Upload folder using huggingface_hub

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aca39d27d35c45901d25b198af486289904f65699c9100bc2af1fe253eff2b7
+size 80755416

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/added_tokens.json

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

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-11256/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-11256/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-11256/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ce11cf98f9c5b5e53867810f69f35856ef20a64ce686a2564072b413b5bcfb1
+size 80755416

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-11256/added_tokens.json

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

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-11256/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10feab5d93ea7e3ac4d7d91f34ac21ca311403d4e726c9b23d948df71c22a2d5
+size 41136570

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-11256/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e2e232c77d2b8ebe907bd3b2ce6b41e33d268dac961fb38308fb7b3428a421
+size 14244

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-11256/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff60cb8f0f603641639aa7fe47a2d17952f9b05a3cce10988b1e319586c5aab0
+size 1064

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-11256/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-11256/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-11256/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d275255dce8376488e75407256065fb6f35be7731d4937a9fd7ad6e8036803
+size 5560

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-12864/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-12864/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-12864/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe3e1cb02dce1c94942e188ca2a9ebfce6dd9d483b47a8e7d1009ce9bc558b34
+size 80755416

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-12864/added_tokens.json

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

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-12864/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78503c65f5e2d330e1a51041ddcc6051d3fb55326fe73caab03dd2d8ad693668
+size 41136570

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-12864/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c878d98405727f08ac8d6474f14659bafa8bb09c876ec7323942dec78fe8efb7
+size 14244

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-12864/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec063a341f83788df2ebef3f0fe15f2aaf4aeaff0f2f2238abb93c0cab4b712
+size 1064

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-12864/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-12864/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-12864/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d275255dce8376488e75407256065fb6f35be7731d4937a9fd7ad6e8036803
+size 5560

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-1608/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-1608/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-1608/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a853b9d7e904d77f1f7328c18af0ada13a4f25ba21d3cbc4f4e9079296b534c4
+size 80755416

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-1608/added_tokens.json

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

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-1608/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e12daa79c864e1510a1747313a05813498d2c66c12c4b5c4634389a75ca4267f
+size 41136570

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-1608/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cd601787b9df8c699f21f0a6e2ea590eac2ad9a442df10606058edcb85e376f
+size 14244

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-1608/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b865aa46b3025c2be17ca07df1e401f553d621d03b14541d2ca146aacb6ef1
+size 1064

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-1608/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-1608/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-1608/trainer_state.json

