, {"loss": 0.7913, "grad_norm": 0.7775155901908875, "learning_rate": 0.0002, "epoch": 3.7760702524698133, "step": 1720}, {"loss": 0.8081, "grad_norm": 0.765260636806488, "learning_rate": 0.0002, "epoch": 3.7980241492864986, "step": 1730}, {"loss": 0.9231, "grad_norm": 0.7982407808303833, "learning_rate": 0.0002, "epoch": 3.8199780461031834, "step": 1740}, {"loss": 0.7755, "grad_norm": 0.7431730628013611, "learning_rate": 0.0002, "epoch": 3.841931942919868, "step": 1750}, {"loss": 0.9236, "grad_norm": 0.9758927226066589, "learning_rate": 0.0002, "epoch": 3.863885839736553, "step": 1760}, {"loss": 0.9118, "grad_norm": 0.8014697432518005, "learning_rate": 0.0002, "epoch": 3.885839736553238, "step": 1770}, {"loss": 0.7503, "grad_norm": 0.7212756276130676, "learning_rate": 0.0002, "epoch": 3.907793633369923, "step": 1780}, {"loss": 0.7978, "grad_norm": 0.584318220615387, "learning_rate": 0.0002, "epoch": 3.9297475301866083, "step": 1790}, {"loss": 0.7894, "grad_norm": 0.7612535953521729, "learning_rate": 0.0002, "epoch": 3.951701427003293, "step": 1800}, {"loss": 0.8589, "grad_norm": 0.735103189945221, "learning_rate": 0.0002, "epoch": 3.973655323819978, "step": 1810}, {"loss": 0.8192, "grad_norm": 0.9074980020523071, "learning_rate": 0.0002, "epoch": 3.995609220636663, "step": 1820}, {"eval_loss": 1.279890537261963, "eval_runtime": 88.8969, "eval_samples_per_second": 4.848, "eval_steps_per_second": 0.607, "epoch": 4.0, "step": 1822}, {"loss": 0.7312, "grad_norm": 0.9290254712104797, "learning_rate": 0.0002, "epoch": 4.017563117453348, "step": 1830}, {"loss": 0.6896, "grad_norm": 0.723889946937561, "learning_rate": 0.0002, "epoch": 4.039517014270033, "step": 1840}, {"loss": 0.632, "grad_norm": 0.5906972289085388, "learning_rate": 0.0002, "epoch": 4.061470911086718, "step": 1850}, {"loss": 0.6594, "grad_norm": 0.8078910708427429, "learning_rate": 0.0002, "epoch": 4.083424807903403, "step": 1860}, {"loss": 0.6242, "grad_norm": 1.0101137161254883, "learning_rate": 0.0002, "epoch": 4.105378704720088, "step": 1870}, {"loss": 0.7259, "grad_norm": 0.8710281848907471, "learning_rate": 0.0002, "epoch": 4.127332601536772, "step": 1880}, {"loss": 0.6993, "grad_norm": 0.9604734778404236, "learning_rate": 0.0002, "epoch": 4.149286498353458, "step": 1890}, {"loss": 0.6706, "grad_norm": 0.9829702377319336, "learning_rate": 0.0002, "epoch": 4.171240395170143, "step": 1900}, {"loss": 0.7013, "grad_norm": 0.6572765707969666, "learning_rate": 0.0002, "epoch": 4.193194291986828, "step": 1910}, {"loss": 0.5539, "grad_norm": 0.8459188938140869, "learning_rate": 0.0002, "epoch": 4.2151481888035125, "step": 1920}, {"loss": 0.6235, "grad_norm": 0.8321021795272827, "learning_rate": 0.0002, "epoch": 4.237102085620197, "step": 1930}, {"loss": 0.6442, "grad_norm": 0.8611727356910706, "learning_rate": 0.0002, "epoch": 4.259055982436882, "step": 1940}, {"loss": 0.6852, "grad_norm": 0.8490208387374878, "learning_rate": 0.0002, "epoch": 4.281009879253568, "step": 1950}, {"loss": 0.6175, "grad_norm": 0.9628722667694092, "learning_rate": 0.0002, "epoch": 4.302963776070253, "step": 1960}, {"loss": 0.5982, "grad_norm": 0.9632807374000549, "learning_rate": 0.0002, "epoch": 4.324917672886937, "step": 1970}, {"loss": 0.6138, "grad_norm": 0.7023298740386963, "learning_rate": 0.0002, "epoch": 4.346871569703622, "step": 1980}, {"loss": 0.6012, "grad_norm": 0.7912909388542175, "learning_rate": 0.0002, "epoch": 4.368825466520307, "step": 1990}, {"loss": 0.6767, "grad_norm": 1.1463429927825928, "learning_rate": 0.0002, "epoch": 4.390779363336993, "step": 2000}, {"loss": 0.6607, "grad_norm": 1.1780626773834229, "learning_rate": 0.0002, "epoch": 4.4127332601536775, "step": 2010}, {"loss": 0.6746, "grad_norm": 0.9349206686019897, "learning_rate": 0.0002, "epoch": 4.434687156970362, "step": 2020}, {"loss": 0.7087, "grad_norm": 0.7816639542579651, "learning_rate": 0.0002, "epoch": 4.456641053787047, "step": 2030}, {"loss": 0.6222, "grad_norm": 0.7005311250686646, "learning_rate": 0.0002, "epoch": 4.478594950603732, "step": 2040}, {"loss": 0.6608, "grad_norm": 0.7746558785438538, "learning_rate": 0.0002, "epoch": 4.500548847420417, "step": 2050}, {"loss": 0.6305, "grad_norm": 0.8261151313781738, "learning_rate": 0.0002, "epoch": 4.522502744237102, "step": 2060}, {"loss": 0.6502, "grad_norm": 1.0917805433273315, "learning_rate": 0.0002, "epoch": 4.544456641053787, "step": 2070}, {"loss": 0.6798, "grad_norm": 1.1570647954940796, "learning_rate": 0.0002, "epoch": 4.566410537870472, "step": 2080}, {"loss": 0.6296, "grad_norm": 0.9936433434486389, "learning_rate": 0.0002, "epoch": 4.588364434687157, "step": 2090}, {"loss": 0.5936, "grad_norm": 0.8574427366256714, "learning_rate": 0.0002, "epoch": 4.610318331503842, "step": 2100}, {"loss": 0.6529, "grad_norm": 0.7630168795585632, "learning_rate": 0.0002, "epoch": 4.632272228320527, "step": 2110}, {"loss": 0.5935, "grad_norm": 0.8146462440490723, "learning_rate": 0.0002, "epoch": 4.654226125137212, "step": 2120}, {"loss": 0.7102, "grad_norm": 0.7090407609939575, "learning_rate": 0.0002, "epoch": 4.676180021953897, "step": 2130}, {"loss": 0.6575, "grad_norm": 0.8278160095214844, "learning_rate": 0.0002, "epoch": 4.698133918770582, "step": 2140}, {"loss": 0.664, "grad_norm": 0.9415683746337891, "learning_rate": 0.0002, "epoch": 4.7200878155872665, "step": 2150}, {"loss": 0.7283, "grad_norm": 1.0056205987930298, "learning_rate": 0.0002, "epoch": 4.742041712403951, "step": 2160}, {"loss": 0.6845, "grad_norm": 0.768304705619812, "learning_rate": 0.0002, "epoch": 4.763995609220637, "step": 2170}, {"loss": 0.6922, "grad_norm": 1.0604112148284912, "learning_rate": 0.0002, "epoch": 4.785949506037322, "step": 2180}, {"loss": 0.7092, "grad_norm": 1.132864236831665, "learning_rate": 0.0002, "epoch": 4.807903402854007, "step": 2190}, {"loss": 0.6936, "grad_norm": 0.7543689608573914, "learning_rate": 0.0002, "epoch": 4.829857299670691, "step": 2200}, {"loss": 0.6921, "grad_norm": 0.8047362565994263, "learning_rate": 0.0002, "epoch": 4.851811196487376, "step": 2210}, {"loss": 0.6753, "grad_norm": 1.135778546333313, "learning_rate": 0.0002, "epoch": 4.873765093304062, "step": 2220}, {"loss": 0.6443, "grad_norm": 0.9068503379821777, "learning_rate": 0.0002, "epoch": 4.895718990120747, "step": 2230}, {"loss": 0.7419, "grad_norm": 1.822325587272644, "learning_rate": 0.0002, "epoch": 4.9176728869374315, "step": 2240}, {"loss": 0.6436, "grad_norm": 1.1124998331069946, "learning_rate": 0.0002, "epoch": 4.939626783754116, "step": 2250}, {"loss": 0.7423, "grad_norm": 0.818484365940094, "learning_rate": 0.0002, "epoch": 4.961580680570801, "step": 2260}, {"loss": 0.6872, "grad_norm": 1.0057194232940674, "learning_rate": 0.0002, "epoch": 4.983534577387486, "step": 2270}, {"eval_loss": 1.4120490550994873, "eval_runtime": 87.5617, "eval_samples_per_second": 4.922, "eval_steps_per_second": 0.617, "epoch": 4.998902305159166, "step": 2277}, {"loss": 0.5451, "grad_norm": 0.8211547136306763, "learning_rate": 0.0002, "epoch": 5.005488474204172, "step": 2280}, {"loss": 0.4965, "grad_norm": 1.1704130172729492, "learning_rate": 0.0002, "epoch": 5.0274423710208564, "step": 2290}, {"loss": 0.4827, "grad_norm": 1.033539891242981, "learning_rate": 0.0002, "epoch": 5.049396267837541, "step": 2300}, {"loss": 0.447, "grad_norm": 0.8830313682556152, "learning_rate": 0.0002, "epoch": 5.071350164654226, "step": 2310}, {"loss": 0.5502, "grad_norm": 1.160437822341919, "learning_rate": 0.0002, "epoch": 5.093304061470911, "step": 2320}, {"loss": 0.5123, "grad_norm": 0.919956386089325, "learning_rate": 0.0002, "epoch": 5.115257958287596, "step": 2330}, {"loss": 0.4784, "grad_norm": 1.0099905729293823, "learning_rate": 0.0002, "epoch": 5.137211855104281, "step": 2340}, {"loss": 0.5109, "grad_norm": 