Upload folder using huggingface_hub

.gitattributes

@@ -2071,3 +2071,12 @@ gemma-2b-it_int4_winogrande-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-
 gemma-2b-it_int4_winogrande-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-0.7-num-620-sd-4/checkpoint-38/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-2b-it_int4_winogrande-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-0.7-num-620-sd-4/checkpoint-76/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-2b-it_int4_winogrande-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-0.7-num-620-sd-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-191/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-286/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-382/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-477/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-573/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-668/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-760/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-95/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-7B-Instruct
+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

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b90b77fde672b6c6c36c7f343b2aa77705c15b2ed49b0b66c304399b0b98e59f
+size 80755416

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-191/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-7B-Instruct
+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

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-191/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-191/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24bf9970b828381b1b1dd2b1db61ea5071d85a190f73cdbcc94891328294dab2
+size 80755416

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-191/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-191/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1a2735d57e5a55df3a69710732c13dc6916c17da6aac2313c667123bf968a98
+size 41136442

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-191/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1f0d986df2e3d730bc994f3ae1e979790e1bbfad68e0cf2f746195cc2c6ce7c
+size 14244

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-191/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f787e63e7f215f0a7faa7589629b6f28490b5c49fd92feab6cf53a71aeb3980
+size 1064

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-191/special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-191/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-191/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-191/trainer_state.json

@@ -0,0 +1,182 @@
+{
+  "best_metric": 1.246069073677063,
+  "best_model_checkpoint": "outputs-001/Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-191",
+  "epoch": 2.0,
+  "eval_steps": 10,
+  "global_step": 191,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10471204188481675,
+      "grad_norm": 0.19758254289627075,
+      "learning_rate": 0.0002,
+      "loss": 1.634,
+      "step": 10
+    },
+    {
+      "epoch": 0.2094240837696335,
+      "grad_norm": 0.32746484875679016,
+      "learning_rate": 0.0002,
+      "loss": 1.4531,
+      "step": 20
+    },
+    {
+      "epoch": 0.31413612565445026,
+      "grad_norm": 0.2939307689666748,
+      "learning_rate": 0.0002,
+      "loss": 1.3666,
+      "step": 30
+    },
+    {
