Upload folder using huggingface_hub

.gitattributes

@@ -2323,3 +2323,12 @@ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_
 Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-10000/checkpoint-754/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-10000/checkpoint-942/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1323/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1764/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2205/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2646/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-3087/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-3528/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-441/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-882/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/tokenizer.json filter=lfs diff=lfs merge=lfs -text

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **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]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+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
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[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

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "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
+}

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b265b08aa3b965c22c1355e68e889f9f7a85e11299bd18f4a4c2e48518f9afa
+size 29500848

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1323/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **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]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+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
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[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

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1323/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "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
+}

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1323/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b265b08aa3b965c22c1355e68e889f9f7a85e11299bd18f4a4c2e48518f9afa
+size 29500848

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1323/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5f458cd1826277fa3587f31098e7044eba7d2c9574a8cee1d883c31bff7ba2f
+size 15064314

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1323/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d569bab937ecbb882df0eb4ff018cb21cd7eafe1de6088e0f040e8630a49579e
+size 14244

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1323/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3046e60eecb5c9ef3ecd6e32c300fbab8fd731d5983e3b78f98c89d3dd3c37fb
+size 1064

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1323/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1323/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f559f2189f392b4555613965f089e7c4d300b41fbe080bf79da0d676e33ee7f0
+size 34356041

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1323/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1323/tokenizer_config.json

@@ -0,0 +1,1757 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1323/trainer_state.json