1.1484816074371338, "learning_rate": 0.0002, "epoch": 5.159165751920966, "step": 2350}, {"loss": 0.5222, "grad_norm": 1.0373470783233643, "learning_rate": 0.0002, "epoch": 5.181119648737651, "step": 2360}, {"loss": 0.5366, "grad_norm": 1.0824922323226929, "learning_rate": 0.0002, "epoch": 5.203073545554336, "step": 2370}, {"loss": 0.5592, "grad_norm": 1.3817942142486572, "learning_rate": 0.0002, "epoch": 5.225027442371021, "step": 2380}, {"loss": 0.504, "grad_norm": 1.197035551071167, "learning_rate": 0.0002, "epoch": 5.246981339187705, "step": 2390}, {"loss": 0.5326, "grad_norm": 1.098778486251831, "learning_rate": 0.0002, "epoch": 5.268935236004391, "step": 2400}, {"loss": 0.5039, "grad_norm": 0.9713385105133057, "learning_rate": 0.0002, "epoch": 5.290889132821076, "step": 2410}, {"loss": 0.5735, "grad_norm": 1.321574330329895, "learning_rate": 0.0002, "epoch": 5.312843029637761, "step": 2420}, {"loss": 0.4777, "grad_norm": 0.9402496218681335, "learning_rate": 0.0002, "epoch": 5.3347969264544455, "step": 2430}, {"loss": 0.5604, "grad_norm": 0.8644852042198181, "learning_rate": 0.0002, "epoch": 5.35675082327113, "step": 2440}, {"loss": 0.5324, "grad_norm": 1.060290813446045, "learning_rate": 0.0002, "epoch": 5.378704720087816, "step": 2450}, {"loss": 0.5366, "grad_norm": 1.0725265741348267, "learning_rate": 0.0002, "epoch": 5.400658616904501, "step": 2460}, {"loss": 0.5469, "grad_norm": 0.9409431219100952, "learning_rate": 0.0002, "epoch": 5.422612513721186, "step": 2470}, {"loss": 0.5186, "grad_norm": 1.1108187437057495, "learning_rate": 0.0002, "epoch": 5.44456641053787, "step": 2480}, {"loss": 0.5312, "grad_norm": 1.0210821628570557, "learning_rate": 0.0002, "epoch": 5.466520307354555, "step": 2490}, {"loss": 0.5016, "grad_norm": 1.110597014427185, "learning_rate": 0.0002, "epoch": 5.48847420417124, "step": 2500}, {"loss": 0.511, "grad_norm": 1.2534265518188477, "learning_rate": 0.0002, "epoch": 5.510428100987926, "step": 2510}, {"loss": 0.6062, "grad_norm": 1.3389744758605957, "learning_rate": 0.0002, "epoch": 5.5323819978046105, "step": 2520}, {"loss": 0.4653, "grad_norm": 0.9520368576049805, "learning_rate": 0.0002, "epoch": 5.554335894621295, "step": 2530}, {"loss": 0.4746, "grad_norm": 1.4737157821655273, "learning_rate": 0.0002, "epoch": 5.57628979143798, "step": 2540}, {"loss": 0.5432, "grad_norm": 1.4143685102462769, "learning_rate": 0.0002, "epoch": 5.598243688254665, "step": 2550}, {"loss": 0.4722, "grad_norm": 1.3573999404907227, "learning_rate": 0.0002, "epoch": 5.620197585071351, "step": 2560}, {"loss": 0.5063, "grad_norm": 0.8475444316864014, "learning_rate": 0.0002, "epoch": 5.642151481888035, "step": 2570}, {"loss": 0.4911, "grad_norm": 1.2670329809188843, "learning_rate": 0.0002, "epoch": 5.66410537870472, "step": 2580}, {"loss": 0.5137, "grad_norm": 0.9688172936439514, "learning_rate": 0.0002, "epoch": 5.686059275521405, "step": 2590}, {"loss": 0.5116, "grad_norm": 1.3652743101119995, "learning_rate": 0.0002, "epoch": 5.70801317233809, "step": 2600}, {"loss": 0.5661, "grad_norm": 1.1475377082824707, "learning_rate": 0.0002, "epoch": 5.729967069154775, "step": 2610}, {"loss": 0.567, "grad_norm": 1.3105946779251099, "learning_rate": 0.0002, "epoch": 5.75192096597146, "step": 2620}, {"loss": 0.4964, "grad_norm": 0.920238196849823, "learning_rate": 0.0002, "epoch": 5.773874862788145, "step": 2630}, {"loss": 0.5473, "grad_norm": 1.0981792211532593, "learning_rate": 0.0002, "epoch": 5.79582875960483, "step": 2640}, {"loss": 0.5132, "grad_norm": 1.0734144449234009, "learning_rate": 0.0002, "epoch": 5.817782656421515, "step": 2650}, {"loss": 0.5404, "grad_norm": 1.0541702508926392, "learning_rate": 0.0002, "epoch": 5.8397365532381995, "step": 2660}, {"loss": 0.5056, "grad_norm": 1.0913143157958984, "learning_rate": 0.0002, "epoch": 5.861690450054885, "step": 2670}, {"loss": 0.5425, "grad_norm": 1.0431408882141113, "learning_rate": 0.0002, "epoch": 5.88364434687157, "step": 2680}, {"loss": 0.5398, "grad_norm": 1.3515729904174805, "learning_rate": 0.0002, "epoch": 5.905598243688255, "step": 2690}, {"loss": 0.5936, "grad_norm": 1.3153903484344482, "learning_rate": 0.0002, "epoch": 5.92755214050494, "step": 2700}, {"loss": 0.5643, "grad_norm": 1.024109125137329, "learning_rate": 0.0002, "epoch": 5.949506037321624, "step": 2710}, {"loss": 0.5143, "grad_norm": 1.0308483839035034, "learning_rate": 0.0002, "epoch": 5.971459934138309, "step": 2720}, {"loss": 0.4835, "grad_norm": 0.8329401016235352, "learning_rate": 0.0002, "epoch": 5.993413830954994, "step": 2730}, {"eval_loss": 1.510581612586975, "eval_runtime": 89.0047, "eval_samples_per_second": 4.842, "eval_steps_per_second": 0.607, "epoch": 6.0, "step": 2733}, {"loss": 0.4282, "grad_norm": 1.1903921365737915, "learning_rate": 0.0002, "epoch": 6.01536772777168, "step": 2740}, {"loss": 0.3844, "grad_norm": 1.0170859098434448, "learning_rate": 0.0002, "epoch": 6.0373216245883645, "step": 2750}, {"loss": 0.4116, "grad_norm": 1.269655704498291, "learning_rate": 0.0002, "epoch": 6.059275521405049, "step": 2760}, {"loss": 0.381, "grad_norm": 1.1271249055862427, "learning_rate": 0.0002, "epoch": 6.081229418221734, "step": 2770}, {"loss": 0.391, "grad_norm": 1.0269793272018433, "learning_rate": 0.0002, "epoch": 6.103183315038419, "step": 2780}, {"loss": 0.3896, "grad_norm": 1.1622686386108398, "learning_rate": 0.0002, "epoch": 6.125137211855105, "step": 2790}, {"loss": 0.3907, "grad_norm": 1.3457845449447632, "learning_rate": 0.0002, "epoch": 6.147091108671789, "step": 2800}, {"loss": 0.3447, "grad_norm": 1.008620262145996, "learning_rate": 0.0002, "epoch": 6.169045005488474, "step": 2810}, {"loss": 0.3437, "grad_norm": 0.9964058995246887, "learning_rate": 0.0002, "epoch": 6.190998902305159, "step": 2820}, {"loss": 0.4073, "grad_norm": 1.265552043914795, "learning_rate": 0.0002, "epoch": 6.212952799121844, "step": 2830}, {"loss": 0.4199, "grad_norm": 1.0481451749801636, "learning_rate": 0.0002, "epoch": 6.234906695938529, "step": 2840}, {"loss": 0.4243, "grad_norm": 1.3813395500183105, "learning_rate": 0.0002, "epoch": 6.256860592755214, "step": 2850}, {"loss": 0.4039, "grad_norm": 1.1307486295700073, "learning_rate": 0.0002, "epoch": 6.278814489571899, "step": 2860}, {"loss": 0.3665, "grad_norm": 1.122252106666565, "learning_rate": 0.0002, "epoch": 6.300768386388584, "step": 2870}, {"loss": 0.4377, "grad_norm": 0.9570856094360352, "learning_rate": 0.0002, "epoch": 6.322722283205269, "step": 2880}, {"loss": 0.3762, "grad_norm": 1.429248332977295, "learning_rate": 0.0002, "epoch": 6.3446761800219535, "step": 2890}, {"loss": 0.3746, "grad_norm": 1.228832483291626, "learning_rate": 0.0002, "epoch": 6.366630076838639, "step": 2900}, {"loss": 0.3714, "grad_norm": 0.9634972810745239, "learning_rate": 0.0002, "epoch": 6.388583973655324, "step": 2910}, {"loss": 0.3856, "grad_norm": 1.392120599746704, "learning_rate": 0.0002, "epoch": 6.410537870472009, "step": 2920}, {"loss": 0.4395, "grad_norm": 1.0452295541763306, "learning_rate": 0.0002, "epoch": 6.432491767288694, "step": 2930}, {"loss": 0.4559, "grad_norm": 0.9953978657722473, "learning_rate": 0.0002, "epoch": 6.4544456641053785, "step": 2940}, {"loss": 0.4108, "grad_norm": 1.090386986732483, "learning_rate": 0.0002, "epoch": 6.476399560922063, "step": 2950}, {"loss": 0.4059, "grad_norm": 1.2177232503890991, "learning_rate": 0.0002, "epoch": 6.498353457738749, "step": 2960}, {"loss": 0.4403, "grad_norm": 0.8435868620872498, "learning_rate": 0.0002, "epoch": 6.520307354555434, "step": 2970}, {"loss": 0.4143, "grad_norm": 1.0110384225845337, "learning_rate": 0.0002, "epoch": 6.542261251372119, "step": 2980}, {"loss": 0.4396, "grad_norm": 0.8551704287528992, "learning_rate": 0.0002, "epoch": 6.564215148188803, "step": 2990}, {"loss": 