+      "epoch": 0.418848167539267,
+      "grad_norm": 0.4865039587020874,
+      "learning_rate": 0.0002,
+      "loss": 1.3884,
+      "step": 40
+    },
+    {
+      "epoch": 0.5235602094240838,
+      "grad_norm": 0.25857967138290405,
+      "learning_rate": 0.0002,
+      "loss": 1.3453,
+      "step": 50
+    },
+    {
+      "epoch": 0.6282722513089005,
+      "grad_norm": 0.27348533272743225,
+      "learning_rate": 0.0002,
+      "loss": 1.3206,
+      "step": 60
+    },
+    {
+      "epoch": 0.7329842931937173,
+      "grad_norm": 0.2988259196281433,
+      "learning_rate": 0.0002,
+      "loss": 1.3141,
+      "step": 70
+    },
+    {
+      "epoch": 0.837696335078534,
+      "grad_norm": 0.277259886264801,
+      "learning_rate": 0.0002,
+      "loss": 1.2931,
+      "step": 80
+    },
+    {
+      "epoch": 0.9424083769633508,
+      "grad_norm": 0.34198081493377686,
+      "learning_rate": 0.0002,
+      "loss": 1.3112,
+      "step": 90
+    },
+    {
+      "epoch": 0.9947643979057592,
+      "eval_loss": 1.2753487825393677,
+      "eval_runtime": 21.375,
+      "eval_samples_per_second": 4.491,
+      "eval_steps_per_second": 0.561,
+      "step": 95
+    },
+    {
+      "epoch": 1.0471204188481675,
+      "grad_norm": 0.2599162459373474,
+      "learning_rate": 0.0002,
+      "loss": 1.2368,
+      "step": 100
+    },
+    {
+      "epoch": 1.1518324607329844,
+      "grad_norm": 0.28724443912506104,
+      "learning_rate": 0.0002,
+      "loss": 1.2015,
+      "step": 110
+    },
+    {
+      "epoch": 1.256544502617801,
+      "grad_norm": 0.2874450087547302,
+      "learning_rate": 0.0002,
+      "loss": 1.2785,
+      "step": 120
+    },
+    {
+      "epoch": 1.3612565445026177,
+      "grad_norm": 0.2946247458457947,
+      "learning_rate": 0.0002,
+      "loss": 1.2254,
+      "step": 130
+    },
+    {
+      "epoch": 1.4659685863874345,
+      "grad_norm": 0.29081839323043823,
+      "learning_rate": 0.0002,
+      "loss": 1.2094,
+      "step": 140
+    },
+    {
+      "epoch": 1.5706806282722514,
+      "grad_norm": 0.3117203712463379,
+      "learning_rate": 0.0002,
+      "loss": 1.2091,
+      "step": 150
+    },
+    {
+      "epoch": 1.675392670157068,
+      "grad_norm": 0.4307788610458374,
+      "learning_rate": 0.0002,
+      "loss": 1.2503,
+      "step": 160
+    },
+    {
+      "epoch": 1.7801047120418847,
+      "grad_norm": 0.4271780252456665,
+      "learning_rate": 0.0002,
+      "loss": 1.2886,
+      "step": 170
+    },
+    {
+      "epoch": 1.8848167539267016,
+      "grad_norm": 0.3049869239330292,
+      "learning_rate": 0.0002,
+      "loss": 1.2744,
+      "step": 180
+    },
+    {
+      "epoch": 1.9895287958115184,
+      "grad_norm": 0.3276447355747223,
+      "learning_rate": 0.0002,
+      "loss": 1.2275,
+      "step": 190
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.246069073677063,
+      "eval_runtime": 21.7078,
+      "eval_samples_per_second": 4.422,
+      "eval_steps_per_second": 0.553,
+      "step": 191
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 760,
+  "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": 8321087120080896.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-191/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66b56b5a1635548dcb5aa08f01d4d0f065dec7a3ac400babdffd741b96b8639b
+size 5560