@@ -0,0 +1,981 @@
+{
+  "best_metric": 2.061427116394043,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1323",
+  "epoch": 3.0,
+  "eval_steps": 10,
+  "global_step": 1323,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022675736961451247,
+      "grad_norm": 1.8457136154174805,
+      "learning_rate": 0.0002,
+      "loss": 4.7982,
+      "step": 10
+    },
+    {
+      "epoch": 0.045351473922902494,
+      "grad_norm": 1.0967960357666016,
+      "learning_rate": 0.0002,
+      "loss": 3.71,
+      "step": 20
+    },
+    {
+      "epoch": 0.06802721088435375,
+      "grad_norm": 0.8257759213447571,
+      "learning_rate": 0.0002,
+      "loss": 3.3086,
+      "step": 30
+    },
+    {
+      "epoch": 0.09070294784580499,
+      "grad_norm": 0.8248435258865356,
+      "learning_rate": 0.0002,
+      "loss": 2.923,
+      "step": 40
+    },
+    {
+      "epoch": 0.11337868480725624,
+      "grad_norm": 1.1190264225006104,
+      "learning_rate": 0.0002,
+      "loss": 2.8263,
+      "step": 50
+    },
+    {
+      "epoch": 0.1360544217687075,
+      "grad_norm": 1.273951768875122,
+      "learning_rate": 0.0002,
+      "loss": 2.6239,
+      "step": 60
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 1.0004316568374634,
+      "learning_rate": 0.0002,
+      "loss": 2.5203,
+      "step": 70
+    },
+    {
+      "epoch": 0.18140589569160998,
+      "grad_norm": 0.8296012878417969,
+      "learning_rate": 0.0002,
+      "loss": 2.5055,
+      "step": 80
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 1.1563128232955933,
+      "learning_rate": 0.0002,
+      "loss": 2.5255,
+      "step": 90
+    },
+    {
+      "epoch": 0.22675736961451248,
+      "grad_norm": 0.7863451838493347,
+      "learning_rate": 0.0002,
+      "loss": 2.4731,
+      "step": 100
+    },
+    {
+      "epoch": 0.2494331065759637,
+      "grad_norm": 0.9167478680610657,
+      "learning_rate": 0.0002,
+      "loss": 2.3688,
+      "step": 110
+    },
+    {
+      "epoch": 0.272108843537415,
+      "grad_norm": 1.104406476020813,
+      "learning_rate": 0.0002,
+      "loss": 2.336,
+      "step": 120
+    },
+    {
+      "epoch": 0.2947845804988662,
+      "grad_norm": 1.109564185142517,
+      "learning_rate": 0.0002,
+      "loss": 2.3063,
+      "step": 130
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.7416750192642212,
+      "learning_rate": 0.0002,
+      "loss": 2.23,
+      "step": 140
+    },
+    {
+      "epoch": 0.3401360544217687,
+      "grad_norm": 1.1499258279800415,
+      "learning_rate": 0.0002,
+      "loss": 2.3346,
+      "step": 150
+    },
+    {
+      "epoch": 0.36281179138321995,
+      "grad_norm": 0.9961133599281311,
+      "learning_rate": 0.0002,
+      "loss": 2.2853,
+      "step": 160
+    },
+    {
+      "epoch": 0.3854875283446712,
+      "grad_norm": 0.9257232546806335,
+      "learning_rate": 0.0002,
+      "loss": 2.2731,
+      "step": 170
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 1.098513126373291,
+      "learning_rate": 0.0002,
+      "loss": 2.1986,
+      "step": 180
+    },
+    {
+      "epoch": 0.4308390022675737,
+      "grad_norm": 0.8935237526893616,
+      "learning_rate": 0.0002,
+      "loss": 2.1685,
+      "step": 190
+    },
+    {
+      "epoch": 0.45351473922902497,
+      "grad_norm": 0.9654302597045898,
+      "learning_rate": 0.0002,
+      "loss": 2.2077,
+      "step": 200
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.9273215532302856,
+      "learning_rate": 0.0002,
+      "loss": 2.2421,
+      "step": 210
+    },
+    {
+      "epoch": 0.4988662131519274,
+      "grad_norm": 0.7222742438316345,
+      "learning_rate": 0.0002,
+      "loss": 2.1973,
+      "step": 220
+    },
+    {
+      "epoch": 0.5215419501133787,
+      "grad_norm": 0.7825018763542175,
+      "learning_rate": 0.0002,
+      "loss": 2.0619,
+      "step": 230
+    },
+    {
+      "epoch": 0.54421768707483,
+      "grad_norm": 0.7758685350418091,
+      "learning_rate": 0.0002,
+      "loss": 2.2247,
+      "step": 240
+    },
+    {
+      "epoch": 0.5668934240362812,
+      "grad_norm": 0.916719913482666,
+      "learning_rate": 0.0002,
+      "loss": 2.1518,
+      "step": 250
+    },
+    {
+      "epoch": 0.5895691609977324,
+      "grad_norm": 0.696332573890686,
+      "learning_rate": 0.0002,
+      "loss": 2.0614,
+      "step": 260
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 0.7362682223320007,
+      "learning_rate": 0.0002,
+      "loss": 2.0763,
+      "step": 270
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.8184517025947571,
+      "learning_rate": 0.0002,
+      "loss": 2.223,
+      "step": 280
+    },
+    {
+      "epoch": 0.6575963718820862,
+      "grad_norm": 0.7944937348365784,
+      "learning_rate": 0.0002,
+      "loss": 2.1634,
+      "step": 290
+    },
+    {
+      "epoch": 0.6802721088435374,
+      "grad_norm": 0.7258933186531067,
+      "learning_rate": 0.0002,
+      "loss": 2.0922,
+      "step": 300
+    },
+    {
+      "epoch": 0.7029478458049887,
+      "grad_norm": 0.7037094831466675,
+      "learning_rate": 0.0002,
+      "loss": 2.1221,
+      "step": 310
+    },
+    {
+      "epoch": 0.7256235827664399,
+      "grad_norm": 0.7499093413352966,
+      "learning_rate": 0.0002,
+      "loss": 2.1132,
+      "step": 320
+    },
+    {
+      "epoch": 0.7482993197278912,
+      "grad_norm": 0.7725803256034851,
+      "learning_rate": 0.0002,
+      "loss": 2.2321,
+      "step": 330
+    },
+    {
+      "epoch": 0.7709750566893424,
+      "grad_norm": 0.6771686673164368,
+      "learning_rate": 0.0002,
+      "loss": 2.1611,
+      "step": 340
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "grad_norm": 0.7557646036148071,
+      "learning_rate": 0.0002,
+      "loss": 2.0693,
+      "step": 350
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.7430537939071655,
+      "learning_rate": 0.0002,
+      "loss": 2.0629,
+      "step": 360
+    },
+    {
+      "epoch": 0.8390022675736961,
+      "grad_norm": 0.8602280616760254,
+      "learning_rate": 0.0002,
+      "loss": 2.0731,
+      "step": 370
+    },
+    {
+      "epoch": 0.8616780045351474,
+      "grad_norm": 0.753440260887146,
+      "learning_rate": 0.0002,
+      "loss": 2.1836,
+      "step": 380
+    },
+    {
+      "epoch": 0.8843537414965986,
+      "grad_norm": 0.7217596769332886,
+      "learning_rate": 0.0002,
+      "loss": 2.1186,
+      "step": 390
+    },
+    {
+      "epoch": 0.9070294784580499,
+      "grad_norm": 0.6116304397583008,
+      "learning_rate": 0.0002,
+      "loss": 2.0223,
+      "step": 400
+    },
+    {
+      "epoch": 0.9297052154195011,
+      "grad_norm": 0.6829515695571899,
+      "learning_rate": 0.0002,
+      "loss": 2.0491,
+      "step": 410
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.733259916305542,
+      "learning_rate": 0.0002,
+      "loss": 2.1518,
+      "step": 420
+    },
+    {
+      "epoch": 0.9750566893424036,
+      "grad_norm": 0.6036455035209656,
+      "learning_rate": 0.0002,
+      "loss": 2.076,
+      "step": 430
+    },
+    {
+      "epoch": 0.9977324263038548,
+      "grad_norm": 0.8478217720985413,
+      "learning_rate": 0.0002,
+      "loss": 2.1526,
+      "step": 440
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.114302158355713,
+      "eval_runtime": 16.5108,
+      "eval_samples_per_second": 30.707,
+      "eval_steps_per_second": 3.876,
+      "step": 441
+    },
+    {
+      "epoch": 1.0204081632653061,
+      "grad_norm": 0.6996896266937256,
+      "learning_rate": 0.0002,
+      "loss": 1.9967,
+      "step": 450
+    },
+    {
+      "epoch": 1.0430839002267573,
+      "grad_norm": 0.7616267800331116,
+      "learning_rate": 0.0002,
+      "loss": 2.0471,
+      "step": 460
+    },
+    {
+      "epoch": 1.0657596371882085,
+      "grad_norm": 0.5978519320487976,
+      "learning_rate": 0.0002,
+      "loss": 2.0674,
+      "step": 470
+    },
+    {
+      "epoch": 1.08843537414966,
+      "grad_norm": 0.703987717628479,
+      "learning_rate": 0.0002,
+      "loss": 2.0803,
+      "step": 480
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.6707539558410645,
+      "learning_rate": 0.0002,
+      "loss": 2.0215,
+      "step": 490
+    },
+    {
+      "epoch": 1.1337868480725624,
+      "grad_norm": 0.6343862414360046,
+      "learning_rate": 0.0002,
+      "loss": 2.045,
+      "step": 500
+    },
+    {
+      "epoch": 1.1564625850340136,
+      "grad_norm": 0.8836050033569336,
+      "learning_rate": 0.0002,
+      "loss": 1.9753,
+      "step": 510
+    },
+    {
+      "epoch": 1.179138321995465,
+      "grad_norm": 0.6288692951202393,
+      "learning_rate": 0.0002,
+      "loss": 1.9537,
+      "step": 520
+    },
+    {
+      "epoch": 1.2018140589569162,
+      "grad_norm": 0.6671382784843445,
+      "learning_rate": 0.0002,
+      "loss": 2.0072,
+      "step": 530
+    },
+    {
+      "epoch": 1.2244897959183674,
+      "grad_norm": 0.7260547876358032,
+      "learning_rate": 0.0002,
+      "loss": 2.0631,
+      "step": 540
+    },
+    {
+      "epoch": 1.2471655328798186,
+      "grad_norm": 0.6919140219688416,
+      "learning_rate": 0.0002,
+      "loss": 2.1395,
+      "step": 550
+    },
+    {
+      "epoch": 1.2698412698412698,
+      "grad_norm": 0.6895381212234497,
+      "learning_rate": 0.0002,
+      "loss": 2.1162,
+      "step": 560
+    },
+    {
+      "epoch": 1.2925170068027212,
+      "grad_norm": 0.7131213545799255,
+      "learning_rate": 0.0002,
+      "loss": 2.1023,
+      "step": 570
+    },
+    {
+      "epoch": 1.3151927437641724,
+      "grad_norm": 0.6087185144424438,
+      "learning_rate": 0.0002,
+      "loss": 2.0381,
+      "step": 580
+    },
+    {
+      "epoch": 1.3378684807256236,
+      "grad_norm": 0.6506251096725464,
+      "learning_rate": 0.0002,
+      "loss": 2.054,
+      "step": 590
+    },
+    {
+      "epoch": 1.3605442176870748,
+      "grad_norm": 0.6999365091323853,
+      "learning_rate": 0.0002,
+      "loss": 2.0669,
+      "step": 600
+    },
+    {
+      "epoch": 1.383219954648526,
+      "grad_norm": 0.6305016875267029,
+      "learning_rate": 0.0002,
+      "loss": 2.0121,
+      "step": 610
+    },
+    {
+      "epoch": 1.4058956916099774,
+      "grad_norm": 0.6413465142250061,
+      "learning_rate": 0.0002,
+      "loss": 1.9727,
+      "step": 620
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.7571105360984802,
+      "learning_rate": 0.0002,
+      "loss": 2.0676,
+      "step": 630
+    },
+    {
+      "epoch": 1.4512471655328798,
+      "grad_norm": 0.8087857365608215,
+      "learning_rate": 0.0002,
+      "loss": 2.0838,
+      "step": 640
+    },
+    {
+      "epoch": 1.473922902494331,
+      "grad_norm": 0.6284025311470032,
+      "learning_rate": 0.0002,
+      "loss": 1.9932,
+      "step": 650
+    },
+    {
+      "epoch": 1.4965986394557822,
+      "grad_norm": 0.6630339026451111,
+      "learning_rate": 0.0002,
+      "loss": 2.0456,
+      "step": 660
+    },
+    {
+      "epoch": 1.5192743764172336,
+      "grad_norm": 0.6777389645576477,
+      "learning_rate": 0.0002,
+      "loss": 2.0778,
+      "step": 670
+    },
+    {
+      "epoch": 1.5419501133786848,
+      "grad_norm": 0.6965354681015015,