0.3908, "grad_norm": 1.2663729190826416, "learning_rate": 0.0002, "epoch": 6.586169045005488, "step": 3000}, {"loss": 0.3927, "grad_norm": 1.2262762784957886, "learning_rate": 0.0002, "epoch": 6.608122941822174, "step": 3010}, {"loss": 0.4183, "grad_norm": 1.3794647455215454, "learning_rate": 0.0002, "epoch": 6.630076838638859, "step": 3020}, {"loss": 0.3903, "grad_norm": 0.9994757175445557, "learning_rate": 0.0002, "epoch": 6.6520307354555435, "step": 3030}, {"loss": 0.4083, "grad_norm": 1.067501187324524, "learning_rate": 0.0002, "epoch": 6.673984632272228, "step": 3040}, {"loss": 0.4551, "grad_norm": 1.1194695234298706, "learning_rate": 0.0002, "epoch": 6.695938529088913, "step": 3050}, {"loss": 0.4276, "grad_norm": 1.572695255279541, "learning_rate": 0.0002, "epoch": 6.717892425905598, "step": 3060}, {"loss": 0.3681, "grad_norm": 1.063094139099121, "learning_rate": 0.0002, "epoch": 6.739846322722284, "step": 3070}, {"loss": 0.3656, "grad_norm": 1.2257463932037354, "learning_rate": 0.0002, "epoch": 6.761800219538968, "step": 3080}, {"loss": 0.4504, "grad_norm": 1.259731411933899, "learning_rate": 0.0002, "epoch": 6.783754116355653, "step": 3090}, {"loss": 0.4067, "grad_norm": 1.3234009742736816, "learning_rate": 0.0002, "epoch": 6.805708013172338, "step": 3100}, {"loss": 0.4913, "grad_norm": 1.4324477910995483, "learning_rate": 0.0002, "epoch": 6.827661909989023, "step": 3110}, {"loss": 0.4408, "grad_norm": 1.4183896780014038, "learning_rate": 0.0002, "epoch": 6.8496158068057085, "step": 3120}, {"loss": 0.4517, "grad_norm": 1.1369833946228027, "learning_rate": 0.0002, "epoch": 6.871569703622393, "step": 3130}, {"loss": 0.458, "grad_norm": 1.2804654836654663, "learning_rate": 0.0002, "epoch": 6.893523600439078, "step": 3140}, {"loss": 0.4616, "grad_norm": 1.535305380821228, "learning_rate": 0.0002, "epoch": 6.915477497255763, "step": 3150}, {"loss": 0.4178, "grad_norm": 1.2820420265197754, "learning_rate": 0.0002, "epoch": 6.937431394072448, "step": 3160}, {"loss": 0.442, "grad_norm": 1.1014128923416138, "learning_rate": 0.0002, "epoch": 6.9593852908891325, "step": 3170}, {"loss": 0.4379, "grad_norm": 0.9979909658432007, "learning_rate": 0.0002, "epoch": 6.981339187705817, "step": 3180}]} +{"epoch": 7.991218441273326, "step": 3640, "epoch_duration": 1551.8190340995789, "total_accumulated_duration": 12424.70075583458, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7568.4541015625}, "peak_memory_usage": {"GPU_0": 13792.75439453125}, "avg_memory_reserved": {"GPU_0": 17416.0}, "peak_memory_reserved": {"GPU_0": 17416.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 1.9887, "grad_norm": 0.6144012212753296, "learning_rate": 0.0002, "epoch": 0.021953896816684963, "step": 10}, {"loss": 1.6882, "grad_norm": 0.5587220788002014, "learning_rate": 0.0002, "epoch": 0.043907793633369926, "step": 20}, {"loss": 1.399, "grad_norm": 0.43262454867362976, "learning_rate": 0.0002, "epoch": 0.06586169045005488, "step": 30}, {"loss": 1.4675, "grad_norm": 0.4783053994178772, "learning_rate": 0.0002, "epoch": 0.08781558726673985, "step": 40}, {"loss": 1.1771, "grad_norm": 0.44338956475257874, "learning_rate": 0.0002, "epoch": 0.10976948408342481, "step": 50}, {"loss": 1.3706, "grad_norm": 0.7255092263221741, "learning_rate": 0.0002, "epoch": 0.13172338090010977, "step": 60}, {"loss": 1.2601, "grad_norm": 0.46073833107948303, "learning_rate": 0.0002, "epoch": 0.15367727771679474, "step": 70}, {"loss": 1.3049, "grad_norm": 0.6698123216629028, "learning_rate": 0.0002, "epoch": 0.1756311745334797, "step": 80}, {"loss": 1.2975, "grad_norm": 0.4190150201320648, "learning_rate": 0.0002, "epoch": 0.19758507135016465, "step": 90}, {"loss": 1.2797, "grad_norm": 0.4110015034675598, "learning_rate": 0.0002, "epoch": 0.21953896816684962, "step": 100}, {"loss": 1.2896, "grad_norm": 0.33374306559562683, "learning_rate": 0.0002, "epoch": 0.2414928649835346, "step": 110}, {"loss": 1.2268, "grad_norm": 0.3061307370662689, "learning_rate": 0.0002, "epoch": 0.26344676180021953, "step": 120}, {"loss": 1.376, "grad_norm": 0.4386885166168213, "learning_rate": 0.0002, "epoch": 0.2854006586169045, "step": 130}, {"loss": 1.1814, "grad_norm": 0.40116462111473083, "learning_rate": 0.0002, "epoch": 0.30735455543358947, "step": 140}, {"loss": 1.2592, "grad_norm": 0.5887949466705322, "learning_rate": 0.0002, "epoch": 0.32930845225027444, "step": 150}, {"loss": 1.2372, "grad_norm": 0.3401573896408081, "learning_rate": 0.0002, "epoch": 0.3512623490669594, "step": 160}, {"loss": 1.1901, "grad_norm": 0.3288364112377167, "learning_rate": 0.0002, "epoch": 0.3732162458836443, "step": 170}, {"loss": 1.2335, "grad_norm": 0.4853297472000122, "learning_rate": 0.0002, "epoch": 0.3951701427003293, "step": 180}, {"loss": 1.227, "grad_norm": 2.6253697872161865, "learning_rate": 0.0002, "epoch": 0.41712403951701427, "step": 190}, {"loss": 1.2673, "grad_norm": 0.5598543286323547, "learning_rate": 0.0002, "epoch": 0.43907793633369924, "step": 200}, {"loss": 1.3459, "grad_norm": 0.4046548902988434, "learning_rate": 0.0002, "epoch": 0.4610318331503842, "step": 210}, {"loss": 1.265, "grad_norm": 0.3686952590942383, "learning_rate": 0.0002, "epoch": 0.4829857299670692, "step": 220}, {"loss": 1.1364, "grad_norm": 0.42458799481391907, "learning_rate": 0.0002, "epoch": 0.5049396267837541, "step": 230}, {"loss": 1.2094, "grad_norm": 0.5839895009994507, "learning_rate": 0.0002, "epoch": 0.5268935236004391, "step": 240}, {"loss": 1.2073, "grad_norm": 0.408288836479187, "learning_rate": 0.0002, "epoch": 0.5488474204171241, "step": 250}, {"loss": 1.3121, "grad_norm": 0.45887550711631775, "learning_rate": 0.0002, "epoch": 0.570801317233809, "step": 260}, {"loss": 1.2257, "grad_norm": 0.5440235733985901, "learning_rate": 0.0002, "epoch": 0.5927552140504939, "step": 270}, {"loss": 1.1003, "grad_norm": 0.3725181519985199, "learning_rate": 0.0002, "epoch": 0.6147091108671789, "step": 280}, {"loss": 1.1538, "grad_norm": 0.4309018850326538, "learning_rate": 0.0002, "epoch": 0.6366630076838639, "step": 290}, {"loss": 1.2097, "grad_norm": 0.31488674879074097, "learning_rate": 0.0002, "epoch": 0.6586169045005489, "step": 300}, {"loss": 1.1689, "grad_norm": 0.34194841980934143, "learning_rate": 0.0002, "epoch": 0.6805708013172338, "step": 310}, {"loss": 1.2579, "grad_norm": 0.3407684862613678, "learning_rate": 0.0002, "epoch": 0.7025246981339188, "step": 320}, {"loss": 1.1144, "grad_norm": 0.2985728085041046, "learning_rate": 0.0002, "epoch": 0.7244785949506037, "step": 330}, {"loss": 1.2056, "grad_norm": 0.42316871881484985, "learning_rate": 0.0002, "epoch": 0.7464324917672887, "step": 340}, {"loss": 1.1753, "grad_norm": 0.3124258816242218, "learning_rate": 0.0002, "epoch": 0.7683863885839737, "step": 350}, {"loss": 1.2547, "grad_norm": 0.7727567553520203, "learning_rate": 0.0002, "epoch": 0.7903402854006586, "step": 360}, {"loss": 1.124, "grad_norm": 0.363765686750412, "learning_rate": 0.0002, "epoch": 0.8122941822173436, "step": 370}, {"loss": 1.1302, "grad_norm": 0.35582536458969116, "learning_rate": 0.0002, "epoch": 0.8342480790340285, "step": 380}, {"loss": 1.1787, "grad_norm": 0.31982025504112244, "learning_rate": 0.0002, "epoch": 0.8562019758507134, "step": 390}, {"loss": 1.2056, "grad_norm": 0.34978964924812317, "learning_rate": 0.0002, "epoch": 0.8781558726673985, "step": 400}, {"loss": 1.3577, "grad_norm": 0.8346716165542603, "learning_rate": 0.0002, "epoch": 0.9001097694840834, "step": 410}, {"loss": 1.1029, "grad_norm": 0.31984028220176697, "learning_rate": 0.0002, "epoch": 0.9220636663007684, "step": 420}, {"loss": 1.0967, "grad_norm": 0.32078951597213745, "learning_rate": 0.0002, "epoch": 0.9440175631174533, "step": 430}, {"loss": 1.0936, "grad_norm": 0.3417500853538513, "learning_rate": 0.0002, "epoch": 