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-286/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-7B-Instruct
+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

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-286/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-286/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b90b77fde672b6c6c36c7f343b2aa77705c15b2ed49b0b66c304399b0b98e59f
+size 80755416

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-286/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-286/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3845ac056c494e25b50e119e84c6c6fad3435923eb8a0b533a29da97f925c0db
+size 41136570

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-286/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2808bde47abfb679c4dbbad68cb275e1f3929884890730a4f2bf106d5ef4b7
+size 14244

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-286/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe3f3e7647cce133ea9216d16b7a1fbbd8fa0228ef2b5516960a992facc56ae
+size 1064

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-286/special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-286/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-286/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-286/trainer_state.json

@@ -0,0 +1,253 @@
+{
+  "best_metric": 1.2453244924545288,
+  "best_model_checkpoint": "outputs-001/Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-286",
+  "epoch": 2.994764397905759,
+  "eval_steps": 10,
+  "global_step": 286,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10471204188481675,
+      "grad_norm": 0.19758254289627075,
+      "learning_rate": 0.0002,
+      "loss": 1.634,
+      "step": 10
+    },
+    {
+      "epoch": 0.2094240837696335,
+      "grad_norm": 0.32746484875679016,
+      "learning_rate": 0.0002,
+      "loss": 1.4531,
+      "step": 20
+    },
+    {
+      "epoch": 0.31413612565445026,
+      "grad_norm": 0.2939307689666748,
+      "learning_rate": 0.0002,
+      "loss": 1.3666,
+      "step": 30
+    },
+    {
+      "epoch": 0.418848167539267,
+      "grad_norm": 0.4865039587020874,
+      "learning_rate": 0.0002,
+      "loss": 1.3884,
+      "step": 40
+    },
+    {
+      "epoch": 0.5235602094240838,
+      "grad_norm": 0.25857967138290405,
+      "learning_rate": 0.0002,
+      "loss": 1.3453,
+      "step": 50
+    },
+    {
+      "epoch": 0.6282722513089005,
+      "grad_norm": 0.27348533272743225,
+      "learning_rate": 0.0002,
+      "loss": 1.3206,
+      "step": 60
+    },
+    {
+      "epoch": 0.7329842931937173,
+      "grad_norm": 0.2988259196281433,
+      "learning_rate": 0.0002,
+      "loss": 1.3141,
+      "step": 70
+    },
+    {
+      "epoch": 0.837696335078534,
+      "grad_norm": 0.277259886264801,
+      "learning_rate": 0.0002,
+      "loss": 1.2931,
+      "step": 80
+    },
+    {
+      "epoch": 0.9424083769633508,
+      "grad_norm": 0.34198081493377686,
+      "learning_rate": 0.0002,
+      "loss": 1.3112,
+      "step": 90
+    },
+    {
+      "epoch": 0.9947643979057592,
+      "eval_loss": 1.2753487825393677,
+      "eval_runtime": 21.375,
+      "eval_samples_per_second": 4.491,
+      "eval_steps_per_second": 0.561,
+      "step": 95
+    },
+    {
+      "epoch": 1.0471204188481675,
+      "grad_norm": 0.2599162459373474,
+      "learning_rate": 0.0002,
+      "loss": 1.2368,
+      "step": 100
+    },
+    {
+      "epoch": 1.1518324607329844,
+      "grad_norm": 0.28724443912506104,
+      "learning_rate": 0.0002,
+      "loss": 1.2015,