+      "learning_rate": 0.0002,
+      "loss": 2.0437,
+      "step": 680
+    },
+    {
+      "epoch": 1.564625850340136,
+      "grad_norm": 0.7124104499816895,
+      "learning_rate": 0.0002,
+      "loss": 2.056,
+      "step": 690
+    },
+    {
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.6652887463569641,
+      "learning_rate": 0.0002,
+      "loss": 1.989,
+      "step": 700
+    },
+    {
+      "epoch": 1.6099773242630384,
+      "grad_norm": 0.6061141490936279,
+      "learning_rate": 0.0002,
+      "loss": 2.0419,
+      "step": 710
+    },
+    {
+      "epoch": 1.6326530612244898,
+      "grad_norm": 0.8291212320327759,
+      "learning_rate": 0.0002,
+      "loss": 2.0257,
+      "step": 720
+    },
+    {
+      "epoch": 1.655328798185941,
+      "grad_norm": 0.6672369241714478,
+      "learning_rate": 0.0002,
+      "loss": 2.0776,
+      "step": 730
+    },
+    {
+      "epoch": 1.6780045351473922,
+      "grad_norm": 0.6301238536834717,
+      "learning_rate": 0.0002,
+      "loss": 1.9834,
+      "step": 740
+    },
+    {
+      "epoch": 1.7006802721088436,
+      "grad_norm": 0.7217460870742798,
+      "learning_rate": 0.0002,
+      "loss": 2.0176,
+      "step": 750
+    },
+    {
+      "epoch": 1.7233560090702946,
+      "grad_norm": 0.6720302104949951,
+      "learning_rate": 0.0002,
+      "loss": 2.0793,
+      "step": 760
+    },
+    {
+      "epoch": 1.746031746031746,
+      "grad_norm": 0.8228253722190857,
+      "learning_rate": 0.0002,
+      "loss": 2.0417,
+      "step": 770
+    },
+    {
+      "epoch": 1.7687074829931972,
+      "grad_norm": 0.6359929442405701,
+      "learning_rate": 0.0002,
+      "loss": 2.0198,
+      "step": 780
+    },
+    {
+      "epoch": 1.7913832199546484,
+      "grad_norm": 0.6594814658164978,
+      "learning_rate": 0.0002,
+      "loss": 1.99,
+      "step": 790
+    },
+    {
+      "epoch": 1.8140589569160999,
+      "grad_norm": 0.6135239601135254,
+      "learning_rate": 0.0002,
+      "loss": 2.0752,
+      "step": 800
+    },
+    {
+      "epoch": 1.836734693877551,
+      "grad_norm": 0.6736067533493042,
+      "learning_rate": 0.0002,
+      "loss": 2.0397,
+      "step": 810
+    },
+    {
+      "epoch": 1.8594104308390023,
+      "grad_norm": 0.7712678909301758,
+      "learning_rate": 0.0002,
+      "loss": 2.0545,
+      "step": 820
+    },
+    {
+      "epoch": 1.8820861678004537,
+      "grad_norm": 0.6950375437736511,
+      "learning_rate": 0.0002,
+      "loss": 1.9644,
+      "step": 830
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.5913259387016296,
+      "learning_rate": 0.0002,
+      "loss": 1.9272,
+      "step": 840
+    },
+    {
+      "epoch": 1.927437641723356,
+      "grad_norm": 0.626690149307251,
+      "learning_rate": 0.0002,
+      "loss": 2.0068,
+      "step": 850
+    },
+    {
+      "epoch": 1.9501133786848073,
+      "grad_norm": 0.6986100673675537,
+      "learning_rate": 0.0002,
+      "loss": 2.0443,
+      "step": 860
+    },
+    {
+      "epoch": 1.9727891156462585,
+      "grad_norm": 0.6573156118392944,
+      "learning_rate": 0.0002,
+      "loss": 2.0585,
+      "step": 870
+    },
+    {
+      "epoch": 1.99546485260771,
+      "grad_norm": 0.7589707374572754,
+      "learning_rate": 0.0002,
+      "loss": 2.0454,
+      "step": 880
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.073181629180908,
+      "eval_runtime": 14.6998,
+      "eval_samples_per_second": 34.49,
+      "eval_steps_per_second": 4.354,
+      "step": 882
+    },
+    {
+      "epoch": 2.018140589569161,
+      "grad_norm": 0.7971214056015015,
+      "learning_rate": 0.0002,
+      "loss": 2.015,
+      "step": 890
+    },
+    {
+      "epoch": 2.0408163265306123,
+      "grad_norm": 0.6144835948944092,
+      "learning_rate": 0.0002,
+      "loss": 1.982,
+      "step": 900
+    },
+    {
+      "epoch": 2.0634920634920633,
+      "grad_norm": 0.7324559688568115,
+      "learning_rate": 0.0002,
+      "loss": 1.9391,
+      "step": 910
+    },
+    {
+      "epoch": 2.0861678004535147,
+      "grad_norm": 0.6465244293212891,
+      "learning_rate": 0.0002,
+      "loss": 1.9066,
+      "step": 920
+    },
+    {
+      "epoch": 2.108843537414966,
+      "grad_norm": 0.7424528002738953,
+      "learning_rate": 0.0002,
+      "loss": 1.9893,
+      "step": 930
+    },
+    {
+      "epoch": 2.131519274376417,
+      "grad_norm": 0.6717734336853027,
+      "learning_rate": 0.0002,
+      "loss": 1.9193,
+      "step": 940
+    },
+    {
+      "epoch": 2.1541950113378685,
+      "grad_norm": 0.7873768210411072,
+      "learning_rate": 0.0002,
+      "loss": 1.9569,
+      "step": 950
+    },
+    {
+      "epoch": 2.17687074829932,
+      "grad_norm": 0.6752461194992065,
+      "learning_rate": 0.0002,
+      "loss": 1.9563,
+      "step": 960
+    },
+    {
+      "epoch": 2.199546485260771,
+      "grad_norm": 0.6919583082199097,
+      "learning_rate": 0.0002,
+      "loss": 2.0406,
+      "step": 970
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.6355509161949158,
+      "learning_rate": 0.0002,
+      "loss": 1.9281,
+      "step": 980
+    },
+    {
+      "epoch": 2.2448979591836733,
+      "grad_norm": 0.770007312297821,
+      "learning_rate": 0.0002,
+      "loss": 1.9953,
+      "step": 990
+    },
+    {
+      "epoch": 2.2675736961451247,
+      "grad_norm": 0.6216670870780945,
+      "learning_rate": 0.0002,
+      "loss": 1.9589,
+      "step": 1000
+    },
+    {
+      "epoch": 2.290249433106576,
+      "grad_norm": 0.6880573034286499,
+      "learning_rate": 0.0002,
+      "loss": 1.9247,
+      "step": 1010
+    },
+    {
+      "epoch": 2.312925170068027,
+      "grad_norm": 0.7346075177192688,
+      "learning_rate": 0.0002,
+      "loss": 1.9426,
+      "step": 1020
+    },
+    {
+      "epoch": 2.3356009070294785,
+      "grad_norm": 0.6651889681816101,
+      "learning_rate": 0.0002,
+      "loss": 1.9461,
+      "step": 1030
+    },
+    {
+      "epoch": 2.35827664399093,
+      "grad_norm": 0.7324103713035583,
+      "learning_rate": 0.0002,
+      "loss": 1.9147,
+      "step": 1040
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.7186149954795837,
+      "learning_rate": 0.0002,
+      "loss": 1.9142,
+      "step": 1050
+    },
+    {
+      "epoch": 2.4036281179138324,
+      "grad_norm": 0.6849178671836853,
+      "learning_rate": 0.0002,
+      "loss": 1.9501,
+      "step": 1060
+    },
+    {
+      "epoch": 2.4263038548752833,
+      "grad_norm": 0.6259638667106628,
+      "learning_rate": 0.0002,
+      "loss": 1.889,
+      "step": 1070
+    },
+    {
+      "epoch": 2.4489795918367347,
+      "grad_norm": 0.6821024417877197,
+      "learning_rate": 0.0002,
+      "loss": 1.9446,
+      "step": 1080
+    },
+    {
+      "epoch": 2.471655328798186,
+      "grad_norm": 0.7019884586334229,
+      "learning_rate": 0.0002,
+      "loss": 1.9398,
+      "step": 1090
+    },
+    {
+      "epoch": 2.494331065759637,
+      "grad_norm": 0.6368714570999146,
+      "learning_rate": 0.0002,
+      "loss": 1.9325,
+      "step": 1100
+    },
+    {
+      "epoch": 2.5170068027210886,
+      "grad_norm": 0.6608313918113708,
+      "learning_rate": 0.0002,
+      "loss": 1.9773,
+      "step": 1110
+    },
+    {
+      "epoch": 2.5396825396825395,
+      "grad_norm": 0.6855525970458984,
+      "learning_rate": 0.0002,
+      "loss": 1.9337,
+      "step": 1120
+    },
+    {
+      "epoch": 2.562358276643991,
+      "grad_norm": 0.7279609441757202,
+      "learning_rate": 0.0002,
+      "loss": 1.9347,
+      "step": 1130
+    },
+    {
+      "epoch": 2.5850340136054424,
+      "grad_norm": 0.6539294123649597,
+      "learning_rate": 0.0002,
+      "loss": 1.9508,
+      "step": 1140
+    },
+    {
+      "epoch": 2.6077097505668934,
+      "grad_norm": 0.7035511136054993,
+      "learning_rate": 0.0002,
+      "loss": 2.0517,
+      "step": 1150
+    },
+    {
+      "epoch": 2.630385487528345,
+      "grad_norm": 0.7031794786453247,
+      "learning_rate": 0.0002,
+      "loss": 1.9955,
+      "step": 1160
+    },
+    {
+      "epoch": 2.6530612244897958,
+      "grad_norm": 0.7587798833847046,
+      "learning_rate": 0.0002,
+      "loss": 1.9549,
+      "step": 1170
+    },
+    {
+      "epoch": 2.675736961451247,
+      "grad_norm": 0.707339882850647,
+      "learning_rate": 0.0002,
+      "loss": 2.0014,
+      "step": 1180
+    },
+    {
+      "epoch": 2.6984126984126986,
+      "grad_norm": 0.6633496880531311,
+      "learning_rate": 0.0002,
+      "loss": 1.955,
+      "step": 1190
+    },
+    {
+      "epoch": 2.7210884353741496,
+      "grad_norm": 0.9233061671257019,
+      "learning_rate": 0.0002,
+      "loss": 1.9434,
+      "step": 1200
+    },
+    {
+      "epoch": 2.743764172335601,
+      "grad_norm": 0.6396011710166931,
+      "learning_rate": 0.0002,
+      "loss": 1.9146,
+      "step": 1210
+    },
+    {
+      "epoch": 2.766439909297052,
+      "grad_norm": 0.6500924229621887,
+      "learning_rate": 0.0002,
+      "loss": 1.9934,
+      "step": 1220
+    },
+    {
+      "epoch": 2.7891156462585034,
+      "grad_norm": 0.6185927391052246,
+      "learning_rate": 0.0002,
+      "loss": 1.9197,
+      "step": 1230
+    },
+    {
+      "epoch": 2.811791383219955,
+      "grad_norm": 0.6737818717956543,
+      "learning_rate": 0.0002,
+      "loss": 1.9809,
+      "step": 1240
+    },
+    {
+      "epoch": 2.834467120181406,
+      "grad_norm": 0.8148701786994934,
+      "learning_rate": 0.0002,
+      "loss": 1.9508,
+      "step": 1250
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.7563779354095459,
+      "learning_rate": 0.0002,
+      "loss": 1.9848,
+      "step": 1260
+    },
+    {
+      "epoch": 2.879818594104308,
+      "grad_norm": 0.6679276823997498,
+      "learning_rate": 0.0002,
+      "loss": 1.9822,
+      "step": 1270
+    },
+    {
+      "epoch": 2.9024943310657596,
+      "grad_norm": 0.7446274757385254,
+      "learning_rate": 0.0002,
+      "loss": 2.0609,
+      "step": 1280
+    },
+    {
+      "epoch": 2.925170068027211,
+      "grad_norm": 0.6530991196632385,
+      "learning_rate": 0.0002,
+      "loss": 1.9251,
+      "step": 1290
+    },
+    {
+      "epoch": 2.947845804988662,
+      "grad_norm": 0.6491292119026184,
+      "learning_rate": 0.0002,
+      "loss": 1.9555,
+      "step": 1300
+    },
+    {
+      "epoch": 2.9705215419501134,
+      "grad_norm": 0.6711354851722717,
+      "learning_rate": 0.0002,
+      "loss": 1.913,
+      "step": 1310
+    },
+    {
+      "epoch": 2.9931972789115644,
+      "grad_norm": 0.6327161192893982,
+      "learning_rate": 0.0002,
+      "loss": 2.0005,
+      "step": 1320
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.061427116394043,
+      "eval_runtime": 19.6731,
+      "eval_samples_per_second": 25.771,
+      "eval_steps_per_second": 3.253,
+      "step": 1323
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3528,
+  "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": 1.6169701151342592e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1323/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49bd01b61e91780113d7cfd71d7d1da24fc61dfbff2f52441a1dd4793ec50fda
+size 5560