0.9659714599341384, "step": 440}, {"loss": 1.3412, "grad_norm": 0.42359477281570435, "learning_rate": 0.0002, "epoch": 0.9879253567508233, "step": 450}, {"eval_loss": 1.2201528549194336, "eval_runtime": 87.152, "eval_samples_per_second": 4.945, "eval_steps_per_second": 0.62, "epoch": 0.9989023051591658, "step": 455}, {"loss": 1.1909, "grad_norm": 0.37914523482322693, "learning_rate": 0.0002, "epoch": 1.0098792535675083, "step": 460}, {"loss": 1.0948, "grad_norm": 0.43655872344970703, "learning_rate": 0.0002, "epoch": 1.031833150384193, "step": 470}, {"loss": 1.0873, "grad_norm": 0.3673796057701111, "learning_rate": 0.0002, "epoch": 1.0537870472008781, "step": 480}, {"loss": 1.0483, "grad_norm": 0.37673917412757874, "learning_rate": 0.0002, "epoch": 1.0757409440175631, "step": 490}, {"loss": 1.0799, "grad_norm": 0.2893829345703125, "learning_rate": 0.0002, "epoch": 1.0976948408342482, "step": 500}, {"loss": 1.1847, "grad_norm": 0.5551970601081848, "learning_rate": 0.0002, "epoch": 1.119648737650933, "step": 510}, {"loss": 1.0885, "grad_norm": 0.442104309797287, "learning_rate": 0.0002, "epoch": 1.141602634467618, "step": 520}, {"loss": 1.1766, "grad_norm": 0.4035094976425171, "learning_rate": 0.0002, "epoch": 1.163556531284303, "step": 530}, {"loss": 1.0282, "grad_norm": 0.47009000182151794, "learning_rate": 0.0002, "epoch": 1.1855104281009878, "step": 540}, {"loss": 1.2625, "grad_norm": 0.4118749797344208, "learning_rate": 0.0002, "epoch": 1.2074643249176729, "step": 550}, {"loss": 1.0988, "grad_norm": 0.35173165798187256, "learning_rate": 0.0002, "epoch": 1.2294182217343579, "step": 560}, {"loss": 1.0498, "grad_norm": 0.7024672031402588, "learning_rate": 0.0002, "epoch": 1.2513721185510427, "step": 570}, {"loss": 1.1339, "grad_norm": 0.42657527327537537, "learning_rate": 0.0002, "epoch": 1.2733260153677277, "step": 580}, {"loss": 1.0545, "grad_norm": 0.3815029561519623, "learning_rate": 0.0002, "epoch": 1.2952799121844127, "step": 590}, {"loss": 1.1528, "grad_norm": 0.7031055688858032, "learning_rate": 0.0002, "epoch": 1.3172338090010978, "step": 600}, {"loss": 1.1347, "grad_norm": 0.393911212682724, "learning_rate": 0.0002, "epoch": 1.3391877058177828, "step": 610}, {"loss": 1.1901, "grad_norm": 0.5077702403068542, "learning_rate": 0.0002, "epoch": 1.3611416026344676, "step": 620}, {"loss": 1.1251, "grad_norm": 2.330033302307129, "learning_rate": 0.0002, "epoch": 1.3830954994511526, "step": 630}, {"loss": 1.0477, "grad_norm": 0.35322949290275574, "learning_rate": 0.0002, "epoch": 1.4050493962678376, "step": 640}, {"loss": 1.14, "grad_norm": 0.44401052594184875, "learning_rate": 0.0002, "epoch": 1.4270032930845225, "step": 650}, {"loss": 1.0318, "grad_norm": 0.35945481061935425, "learning_rate": 0.0002, "epoch": 1.4489571899012075, "step": 660}, {"loss": 1.1988, "grad_norm": 0.3058856129646301, "learning_rate": 0.0002, "epoch": 1.4709110867178925, "step": 670}, {"loss": 1.1545, "grad_norm": 0.7067602872848511, "learning_rate": 0.0002, "epoch": 1.4928649835345773, "step": 680}, {"loss": 1.0925, "grad_norm": 0.4219357371330261, "learning_rate": 0.0002, "epoch": 1.5148188803512623, "step": 690}, {"loss": 1.1622, "grad_norm": 0.5970841646194458, "learning_rate": 0.0002, "epoch": 1.5367727771679474, "step": 700}, {"loss": 1.0803, "grad_norm": 0.4381934404373169, "learning_rate": 0.0002, "epoch": 1.5587266739846322, "step": 710}, {"loss": 1.0961, "grad_norm": 0.4101450443267822, "learning_rate": 0.0002, "epoch": 1.5806805708013172, "step": 720}, {"loss": 1.0474, "grad_norm": 0.3657490015029907, "learning_rate": 0.0002, "epoch": 1.6026344676180022, "step": 730}, {"loss": 1.0936, "grad_norm": 0.36240628361701965, "learning_rate": 0.0002, "epoch": 1.624588364434687, "step": 740}, {"loss": 1.0489, "grad_norm": 0.4103568494319916, "learning_rate": 0.0002, "epoch": 1.6465422612513723, "step": 750}, {"loss": 1.0919, "grad_norm": 0.3138505816459656, "learning_rate": 0.0002, "epoch": 1.668496158068057, "step": 760}, {"loss": 1.2308, "grad_norm": 0.41215717792510986, "learning_rate": 0.0002, "epoch": 1.690450054884742, "step": 770}, {"loss": 1.1659, "grad_norm": 0.4589519202709198, "learning_rate": 0.0002, "epoch": 1.7124039517014271, "step": 780}, {"loss": 1.0913, "grad_norm": 0.4049508571624756, "learning_rate": 0.0002, "epoch": 1.734357848518112, "step": 790}, {"loss": 1.1329, "grad_norm": 0.48557212948799133, "learning_rate": 0.0002, "epoch": 1.756311745334797, "step": 800}, {"loss": 1.0729, "grad_norm": 0.5331754088401794, "learning_rate": 0.0002, "epoch": 1.778265642151482, "step": 810}, {"loss": 1.1452, "grad_norm": 0.3853185772895813, "learning_rate": 0.0002, "epoch": 1.8002195389681668, "step": 820}, {"loss": 1.1061, "grad_norm": 0.424062579870224, "learning_rate": 0.0002, "epoch": 1.8221734357848518, "step": 830}, {"loss": 1.1104, "grad_norm": 0.3418445289134979, "learning_rate": 0.0002, "epoch": 1.8441273326015368, "step": 840}, {"loss": 1.0546, "grad_norm": 0.4045565128326416, "learning_rate": 0.0002, "epoch": 1.8660812294182216, "step": 850}, {"loss": 1.1608, "grad_norm": 0.42155781388282776, "learning_rate": 0.0002, "epoch": 1.8880351262349067, "step": 860}, {"loss": 1.0628, "grad_norm": 0.40554770827293396, "learning_rate": 0.0002, "epoch": 1.9099890230515917, "step": 870}, {"loss": 1.1609, "grad_norm": 0.42644748091697693, "learning_rate": 0.0002, "epoch": 1.9319429198682765, "step": 880}, {"loss": 1.1132, "grad_norm": 0.45260652899742126, "learning_rate": 0.0002, "epoch": 1.9538968166849617, "step": 890}, {"loss": 1.048, "grad_norm": 0.4114069938659668, "learning_rate": 0.0002, "epoch": 1.9758507135016465, "step": 900}, {"loss": 1.1941, "grad_norm": 0.375802218914032, "learning_rate": 0.0002, "epoch": 1.9978046103183313, "step": 910}, {"eval_loss": 1.205152153968811, "eval_runtime": 86.8795, "eval_samples_per_second": 4.961, "eval_steps_per_second": 0.622, "epoch": 2.0, "step": 911}, {"loss": 1.0897, "grad_norm": 0.47718703746795654, "learning_rate": 0.0002, "epoch": 2.0197585071350166, "step": 920}, {"loss": 1.0329, "grad_norm": 0.45628082752227783, "learning_rate": 0.0002, "epoch": 2.0417124039517014, "step": 930}, {"loss": 1.0538, "grad_norm": 0.5933247804641724, "learning_rate": 0.0002, "epoch": 2.063666300768386, "step": 940}, {"loss": 1.0152, "grad_norm": 0.5355812907218933, "learning_rate": 0.0002, "epoch": 2.0856201975850714, "step": 950}, {"loss": 1.0726, "grad_norm": 0.5860010385513306, "learning_rate": 0.0002, "epoch": 2.1075740944017562, "step": 960}, {"loss": 1.025, "grad_norm": 0.7471673488616943, "learning_rate": 0.0002, "epoch": 2.129527991218441, "step": 970}, {"loss": 1.0247, "grad_norm": 2.0918211936950684, "learning_rate": 0.0002, "epoch": 2.1514818880351263, "step": 980}, {"loss": 0.8947, "grad_norm": 0.4021058678627014, "learning_rate": 0.0002, "epoch": 2.173435784851811, "step": 990}, {"loss": 0.8875, "grad_norm": 0.564975380897522, "learning_rate": 0.0002, "epoch": 2.1953896816684964, "step": 1000}, {"loss": 1.0264, "grad_norm": 0.46260079741477966, "learning_rate": 0.0002, "epoch": 2.217343578485181, "step": 1010}, {"loss": 0.9265, "grad_norm": 0.4791034460067749, "learning_rate": 0.0002, "epoch": 2.239297475301866, "step": 1020}, {"loss": 0.8869, "grad_norm": 0.5272043943405151, "learning_rate": 0.0002, "epoch": 2.261251372118551, "step": 1030}, {"loss": 1.0007, "grad_norm": 0.5221094489097595, "learning_rate": 0.0002, "epoch": 2.283205268935236, "step": 1040}, {"loss": 0.9472, "grad_norm": 0.558032751083374, "learning_rate": 0.0002, "epoch": 2.305159165751921, "step": 1050}, {"loss": 0.9617, "grad_norm": 0.5905590653419495, "learning_rate": 0.0002, "epoch": 2.327113062568606, "step": 1060}, {"loss": 0.9592, "grad_norm": 0.5308699607849121, "learning_rate": 0.0002, "epoch": 2.349066959385291, "step": 