+      "step": 110
+    },
+    {
+      "epoch": 1.256544502617801,
+      "grad_norm": 0.2874450087547302,
+      "learning_rate": 0.0002,
+      "loss": 1.2785,
+      "step": 120
+    },
+    {
+      "epoch": 1.3612565445026177,
+      "grad_norm": 0.2946247458457947,
+      "learning_rate": 0.0002,
+      "loss": 1.2254,
+      "step": 130
+    },
+    {
+      "epoch": 1.4659685863874345,
+      "grad_norm": 0.29081839323043823,
+      "learning_rate": 0.0002,
+      "loss": 1.2094,
+      "step": 140
+    },
+    {
+      "epoch": 1.5706806282722514,
+      "grad_norm": 0.3117203712463379,
+      "learning_rate": 0.0002,
+      "loss": 1.2091,
+      "step": 150
+    },
+    {
+      "epoch": 1.675392670157068,
+      "grad_norm": 0.4307788610458374,
+      "learning_rate": 0.0002,
+      "loss": 1.2503,
+      "step": 160
+    },
+    {
+      "epoch": 1.7801047120418847,
+      "grad_norm": 0.4271780252456665,
+      "learning_rate": 0.0002,
+      "loss": 1.2886,
+      "step": 170
+    },
+    {
+      "epoch": 1.8848167539267016,
+      "grad_norm": 0.3049869239330292,
+      "learning_rate": 0.0002,
+      "loss": 1.2744,
+      "step": 180
+    },
+    {
+      "epoch": 1.9895287958115184,
+      "grad_norm": 0.3276447355747223,
+      "learning_rate": 0.0002,
+      "loss": 1.2275,
+      "step": 190
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.246069073677063,
+      "eval_runtime": 21.7078,
+      "eval_samples_per_second": 4.422,
+      "eval_steps_per_second": 0.553,
+      "step": 191
+    },
+    {
+      "epoch": 2.094240837696335,
+      "grad_norm": 0.35667529702186584,
+      "learning_rate": 0.0002,
+      "loss": 1.1839,
+      "step": 200
+    },
+    {
+      "epoch": 2.1989528795811517,
+      "grad_norm": 0.37533891201019287,
+      "learning_rate": 0.0002,
+      "loss": 1.1889,
+      "step": 210
+    },
+    {
+      "epoch": 2.303664921465969,
+      "grad_norm": 0.3843613862991333,
+      "learning_rate": 0.0002,
+      "loss": 1.1663,
+      "step": 220
+    },
+    {
+      "epoch": 2.4083769633507854,
+      "grad_norm": 0.42571955919265747,
+      "learning_rate": 0.0002,
+      "loss": 1.1277,
+      "step": 230
+    },
+    {
+      "epoch": 2.513089005235602,
+      "grad_norm": 0.4841604232788086,
+      "learning_rate": 0.0002,
+      "loss": 1.1661,
+      "step": 240
+    },
+    {
+      "epoch": 2.6178010471204187,
+      "grad_norm": 0.486310750246048,
+      "learning_rate": 0.0002,
+      "loss": 1.1448,
+      "step": 250
+    },
+    {
+      "epoch": 2.7225130890052354,
+      "grad_norm": 0.4195743501186371,
+      "learning_rate": 0.0002,
+      "loss": 1.1523,
+      "step": 260
+    },
+    {
+      "epoch": 2.8272251308900525,
+      "grad_norm": 0.3464842736721039,
+      "learning_rate": 0.0002,
+      "loss": 1.1628,
+      "step": 270
+    },
+    {
+      "epoch": 2.931937172774869,
+      "grad_norm": 0.39531266689300537,
+      "learning_rate": 0.0002,
+      "loss": 1.2008,
+      "step": 280
+    },
+    {
+      "epoch": 2.994764397905759,
+      "eval_loss": 1.2453244924545288,
+      "eval_runtime": 21.5594,
+      "eval_samples_per_second": 4.453,
+      "eval_steps_per_second": 0.557,
+      "step": 286
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 760,
+  "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": 1.2481630680121344e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-286/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66b56b5a1635548dcb5aa08f01d4d0f065dec7a3ac400babdffd741b96b8639b
+size 5560