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1764/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **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]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+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
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[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

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1764/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "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
+}

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1764/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d40dc0076f9408cf439ef597eee90d25c8010d4c697cbdb72719852ccc93301
+size 29500848

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1764/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f386c7ebef35dc79f063801ee7f6df708cd069f8df5cca7ad7f88b066b8e4643
+size 15064314

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1764/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d862ecc16e3b212ed748acf953a6d6fd8467788b13353a8a7f520862115f016
+size 14244

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1764/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c56e47336a16ef9e258bc2b03be58373a485c239c4356f8555fd6d380b5e131c
+size 1064

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1764/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1764/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f559f2189f392b4555613965f089e7c4d300b41fbe080bf79da0d676e33ee7f0
+size 34356041

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1764/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1764/tokenizer_config.json

@@ -0,0 +1,1757 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1764/trainer_state.json

@@ -0,0 +1,1297 @@
+{
+  "best_metric": 2.061427116394043,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1323",
+  "epoch": 4.0,
+  "eval_steps": 10,
+  "global_step": 1764,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022675736961451247,
+      "grad_norm": 1.8457136154174805,
+      "learning_rate": 0.0002,
+      "loss": 4.7982,
+      "step": 10
+    },
+    {
+      "epoch": 0.045351473922902494,
+      "grad_norm": 1.0967960357666016,
+      "learning_rate": 0.0002,
+      "loss": 3.71,
+      "step": 20
+    },
+    {
+      "epoch": 0.06802721088435375,
+      "grad_norm": 0.8257759213447571,
+      "learning_rate": 0.0002,
+      "loss": 3.3086,
+      "step": 30
+    },
+    {
+      "epoch": 0.09070294784580499,
+      "grad_norm": 0.8248435258865356,
+      "learning_rate": 0.0002,
+      "loss": 2.923,
+      "step": 40
+    },
+    {
+      "epoch": 0.11337868480725624,
+      "grad_norm": 1.1190264225006104,
+      "learning_rate": 0.0002,
+      "loss": 2.8263,
+      "step": 50
+    },
+    {
+      "epoch": 0.1360544217687075,
+      "grad_norm": 1.273951768875122,
+      "learning_rate": 0.0002,
+      "loss": 2.6239,
+      "step": 60
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 1.0004316568374634,
+      "learning_rate": 0.0002,
+      "loss": 2.5203,
+      "step": 70
+    },
+    {
+      "epoch": 0.18140589569160998,
+      "grad_norm": 0.8296012878417969,
+      "learning_rate": 0.0002,
+      "loss": 2.5055,
+      "step": 80
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 1.1563128232955933,
+      "learning_rate": 0.0002,
+      "loss": 2.5255,
+      "step": 90
+    },
+    {
+      "epoch": 0.22675736961451248,
+      "grad_norm": 0.7863451838493347,
+      "learning_rate": 0.0002,
+      "loss": 2.4731,
+      "step": 100
+    },
+    {
+      "epoch": 0.2494331065759637,
+      "grad_norm": 0.9167478680610657,
+      "learning_rate": 0.0002,
+      "loss": 2.3688,
+      "step": 110
+    },
+    {
+      "epoch": 0.272108843537415,
+      "grad_norm": 1.104406476020813,
+      "learning_rate": 0.0002,
+      "loss": 2.336,
+      "step": 120
+    },
+    {
+      "epoch": 0.2947845804988662,
+      "grad_norm": 1.109564185142517,
+      "learning_rate": 0.0002,
+      "loss": 2.3063,
+      "step": 130
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.7416750192642212,
+      "learning_rate": 0.0002,
+      "loss": 2.23,
+      "step": 140
+    },
+    {
+      "epoch": 0.3401360544217687,
+      "grad_norm": 1.1499258279800415,
+      "learning_rate": 0.0002,
+      "loss": 2.3346,
+      "step": 150
+    },
+    {
+      "epoch": 0.36281179138321995,
+      "grad_norm": 0.9961133599281311,
+      "learning_rate": 0.0002,
+      "loss": 2.2853,
+      "step": 160
+    },
+    {
+      "epoch": 0.3854875283446712,
+      "grad_norm": 0.9257232546806335,
+      "learning_rate": 0.0002,
+      "loss": 2.2731,
+      "step": 170
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 1.098513126373291,
+      "learning_rate": 0.0002,
+      "loss": 2.1986,
+      "step": 180
+    },
+    {
+      "epoch": 0.4308390022675737,
+      "grad_norm": 0.8935237526893616,
+      "learning_rate": 0.0002,
+      "loss": 2.1685,
+      "step": 190
+    },
+    {
+      "epoch": 0.45351473922902497,
+      "grad_norm": 0.9654302597045898,
+      "learning_rate": 0.0002,
+      "loss": 2.2077,
+      "step": 200
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.9273215532302856,
+      "learning_rate": 0.0002,
+      "loss": 2.2421,
+      "step": 210
+    },
+    {
+      "epoch": 0.4988662131519274,
+      "grad_norm": 0.7222742438316345,
+      "learning_rate": 0.0002,
+      "loss": 2.1973,
+      "step": 220
+    },
+    {
+      "epoch": 0.5215419501133787,
+      "grad_norm": 0.7825018763542175,
+      "learning_rate": 0.0002,
+      "loss": 2.0619,
+      "step": 230
+    },
+    {
+      "epoch": 0.54421768707483,
+      "grad_norm": 0.7758685350418091,
+      "learning_rate": 0.0002,
+      "loss": 2.2247,
+      "step": 240
+    },
+    {
+      "epoch": 0.5668934240362812,
+      "grad_norm": 0.916719913482666,
+      "learning_rate": 0.0002,
+      "loss": 2.1518,
+      "step": 250
+    },
+    {
+      "epoch": 0.5895691609977324,
+      "grad_norm": 0.696332573890686,
+      "learning_rate": 0.0002,
+      "loss": 2.0614,
+      "step": 260
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 0.7362682223320007,
+      "learning_rate": 0.0002,
+      "loss": 2.0763,
+      "step": 270
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.8184517025947571,
+      "learning_rate": 0.0002,
+      "loss": 2.223,
+      "step": 280
+    },
+    {
+      "epoch": 0.6575963718820862,
+      "grad_norm": 0.7944937348365784,
+      "learning_rate": 0.0002,
+      "loss": 2.1634,
+      "step": 290
+    },
+    {
+      "epoch": 0.6802721088435374,
+      "grad_norm": 0.7258933186531067,
+      "learning_rate": 0.0002,
+      "loss": 2.0922,
+      "step": 300
+    },
+    {
+      "epoch": 0.7029478458049887,
+      "grad_norm": 0.7037094831466675,
+      "learning_rate": 0.0002,
+      "loss": 2.1221,
+      "step": 310
+    },
+    {
+      "epoch": 0.7256235827664399,
+      "grad_norm": 0.7499093413352966,
+      "learning_rate": 0.0002,
+      "loss": 2.1132,
+      "step": 320
+    },
+    {
+      "epoch": 0.7482993197278912,
+      "grad_norm": 0.7725803256034851,
+      "learning_rate": 0.0002,
+      "loss": 2.2321,
+      "step": 330
+    },
+    {
+      "epoch": 0.7709750566893424,
+      "grad_norm": 0.6771686673164368,
+      "learning_rate": 0.0002,
+      "loss": 2.1611,
+      "step": 340
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "grad_norm": 0.7557646036148071,
+      "learning_rate": 0.0002,
+      "loss": 2.0693,
+      "step": 350
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.7430537939071655,
+      "learning_rate": 0.0002,
+      "loss": 2.0629,
+      "step": 360
+    },
+    {
+      "epoch": 0.8390022675736961,
+      "grad_norm": 0.8602280616760254,
+      "learning_rate": 0.0002,
+      "loss": 2.0731,
+      "step": 370
+    },
+    {
+      "epoch": 0.8616780045351474,
+      "grad_norm": 0.753440260887146,
+      "learning_rate": 0.0002,
+      "loss": 2.1836,
+      "step": 380
+    },
+    {
+      "epoch": 0.8843537414965986,
+      "grad_norm": 0.7217596769332886,
+      "learning_rate": 0.0002,
+      "loss": 2.1186,
+      "step": 390
+    },
+    {
+      "epoch": 0.9070294784580499,
+      "grad_norm": 0.6116304397583008,
+      "learning_rate": 0.0002,
+      "loss": 2.0223,
+      "step": 400
+    },
+    {
+      "epoch": 0.9297052154195011,
+      "grad_norm": 0.6829515695571899,
+      "learning_rate": 0.0002,
+      "loss": 2.0491,
+      "step": 410
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.733259916305542,
+      "learning_rate": 0.0002,
+      "loss": 2.1518,
+      "step": 420
+    },
+    {
+      "epoch": 0.9750566893424036,
+      "grad_norm": 0.6036455035209656,
+      "learning_rate": 0.0002,
+      "loss": 2.076,
+      "step": 430
+    },
+    {
+      "epoch": 0.9977324263038548,
+      "grad_norm": 0.8478217720985413,
+      "learning_rate": 0.0002,
+      "loss": 2.1526,
+      "step": 440
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.114302158355713,
+      "eval_runtime": 16.5108,
+      "eval_samples_per_second": 30.707,
+      "eval_steps_per_second": 3.876,
+      "step": 441
+    },
+    {
+      "epoch": 1.0204081632653061,
+      "grad_norm": 0.6996896266937256,
+      "learning_rate": 0.0002,
+      "loss": 1.9967,
+      "step": 450
+    },
+    {
+      "epoch": 1.0430839002267573,
+      "grad_norm": 0.7616267800331116,
+      "learning_rate": 0.0002,
+      "loss": 2.0471,
+      "step": 460
+    },
+    {
+      "epoch": 1.0657596371882085,
+      "grad_norm": 0.5978519320487976,
+      "learning_rate": 0.0002,
+      "loss": 2.0674,
+      "step": 470
+    },
+    {
+      "epoch": 1.08843537414966,
+      "grad_norm": 0.703987717628479,
+      "learning_rate": 0.0002,
+      "loss": 2.0803,
+      "step": 480
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.6707539558410645,
+      "learning_rate": 0.0002,
+      "loss": 2.0215,
+      "step": 490
+    },
+    {
+      "epoch": 1.1337868480725624,
+      "grad_norm": 0.6343862414360046,
+      "learning_rate": 0.0002,
+      "loss": 2.045,
+      "step": 500
+    },
+    {
+      "epoch": 1.1564625850340136,
+      "grad_norm": 0.8836050033569336,
+      "learning_rate": 0.0002,
+      "loss": 1.9753,
+      "step": 510
+    },
+    {
+      "epoch": 1.179138321995465,
+      "grad_norm": 0.6288692951202393,
+      "learning_rate": 0.0002,
+      "loss": 1.9537,
+      "step": 520
+    },
+    {
+      "epoch": 1.2018140589569162,
+      "grad_norm": 0.6671382784843445,
+      "learning_rate": 0.0002,
+      "loss": 2.0072,
+      "step": 530
+    },
+    {
+      "epoch": 1.2244897959183674,
+      "grad_norm": 0.7260547876358032,
+      "learning_rate": 0.0002,
+      "loss": 2.0631,
+      "step": 540
+    },
+    {
+      "epoch": 1.2471655328798186,
+      "grad_norm": 0.6919140219688416,
+      "learning_rate": 0.0002,
+      "loss": 2.1395,
+      "step": 550
+    },
+    {
+      "epoch": 1.2698412698412698,
+      "grad_norm": 0.6895381212234497,
+      "learning_rate": 0.0002,
+      "loss": 2.1162,
+      "step": 560
+    },
+    {
+      "epoch": 1.2925170068027212,
+      "grad_norm": 0.7131213545799255,
+      "learning_rate": 0.0002,
+      "loss": 2.1023,
+      "step": 570
+    },
+    {
+      "epoch": 1.3151927437641724,
+      "grad_norm": 0.6087185144424438,
+      "learning_rate": 0.0002,
+      "loss": 2.0381,
+      "step": 580
+    },
+    {
+      "epoch": 1.3378684807256236,
+      "grad_norm": 0.6506251096725464,
+      "learning_rate": 0.0002,
+      "loss": 2.054,
+      "step": 590
+    },
+    {
+      "epoch": 1.3605442176870748,
+      "grad_norm": 0.6999365091323853,
+      "learning_rate": 0.0002,
+      "loss": 2.0669,
+      "step": 600
+    },
+    {
+      "epoch": 1.383219954648526,
+      "grad_norm": 0.6305016875267029,
+      "learning_rate": 0.0002,
+      "loss": 2.0121,
+      "step": 610
+    },
+    {
+      "epoch": 1.4058956916099774,
+      "grad_norm": 0.6413465142250061,
+      "learning_rate": 0.0002,
+      "loss": 1.9727,
+      "step": 620
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.7571105360984802,
+      "learning_rate": 0.0002,
+      "loss": 2.0676,
+      "step": 630
+    },
+    {
+      "epoch": 1.4512471655328798,
+      "grad_norm": 0.8087857365608215,
+      "learning_rate": 0.0002,
+      "loss": 2.0838,
+      "step": 640
+    },
+    {
+      "epoch": 1.473922902494331,
+      "grad_norm": 0.6284025311470032,
+      "learning_rate": 0.0002,
+      "loss": 1.9932,
+      "step": 650
+    },
+    {
+      "epoch": 1.4965986394557822,
+      "grad_norm": 0.6630339026451111,
+      "learning_rate": 0.0002,
+      "loss": 2.0456,
+      "step": 660
+    },
+    {
+      "epoch": 1.5192743764172336,
+      "grad_norm": 0.6777389645576477,
+      "learning_rate": 0.0002,
+      "loss": 2.0778,
+      "step": 670
+    },
+    {
+      "epoch": 1.5419501133786848,
+      "grad_norm": 0.6965354681015015,
+      "learning_rate": 0.0002,
+      "loss": 2.0437,
+      "step": 680
+    },
+    {
+      "epoch": 1.564625850340136,
+      "grad_norm": 0.7124104499816895,
+      "learning_rate": 0.0002,
+      "loss": 2.056,
+      "step": 690
+    },
+    {
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.6652887463569641,
+      "learning_rate": 0.0002,
+      "loss": 1.989,
+      "step": 700
+    },
+    {
+      "epoch": 1.6099773242630384,
+      "grad_norm": 0.6061141490936279,
+      "learning_rate": 0.0002,
+      "loss": 2.0419,
+      "step": 710
+    },
+    {
+      "epoch": 1.6326530612244898,
+      "grad_norm": 0.8291212320327759,
+      "learning_rate": 0.0002,
+      "loss": 2.0257,
+      "step": 720
+    },
+    {
+      "epoch": 1.655328798185941,
+      "grad_norm": 0.6672369241714478,
+      "learning_rate": 0.0002,
+      "loss": 2.0776,
+      "step": 730
+    },
+    {
+      "epoch": 1.6780045351473922,
+      "grad_norm": 0.6301238536834717,
+      "learning_rate": 0.0002,
+      "loss": 1.9834,
+      "step": 740
+    },
+    {
+      "epoch": 1.7006802721088436,
+      "grad_norm": 0.7217460870742798,
+      "learning_rate": 0.0002,
+      "loss": 2.0176,
+      "step": 750
+    },
+    {
+      "epoch": 1.7233560090702946,
+      "grad_norm": 0.6720302104949951,
+      "learning_rate": 0.0002,
+      "loss": 2.0793,
+      "step": 760
+    },
+    {
+      "epoch": 1.746031746031746,
+      "grad_norm": 0.8228253722190857,
+      "learning_rate": 0.0002,
+      "loss": 2.0417,
+      "step": 770
+    },
+    {
+      "epoch": 1.7687074829931972,
+      "grad_norm": 0.6359929442405701,
+      "learning_rate": 0.0002,
+      "loss": 2.0198,
+      "step": 780
+    },
+    {
+      "epoch": 1.7913832199546484,
+      "grad_norm": 0.6594814658164978,
+      "learning_rate": 0.0002,
+      "loss": 1.99,
+      "step": 790
+    },
+    {
+      "epoch": 1.8140589569160999,
+      "grad_norm": 0.6135239601135254,
+      "learning_rate": 0.0002,
+      "loss": 2.0752,
+      "step": 800
+    },
+    {
+      "epoch": 1.836734693877551,
+      "grad_norm": 0.6736067533493042,
+      "learning_rate": 0.0002,
+      "loss": 2.0397,
+      "step": 810
+    },
+    {
+      "epoch": 1.8594104308390023,
+      "grad_norm": 0.7712678909301758,
+      "learning_rate": 0.0002,
+      "loss": 2.0545,
+      "step": 820
+    },
+    {
+      "epoch": 1.8820861678004537,
+      "grad_norm": 0.6950375437736511,
+      "learning_rate": 0.0002,
+      "loss": 1.9644,
+      "step": 830
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.5913259387016296,
+      "learning_rate": 0.0002,
+      "loss": 1.9272,
+      "step": 840
+    },
+    {
+      "epoch": 1.927437641723356,
+      "grad_norm": 0.626690149307251,
+      "learning_rate": 0.0002,