1070}, {"loss": 1.0646, "grad_norm": 0.6375027894973755, "learning_rate": 0.0002, "epoch": 2.3710208562019757, "step": 1080}, {"loss": 1.0354, "grad_norm": 0.7439115643501282, "learning_rate": 0.0002, "epoch": 2.392974753018661, "step": 1090}, {"loss": 1.0212, "grad_norm": 0.41945117712020874, "learning_rate": 0.0002, "epoch": 2.4149286498353457, "step": 1100}, {"loss": 0.9609, "grad_norm": 0.4891968369483948, "learning_rate": 0.0002, "epoch": 2.436882546652031, "step": 1110}, {"loss": 0.9829, "grad_norm": 0.4686794579029083, "learning_rate": 0.0002, "epoch": 2.4588364434687158, "step": 1120}, {"loss": 0.8919, "grad_norm": 0.5204509496688843, "learning_rate": 0.0002, "epoch": 2.4807903402854006, "step": 1130}, {"loss": 0.8983, "grad_norm": 0.6779005527496338, "learning_rate": 0.0002, "epoch": 2.5027442371020854, "step": 1140}, {"loss": 0.9733, "grad_norm": 0.682621955871582, "learning_rate": 0.0002, "epoch": 2.5246981339187706, "step": 1150}, {"loss": 1.051, "grad_norm": 0.5744376182556152, "learning_rate": 0.0002, "epoch": 2.5466520307354554, "step": 1160}, {"loss": 0.8764, "grad_norm": 0.49954667687416077, "learning_rate": 0.0002, "epoch": 2.5686059275521407, "step": 1170}, {"loss": 0.9896, "grad_norm": 0.4761793315410614, "learning_rate": 0.0002, "epoch": 2.5905598243688255, "step": 1180}, {"loss": 0.8593, "grad_norm": 0.548299252986908, "learning_rate": 0.0002, "epoch": 2.6125137211855103, "step": 1190}, {"loss": 1.0017, "grad_norm": 0.5771360993385315, "learning_rate": 0.0002, "epoch": 2.6344676180021955, "step": 1200}, {"loss": 0.9858, "grad_norm": 0.5543120503425598, "learning_rate": 0.0002, "epoch": 2.6564215148188803, "step": 1210}, {"loss": 0.9565, "grad_norm": 0.7564870715141296, "learning_rate": 0.0002, "epoch": 2.6783754116355656, "step": 1220}, {"loss": 0.9753, "grad_norm": 0.8222362399101257, "learning_rate": 0.0002, "epoch": 2.7003293084522504, "step": 1230}, {"loss": 1.0079, "grad_norm": 0.6894469857215881, "learning_rate": 0.0002, "epoch": 2.722283205268935, "step": 1240}, {"loss": 1.0106, "grad_norm": 0.6121546030044556, "learning_rate": 0.0002, "epoch": 2.74423710208562, "step": 1250}, {"loss": 0.9801, "grad_norm": 0.521809995174408, "learning_rate": 0.0002, "epoch": 2.7661909989023052, "step": 1260}, {"loss": 1.0196, "grad_norm": 0.766968309879303, "learning_rate": 0.0002, "epoch": 2.78814489571899, "step": 1270}, {"loss": 0.976, "grad_norm": 0.522331714630127, "learning_rate": 0.0002, "epoch": 2.8100987925356753, "step": 1280}, {"loss": 0.8866, "grad_norm": 0.42923519015312195, "learning_rate": 0.0002, "epoch": 2.83205268935236, "step": 1290}, {"loss": 0.9049, "grad_norm": 0.47810837626457214, "learning_rate": 0.0002, "epoch": 2.854006586169045, "step": 1300}, {"loss": 1.0291, "grad_norm": 1.0958846807479858, "learning_rate": 0.0002, "epoch": 2.8759604829857297, "step": 1310}, {"loss": 0.8724, "grad_norm": 0.4755791127681732, "learning_rate": 0.0002, "epoch": 2.897914379802415, "step": 1320}, {"loss": 0.9317, "grad_norm": 0.5575157403945923, "learning_rate": 0.0002, "epoch": 2.9198682766190998, "step": 1330}, {"loss": 1.0131, "grad_norm": 0.5938076376914978, "learning_rate": 0.0002, "epoch": 2.941822173435785, "step": 1340}, {"loss": 0.9857, "grad_norm": 0.5751763582229614, "learning_rate": 0.0002, "epoch": 2.96377607025247, "step": 1350}, {"loss": 1.0212, "grad_norm": 0.5590175986289978, "learning_rate": 0.0002, "epoch": 2.9857299670691546, "step": 1360}, {"eval_loss": 1.2402944564819336, "eval_runtime": 88.822, "eval_samples_per_second": 4.852, "eval_steps_per_second": 0.608, "epoch": 2.9989023051591657, "step": 1366}, {"loss": 0.844, "grad_norm": 0.463539719581604, "learning_rate": 0.0002, "epoch": 3.00768386388584, "step": 1370}, {"loss": 0.8955, "grad_norm": 0.6667885780334473, "learning_rate": 0.0002, "epoch": 3.0296377607025247, "step": 1380}, {"loss": 0.8765, "grad_norm": 0.5849342942237854, "learning_rate": 0.0002, "epoch": 3.0515916575192095, "step": 1390}, {"loss": 0.7808, "grad_norm": 0.5571770668029785, "learning_rate": 0.0002, "epoch": 3.0735455543358947, "step": 1400}, {"loss": 0.7448, "grad_norm": 0.5761234164237976, "learning_rate": 0.0002, "epoch": 3.0954994511525795, "step": 1410}, {"loss": 0.7854, "grad_norm": 0.7277371883392334, "learning_rate": 0.0002, "epoch": 3.1174533479692643, "step": 1420}, {"loss": 0.817, "grad_norm": 0.5190334320068359, "learning_rate": 0.0002, "epoch": 3.1394072447859496, "step": 1430}, {"loss": 0.7548, "grad_norm": 0.632939875125885, "learning_rate": 0.0002, "epoch": 3.1613611416026344, "step": 1440}, {"loss": 0.8447, "grad_norm": 0.7229540944099426, "learning_rate": 0.0002, "epoch": 3.1833150384193196, "step": 1450}, {"loss": 0.8595, "grad_norm": 0.7584632039070129, "learning_rate": 0.0002, "epoch": 3.2052689352360044, "step": 1460}, {"loss": 0.7456, "grad_norm": 0.6546088457107544, "learning_rate": 0.0002, "epoch": 3.2272228320526892, "step": 1470}, {"loss": 0.8531, "grad_norm": 0.8116684556007385, "learning_rate": 0.0002, "epoch": 3.2491767288693745, "step": 1480}, {"loss": 0.9272, "grad_norm": 0.6206557750701904, "learning_rate": 0.0002, "epoch": 3.2711306256860593, "step": 1490}, {"loss": 0.7972, "grad_norm": 0.5393369197845459, "learning_rate": 0.0002, "epoch": 3.293084522502744, "step": 1500}, {"loss": 0.7614, "grad_norm": 0.7006453275680542, "learning_rate": 0.0002, "epoch": 3.3150384193194293, "step": 1510}, {"loss": 0.7358, "grad_norm": 0.95253986120224, "learning_rate": 0.0002, "epoch": 3.336992316136114, "step": 1520}, {"loss": 0.8131, "grad_norm": 0.8138132095336914, "learning_rate": 0.0002, "epoch": 3.358946212952799, "step": 1530}, {"loss": 0.7738, "grad_norm": 0.7974302172660828, "learning_rate": 0.0002, "epoch": 3.380900109769484, "step": 1540}, {"loss": 0.8161, "grad_norm": 0.6694685220718384, "learning_rate": 0.0002, "epoch": 3.402854006586169, "step": 1550}, {"loss": 0.8503, "grad_norm": 0.908634603023529, "learning_rate": 0.0002, "epoch": 3.4248079034028542, "step": 1560}, {"loss": 0.7609, "grad_norm": 0.5625193119049072, "learning_rate": 0.0002, "epoch": 3.446761800219539, "step": 1570}, {"loss": 0.7658, "grad_norm": 0.779325544834137, "learning_rate": 0.0002, "epoch": 3.468715697036224, "step": 1580}, {"loss": 0.7485, "grad_norm": 0.7133058905601501, "learning_rate": 0.0002, "epoch": 3.4906695938529086, "step": 1590}, {"loss": 0.8847, "grad_norm": 0.6741108298301697, "learning_rate": 0.0002, "epoch": 3.512623490669594, "step": 1600}, {"loss": 0.7838, "grad_norm": 0.696982204914093, "learning_rate": 0.0002, "epoch": 3.5345773874862787, "step": 1610}, {"loss": 0.7195, "grad_norm": 0.7946001291275024, "learning_rate": 0.0002, "epoch": 3.556531284302964, "step": 1620}, {"loss": 0.7772, "grad_norm": 0.6313548684120178, "learning_rate": 0.0002, "epoch": 3.5784851811196488, "step": 1630}, {"loss": 0.8267, "grad_norm": 0.9246852397918701, "learning_rate": 0.0002, "epoch": 3.6004390779363336, "step": 1640}, {"loss": 0.779, "grad_norm": 0.6615420579910278, "learning_rate": 0.0002, "epoch": 3.622392974753019, "step": 1650}, {"loss": 0.883, "grad_norm": 1.5050125122070312, "learning_rate": 0.0002, "epoch": 3.6443468715697036, "step": 1660}, {"loss": 0.7763, "grad_norm": 0.5023762583732605, "learning_rate": 0.0002, "epoch": 3.666300768386389, "step": 1670}, {"loss": 0.8173, "grad_norm": 0.6289586424827576, "learning_rate": 0.0002, "epoch": 3.6882546652030737, "step": 1680}, {"loss": 0.9028, "grad_norm": 1.050397515296936, "learning_rate": 0.0002, "epoch": 3.7102085620197585, "step": 1690}, {"loss": 0.7747, "grad_norm": 0.6785626411437988, "learning_rate": 0.0002, "epoch": 3.7321624588364433, "step": 1700}, {"loss": 0.9215, "grad_norm": 0.7565035223960876, "learning_rate": 0.0002, "epoch": 3.7541163556531285, "step": 1710}, {"loss": 0.7913, "grad_norm": 