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-382/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-7B-Instruct
+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

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-382/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-382/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12cf597fc99be27885c881a326743b53f5c437762d9d1b90d5e2dc88e53f528f
+size 80755416

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-382/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-382/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37178205bf325e577440fc272cbca5f7d6c2ac85f281882ca8d3801c31e2678d
+size 41136570

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-382/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d83f2b020535dc2edf2ea342d064c87772d46549e8ed54d498752cfcb10bae57
+size 14244

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-382/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e2d7627a361742458a1a0b28721bba13c09cfc16c2b274fba770d9e7ffedf2
+size 1064

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-382/special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-382/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-382/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-382/trainer_state.json

@@ -0,0 +1,331 @@
+{
+  "best_metric": 1.2453244924545288,
+  "best_model_checkpoint": "outputs-001/Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-286",
+  "epoch": 4.0,
+  "eval_steps": 10,
+  "global_step": 382,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10471204188481675,
+      "grad_norm": 0.19758254289627075,
+      "learning_rate": 0.0002,
+      "loss": 1.634,
+      "step": 10
+    },
+    {
+      "epoch": 0.2094240837696335,
+      "grad_norm": 0.32746484875679016,
+      "learning_rate": 0.0002,
+      "loss": 1.4531,
+      "step": 20
+    },
+    {
+      "epoch": 0.31413612565445026,
+      "grad_norm": 0.2939307689666748,
+      "learning_rate": 0.0002,
+      "loss": 1.3666,
+      "step": 30
+    },
+    {
+      "epoch": 0.418848167539267,
+      "grad_norm": 0.4865039587020874,
+      "learning_rate": 0.0002,
+      "loss": 1.3884,
+      "step": 40
+    },
+    {
+      "epoch": 0.5235602094240838,
+      "grad_norm": 0.25857967138290405,
+      "learning_rate": 0.0002,
+      "loss": 1.3453,
+      "step": 50
+    },
+    {
+      "epoch": 0.6282722513089005,
+      "grad_norm": 0.27348533272743225,
+      "learning_rate": 0.0002,
+      "loss": 1.3206,
+      "step": 60
+    },
+    {
+      "epoch": 0.7329842931937173,
+      "grad_norm": 0.2988259196281433,
+      "learning_rate": 0.0002,
+      "loss": 1.3141,
+      "step": 70
+    },
+    {
+      "epoch": 0.837696335078534,
+      "grad_norm": 0.277259886264801,
+      "learning_rate": 0.0002,
+      "loss": 1.2931,
+      "step": 80
+    },
+    {
+      "epoch": 0.9424083769633508,
+      "grad_norm": 0.34198081493377686,
+      "learning_rate": 0.0002,
+      "loss": 1.3112,
+      "step": 90
+    },
+    {
+      "epoch": 0.9947643979057592,
+      "eval_loss": 1.2753487825393677,
+      "eval_runtime": 21.375,
+      "eval_samples_per_second": 4.491,
+      "eval_steps_per_second": 0.561,
+      "step": 95
+    },
+    {
+      "epoch": 1.0471204188481675,
+      "grad_norm": 0.2599162459373474,
+      "learning_rate": 0.0002,
+      "loss": 1.2368,
+      "step": 100
+    },
+    {
+      "epoch": 1.1518324607329844,
+      "grad_norm": 0.28724443912506104,
+      "learning_rate": 0.0002,
+      "loss": 1.2015,
+      "step": 110
+    },
+    {
+      "epoch": 1.256544502617801,
+      "grad_norm": 0.2874450087547302,
+      "learning_rate": 0.0002,
+      "loss": 1.2785,
+      "step": 120
+    },
+    {
+      "epoch": 1.3612565445026177,
+      "grad_norm": 0.2946247458457947,
+      "learning_rate": 0.0002,
+      "loss": 1.2254,
+      "step": 130
+    },
+    {
+      "epoch": 1.4659685863874345,
+      "grad_norm": 0.29081839323043823,
+      "learning_rate": 0.0002,
+      "loss": 1.2094,
+      "step": 140
+    },
+    {
+      "epoch": 1.5706806282722514,
+      "grad_norm": 0.3117203712463379,
+      "learning_rate": 0.0002,
+      "loss": 1.2091,
+      "step": 150
+    },
+    {
+      "epoch": 1.675392670157068,
+      "grad_norm": 0.4307788610458374,
+      "learning_rate": 0.0002,
+      "loss": 1.2503,
+      "step": 160
+    },
+    {
+      "epoch": 1.7801047120418847,
+      "grad_norm": 0.4271780252456665,
+      "learning_rate": 0.0002,
+      "loss": 1.2886,
+      "step": 170
+    },
+    {
+      "epoch": 1.8848167539267016,
+      "grad_norm": 0.3049869239330292,
+      "learning_rate": 0.0002,
+      "loss": 1.2744,