+      "loss": 2.0068,
+      "step": 850
+    },
+    {
+      "epoch": 1.9501133786848073,
+      "grad_norm": 0.6986100673675537,
+      "learning_rate": 0.0002,
+      "loss": 2.0443,
+      "step": 860
+    },
+    {
+      "epoch": 1.9727891156462585,
+      "grad_norm": 0.6573156118392944,
+      "learning_rate": 0.0002,
+      "loss": 2.0585,
+      "step": 870
+    },
+    {
+      "epoch": 1.99546485260771,
+      "grad_norm": 0.7589707374572754,
+      "learning_rate": 0.0002,
+      "loss": 2.0454,
+      "step": 880
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.073181629180908,
+      "eval_runtime": 14.6998,
+      "eval_samples_per_second": 34.49,
+      "eval_steps_per_second": 4.354,
+      "step": 882
+    },
+    {
+      "epoch": 2.018140589569161,
+      "grad_norm": 0.7971214056015015,
+      "learning_rate": 0.0002,
+      "loss": 2.015,
+      "step": 890
+    },
+    {
+      "epoch": 2.0408163265306123,
+      "grad_norm": 0.6144835948944092,
+      "learning_rate": 0.0002,
+      "loss": 1.982,
+      "step": 900
+    },
+    {
+      "epoch": 2.0634920634920633,
+      "grad_norm": 0.7324559688568115,
+      "learning_rate": 0.0002,
+      "loss": 1.9391,
+      "step": 910
+    },
+    {
+      "epoch": 2.0861678004535147,
+      "grad_norm": 0.6465244293212891,
+      "learning_rate": 0.0002,
+      "loss": 1.9066,
+      "step": 920
+    },
+    {
+      "epoch": 2.108843537414966,
+      "grad_norm": 0.7424528002738953,
+      "learning_rate": 0.0002,
+      "loss": 1.9893,
+      "step": 930
+    },
+    {
+      "epoch": 2.131519274376417,
+      "grad_norm": 0.6717734336853027,
+      "learning_rate": 0.0002,
+      "loss": 1.9193,
+      "step": 940
+    },
+    {
+      "epoch": 2.1541950113378685,
+      "grad_norm": 0.7873768210411072,
+      "learning_rate": 0.0002,
+      "loss": 1.9569,
+      "step": 950
+    },
+    {
+      "epoch": 2.17687074829932,
+      "grad_norm": 0.6752461194992065,
+      "learning_rate": 0.0002,
+      "loss": 1.9563,
+      "step": 960
+    },
+    {
+      "epoch": 2.199546485260771,
+      "grad_norm": 0.6919583082199097,
+      "learning_rate": 0.0002,
+      "loss": 2.0406,
+      "step": 970
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.6355509161949158,
+      "learning_rate": 0.0002,
+      "loss": 1.9281,
+      "step": 980
+    },
+    {
+      "epoch": 2.2448979591836733,
+      "grad_norm": 0.770007312297821,
+      "learning_rate": 0.0002,
+      "loss": 1.9953,
+      "step": 990
+    },
+    {
+      "epoch": 2.2675736961451247,
+      "grad_norm": 0.6216670870780945,
+      "learning_rate": 0.0002,
+      "loss": 1.9589,
+      "step": 1000
+    },
+    {
+      "epoch": 2.290249433106576,
+      "grad_norm": 0.6880573034286499,
+      "learning_rate": 0.0002,
+      "loss": 1.9247,
+      "step": 1010
+    },
+    {
+      "epoch": 2.312925170068027,
+      "grad_norm": 0.7346075177192688,
+      "learning_rate": 0.0002,
+      "loss": 1.9426,
+      "step": 1020
+    },
+    {
+      "epoch": 2.3356009070294785,
+      "grad_norm": 0.6651889681816101,
+      "learning_rate": 0.0002,
+      "loss": 1.9461,
+      "step": 1030
+    },
+    {
+      "epoch": 2.35827664399093,
+      "grad_norm": 0.7324103713035583,
+      "learning_rate": 0.0002,
+      "loss": 1.9147,
+      "step": 1040
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.7186149954795837,
+      "learning_rate": 0.0002,
+      "loss": 1.9142,
+      "step": 1050
+    },
+    {
+      "epoch": 2.4036281179138324,
+      "grad_norm": 0.6849178671836853,
+      "learning_rate": 0.0002,
+      "loss": 1.9501,
+      "step": 1060
+    },
+    {
+      "epoch": 2.4263038548752833,
+      "grad_norm": 0.6259638667106628,
+      "learning_rate": 0.0002,
+      "loss": 1.889,
+      "step": 1070
+    },
+    {
+      "epoch": 2.4489795918367347,
+      "grad_norm": 0.6821024417877197,
+      "learning_rate": 0.0002,
+      "loss": 1.9446,
+      "step": 1080
+    },
+    {
+      "epoch": 2.471655328798186,
+      "grad_norm": 0.7019884586334229,
+      "learning_rate": 0.0002,
+      "loss": 1.9398,
+      "step": 1090
+    },
+    {
+      "epoch": 2.494331065759637,
+      "grad_norm": 0.6368714570999146,
+      "learning_rate": 0.0002,
+      "loss": 1.9325,
+      "step": 1100
+    },
+    {
+      "epoch": 2.5170068027210886,
+      "grad_norm": 0.6608313918113708,
+      "learning_rate": 0.0002,
+      "loss": 1.9773,
+      "step": 1110
+    },
+    {
+      "epoch": 2.5396825396825395,
+      "grad_norm": 0.6855525970458984,
+      "learning_rate": 0.0002,
+      "loss": 1.9337,
+      "step": 1120
+    },
+    {
+      "epoch": 2.562358276643991,
+      "grad_norm": 0.7279609441757202,
+      "learning_rate": 0.0002,
+      "loss": 1.9347,
+      "step": 1130
+    },
+    {
+      "epoch": 2.5850340136054424,
+      "grad_norm": 0.6539294123649597,
+      "learning_rate": 0.0002,
+      "loss": 1.9508,
+      "step": 1140
+    },
+    {
+      "epoch": 2.6077097505668934,
+      "grad_norm": 0.7035511136054993,
+      "learning_rate": 0.0002,
+      "loss": 2.0517,
+      "step": 1150
+    },
+    {
+      "epoch": 2.630385487528345,
+      "grad_norm": 0.7031794786453247,
+      "learning_rate": 0.0002,
+      "loss": 1.9955,
+      "step": 1160
+    },
+    {
+      "epoch": 2.6530612244897958,
+      "grad_norm": 0.7587798833847046,
+      "learning_rate": 0.0002,
+      "loss": 1.9549,
+      "step": 1170
+    },
+    {
+      "epoch": 2.675736961451247,
+      "grad_norm": 0.707339882850647,
+      "learning_rate": 0.0002,
+      "loss": 2.0014,
+      "step": 1180
+    },
+    {
+      "epoch": 2.6984126984126986,
+      "grad_norm": 0.6633496880531311,
+      "learning_rate": 0.0002,
+      "loss": 1.955,
+      "step": 1190
+    },
+    {
+      "epoch": 2.7210884353741496,
+      "grad_norm": 0.9233061671257019,
+      "learning_rate": 0.0002,
+      "loss": 1.9434,
+      "step": 1200
+    },
+    {
+      "epoch": 2.743764172335601,
+      "grad_norm": 0.6396011710166931,
+      "learning_rate": 0.0002,
+      "loss": 1.9146,
+      "step": 1210
+    },
+    {
+      "epoch": 2.766439909297052,
+      "grad_norm": 0.6500924229621887,
+      "learning_rate": 0.0002,
+      "loss": 1.9934,
+      "step": 1220
+    },
+    {
+      "epoch": 2.7891156462585034,
+      "grad_norm": 0.6185927391052246,
+      "learning_rate": 0.0002,
+      "loss": 1.9197,
+      "step": 1230
+    },
+    {
+      "epoch": 2.811791383219955,
+      "grad_norm": 0.6737818717956543,
+      "learning_rate": 0.0002,
+      "loss": 1.9809,
+      "step": 1240
+    },
+    {
+      "epoch": 2.834467120181406,
+      "grad_norm": 0.8148701786994934,
+      "learning_rate": 0.0002,
+      "loss": 1.9508,
+      "step": 1250
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.7563779354095459,
+      "learning_rate": 0.0002,
+      "loss": 1.9848,
+      "step": 1260
+    },
+    {
+      "epoch": 2.879818594104308,
+      "grad_norm": 0.6679276823997498,
+      "learning_rate": 0.0002,
+      "loss": 1.9822,
+      "step": 1270
+    },
+    {
+      "epoch": 2.9024943310657596,
+      "grad_norm": 0.7446274757385254,
+      "learning_rate": 0.0002,
+      "loss": 2.0609,
+      "step": 1280
+    },
+    {
+      "epoch": 2.925170068027211,
+      "grad_norm": 0.6530991196632385,
+      "learning_rate": 0.0002,
+      "loss": 1.9251,
+      "step": 1290
+    },
+    {
+      "epoch": 2.947845804988662,
+      "grad_norm": 0.6491292119026184,
+      "learning_rate": 0.0002,
+      "loss": 1.9555,
+      "step": 1300
+    },
+    {
+      "epoch": 2.9705215419501134,
+      "grad_norm": 0.6711354851722717,
+      "learning_rate": 0.0002,
+      "loss": 1.913,
+      "step": 1310
+    },
+    {
+      "epoch": 2.9931972789115644,
+      "grad_norm": 0.6327161192893982,
+      "learning_rate": 0.0002,
+      "loss": 2.0005,
+      "step": 1320
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.061427116394043,
+      "eval_runtime": 19.6731,
+      "eval_samples_per_second": 25.771,
+      "eval_steps_per_second": 3.253,
+      "step": 1323
+    },
+    {
+      "epoch": 3.015873015873016,
+      "grad_norm": 0.625606119632721,
+      "learning_rate": 0.0002,
+      "loss": 1.8798,
+      "step": 1330
+    },
+    {
+      "epoch": 3.0385487528344672,
+      "grad_norm": 0.6679854989051819,
+      "learning_rate": 0.0002,
+      "loss": 1.8229,
+      "step": 1340
+    },
+    {
+      "epoch": 3.061224489795918,
+      "grad_norm": 0.6756007671356201,
+      "learning_rate": 0.0002,
+      "loss": 1.8593,
+      "step": 1350
+    },
+    {
+      "epoch": 3.0839002267573696,
+      "grad_norm": 0.8019710779190063,
+      "learning_rate": 0.0002,
+      "loss": 1.8126,
+      "step": 1360
+    },
+    {
+      "epoch": 3.106575963718821,
+      "grad_norm": 0.9087499976158142,
+      "learning_rate": 0.0002,
+      "loss": 1.8593,
+      "step": 1370
+    },
+    {
+      "epoch": 3.129251700680272,
+      "grad_norm": 0.7627860903739929,
+      "learning_rate": 0.0002,
+      "loss": 1.8951,
+      "step": 1380
+    },
+    {
+      "epoch": 3.1519274376417235,
+      "grad_norm": 0.761993944644928,
+      "learning_rate": 0.0002,
+      "loss": 1.8308,
+      "step": 1390
+    },
+    {
+      "epoch": 3.1746031746031744,
+      "grad_norm": 0.6993107795715332,
+      "learning_rate": 0.0002,
+      "loss": 1.9513,
+      "step": 1400
+    },
+    {
+      "epoch": 3.197278911564626,
+      "grad_norm": 0.6398035287857056,
+      "learning_rate": 0.0002,
+      "loss": 1.8857,
+      "step": 1410
+    },
+    {
+      "epoch": 3.2199546485260773,
+      "grad_norm": 0.8602580428123474,
+      "learning_rate": 0.0002,
+      "loss": 1.9041,
+      "step": 1420
+    },
+    {
+      "epoch": 3.2426303854875282,
+      "grad_norm": 0.7799932360649109,
+      "learning_rate": 0.0002,
+      "loss": 1.9629,
+      "step": 1430
+    },
+    {
+      "epoch": 3.2653061224489797,
+      "grad_norm": 0.6598666906356812,
+      "learning_rate": 0.0002,
+      "loss": 1.8352,
+      "step": 1440
+    },
+    {
+      "epoch": 3.287981859410431,
+      "grad_norm": 0.6513776779174805,
+      "learning_rate": 0.0002,
+      "loss": 1.8772,
+      "step": 1450
+    },
+    {
+      "epoch": 3.310657596371882,
+      "grad_norm": 0.7690088748931885,
+      "learning_rate": 0.0002,
+      "loss": 1.8568,
+      "step": 1460
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 1.0070042610168457,
+      "learning_rate": 0.0002,
+      "loss": 1.8535,
+      "step": 1470
+    },
+    {
+      "epoch": 3.3560090702947845,
+      "grad_norm": 0.8606905341148376,
+      "learning_rate": 0.0002,
+      "loss": 1.8971,
+      "step": 1480
+    },
+    {
+      "epoch": 3.378684807256236,
+      "grad_norm": 0.7596806287765503,
+      "learning_rate": 0.0002,
+      "loss": 1.8386,
+      "step": 1490
+    },
+    {
+      "epoch": 3.4013605442176873,
+      "grad_norm": 0.6961908936500549,
+      "learning_rate": 0.0002,
+      "loss": 1.9278,
+      "step": 1500
+    },
+    {
+      "epoch": 3.4240362811791383,
+      "grad_norm": 0.8368703126907349,
+      "learning_rate": 0.0002,
+      "loss": 1.8908,
+      "step": 1510
+    },
+    {
+      "epoch": 3.4467120181405897,
+      "grad_norm": 0.6655045747756958,
+      "learning_rate": 0.0002,
+      "loss": 1.924,
+      "step": 1520
+    },
+    {
+      "epoch": 3.4693877551020407,
+      "grad_norm": 0.7557174563407898,
+      "learning_rate": 0.0002,
+      "loss": 1.8273,
+      "step": 1530
+    },
+    {
+      "epoch": 3.492063492063492,
+      "grad_norm": 0.6713934540748596,
+      "learning_rate": 0.0002,
+      "loss": 1.8435,
+      "step": 1540
+    },
+    {
+      "epoch": 3.5147392290249435,
+      "grad_norm": 0.7006916999816895,
+      "learning_rate": 0.0002,
+      "loss": 1.9016,
+      "step": 1550
+    },
+    {
+      "epoch": 3.5374149659863945,
+      "grad_norm": 0.6728846430778503,
+      "learning_rate": 0.0002,
+      "loss": 1.9208,
+      "step": 1560
+    },
+    {
+      "epoch": 3.560090702947846,
+      "grad_norm": 0.7479315400123596,
+      "learning_rate": 0.0002,
+      "loss": 1.8769,
+      "step": 1570
+    },
+    {
+      "epoch": 3.582766439909297,
+      "grad_norm": 0.7596876621246338,
+      "learning_rate": 0.0002,
+      "loss": 1.8558,
+      "step": 1580
+    },
+    {
+      "epoch": 3.6054421768707483,
+      "grad_norm": 0.8948362469673157,
+      "learning_rate": 0.0002,
+      "loss": 1.876,
+      "step": 1590
+    },
+    {
+      "epoch": 3.6281179138321997,
+      "grad_norm": 0.6952481269836426,
+      "learning_rate": 0.0002,
+      "loss": 1.8552,
+      "step": 1600
+    },
+    {
+      "epoch": 3.6507936507936507,
+      "grad_norm": 0.6494414210319519,
+      "learning_rate": 0.0002,
+      "loss": 1.933,
+      "step": 1610
+    },
+    {
+      "epoch": 3.673469387755102,
+      "grad_norm": 0.7438889145851135,
+      "learning_rate": 0.0002,
+      "loss": 1.8516,
+      "step": 1620
+    },
+    {
+      "epoch": 3.696145124716553,
+      "grad_norm": 0.7470757961273193,
+      "learning_rate": 0.0002,
+      "loss": 1.9441,
+      "step": 1630
+    },
+    {
+      "epoch": 3.7188208616780045,
+      "grad_norm": 0.8727335333824158,
+      "learning_rate": 0.0002,
+      "loss": 1.8685,
+      "step": 1640
+    },
+    {
+      "epoch": 3.741496598639456,
+      "grad_norm": 0.7064452767372131,
+      "learning_rate": 0.0002,
+      "loss": 1.8831,
+      "step": 1650
+    },
+    {
+      "epoch": 3.764172335600907,
+      "grad_norm": 0.6958122849464417,
+      "learning_rate": 0.0002,
+      "loss": 1.9743,
+      "step": 1660
+    },
+    {
+      "epoch": 3.7868480725623583,
+      "grad_norm": 0.6751590371131897,
+      "learning_rate": 0.0002,
+      "loss": 1.927,
+      "step": 1670
+    },
+    {
+      "epoch": 3.8095238095238093,
+      "grad_norm": 0.7274497151374817,
+      "learning_rate": 0.0002,
+      "loss": 1.8868,
+      "step": 1680
+    },
+    {
+      "epoch": 3.8321995464852607,
+      "grad_norm": 0.7311708331108093,
+      "learning_rate": 0.0002,
+      "loss": 1.942,
+      "step": 1690
+    },
+    {
+      "epoch": 3.854875283446712,
+      "grad_norm": 0.6703173518180847,
+      "learning_rate": 0.0002,
+      "loss": 1.8134,
+      "step": 1700
+    },
+    {
+      "epoch": 3.877551020408163,
+      "grad_norm": 0.6263390779495239,
+      "learning_rate": 0.0002,
+      "loss": 1.8687,
+      "step": 1710
+    },
+    {
+      "epoch": 3.9002267573696145,
+      "grad_norm": 0.744022011756897,
+      "learning_rate": 0.0002,
+      "loss": 1.9206,
+      "step": 1720
+    },
+    {
+      "epoch": 3.9229024943310655,
+      "grad_norm": 0.7496722340583801,
+      "learning_rate": 0.0002,
+      "loss": 1.8961,
+      "step": 1730
+    },
+    {
+      "epoch": 3.945578231292517,
+      "grad_norm": 0.6877635717391968,
+      "learning_rate": 0.0002,
+      "loss": 1.9212,
+      "step": 1740
+    },
+    {
+      "epoch": 3.9682539682539684,
+      "grad_norm": 0.711262047290802,
+      "learning_rate": 0.0002,
+      "loss": 1.8504,
+      "step": 1750
+    },
+    {
+      "epoch": 3.9909297052154193,
+      "grad_norm": 0.7452033758163452,
+      "learning_rate": 0.0002,
+      "loss": 1.9315,
+      "step": 1760
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.065720319747925,
+      "eval_runtime": 14.7103,
+      "eval_samples_per_second": 34.466,
+      "eval_steps_per_second": 4.351,
+      "step": 1764
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3528,
+  "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": 2.1559601535123456e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1764/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49bd01b61e91780113d7cfd71d7d1da24fc61dfbff2f52441a1dd4793ec50fda
+size 5560