0.7775155901908875, "learning_rate": 0.0002, "epoch": 3.7760702524698133, "step": 1720}, {"loss": 0.8081, "grad_norm": 0.765260636806488, "learning_rate": 0.0002, "epoch": 3.7980241492864986, "step": 1730}, {"loss": 0.9231, "grad_norm": 0.7982407808303833, "learning_rate": 0.0002, "epoch": 3.8199780461031834, "step": 1740}, {"loss": 0.7755, "grad_norm": 0.7431730628013611, "learning_rate": 0.0002, "epoch": 3.841931942919868, "step": 1750}, {"loss": 0.9236, "grad_norm": 0.9758927226066589, "learning_rate": 0.0002, "epoch": 3.863885839736553, "step": 1760}, {"loss": 0.9118, "grad_norm": 0.8014697432518005, "learning_rate": 0.0002, "epoch": 3.885839736553238, "step": 1770}, {"loss": 0.7503, "grad_norm": 0.7212756276130676, "learning_rate": 0.0002, "epoch": 3.907793633369923, "step": 1780}, {"loss": 0.7978, "grad_norm": 0.584318220615387, "learning_rate": 0.0002, "epoch": 3.9297475301866083, "step": 1790}, {"loss": 0.7894, "grad_norm": 0.7612535953521729, "learning_rate": 0.0002, "epoch": 3.951701427003293, "step": 1800}, {"loss": 0.8589, "grad_norm": 0.735103189945221, "learning_rate": 0.0002, "epoch": 3.973655323819978, "step": 1810}, {"loss": 0.8192, "grad_norm": 0.9074980020523071, "learning_rate": 0.0002, "epoch": 3.995609220636663, "step": 1820}, {"eval_loss": 1.279890537261963, "eval_runtime": 88.8969, "eval_samples_per_second": 4.848, "eval_steps_per_second": 0.607, "epoch": 4.0, "step": 1822}, {"loss": 0.7312, "grad_norm": 0.9290254712104797, "learning_rate": 0.0002, "epoch": 4.017563117453348, "step": 1830}, {"loss": 0.6896, "grad_norm": 0.723889946937561, "learning_rate": 0.0002, "epoch": 4.039517014270033, "step": 1840}, {"loss": 0.632, "grad_norm": 0.5906972289085388, "learning_rate": 0.0002, "epoch": 4.061470911086718, "step": 1850}, {"loss": 0.6594, "grad_norm": 0.8078910708427429, "learning_rate": 0.0002, "epoch": 4.083424807903403, "step": 1860}, {"loss": 0.6242, "grad_norm": 1.0101137161254883, "learning_rate": 0.0002, "epoch": 4.105378704720088, "step": 1870}, {"loss": 0.7259, "grad_norm": 0.8710281848907471, "learning_rate": 0.0002, "epoch": 4.127332601536772, "step": 1880}, {"loss": 0.6993, "grad_norm": 0.9604734778404236, "learning_rate": 0.0002, "epoch": 4.149286498353458, "step": 1890}, {"loss": 0.6706, "grad_norm": 0.9829702377319336, "learning_rate": 0.0002, "epoch": 4.171240395170143, "step": 1900}, {"loss": 0.7013, "grad_norm": 0.6572765707969666, "learning_rate": 0.0002, "epoch": 4.193194291986828, "step": 1910}, {"loss": 0.5539, "grad_norm": 0.8459188938140869, "learning_rate": 0.0002, "epoch": 4.2151481888035125, "step": 1920}, {"loss": 0.6235, "grad_norm": 0.8321021795272827, "learning_rate": 0.0002, "epoch": 4.237102085620197, "step": 1930}, {"loss": 0.6442, "grad_norm": 0.8611727356910706, "learning_rate": 0.0002, "epoch": 4.259055982436882, "step": 1940}, {"loss": 0.6852, "grad_norm": 0.8490208387374878, "learning_rate": 0.0002, "epoch": 4.281009879253568, "step": 1950}, {"loss": 0.6175, "grad_norm": 0.9628722667694092, "learning_rate": 0.0002, "epoch": 4.302963776070253, "step": 1960}, {"loss": 0.5982, "grad_norm": 0.9632807374000549, "learning_rate": 0.0002, "epoch": 4.324917672886937, "step": 1970}, {"loss": 0.6138, "grad_norm": 0.7023298740386963, "learning_rate": 0.0002, "epoch": 4.346871569703622, "step": 1980}, {"loss": 0.6012, "grad_norm": 0.7912909388542175, "learning_rate": 0.0002, "epoch": 4.368825466520307, "step": 1990}, {"loss": 0.6767, "grad_norm": 1.1463429927825928, "learning_rate": 0.0002, "epoch": 4.390779363336993, "step": 2000}, {"loss": 0.6607, "grad_norm": 1.1780626773834229, "learning_rate": 0.0002, "epoch": 4.4127332601536775, "step": 2010}, {"loss": 0.6746, "grad_norm": 0.9349206686019897, "learning_rate": 0.0002, "epoch": 4.434687156970362, "step": 2020}, {"loss": 0.7087, "grad_norm": 0.7816639542579651, "learning_rate": 0.0002, "epoch": 4.456641053787047, "step": 2030}, {"loss": 0.6222, "grad_norm": 0.7005311250686646, "learning_rate": 0.0002, "epoch": 4.478594950603732, "step": 2040}, {"loss": 0.6608, "grad_norm": 0.7746558785438538, "learning_rate": 0.0002, "epoch": 4.500548847420417, "step": 2050}, {"loss": 0.6305, "grad_norm": 0.8261151313781738, "learning_rate": 0.0002, "epoch": 4.522502744237102, "step": 2060}, {"loss": 0.6502, "grad_norm": 1.0917805433273315, "learning_rate": 0.0002, "epoch": 4.544456641053787, "step": 2070}, {"loss": 0.6798, "grad_norm": 1.1570647954940796, "learning_rate": 0.0002, "epoch": 4.566410537870472, "step": 2080}, {"loss": 0.6296, "grad_norm": 0.9936433434486389, "learning_rate": 0.0002, "epoch": 4.588364434687157, "step": 2090}, {"loss": 0.5936, "grad_norm": 0.8574427366256714, "learning_rate": 0.0002, "epoch": 4.610318331503842, "step": 2100}, {"loss": 0.6529, "grad_norm": 0.7630168795585632, "learning_rate": 0.0002, "epoch": 4.632272228320527, "step": 2110}, {"loss": 0.5935, "grad_norm": 0.8146462440490723, "learning_rate": 0.0002, "epoch": 4.654226125137212, "step": 2120}, {"loss": 0.7102, "grad_norm": 0.7090407609939575, "learning_rate": 0.0002, "epoch": 4.676180021953897, "step": 2130}, {"loss": 0.6575, "grad_norm": 0.8278160095214844, "learning_rate": 0.0002, "epoch": 4.698133918770582, "step": 2140}, {"loss": 0.664, "grad_norm": 0.9415683746337891, "learning_rate": 0.0002, "epoch": 4.7200878155872665, "step": 2150}, {"loss": 0.7283, "grad_norm": 1.0056205987930298, "learning_rate": 0.0002, "epoch": 4.742041712403951, "step": 2160}, {"loss": 0.6845, "grad_norm": 0.768304705619812, "learning_rate": 0.0002, "epoch": 4.763995609220637, "step": 2170}, {"loss": 0.6922, "grad_norm": 1.0604112148284912, "learning_rate": 0.0002, "epoch": 4.785949506037322, "step": 2180}, {"loss": 0.7092, "grad_norm": 1.132864236831665, "learning_rate": 0.0002, "epoch": 4.807903402854007, "step": 2190}, {"loss": 0.6936, "grad_norm": 0.7543689608573914, "learning_rate": 0.0002, "epoch": 4.829857299670691, "step": 2200}, {"loss": 0.6921, "grad_norm": 0.8047362565994263, "learning_rate": 0.0002, "epoch": 4.851811196487376, "step": 2210}, {"loss": 0.6753, "grad_norm": 1.135778546333313, "learning_rate": 0.0002, "epoch": 4.873765093304062, "step": 2220}, {"loss": 0.6443, "grad_norm": 0.9068503379821777, "learning_rate": 0.0002, "epoch": 4.895718990120747, "step": 2230}, {"loss": 0.7419, "grad_norm": 1.822325587272644, "learning_rate": 0.0002, "epoch": 4.9176728869374315, "step": 2240}, {"loss": 0.6436, "grad_norm": 1.1124998331069946, "learning_rate": 0.0002, "epoch": 4.939626783754116, "step": 2250}, {"loss": 0.7423, "grad_norm": 0.818484365940094, "learning_rate": 0.0002, "epoch": 4.961580680570801, "step": 2260}, {"loss": 0.6872, "grad_norm": 1.0057194232940674, "learning_rate": 0.0002, "epoch": 4.983534577387486, "step": 2270}, {"eval_loss": 1.4120490550994873, "eval_runtime": 87.5617, "eval_samples_per_second": 4.922, "eval_steps_per_second": 0.617, "epoch": 4.998902305159166, "step": 2277}, {"loss": 0.5451, "grad_norm": 0.8211547136306763, "learning_rate": 0.0002, "epoch": 5.005488474204172, "step": 2280}, {"loss": 0.4965, "grad_norm": 1.1704130172729492, "learning_rate": 0.0002, "epoch": 5.0274423710208564, "step": 2290}, {"loss": 0.4827, "grad_norm": 1.033539891242981, "learning_rate": 0.0002, "epoch": 5.049396267837541, "step": 2300}, {"loss": 0.447, "grad_norm": 0.8830313682556152, "learning_rate": 0.0002, "epoch": 5.071350164654226, "step": 2310}, {"loss": 0.5502, "grad_norm": 1.160437822341919, "learning_rate": 0.0002, "epoch": 5.093304061470911, "step": 2320}, {"loss": 0.5123, "grad_norm": 0.919956386089325, "learning_rate": 0.0002, "epoch": 5.115257958287596, "step": 2330}, {"loss": 0.4784, "grad_norm": 1.0099905729293823, "learning_rate": 0.0002, "epoch": 5.137211855104281, "step": 2340}, {"loss": 0.5109, "grad_norm": 1.1484816074371338, "learning_rate": 