+      "step": 180
+    },
+    {
+      "epoch": 1.9895287958115184,
+      "grad_norm": 0.3276447355747223,
+      "learning_rate": 0.0002,
+      "loss": 1.2275,
+      "step": 190
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.246069073677063,
+      "eval_runtime": 21.7078,
+      "eval_samples_per_second": 4.422,
+      "eval_steps_per_second": 0.553,
+      "step": 191
+    },
+    {
+      "epoch": 2.094240837696335,
+      "grad_norm": 0.35667529702186584,
+      "learning_rate": 0.0002,
+      "loss": 1.1839,
+      "step": 200
+    },
+    {
+      "epoch": 2.1989528795811517,
+      "grad_norm": 0.37533891201019287,
+      "learning_rate": 0.0002,
+      "loss": 1.1889,
+      "step": 210
+    },
+    {
+      "epoch": 2.303664921465969,
+      "grad_norm": 0.3843613862991333,
+      "learning_rate": 0.0002,
+      "loss": 1.1663,
+      "step": 220
+    },
+    {
+      "epoch": 2.4083769633507854,
+      "grad_norm": 0.42571955919265747,
+      "learning_rate": 0.0002,
+      "loss": 1.1277,
+      "step": 230
+    },
+    {
+      "epoch": 2.513089005235602,
+      "grad_norm": 0.4841604232788086,
+      "learning_rate": 0.0002,
+      "loss": 1.1661,
+      "step": 240
+    },
+    {
+      "epoch": 2.6178010471204187,
+      "grad_norm": 0.486310750246048,
+      "learning_rate": 0.0002,
+      "loss": 1.1448,
+      "step": 250
+    },
+    {
+      "epoch": 2.7225130890052354,
+      "grad_norm": 0.4195743501186371,
+      "learning_rate": 0.0002,
+      "loss": 1.1523,
+      "step": 260
+    },
+    {
+      "epoch": 2.8272251308900525,
+      "grad_norm": 0.3464842736721039,
+      "learning_rate": 0.0002,
+      "loss": 1.1628,
+      "step": 270
+    },
+    {
+      "epoch": 2.931937172774869,
+      "grad_norm": 0.39531266689300537,
+      "learning_rate": 0.0002,
+      "loss": 1.2008,
+      "step": 280
+    },
+    {
+      "epoch": 2.994764397905759,
+      "eval_loss": 1.2453244924545288,
+      "eval_runtime": 21.5594,
+      "eval_samples_per_second": 4.453,
+      "eval_steps_per_second": 0.557,
+      "step": 286
+    },
+    {
+      "epoch": 3.0366492146596857,
+      "grad_norm": 0.36510857939720154,
+      "learning_rate": 0.0002,
+      "loss": 1.1118,
+      "step": 290
+    },
+    {
+      "epoch": 3.141361256544503,
+      "grad_norm": 0.3765343725681305,
+      "learning_rate": 0.0002,
+      "loss": 1.0969,
+      "step": 300
+    },
+    {
+      "epoch": 3.2460732984293195,
+      "grad_norm": 0.4850059151649475,
+      "learning_rate": 0.0002,
+      "loss": 1.0928,
+      "step": 310
+    },
+    {
+      "epoch": 3.350785340314136,
+      "grad_norm": 0.5310692191123962,
+      "learning_rate": 0.0002,
+      "loss": 1.0539,
+      "step": 320
+    },
+    {
+      "epoch": 3.4554973821989527,
+      "grad_norm": 0.5328142046928406,
+      "learning_rate": 0.0002,
+      "loss": 1.0585,
+      "step": 330
+    },
+    {
+      "epoch": 3.5602094240837694,
+      "grad_norm": 0.5113003849983215,
+      "learning_rate": 0.0002,
+      "loss": 1.0704,
+      "step": 340
+    },
+    {
+      "epoch": 3.6649214659685865,
+      "grad_norm": 0.44217362999916077,
+      "learning_rate": 0.0002,
+      "loss": 1.0687,
+      "step": 350
+    },
+    {
+      "epoch": 3.769633507853403,
+      "grad_norm": 0.4684664011001587,
+      "learning_rate": 0.0002,
+      "loss": 1.0597,
+      "step": 360
+    },
+    {
+      "epoch": 3.8743455497382198,
+      "grad_norm": 0.4604615867137909,
+      "learning_rate": 0.0002,
+      "loss": 1.0873,
+      "step": 370
+    },
+    {
+      "epoch": 3.979057591623037,
+      "grad_norm": 0.46551817655563354,
+      "learning_rate": 0.0002,
+      "loss": 1.0743,
+      "step": 380
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.2580546140670776,
+      "eval_runtime": 21.8045,
+      "eval_samples_per_second": 4.403,
+      "eval_steps_per_second": 0.55,
+      "step": 382
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 760,
+  "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": 1.6642174240161792e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-382/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66b56b5a1635548dcb5aa08f01d4d0f065dec7a3ac400babdffd741b96b8639b
+size 5560

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-477/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-7B-Instruct
+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

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-477/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-10000/checkpoint-477/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:597e72069e4079d31ccceea8333139f2de1b444f69c13daf85af2b4147b25a50
+size 80755416