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2205/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **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]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+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
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[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

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2205/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "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
+}

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2205/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bfa581613822d5b479a2aad8252e23ff88d88624469f545cd35060a48323076
+size 29500848

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2205/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2c38485d449470b16ebc509248b9bf232bbb8a88fea9517a6fdc2b483160e2a
+size 15064314

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2205/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc704d2bc5a01caab7b4a7b5ca1c1a11b4dc79579e11338ae1a603a99cbe42c4
+size 14244

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2205/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54c9da8a02a9846b4fa97e500528bf4b60b78e598eeffb8c8538e5ef0a14a2b6
+size 1064

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2205/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2205/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f559f2189f392b4555613965f089e7c4d300b41fbe080bf79da0d676e33ee7f0
+size 34356041

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2205/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2205/tokenizer_config.json

@@ -0,0 +1,1757 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2205/trainer_state.json

@@ -0,0 +1,1613 @@
+{
+  "best_metric": 2.061427116394043,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1323",
+  "epoch": 5.0,
+  "eval_steps": 10,
+  "global_step": 2205,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022675736961451247,
+      "grad_norm": 1.8457136154174805,
+      "learning_rate": 0.0002,
+      "loss": 4.7982,
+      "step": 10
+    },
+    {
+      "epoch": 0.045351473922902494,
+      "grad_norm": 1.0967960357666016,
+      "learning_rate": 0.0002,
+      "loss": 3.71,
+      "step": 20
+    },
+    {
+      "epoch": 0.06802721088435375,
+      "grad_norm": 0.8257759213447571,
+      "learning_rate": 0.0002,
+      "loss": 3.3086,
+      "step": 30
+    },
+    {
+      "epoch": 0.09070294784580499,
+      "grad_norm": 0.8248435258865356,
+      "learning_rate": 0.0002,
+      "loss": 2.923,
+      "step": 40
+    },
+    {
+      "epoch": 0.11337868480725624,
+      "grad_norm": 1.1190264225006104,
+      "learning_rate": 0.0002,
+      "loss": 2.8263,
+      "step": 50
+    },
+    {
+      "epoch": 0.1360544217687075,
+      "grad_norm": 1.273951768875122,
+      "learning_rate": 0.0002,
+      "loss": 2.6239,
+      "step": 60
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 1.0004316568374634,
+      "learning_rate": 0.0002,
+      "loss": 2.5203,
+      "step": 70
+    },
+    {
+      "epoch": 0.18140589569160998,
+      "grad_norm": 0.8296012878417969,
+      "learning_rate": 0.0002,
+      "loss": 2.5055,
+      "step": 80
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 1.1563128232955933,
+      "learning_rate": 0.0002,
+      "loss": 2.5255,
+      "step": 90
+    },
+    {
+      "epoch": 0.22675736961451248,
+      "grad_norm": 0.7863451838493347,
+      "learning_rate": 0.0002,
+      "loss": 2.4731,
+      "step": 100
+    },
+    {
+      "epoch": 0.2494331065759637,
+      "grad_norm": 0.9167478680610657,
+      "learning_rate": 0.0002,
+      "loss": 2.3688,
+      "step": 110
+    },
+    {
+      "epoch": 0.272108843537415,
+      "grad_norm": 1.104406476020813,
+      "learning_rate": 0.0002,
+      "loss": 2.336,
+      "step": 120
+    },
+    {
+      "epoch": 0.2947845804988662,
+      "grad_norm": 1.109564185142517,
+      "learning_rate": 0.0002,
+      "loss": 2.3063,
+      "step": 130
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.7416750192642212,
+      "learning_rate": 0.0002,
+      "loss": 2.23,
+      "step": 140
+    },
+    {
+      "epoch": 0.3401360544217687,
+      "grad_norm": 1.1499258279800415,
+      "learning_rate": 0.0002,
+      "loss": 2.3346,
+      "step": 150
+    },
+    {
+      "epoch": 0.36281179138321995,
+      "grad_norm": 0.9961133599281311,
+      "learning_rate": 0.0002,
+      "loss": 2.2853,
+      "step": 160
+    },
+    {
+      "epoch": 0.3854875283446712,
+      "grad_norm": 0.9257232546806335,
+      "learning_rate": 0.0002,
+      "loss": 2.2731,
+      "step": 170
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 1.098513126373291,
+      "learning_rate": 0.0002,
+      "loss": 2.1986,
+      "step": 180
+    },
+    {
+      "epoch": 0.4308390022675737,
+      "grad_norm": 0.8935237526893616,
+      "learning_rate": 0.0002,
+      "loss": 2.1685,
+      "step": 190
+    },
+    {
+      "epoch": 0.45351473922902497,
+      "grad_norm": 0.9654302597045898,
+      "learning_rate": 0.0002,
+      "loss": 2.2077,
+      "step": 200
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.9273215532302856,
+      "learning_rate": 0.0002,
+      "loss": 2.2421,
+      "step": 210
+    },
+    {
+      "epoch": 0.4988662131519274,
+      "grad_norm": 0.7222742438316345,
+      "learning_rate": 0.0002,
+      "loss": 2.1973,
+      "step": 220
+    },
+    {
+      "epoch": 0.5215419501133787,
+      "grad_norm": 0.7825018763542175,
+      "learning_rate": 0.0002,
+      "loss": 2.0619,
+      "step": 230
+    },
+    {
+      "epoch": 0.54421768707483,
+      "grad_norm": 0.7758685350418091,
+      "learning_rate": 0.0002,
+      "loss": 2.2247,
+      "step": 240
+    },
+    {
+      "epoch": 0.5668934240362812,
+      "grad_norm": 0.916719913482666,
+      "learning_rate": 0.0002,
+      "loss": 2.1518,
+      "step": 250
+    },
+    {
+      "epoch": 0.5895691609977324,
+      "grad_norm": 0.696332573890686,
+      "learning_rate": 0.0002,
+      "loss": 2.0614,
+      "step": 260
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 0.7362682223320007,
+      "learning_rate": 0.0002,
+      "loss": 2.0763,
+      "step": 270
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.8184517025947571,
+      "learning_rate": 0.0002,
+      "loss": 2.223,
+      "step": 280
+    },
+    {
+      "epoch": 0.6575963718820862,
+      "grad_norm": 0.7944937348365784,
+      "learning_rate": 0.0002,
+      "loss": 2.1634,
+      "step": 290
+    },
+    {
+      "epoch": 0.6802721088435374,
+      "grad_norm": 0.7258933186531067,
+      "learning_rate": 0.0002,
+      "loss": 2.0922,
+      "step": 300
+    },
+    {
+      "epoch": 0.7029478458049887,
+      "grad_norm": 0.7037094831466675,
+      "learning_rate": 0.0002,
+      "loss": 2.1221,
+      "step": 310
+    },
+    {
+      "epoch": 0.7256235827664399,
+      "grad_norm": 0.7499093413352966,
+      "learning_rate": 0.0002,
+      "loss": 2.1132,
+      "step": 320
+    },
+    {
+      "epoch": 0.7482993197278912,
+      "grad_norm": 0.7725803256034851,
+      "learning_rate": 0.0002,
+      "loss": 2.2321,
+      "step": 330
+    },
+    {
+      "epoch": 0.7709750566893424,
+      "grad_norm": 0.6771686673164368,
+      "learning_rate": 0.0002,
+      "loss": 2.1611,
+      "step": 340
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "grad_norm": 0.7557646036148071,
+      "learning_rate": 0.0002,
+      "loss": 2.0693,
+      "step": 350
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.7430537939071655,
+      "learning_rate": 0.0002,
+      "loss": 2.0629,
+      "step": 360
+    },
+    {
+      "epoch": 0.8390022675736961,
+      "grad_norm": 0.8602280616760254,
+      "learning_rate": 0.0002,
+      "loss": 2.0731,
+      "step": 370
+    },
+    {
+      "epoch": 0.8616780045351474,
+      "grad_norm": 0.753440260887146,
+      "learning_rate": 0.0002,
+      "loss": 2.1836,
+      "step": 380
+    },
+    {
+      "epoch": 0.8843537414965986,
+      "grad_norm": 0.7217596769332886,
+      "learning_rate": 0.0002,
+      "loss": 2.1186,
+      "step": 390
+    },
+    {
+      "epoch": 0.9070294784580499,
+      "grad_norm": 0.6116304397583008,
+      "learning_rate": 0.0002,
+      "loss": 2.0223,
+      "step": 400
+    },
+    {
+      "epoch": 0.9297052154195011,
+      "grad_norm": 0.6829515695571899,
+      "learning_rate": 0.0002,
+      "loss": 2.0491,
+      "step": 410
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.733259916305542,
+      "learning_rate": 0.0002,
+      "loss": 2.1518,
+      "step": 420
+    },
+    {
+      "epoch": 0.9750566893424036,
+      "grad_norm": 0.6036455035209656,
+      "learning_rate": 0.0002,
+      "loss": 2.076,
+      "step": 430
+    },
+    {
+      "epoch": 0.9977324263038548,
+      "grad_norm": 0.8478217720985413,
+      "learning_rate": 0.0002,
+      "loss": 2.1526,
+      "step": 440
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.114302158355713,
+      "eval_runtime": 16.5108,
+      "eval_samples_per_second": 30.707,
+      "eval_steps_per_second": 3.876,
+      "step": 441
+    },
+    {
+      "epoch": 1.0204081632653061,
+      "grad_norm": 0.6996896266937256,
+      "learning_rate": 0.0002,
+      "loss": 1.9967,
+      "step": 450
+    },
+    {
+      "epoch": 1.0430839002267573,
+      "grad_norm": 0.7616267800331116,
+      "learning_rate": 0.0002,
+      "loss": 2.0471,
+      "step": 460
+    },
+    {
+      "epoch": 1.0657596371882085,
+      "grad_norm": 0.5978519320487976,
+      "learning_rate": 0.0002,
+      "loss": 2.0674,
+      "step": 470
+    },
+    {
+      "epoch": 1.08843537414966,
+      "grad_norm": 0.703987717628479,
+      "learning_rate": 0.0002,
+      "loss": 2.0803,
+      "step": 480
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.6707539558410645,
+      "learning_rate": 0.0002,
+      "loss": 2.0215,
+      "step": 490
+    },
+    {
+      "epoch": 1.1337868480725624,
+      "grad_norm": 0.6343862414360046,
+      "learning_rate": 0.0002,
+      "loss": 2.045,
+      "step": 500
+    },
+    {
+      "epoch": 1.1564625850340136,
+      "grad_norm": 0.8836050033569336,
+      "learning_rate": 0.0002,
+      "loss": 1.9753,
+      "step": 510
+    },
+    {
+      "epoch": 1.179138321995465,
+      "grad_norm": 0.6288692951202393,
+      "learning_rate": 0.0002,
+      "loss": 1.9537,
+      "step": 520
+    },
+    {
+      "epoch": 1.2018140589569162,
+      "grad_norm": 0.6671382784843445,
+      "learning_rate": 0.0002,
+      "loss": 2.0072,
+      "step": 530
+    },
+    {
+      "epoch": 1.2244897959183674,
+      "grad_norm": 0.7260547876358032,
+      "learning_rate": 0.0002,
+      "loss": 2.0631,
+      "step": 540
+    },
+    {
+      "epoch": 1.2471655328798186,
+      "grad_norm": 0.6919140219688416,
+      "learning_rate": 0.0002,
+      "loss": 2.1395,
+      "step": 550
+    },
+    {
+      "epoch": 1.2698412698412698,
+      "grad_norm": 0.6895381212234497,
+      "learning_rate": 0.0002,
+      "loss": 2.1162,
+      "step": 560
+    },
+    {
+      "epoch": 1.2925170068027212,
+      "grad_norm": 0.7131213545799255,
+      "learning_rate": 0.0002,
+      "loss": 2.1023,
+      "step": 570
+    },
+    {
+      "epoch": 1.3151927437641724,
+      "grad_norm": 0.6087185144424438,
+      "learning_rate": 0.0002,
+      "loss": 2.0381,
+      "step": 580
+    },
+    {
+      "epoch": 1.3378684807256236,
+      "grad_norm": 0.6506251096725464,
+      "learning_rate": 0.0002,
+      "loss": 2.054,
+      "step": 590
+    },
+    {
+      "epoch": 1.3605442176870748,
+      "grad_norm": 0.6999365091323853,
+      "learning_rate": 0.0002,
+      "loss": 2.0669,
+      "step": 600
+    },
+    {
+      "epoch": 1.383219954648526,
+      "grad_norm": 0.6305016875267029,
+      "learning_rate": 0.0002,
+      "loss": 2.0121,
+      "step": 610
+    },
+    {
+      "epoch": 1.4058956916099774,
+      "grad_norm": 0.6413465142250061,
+      "learning_rate": 0.0002,
+      "loss": 1.9727,
+      "step": 620
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.7571105360984802,
+      "learning_rate": 0.0002,
+      "loss": 2.0676,
+      "step": 630
+    },
+    {
+      "epoch": 1.4512471655328798,
+      "grad_norm": 0.8087857365608215,
+      "learning_rate": 0.0002,
+      "loss": 2.0838,
+      "step": 640
+    },
+    {
+      "epoch": 1.473922902494331,
+      "grad_norm": 0.6284025311470032,
+      "learning_rate": 0.0002,
+      "loss": 1.9932,
+      "step": 650
+    },
+    {
+      "epoch": 1.4965986394557822,
+      "grad_norm": 0.6630339026451111,
+      "learning_rate": 0.0002,
+      "loss": 2.0456,
+      "step": 660
+    },
+    {
+      "epoch": 1.5192743764172336,
+      "grad_norm": 0.6777389645576477,
+      "learning_rate": 0.0002,
+      "loss": 2.0778,
+      "step": 670
+    },
+    {
+      "epoch": 1.5419501133786848,
+      "grad_norm": 0.6965354681015015,
+      "learning_rate": 0.0002,
+      "loss": 2.0437,
+      "step": 680
+    },
+    {
+      "epoch": 1.564625850340136,
+      "grad_norm": 0.7124104499816895,
+      "learning_rate": 0.0002,
+      "loss": 2.056,
+      "step": 690
+    },
+    {
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.6652887463569641,
+      "learning_rate": 0.0002,
+      "loss": 1.989,
+      "step": 700
+    },
+    {
+      "epoch": 1.6099773242630384,
+      "grad_norm": 0.6061141490936279,
+      "learning_rate": 0.0002,
+      "loss": 2.0419,
+      "step": 710
+    },