0.0002, "epoch": 5.159165751920966, "step": 2350}, {"loss": 0.5222, "grad_norm": 1.0373470783233643, "learning_rate": 0.0002, "epoch": 5.181119648737651, "step": 2360}, {"loss": 0.5366, "grad_norm": 1.0824922323226929, "learning_rate": 0.0002, "epoch": 5.203073545554336, "step": 2370}, {"loss": 0.5592, "grad_norm": 1.3817942142486572, "learning_rate": 0.0002, "epoch": 5.225027442371021, "step": 2380}, {"loss": 0.504, "grad_norm": 1.197035551071167, "learning_rate": 0.0002, "epoch": 5.246981339187705, "step": 2390}, {"loss": 0.5326, "grad_norm": 1.098778486251831, "learning_rate": 0.0002, "epoch": 5.268935236004391, "step": 2400}, {"loss": 0.5039, "grad_norm": 0.9713385105133057, "learning_rate": 0.0002, "epoch": 5.290889132821076, "step": 2410}, {"loss": 0.5735, "grad_norm": 1.321574330329895, "learning_rate": 0.0002, "epoch": 5.312843029637761, "step": 2420}, {"loss": 0.4777, "grad_norm": 0.9402496218681335, "learning_rate": 0.0002, "epoch": 5.3347969264544455, "step": 2430}, {"loss": 0.5604, "grad_norm": 0.8644852042198181, "learning_rate": 0.0002, "epoch": 5.35675082327113, "step": 2440}, {"loss": 0.5324, "grad_norm": 1.060290813446045, "learning_rate": 0.0002, "epoch": 5.378704720087816, "step": 2450}, {"loss": 0.5366, "grad_norm": 1.0725265741348267, "learning_rate": 0.0002, "epoch": 5.400658616904501, "step": 2460}, {"loss": 0.5469, "grad_norm": 0.9409431219100952, "learning_rate": 0.0002, "epoch": 5.422612513721186, "step": 2470}, {"loss": 0.5186, "grad_norm": 1.1108187437057495, "learning_rate": 0.0002, "epoch": 5.44456641053787, "step": 2480}, {"loss": 0.5312, "grad_norm": 1.0210821628570557, "learning_rate": 0.0002, "epoch": 5.466520307354555, "step": 2490}, {"loss": 0.5016, "grad_norm": 1.110597014427185, "learning_rate": 0.0002, "epoch": 5.48847420417124, "step": 2500}, {"loss": 0.511, "grad_norm": 1.2534265518188477, "learning_rate": 0.0002, "epoch": 5.510428100987926, "step": 2510}, {"loss": 0.6062, "grad_norm": 1.3389744758605957, "learning_rate": 0.0002, "epoch": 5.5323819978046105, "step": 2520}, {"loss": 0.4653, "grad_norm": 0.9520368576049805, "learning_rate": 0.0002, "epoch": 5.554335894621295, "step": 2530}, {"loss": 0.4746, "grad_norm": 1.4737157821655273, "learning_rate": 0.0002, "epoch": 5.57628979143798, "step": 2540}, {"loss": 0.5432, "grad_norm": 1.4143685102462769, "learning_rate": 0.0002, "epoch": 5.598243688254665, "step": 2550}, {"loss": 0.4722, "grad_norm": 1.3573999404907227, "learning_rate": 0.0002, "epoch": 5.620197585071351, "step": 2560}, {"loss": 0.5063, "grad_norm": 0.8475444316864014, "learning_rate": 0.0002, "epoch": 5.642151481888035, "step": 2570}, {"loss": 0.4911, "grad_norm": 1.2670329809188843, "learning_rate": 0.0002, "epoch": 5.66410537870472, "step": 2580}, {"loss": 0.5137, "grad_norm": 0.9688172936439514, "learning_rate": 0.0002, "epoch": 5.686059275521405, "step": 2590}, {"loss": 0.5116, "grad_norm": 1.3652743101119995, "learning_rate": 0.0002, "epoch": 5.70801317233809, "step": 2600}, {"loss": 0.5661, "grad_norm": 1.1475377082824707, "learning_rate": 0.0002, "epoch": 5.729967069154775, "step": 2610}, {"loss": 0.567, "grad_norm": 1.3105946779251099, "learning_rate": 0.0002, "epoch": 5.75192096597146, "step": 2620}, {"loss": 0.4964, "grad_norm": 0.920238196849823, "learning_rate": 0.0002, "epoch": 5.773874862788145, "step": 2630}, {"loss": 0.5473, "grad_norm": 1.0981792211532593, "learning_rate": 0.0002, "epoch": 5.79582875960483, "step": 2640}, {"loss": 0.5132, "grad_norm": 1.0734144449234009, "learning_rate": 0.0002, "epoch": 5.817782656421515, "step": 2650}, {"loss": 0.5404, "grad_norm": 1.0541702508926392, "learning_rate": 0.0002, "epoch": 5.8397365532381995, "step": 2660}, {"loss": 0.5056, "grad_norm": 1.0913143157958984, "learning_rate": 0.0002, "epoch": 5.861690450054885, "step": 2670}, {"loss": 0.5425, "grad_norm": 1.0431408882141113, "learning_rate": 0.0002, "epoch": 5.88364434687157, "step": 2680}, {"loss": 0.5398, "grad_norm": 1.3515729904174805, "learning_rate": 0.0002, "epoch": 5.905598243688255, "step": 2690}, {"loss": 0.5936, "grad_norm": 1.3153903484344482, "learning_rate": 0.0002, "epoch": 5.92755214050494, "step": 2700}, {"loss": 0.5643, "grad_norm": 1.024109125137329, "learning_rate": 0.0002, "epoch": 5.949506037321624, "step": 2710}, {"loss": 0.5143, "grad_norm": 1.0308483839035034, "learning_rate": 0.0002, "epoch": 5.971459934138309, "step": 2720}, {"loss": 0.4835, "grad_norm": 0.8329401016235352, "learning_rate": 0.0002, "epoch": 5.993413830954994, "step": 2730}, {"eval_loss": 1.510581612586975, "eval_runtime": 89.0047, "eval_samples_per_second": 4.842, "eval_steps_per_second": 0.607, "epoch": 6.0, "step": 2733}, {"loss": 0.4282, "grad_norm": 1.1903921365737915, "learning_rate": 0.0002, "epoch": 6.01536772777168, "step": 2740}, {"loss": 0.3844, "grad_norm": 1.0170859098434448, "learning_rate": 0.0002, "epoch": 6.0373216245883645, "step": 2750}, {"loss": 0.4116, "grad_norm": 1.269655704498291, "learning_rate": 0.0002, "epoch": 6.059275521405049, "step": 2760}, {"loss": 0.381, "grad_norm": 1.1271249055862427, "learning_rate": 0.0002, "epoch": 6.081229418221734, "step": 2770}, {"loss": 0.391, "grad_norm": 1.0269793272018433, "learning_rate": 0.0002, "epoch": 6.103183315038419, "step": 2780}, {"loss": 0.3896, "grad_norm": 1.1622686386108398, "learning_rate": 0.0002, "epoch": 6.125137211855105, "step": 2790}, {"loss": 0.3907, "grad_norm": 1.3457845449447632, "learning_rate": 0.0002, "epoch": 6.147091108671789, "step": 2800}, {"loss": 0.3447, "grad_norm": 1.008620262145996, "learning_rate": 0.0002, "epoch": 6.169045005488474, "step": 2810}, {"loss": 0.3437, "grad_norm": 0.9964058995246887, "learning_rate": 0.0002, "epoch": 6.190998902305159, "step": 2820}, {"loss": 0.4073, "grad_norm": 1.265552043914795, "learning_rate": 0.0002, "epoch": 6.212952799121844, "step": 2830}, {"loss": 0.4199, "grad_norm": 1.0481451749801636, "learning_rate": 0.0002, "epoch": 6.234906695938529, "step": 2840}, {"loss": 0.4243, "grad_norm": 1.3813395500183105, "learning_rate": 0.0002, "epoch": 6.256860592755214, "step": 2850}, {"loss": 0.4039, "grad_norm": 1.1307486295700073, "learning_rate": 0.0002, "epoch": 6.278814489571899, "step": 2860}, {"loss": 0.3665, "grad_norm": 1.122252106666565, "learning_rate": 0.0002, "epoch": 6.300768386388584, "step": 2870}, {"loss": 0.4377, "grad_norm": 0.9570856094360352, "learning_rate": 0.0002, "epoch": 6.322722283205269, "step": 2880}, {"loss": 0.3762, "grad_norm": 1.429248332977295, "learning_rate": 0.0002, "epoch": 6.3446761800219535, "step": 2890}, {"loss": 0.3746, "grad_norm": 1.228832483291626, "learning_rate": 0.0002, "epoch": 6.366630076838639, "step": 2900}, {"loss": 0.3714, "grad_norm": 0.9634972810745239, "learning_rate": 0.0002, "epoch": 6.388583973655324, "step": 2910}, {"loss": 0.3856, "grad_norm": 1.392120599746704, "learning_rate": 0.0002, "epoch": 6.410537870472009, "step": 2920}, {"loss": 0.4395, "grad_norm": 1.0452295541763306, "learning_rate": 0.0002, "epoch": 6.432491767288694, "step": 2930}, {"loss": 0.4559, "grad_norm": 0.9953978657722473, "learning_rate": 0.0002, "epoch": 6.4544456641053785, "step": 2940}, {"loss": 0.4108, "grad_norm": 1.090386986732483, "learning_rate": 0.0002, "epoch": 6.476399560922063, "step": 2950}, {"loss": 0.4059, "grad_norm": 1.2177232503890991, "learning_rate": 0.0002, "epoch": 6.498353457738749, "step": 2960}, {"loss": 0.4403, "grad_norm": 0.8435868620872498, "learning_rate": 0.0002, "epoch": 6.520307354555434, "step": 2970}, {"loss": 0.4143, "grad_norm": 1.0110384225845337, "learning_rate": 0.0002, "epoch": 6.542261251372119, "step": 2980}, {"loss": 0.4396, "grad_norm": 0.8551704287528992, "learning_rate": 0.0002, "epoch": 6.564215148188803, "step": 2990}, {"loss": 0.3908, "grad_norm": 1.2663729190826416, "learning_rate": 0.0002, "epoch": 6.586169045005488, "step": 3000}, {"loss": 0.3927, "grad_norm": 1.2262762784957886, "learning_rate": 0.0002, "epoch": 6.608122941822174, "step": 3010}, {"loss": 0.4183, "grad_norm": 1.3794647455215454, "learning_rate": 0.0002, "epoch": 6.630076838638859, "step": 3020}, {"loss": 0.3903, "grad_norm": 0.9994757175445557, "learning_rate": 0.0002, "epoch": 6.6520307354555435, "step": 3030}, {"loss": 0.4083, "grad_norm": 1.067501187324524, "learning_rate": 0.0002, "epoch": 6.673984632272228, "step": 3040}, {"loss": 0.4551, "grad_norm": 1.1194695234298706, "learning_rate": 0.0002, "epoch": 6.695938529088913, "step": 3050}, {"loss": 0.4276, "grad_norm": 1.572695255279541, "learning_rate": 0.0002, "epoch": 6.717892425905598, "step": 3060}, {"loss": 0.3681, "grad_norm": 1.063094139099121, "learning_rate": 0.0002, "epoch": 6.739846322722284, "step": 3070}, {"loss": 0.3656, "grad_norm": 1.2257463932037354, "learning_rate": 0.0002, "epoch": 6.761800219538968, "step": 3080}, {"loss": 0.4504, "grad_norm": 1.259731411933899, "learning_rate": 0.0002, "epoch": 6.783754116355653, "step": 3090}, {"loss": 0.4067, "grad_norm": 1.3234009742736816, "learning_rate": 0.0002, "epoch": 6.805708013172338, "step": 3100}, {"loss": 0.4913, "grad_norm": 1.4324477910995483, "learning_rate": 0.0002, "epoch": 6.827661909989023, "step": 3110}, {"loss": 0.4408, "grad_norm": 1.4183896780014038, "learning_rate": 0.0002, "epoch": 6.8496158068057085, "step": 3120}, {"loss": 0.4517, "grad_norm": 1.1369833946228027, "learning_rate": 0.0002, "epoch": 6.871569703622393, "step": 3130}, {"loss": 0.458, "grad_norm": 1.2804654836654663, "learning_rate": 0.0002, "epoch": 6.893523600439078, "step": 3140}, {"loss": 0.4616, "grad_norm": 1.535305380821228, "learning_rate": 0.0002, "epoch": 6.915477497255763, "step": 3150}, {"loss": 0.4178, "grad_norm": 1.2820420265197754, "learning_rate": 0.0002, "epoch": 6.937431394072448, "step": 3160}, {"loss": 0.442, "grad_norm": 1.1014128923416138, "learning_rate": 0.0002, "epoch": 6.9593852908891325, "step": 3170}, {"loss": 0.4379, "grad_norm": 0.9979909658432007, "learning_rate": 0.0002, "epoch": 6.981339187705817, "step": 3180}, {"eval_loss": 1.6552348136901855, "eval_runtime": 88.8609, "eval_samples_per_second": 4.85, "eval_steps_per_second": 0.608, "epoch": 6.998902305159166, "step": 3188}, {"loss": 0.3922, "grad_norm": 0.9172588586807251, "learning_rate": 0.0002, "epoch": 7.003293084522503, "step": 3190}, {"loss": 0.3028, "grad_norm": 1.1526820659637451, "learning_rate": 0.0002, "epoch": 7.025246981339188, "step": 3200}, {"loss": 0.305, "grad_norm": 0.9504580497741699, "learning_rate": 0.0002, "epoch": 7.047200878155873, "step": 3210}, {"loss": 0.321, "grad_norm": 1.0364530086517334, "learning_rate": 0.0002, "epoch": 7.069154774972557, "step": 3220}, {"loss": 0.2887, "grad_norm": 1.133812427520752, "learning_rate": 0.0002, "epoch": 7.091108671789242, "step": 3230}, {"loss": 0.2754, "grad_norm": 0.8940557837486267, "learning_rate": 0.0002, "epoch": 7.113062568605928, "step": 3240}, {"loss": 0.338, "grad_norm": 1.4909859895706177, "learning_rate": 0.0002, "epoch": 7.135016465422613, "step": 3250}, {"loss": 0.2909, "grad_norm": 1.1167937517166138, "learning_rate": 0.0002, "epoch": 7.1569703622392975, "step": 3260}, {"loss": 0.2783, "grad_norm": 1.1566085815429688, "learning_rate": 0.0002, "epoch": 7.178924259055982, "step": 3270}, {"loss": 0.2852, "grad_norm": 1.3751647472381592, "learning_rate": 0.0002, "epoch": 7.200878155872667, "step": 3280}, {"loss": 0.314, "grad_norm": 1.2081550359725952, "learning_rate": 0.0002, "epoch": 7.222832052689352, "step": 3290}, {"loss": 0.3231, "grad_norm": 1.1245852708816528, "learning_rate": 0.0002, "epoch": 7.244785949506038, "step": 3300}, {"loss": 0.3434, "grad_norm": 0.9021703600883484, "learning_rate": 0.0002, "epoch": 7.266739846322722, "step": 3310}, {"loss": 0.3416, "grad_norm": 1.3136515617370605, "learning_rate": 0.0002, "epoch": 7.288693743139407, "step": 3320}, {"loss": 0.3034, "grad_norm": 1.3397585153579712, "learning_rate": 0.0002, "epoch": 7.310647639956092, "step": 3330}, {"loss": 0.3232, "grad_norm": 1.0277947187423706, "learning_rate": 0.0002, "epoch": 7.332601536772777, "step": 3340}, {"loss": 0.3229, "grad_norm": 1.3082621097564697, "learning_rate": 0.0002, "epoch": 7.3545554335894625, "step": 3350}, {"loss": 0.3172, "grad_norm": 1.1663758754730225, "learning_rate": 0.0002, "epoch": 7.376509330406147, "step": 3360}, {"loss": 0.3161, "grad_norm": 0.9822199940681458, "learning_rate": 0.0002, "epoch": 7.398463227222832, "step": 3370}, {"loss": 0.3439, "grad_norm": 1.1240934133529663, "learning_rate": 0.0002, "epoch": 7.420417124039517, "step": 3380}, {"loss": 0.3419, "grad_norm": 1.110464334487915, "learning_rate": 0.0002, "epoch": 7.442371020856202, "step": 3390}, {"loss": 0.3127, "grad_norm": 1.3189985752105713, "learning_rate": 0.0002, "epoch": 7.4643249176728865, "step": 3400}, {"loss": 0.2897, "grad_norm": 1.148912787437439, "learning_rate": 0.0002, "epoch": 7.486278814489572, "step": 3410}, {"loss": 0.362, "grad_norm": 1.8192038536071777, "learning_rate": 0.0002, "epoch": 7.508232711306257, "step": 3420}, {"loss": 0.341, "grad_norm": 1.4294136762619019, "learning_rate": 0.0002, "epoch": 7.530186608122942, "step": 3430}, {"loss": 0.3026, "grad_norm": 1.2051990032196045, "learning_rate": 0.0002, "epoch": 7.552140504939627, "step": 3440}, {"loss": 0.3572, "grad_norm": 0.9924893379211426, "learning_rate": 0.0002, "epoch": 7.574094401756311, "step": 3450}, {"loss": 0.3335, "grad_norm": 1.5764961242675781, "learning_rate": 0.0002, "epoch": 7.596048298572997, "step": 3460}, {"loss": 0.3391, "grad_norm": 1.5812066793441772, "learning_rate": 0.0002, "epoch": 7.618002195389682, "step": 3470}, {"loss": 0.3517, "grad_norm": 1.091802716255188, "learning_rate": 0.0002, "epoch": 7.639956092206367, "step": 3480}, {"loss": 0.3144, "grad_norm": 0.9630248546600342, "learning_rate": 0.0002, "epoch": 7.6619099890230515, "step": 3490}, {"loss": 0.3262, "grad_norm": 1.0193588733673096, "learning_rate": 0.0002, "epoch": 7.683863885839736, "step": 3500}, {"loss": 0.2887, "grad_norm": 1.1763300895690918, "learning_rate": 0.0002, "epoch": 7.705817782656421, "step": 3510}, {"loss": 0.3007, "grad_norm": 1.0153584480285645, "learning_rate": 0.0002, "epoch": 7.727771679473107, "step": 3520}, {"loss": 0.4009, "grad_norm": 1.4637620449066162, "learning_rate": 0.0002, "epoch": 7.749725576289792, "step": 3530}, {"loss": 0.3164, "grad_norm": 1.2255295515060425, "learning_rate": 0.0002, "epoch": 7.771679473106476, "step": 3540}, {"loss": 0.3437, "grad_norm": 1.29080069065094, "learning_rate": 0.0002, "epoch": 7.793633369923161, "step": 3550}, {"loss": 0.3482, "grad_norm": 1.2556861639022827, "learning_rate": 0.0002, "epoch": 7.815587266739846, "step": 3560}, {"loss": 0.3396, "grad_norm": 1.4294195175170898, "learning_rate": 0.0002, "epoch": 7.837541163556532, "step": 3570}, {"loss": 0.3682, "grad_norm": 1.2785801887512207, "learning_rate": 0.0002, "epoch": 7.8594950603732165, "step": 3580}, {"loss": 0.3353, "grad_norm": 1.252855896949768, "learning_rate": 0.0002, "epoch": 7.881448957189901, "step": 3590}, {"loss": 0.3251, "grad_norm": 1.68595552444458, "learning_rate": 0.0002, "epoch": 7.903402854006586, "step": 3600}, {"loss": 0.3276, "grad_norm": 1.2536509037017822, "learning_rate": 0.0002, "epoch": 7.925356750823271, "step": 3610}, {"loss": 0.3154, "grad_norm": 1.4146950244903564, "learning_rate": 0.0002, "epoch": 7.947310647639956, "step": 3620}, {"loss": 0.3299, "grad_norm": 1.49301278591156, "learning_rate": 0.0002, "epoch": 7.969264544456641, "step": 3630}, {"loss": 0.324, "grad_norm": 0.9742516279220581, "learning_rate": 0.0002, "epoch": 7.991218441273326, "step": 3640}]}