+    {
+      "epoch": 1.6326530612244898,
+      "grad_norm": 0.8291212320327759,
+      "learning_rate": 0.0002,
+      "loss": 2.0257,
+      "step": 720
+    },
+    {
+      "epoch": 1.655328798185941,
+      "grad_norm": 0.6672369241714478,
+      "learning_rate": 0.0002,
+      "loss": 2.0776,
+      "step": 730
+    },
+    {
+      "epoch": 1.6780045351473922,
+      "grad_norm": 0.6301238536834717,
+      "learning_rate": 0.0002,
+      "loss": 1.9834,
+      "step": 740
+    },
+    {
+      "epoch": 1.7006802721088436,
+      "grad_norm": 0.7217460870742798,
+      "learning_rate": 0.0002,
+      "loss": 2.0176,
+      "step": 750
+    },
+    {
+      "epoch": 1.7233560090702946,
+      "grad_norm": 0.6720302104949951,
+      "learning_rate": 0.0002,
+      "loss": 2.0793,
+      "step": 760
+    },
+    {
+      "epoch": 1.746031746031746,
+      "grad_norm": 0.8228253722190857,
+      "learning_rate": 0.0002,
+      "loss": 2.0417,
+      "step": 770
+    },
+    {
+      "epoch": 1.7687074829931972,
+      "grad_norm": 0.6359929442405701,
+      "learning_rate": 0.0002,
+      "loss": 2.0198,
+      "step": 780
+    },
+    {
+      "epoch": 1.7913832199546484,
+      "grad_norm": 0.6594814658164978,
+      "learning_rate": 0.0002,
+      "loss": 1.99,
+      "step": 790
+    },
+    {
+      "epoch": 1.8140589569160999,
+      "grad_norm": 0.6135239601135254,
+      "learning_rate": 0.0002,
+      "loss": 2.0752,
+      "step": 800
+    },
+    {
+      "epoch": 1.836734693877551,
+      "grad_norm": 0.6736067533493042,
+      "learning_rate": 0.0002,
+      "loss": 2.0397,
+      "step": 810
+    },
+    {
+      "epoch": 1.8594104308390023,
+      "grad_norm": 0.7712678909301758,
+      "learning_rate": 0.0002,
+      "loss": 2.0545,
+      "step": 820
+    },
+    {
+      "epoch": 1.8820861678004537,
+      "grad_norm": 0.6950375437736511,
+      "learning_rate": 0.0002,
+      "loss": 1.9644,
+      "step": 830
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.5913259387016296,
+      "learning_rate": 0.0002,
+      "loss": 1.9272,
+      "step": 840
+    },
+    {
+      "epoch": 1.927437641723356,
+      "grad_norm": 0.626690149307251,
+      "learning_rate": 0.0002,
+      "loss": 2.0068,
+      "step": 850
+    },
+    {
+      "epoch": 1.9501133786848073,
+      "grad_norm": 0.6986100673675537,
+      "learning_rate": 0.0002,
+      "loss": 2.0443,
+      "step": 860
+    },
+    {
+      "epoch": 1.9727891156462585,
+      "grad_norm": 0.6573156118392944,
+      "learning_rate": 0.0002,
+      "loss": 2.0585,
+      "step": 870
+    },
+    {
+      "epoch": 1.99546485260771,
+      "grad_norm": 0.7589707374572754,
+      "learning_rate": 0.0002,
+      "loss": 2.0454,
+      "step": 880
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.073181629180908,
+      "eval_runtime": 14.6998,
+      "eval_samples_per_second": 34.49,
+      "eval_steps_per_second": 4.354,
+      "step": 882
+    },
+    {
+      "epoch": 2.018140589569161,
+      "grad_norm": 0.7971214056015015,
+      "learning_rate": 0.0002,
+      "loss": 2.015,
+      "step": 890
+    },
+    {
+      "epoch": 2.0408163265306123,
+      "grad_norm": 0.6144835948944092,
+      "learning_rate": 0.0002,
+      "loss": 1.982,
+      "step": 900
+    },
+    {
+      "epoch": 2.0634920634920633,
+      "grad_norm": 0.7324559688568115,
+      "learning_rate": 0.0002,
+      "loss": 1.9391,
+      "step": 910
+    },
+    {
+      "epoch": 2.0861678004535147,
+      "grad_norm": 0.6465244293212891,
+      "learning_rate": 0.0002,
+      "loss": 1.9066,
+      "step": 920
+    },
+    {
+      "epoch": 2.108843537414966,
+      "grad_norm": 0.7424528002738953,
+      "learning_rate": 0.0002,
+      "loss": 1.9893,
+      "step": 930
+    },
+    {
+      "epoch": 2.131519274376417,
+      "grad_norm": 0.6717734336853027,
+      "learning_rate": 0.0002,
+      "loss": 1.9193,
+      "step": 940
+    },
+    {
+      "epoch": 2.1541950113378685,
+      "grad_norm": 0.7873768210411072,
+      "learning_rate": 0.0002,
+      "loss": 1.9569,
+      "step": 950
+    },
+    {
+      "epoch": 2.17687074829932,
+      "grad_norm": 0.6752461194992065,
+      "learning_rate": 0.0002,
+      "loss": 1.9563,
+      "step": 960
+    },
+    {
+      "epoch": 2.199546485260771,
+      "grad_norm": 0.6919583082199097,
+      "learning_rate": 0.0002,
+      "loss": 2.0406,
+      "step": 970
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.6355509161949158,
+      "learning_rate": 0.0002,
+      "loss": 1.9281,
+      "step": 980
+    },
+    {
+      "epoch": 2.2448979591836733,
+      "grad_norm": 0.770007312297821,
+      "learning_rate": 0.0002,
+      "loss": 1.9953,
+      "step": 990
+    },
+    {
+      "epoch": 2.2675736961451247,
+      "grad_norm": 0.6216670870780945,
+      "learning_rate": 0.0002,
+      "loss": 1.9589,
+      "step": 1000
+    },
+    {
+      "epoch": 2.290249433106576,
+      "grad_norm": 0.6880573034286499,
+      "learning_rate": 0.0002,
+      "loss": 1.9247,
+      "step": 1010
+    },
+    {
+      "epoch": 2.312925170068027,
+      "grad_norm": 0.7346075177192688,
+      "learning_rate": 0.0002,
+      "loss": 1.9426,
+      "step": 1020
+    },
+    {
+      "epoch": 2.3356009070294785,
+      "grad_norm": 0.6651889681816101,
+      "learning_rate": 0.0002,
+      "loss": 1.9461,
+      "step": 1030
+    },
+    {
+      "epoch": 2.35827664399093,
+      "grad_norm": 0.7324103713035583,
+      "learning_rate": 0.0002,
+      "loss": 1.9147,
+      "step": 1040
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.7186149954795837,
+      "learning_rate": 0.0002,
+      "loss": 1.9142,
+      "step": 1050
+    },
+    {
+      "epoch": 2.4036281179138324,
+      "grad_norm": 0.6849178671836853,
+      "learning_rate": 0.0002,
+      "loss": 1.9501,
+      "step": 1060
+    },
+    {
+      "epoch": 2.4263038548752833,
+      "grad_norm": 0.6259638667106628,
+      "learning_rate": 0.0002,
+      "loss": 1.889,
+      "step": 1070
+    },
+    {
+      "epoch": 2.4489795918367347,
+      "grad_norm": 0.6821024417877197,
+      "learning_rate": 0.0002,
+      "loss": 1.9446,
+      "step": 1080
+    },
+    {
+      "epoch": 2.471655328798186,
+      "grad_norm": 0.7019884586334229,
+      "learning_rate": 0.0002,
+      "loss": 1.9398,
+      "step": 1090
+    },
+    {
+      "epoch": 2.494331065759637,
+      "grad_norm": 0.6368714570999146,
+      "learning_rate": 0.0002,
+      "loss": 1.9325,
+      "step": 1100
+    },
+    {
+      "epoch": 2.5170068027210886,
+      "grad_norm": 0.6608313918113708,
+      "learning_rate": 0.0002,
+      "loss": 1.9773,
+      "step": 1110
+    },
+    {
+      "epoch": 2.5396825396825395,
+      "grad_norm": 0.6855525970458984,
+      "learning_rate": 0.0002,
+      "loss": 1.9337,
+      "step": 1120
+    },
+    {
+      "epoch": 2.562358276643991,
+      "grad_norm": 0.7279609441757202,
+      "learning_rate": 0.0002,
+      "loss": 1.9347,
+      "step": 1130
+    },
+    {
+      "epoch": 2.5850340136054424,
+      "grad_norm": 0.6539294123649597,
+      "learning_rate": 0.0002,
+      "loss": 1.9508,
+      "step": 1140
+    },
+    {
+      "epoch": 2.6077097505668934,
+      "grad_norm": 0.7035511136054993,
+      "learning_rate": 0.0002,
+      "loss": 2.0517,
+      "step": 1150
+    },
+    {
+      "epoch": 2.630385487528345,
+      "grad_norm": 0.7031794786453247,
+      "learning_rate": 0.0002,
+      "loss": 1.9955,
+      "step": 1160
+    },
+    {
+      "epoch": 2.6530612244897958,
+      "grad_norm": 0.7587798833847046,
+      "learning_rate": 0.0002,
+      "loss": 1.9549,
+      "step": 1170
+    },
+    {
+      "epoch": 2.675736961451247,
+      "grad_norm": 0.707339882850647,
+      "learning_rate": 0.0002,
+      "loss": 2.0014,
+      "step": 1180
+    },
+    {
+      "epoch": 2.6984126984126986,
+      "grad_norm": 0.6633496880531311,
+      "learning_rate": 0.0002,
+      "loss": 1.955,
+      "step": 1190
+    },
+    {
+      "epoch": 2.7210884353741496,
+      "grad_norm": 0.9233061671257019,
+      "learning_rate": 0.0002,
+      "loss": 1.9434,
+      "step": 1200
+    },
+    {
+      "epoch": 2.743764172335601,
+      "grad_norm": 0.6396011710166931,
+      "learning_rate": 0.0002,
+      "loss": 1.9146,
+      "step": 1210
+    },
+    {
+      "epoch": 2.766439909297052,
+      "grad_norm": 0.6500924229621887,
+      "learning_rate": 0.0002,
+      "loss": 1.9934,
+      "step": 1220
+    },
+    {
+      "epoch": 2.7891156462585034,
+      "grad_norm": 0.6185927391052246,
+      "learning_rate": 0.0002,
+      "loss": 1.9197,
+      "step": 1230
+    },
+    {
+      "epoch": 2.811791383219955,
+      "grad_norm": 0.6737818717956543,
+      "learning_rate": 0.0002,
+      "loss": 1.9809,
+      "step": 1240
+    },
+    {
+      "epoch": 2.834467120181406,
+      "grad_norm": 0.8148701786994934,
+      "learning_rate": 0.0002,
+      "loss": 1.9508,
+      "step": 1250
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.7563779354095459,
+      "learning_rate": 0.0002,
+      "loss": 1.9848,
+      "step": 1260
+    },
+    {
+      "epoch": 2.879818594104308,
+      "grad_norm": 0.6679276823997498,
+      "learning_rate": 0.0002,
+      "loss": 1.9822,
+      "step": 1270
+    },
+    {
+      "epoch": 2.9024943310657596,
+      "grad_norm": 0.7446274757385254,
+      "learning_rate": 0.0002,
+      "loss": 2.0609,
+      "step": 1280
+    },
+    {
+      "epoch": 2.925170068027211,
+      "grad_norm": 0.6530991196632385,
+      "learning_rate": 0.0002,
+      "loss": 1.9251,
+      "step": 1290
+    },
+    {
+      "epoch": 2.947845804988662,
+      "grad_norm": 0.6491292119026184,
+      "learning_rate": 0.0002,
+      "loss": 1.9555,
+      "step": 1300
+    },
+    {
+      "epoch": 2.9705215419501134,
+      "grad_norm": 0.6711354851722717,
+      "learning_rate": 0.0002,
+      "loss": 1.913,
+      "step": 1310
+    },
+    {
+      "epoch": 2.9931972789115644,
+      "grad_norm": 0.6327161192893982,
+      "learning_rate": 0.0002,
+      "loss": 2.0005,
+      "step": 1320
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.061427116394043,
+      "eval_runtime": 19.6731,
+      "eval_samples_per_second": 25.771,
+      "eval_steps_per_second": 3.253,
+      "step": 1323
+    },
+    {
+      "epoch": 3.015873015873016,
+      "grad_norm": 0.625606119632721,
+      "learning_rate": 0.0002,
+      "loss": 1.8798,
+      "step": 1330
+    },
+    {
+      "epoch": 3.0385487528344672,
+      "grad_norm": 0.6679854989051819,
+      "learning_rate": 0.0002,
+      "loss": 1.8229,
+      "step": 1340
+    },
+    {
+      "epoch": 3.061224489795918,
+      "grad_norm": 0.6756007671356201,
+      "learning_rate": 0.0002,
+      "loss": 1.8593,
+      "step": 1350
+    },
+    {
+      "epoch": 3.0839002267573696,
+      "grad_norm": 0.8019710779190063,
+      "learning_rate": 0.0002,
+      "loss": 1.8126,
+      "step": 1360
+    },
+    {
+      "epoch": 3.106575963718821,
+      "grad_norm": 0.9087499976158142,
+      "learning_rate": 0.0002,
+      "loss": 1.8593,
+      "step": 1370
+    },
+    {
+      "epoch": 3.129251700680272,
+      "grad_norm": 0.7627860903739929,
+      "learning_rate": 0.0002,
+      "loss": 1.8951,
+      "step": 1380
+    },
+    {
+      "epoch": 3.1519274376417235,
+      "grad_norm": 0.761993944644928,
+      "learning_rate": 0.0002,
+      "loss": 1.8308,
+      "step": 1390
+    },
+    {
+      "epoch": 3.1746031746031744,
+      "grad_norm": 0.6993107795715332,
+      "learning_rate": 0.0002,
+      "loss": 1.9513,
+      "step": 1400
+    },
+    {
+      "epoch": 3.197278911564626,
+      "grad_norm": 0.6398035287857056,
+      "learning_rate": 0.0002,
+      "loss": 1.8857,
+      "step": 1410
+    },
+    {
+      "epoch": 3.2199546485260773,
+      "grad_norm": 0.8602580428123474,
+      "learning_rate": 0.0002,
+      "loss": 1.9041,
+      "step": 1420
+    },
+    {
+      "epoch": 3.2426303854875282,
+      "grad_norm": 0.7799932360649109,
+      "learning_rate": 0.0002,
+      "loss": 1.9629,
+      "step": 1430
+    },
+    {
+      "epoch": 3.2653061224489797,
+      "grad_norm": 0.6598666906356812,
+      "learning_rate": 0.0002,
+      "loss": 1.8352,
+      "step": 1440
+    },
+    {
+      "epoch": 3.287981859410431,
+      "grad_norm": 0.6513776779174805,
+      "learning_rate": 0.0002,
+      "loss": 1.8772,
+      "step": 1450
+    },
+    {
+      "epoch": 3.310657596371882,
+      "grad_norm": 0.7690088748931885,
+      "learning_rate": 0.0002,
+      "loss": 1.8568,
+      "step": 1460
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 1.0070042610168457,
+      "learning_rate": 0.0002,
+      "loss": 1.8535,
+      "step": 1470
+    },
+    {
+      "epoch": 3.3560090702947845,
+      "grad_norm": 0.8606905341148376,
+      "learning_rate": 0.0002,
+      "loss": 1.8971,
+      "step": 1480
+    },
+    {
+      "epoch": 3.378684807256236,
+      "grad_norm": 0.7596806287765503,
+      "learning_rate": 0.0002,
+      "loss": 1.8386,
+      "step": 1490
+    },
+    {
+      "epoch": 3.4013605442176873,
+      "grad_norm": 0.6961908936500549,
+      "learning_rate": 0.0002,
+      "loss": 1.9278,
+      "step": 1500
+    },
+    {
+      "epoch": 3.4240362811791383,
+      "grad_norm": 0.8368703126907349,
+      "learning_rate": 0.0002,
+      "loss": 1.8908,
+      "step": 1510
+    },
+    {
+      "epoch": 3.4467120181405897,
+      "grad_norm": 0.6655045747756958,
+      "learning_rate": 0.0002,
+      "loss": 1.924,
+      "step": 1520
+    },
+    {
+      "epoch": 3.4693877551020407,
+      "grad_norm": 0.7557174563407898,
+      "learning_rate": 0.0002,
+      "loss": 1.8273,
+      "step": 1530
+    },
+    {
+      "epoch": 3.492063492063492,
+      "grad_norm": 0.6713934540748596,
+      "learning_rate": 0.0002,
+      "loss": 1.8435,
+      "step": 1540
+    },
+    {
+      "epoch": 3.5147392290249435,
+      "grad_norm": 0.7006916999816895,
+      "learning_rate": 0.0002,
+      "loss": 1.9016,
+      "step": 1550
+    },
+    {
+      "epoch": 3.5374149659863945,
+      "grad_norm": 0.6728846430778503,
+      "learning_rate": 0.0002,
+      "loss": 1.9208,
+      "step": 1560
+    },
+    {
+      "epoch": 3.560090702947846,
+      "grad_norm": 0.7479315400123596,
+      "learning_rate": 0.0002,
+      "loss": 1.8769,
+      "step": 1570
+    },
+    {
+      "epoch": 3.582766439909297,
+      "grad_norm": 0.7596876621246338,
+      "learning_rate": 0.0002,
+      "loss": 1.8558,
+      "step": 1580
+    },
+    {
+      "epoch": 3.6054421768707483,
+      "grad_norm": 0.8948362469673157,
+      "learning_rate": 0.0002,
+      "loss": 1.876,
+      "step": 1590
+    },
+    {
+      "epoch": 3.6281179138321997,
+      "grad_norm": 0.6952481269836426,
+      "learning_rate": 0.0002,
+      "loss": 1.8552,
+      "step": 1600
+    },
+    {
+      "epoch": 3.6507936507936507,
+      "grad_norm": 0.6494414210319519,
+      "learning_rate": 0.0002,
+      "loss": 1.933,
+      "step": 1610
+    },
+    {
+      "epoch": 3.673469387755102,
+      "grad_norm": 0.7438889145851135,
+      "learning_rate": 0.0002,
+      "loss": 1.8516,
+      "step": 1620
+    },
+    {
+      "epoch": 3.696145124716553,
+      "grad_norm": 0.7470757961273193,
+      "learning_rate": 0.0002,
+      "loss": 1.9441,
+      "step": 1630
+    },
+    {
+      "epoch": 3.7188208616780045,
+      "grad_norm": 0.8727335333824158,
+      "learning_rate": 0.0002,
+      "loss": 1.8685,
+      "step": 1640
+    },
+    {
+      "epoch": 3.741496598639456,
+      "grad_norm": 0.7064452767372131,
+      "learning_rate": 0.0002,
+      "loss": 1.8831,
+      "step": 1650
+    },
+    {
+      "epoch": 3.764172335600907,
+      "grad_norm": 0.6958122849464417,
+      "learning_rate": 0.0002,
+      "loss": 1.9743,
+      "step": 1660
+    },
+    {
+      "epoch": 3.7868480725623583,
+      "grad_norm": 0.6751590371131897,
+      "learning_rate": 0.0002,
+      "loss": 1.927,
+      "step": 1670
+    },
+    {
+      "epoch": 3.8095238095238093,
+      "grad_norm": 0.7274497151374817,
+      "learning_rate": 0.0002,
+      "loss": 1.8868,
+      "step": 1680
+    },
+    {
+      "epoch": 3.8321995464852607,
+      "grad_norm": 0.7311708331108093,
+      "learning_rate": 0.0002,
+      "loss": 1.942,
+      "step": 1690
+    },
+    {
+      "epoch": 3.854875283446712,
+      "grad_norm": 0.6703173518180847,
+      "learning_rate": 0.0002,
+      "loss": 1.8134,
+      "step": 1700
+    },
+    {
+      "epoch": 3.877551020408163,
+      "grad_norm": 0.6263390779495239,
+      "learning_rate": 0.0002,
+      "loss": 1.8687,
+      "step": 1710
+    },
+    {
+      "epoch": 3.9002267573696145,
+      "grad_norm": 0.744022011756897,
+      "learning_rate": 0.0002,
+      "loss": 1.9206,
+      "step": 1720
+    },
+    {
+      "epoch": 3.9229024943310655,
+      "grad_norm": 0.7496722340583801,
+      "learning_rate": 0.0002,
+      "loss": 1.8961,
+      "step": 1730
+    },
+    {
+      "epoch": 3.945578231292517,
+      "grad_norm": 0.6877635717391968,
+      "learning_rate": 0.0002,
+      "loss": 1.9212,
+      "step": 1740
+    },
+    {
+      "epoch": 3.9682539682539684,
+      "grad_norm": 0.711262047290802,
+      "learning_rate": 0.0002,
+      "loss": 1.8504,
+      "step": 1750
+    },
+    {
+      "epoch": 3.9909297052154193,
+      "grad_norm": 0.7452033758163452,
+      "learning_rate": 0.0002,
+      "loss": 1.9315,
+      "step": 1760
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.065720319747925,
+      "eval_runtime": 14.7103,
+      "eval_samples_per_second": 34.466,
+      "eval_steps_per_second": 4.351,
+      "step": 1764
+    },
+    {
+      "epoch": 4.01360544217687,
+      "grad_norm": 0.6913991570472717,
+      "learning_rate": 0.0002,
+      "loss": 1.8729,
+      "step": 1770
+    },
+    {
+      "epoch": 4.036281179138322,
+      "grad_norm": 0.7323354482650757,
+      "learning_rate": 0.0002,
+      "loss": 1.7617,
+      "step": 1780
+    },
+    {
+      "epoch": 4.058956916099773,
+      "grad_norm": 0.7691134214401245,
+      "learning_rate": 0.0002,
+      "loss": 1.7486,
+      "step": 1790
+    },
+    {
+      "epoch": 4.081632653061225,
+      "grad_norm": 0.7871596813201904,
+      "learning_rate": 0.0002,
+      "loss": 1.8102,
+      "step": 1800
+    },
+    {
+      "epoch": 4.104308390022676,
+      "grad_norm": 0.7079440355300903,
+      "learning_rate": 0.0002,
+      "loss": 1.7455,
+      "step": 1810
+    },
+    {
+      "epoch": 4.1269841269841265,
+      "grad_norm": 0.7468329668045044,
+      "learning_rate": 0.0002,
+      "loss": 1.7693,
+      "step": 1820
+    },
+    {
+      "epoch": 4.149659863945578,
+      "grad_norm": 0.8017606139183044,
+      "learning_rate": 0.0002,
+      "loss": 1.772,
+      "step": 1830
+    },
+    {
+      "epoch": 4.172335600907029,
+      "grad_norm": 0.8591130375862122,
+      "learning_rate": 0.0002,
+      "loss": 1.81,
+      "step": 1840
+    },
+    {
+      "epoch": 4.195011337868481,
+      "grad_norm": 0.7866499423980713,
+      "learning_rate": 0.0002,
+      "loss": 1.7356,
+      "step": 1850
+    },
+    {
+      "epoch": 4.217687074829932,
+      "grad_norm": 0.8457089066505432,
+      "learning_rate": 0.0002,
+      "loss": 1.8342,
+      "step": 1860
+    },
+    {
+      "epoch": 4.240362811791384,
+      "grad_norm": 0.8171738386154175,
+      "learning_rate": 0.0002,
+      "loss": 1.8744,
+      "step": 1870
+    },
+    {
+      "epoch": 4.263038548752834,
+      "grad_norm": 0.7377166748046875,
+      "learning_rate": 0.0002,
+      "loss": 1.7786,
+      "step": 1880
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 0.7925628423690796,
+      "learning_rate": 0.0002,
+      "loss": 1.787,
+      "step": 1890
+    },
+    {
+      "epoch": 4.308390022675737,
+      "grad_norm": 1.0107476711273193,
+      "learning_rate": 0.0002,
+      "loss": 1.8634,
+      "step": 1900
+    },
+    {
+      "epoch": 4.331065759637188,
+      "grad_norm": 0.7791350483894348,
+      "learning_rate": 0.0002,
+      "loss": 1.8193,
+      "step": 1910
+    },
+    {
+      "epoch": 4.35374149659864,
+      "grad_norm": 0.7173832654953003,
+      "learning_rate": 0.0002,
+      "loss": 1.8431,
+      "step": 1920
+    },
+    {
+      "epoch": 4.37641723356009,
+      "grad_norm": 0.8341949582099915,
+      "learning_rate": 0.0002,
+      "loss": 1.83,
+      "step": 1930
+    },
+    {
+      "epoch": 4.399092970521542,
+      "grad_norm": 0.7944530844688416,
+      "learning_rate": 0.0002,
+      "loss": 1.7791,
+      "step": 1940
+    },
+    {
+      "epoch": 4.421768707482993,
+      "grad_norm": 0.7409125566482544,
+      "learning_rate": 0.0002,
+      "loss": 1.8161,
+      "step": 1950
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.9393547773361206,
+      "learning_rate": 0.0002,
+      "loss": 1.7994,
+      "step": 1960
+    },
+    {
+      "epoch": 4.467120181405896,
+      "grad_norm": 0.8280852437019348,
+      "learning_rate": 0.0002,
+      "loss": 1.8132,
+      "step": 1970
+    },
+    {
+      "epoch": 4.489795918367347,
+      "grad_norm": 0.7249669432640076,
+      "learning_rate": 0.0002,
+      "loss": 1.6995,
+      "step": 1980
+    },
+    {
+      "epoch": 4.512471655328798,
+      "grad_norm": 0.7199458479881287,
+      "learning_rate": 0.0002,
+      "loss": 1.7846,
+      "step": 1990
+    },
+    {
+      "epoch": 4.535147392290249,
+      "grad_norm": 0.8454286456108093,
+      "learning_rate": 0.0002,
+      "loss": 1.7851,
+      "step": 2000
+    },
+    {
+      "epoch": 4.557823129251701,
+      "grad_norm": 0.7305117249488831,
+      "learning_rate": 0.0002,
+      "loss": 1.8673,
+      "step": 2010
+    },
+    {
+      "epoch": 4.580498866213152,
+      "grad_norm": 0.7819753885269165,
+      "learning_rate": 0.0002,
+      "loss": 1.8234,
+      "step": 2020
+    },
+    {
+      "epoch": 4.603174603174603,
+      "grad_norm": 0.8010004162788391,
+      "learning_rate": 0.0002,
+      "loss": 1.7972,
+      "step": 2030
+    },
+    {
+      "epoch": 4.625850340136054,
+      "grad_norm": 0.7850886583328247,
+      "learning_rate": 0.0002,
+      "loss": 1.7921,
+      "step": 2040
+    },
+    {
+      "epoch": 4.648526077097506,
+      "grad_norm": 0.7433428168296814,
+      "learning_rate": 0.0002,
+      "loss": 1.9024,
+      "step": 2050
+    },
+    {
+      "epoch": 4.671201814058957,
+      "grad_norm": 0.7518399357795715,
+      "learning_rate": 0.0002,
+      "loss": 1.8155,
+      "step": 2060
+    },
+    {
+      "epoch": 4.6938775510204085,
+      "grad_norm": 0.7282178997993469,
+      "learning_rate": 0.0002,
+      "loss": 1.7924,
+      "step": 2070
+    },
+    {
+      "epoch": 4.71655328798186,
+      "grad_norm": 0.6950743794441223,
+      "learning_rate": 0.0002,
+      "loss": 1.8144,
+      "step": 2080
+    },
+    {
+      "epoch": 4.73922902494331,
+      "grad_norm": 0.761830747127533,
+      "learning_rate": 0.0002,
+      "loss": 1.7757,
+      "step": 2090
+    },
+    {
+      "epoch": 4.761904761904762,
+      "grad_norm": 0.8068088293075562,
+      "learning_rate": 0.0002,
+      "loss": 1.8254,
+      "step": 2100
+    },
+    {
+      "epoch": 4.784580498866213,
+      "grad_norm": 0.7580569386482239,
+      "learning_rate": 0.0002,
+      "loss": 1.8092,
+      "step": 2110
+    },
+    {
+      "epoch": 4.807256235827665,
+      "grad_norm": 0.9428760409355164,
+      "learning_rate": 0.0002,
+      "loss": 1.8144,
+      "step": 2120
+    },
+    {
+      "epoch": 4.829931972789115,
+      "grad_norm": 0.7057452201843262,
+      "learning_rate": 0.0002,
+      "loss": 1.829,
+      "step": 2130
+    },
+    {
+      "epoch": 4.852607709750567,
+      "grad_norm": 0.763630211353302,
+      "learning_rate": 0.0002,
+      "loss": 1.7603,
+      "step": 2140
+    },
+    {
+      "epoch": 4.875283446712018,
+      "grad_norm": 0.7298727035522461,
+      "learning_rate": 0.0002,
+      "loss": 1.8348,
+      "step": 2150
+    },
+    {
+      "epoch": 4.8979591836734695,
+      "grad_norm": 0.7376292943954468,
+      "learning_rate": 0.0002,
+      "loss": 1.8652,
+      "step": 2160
+    },
+    {
+      "epoch": 4.920634920634921,
+      "grad_norm": 0.8528493642807007,
+      "learning_rate": 0.0002,
+      "loss": 1.742,
+      "step": 2170
+    },
+    {
+      "epoch": 4.943310657596372,
+      "grad_norm": 0.7652511596679688,
+      "learning_rate": 0.0002,
+      "loss": 1.7706,
+      "step": 2180
+    },
+    {
+      "epoch": 4.965986394557823,
+      "grad_norm": 0.7602494955062866,
+      "learning_rate": 0.0002,
+      "loss": 1.7994,
+      "step": 2190
+    },
+    {
+      "epoch": 4.988662131519274,
+      "grad_norm": 0.758914053440094,
+      "learning_rate": 0.0002,
+      "loss": 1.8278,
+      "step": 2200
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.083296298980713,
+      "eval_runtime": 20.2201,
+      "eval_samples_per_second": 25.074,
+      "eval_steps_per_second": 3.165,
+      "step": 2205
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3528,
+  "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": 2.694950191890432e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2205/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49bd01b61e91780113d7cfd71d7d1da24fc61dfbff2f52441a1dd4793ec50fda
+size 5560

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2646/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **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]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+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
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[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

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2646/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "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
+}

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2646/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:840cfce3e80e39c50f59719cf91e382fb752e24e5a1c6cb8d44bd984a0019662
+size 29500848

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2646/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e5d25578ea19a1964f841d96d5478dd67c82f49bf8221581c3a9edcaff47f2a
+size 15064314

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2646/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6dcf28783c7c05142319c5f409f2aee91b0443fa09563b9e472b607ace45e5a
+size 14244

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2646/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:550791043649ed75b1ff4f32159a98afbcc2337d75003352db8849d24012a186
+size 1064

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2646/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2646/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f559f2189f392b4555613965f089e7c4d300b41fbe080bf79da0d676e33ee7f0
+size 34356041

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2646/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2646/tokenizer_config.json

@@ -0,0 +1,1757 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}