@@ -0,0 +1,1161 @@
+{
+  "best_metric": 1.123377799987793,
+  "best_model_checkpoint": "outputs-001/Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-1608",
+  "epoch": 1.0,
+  "eval_steps": 10,
+  "global_step": 1608,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006218905472636816,
+      "grad_norm": 0.2531508505344391,
+      "learning_rate": 0.0002,
+      "loss": 1.5751,
+      "step": 10
+    },
+    {
+      "epoch": 0.012437810945273632,
+      "grad_norm": 0.1978771686553955,
+      "learning_rate": 0.0002,
+      "loss": 1.4384,
+      "step": 20
+    },
+    {
+      "epoch": 0.018656716417910446,
+      "grad_norm": 0.26382774114608765,
+      "learning_rate": 0.0002,
+      "loss": 1.3542,
+      "step": 30
+    },
+    {
+      "epoch": 0.024875621890547265,
+      "grad_norm": 0.21458084881305695,
+      "learning_rate": 0.0002,
+      "loss": 1.2063,
+      "step": 40
+    },
+    {
+      "epoch": 0.03109452736318408,
+      "grad_norm": 0.3422771990299225,
+      "learning_rate": 0.0002,
+      "loss": 1.3438,
+      "step": 50
+    },
+    {
+      "epoch": 0.03731343283582089,
+      "grad_norm": 0.26461055874824524,
+      "learning_rate": 0.0002,
+      "loss": 1.1952,
+      "step": 60
+    },
+    {
+      "epoch": 0.043532338308457715,
+      "grad_norm": 0.2103150188922882,
+      "learning_rate": 0.0002,
+      "loss": 1.1941,
+      "step": 70
+    },
+    {
+      "epoch": 0.04975124378109453,
+      "grad_norm": 0.2583378553390503,
+      "learning_rate": 0.0002,
+      "loss": 1.173,
+      "step": 80
+    },
+    {
+      "epoch": 0.055970149253731345,
+      "grad_norm": 0.2593613564968109,
+      "learning_rate": 0.0002,
+      "loss": 1.2486,
+      "step": 90
+    },
+    {
+      "epoch": 0.06218905472636816,
+      "grad_norm": 0.23682935535907745,
+      "learning_rate": 0.0002,
+      "loss": 1.167,
+      "step": 100
+    },
+    {
+      "epoch": 0.06840796019900497,
+      "grad_norm": 0.2211347073316574,
+      "learning_rate": 0.0002,
+      "loss": 1.1495,
+      "step": 110
+    },
+    {
+      "epoch": 0.07462686567164178,
+      "grad_norm": 0.2481326162815094,
+      "learning_rate": 0.0002,
+      "loss": 1.0922,
+      "step": 120
+    },
+    {
+      "epoch": 0.08084577114427861,
+      "grad_norm": 0.22804971039295197,
+      "learning_rate": 0.0002,
+      "loss": 1.0818,
+      "step": 130
+    },
+    {
+      "epoch": 0.08706467661691543,
+      "grad_norm": 0.26714611053466797,
+      "learning_rate": 0.0002,
+      "loss": 1.0951,
+      "step": 140
+    },
+    {
+      "epoch": 0.09328358208955224,
+      "grad_norm": 0.24335210025310516,
+      "learning_rate": 0.0002,
+      "loss": 1.1358,
+      "step": 150
+    },
+    {
+      "epoch": 0.09950248756218906,
+      "grad_norm": 0.3499411940574646,
+      "learning_rate": 0.0002,
+      "loss": 1.2285,
+      "step": 160
+    },
+    {
+      "epoch": 0.10572139303482588,
+      "grad_norm": 0.23488348722457886,
+      "learning_rate": 0.0002,
+      "loss": 1.1191,
+      "step": 170
+    },
+    {
+      "epoch": 0.11194029850746269,
+      "grad_norm": 0.29499733448028564,
+      "learning_rate": 0.0002,
+      "loss": 1.0853,
+      "step": 180
+    },
+    {
+      "epoch": 0.1181592039800995,
+      "grad_norm": 0.1835961788892746,
+      "learning_rate": 0.0002,
+      "loss": 1.1756,
+      "step": 190
+    },
+    {
+      "epoch": 0.12437810945273632,
+      "grad_norm": 0.25643354654312134,
+      "learning_rate": 0.0002,
+      "loss": 1.367,
+      "step": 200
+    },
+    {
+      "epoch": 0.13059701492537312,
+      "grad_norm": 0.3161119520664215,
+      "learning_rate": 0.0002,
+      "loss": 1.0878,
+      "step": 210
+    },
+    {
+      "epoch": 0.13681592039800994,
+      "grad_norm": 0.27322304248809814,
+      "learning_rate": 0.0002,
+      "loss": 1.2049,
+      "step": 220
+    },
+    {
+      "epoch": 0.14303482587064675,
+      "grad_norm": 0.21454064548015594,
+      "learning_rate": 0.0002,
+      "loss": 1.1466,
+      "step": 230
+    },
+    {
+      "epoch": 0.14925373134328357,
+      "grad_norm": 0.22792752087116241,
+      "learning_rate": 0.0002,
+      "loss": 1.0986,
+      "step": 240
+    },
+    {
+      "epoch": 0.15547263681592038,
+      "grad_norm": 0.2137063890695572,
+      "learning_rate": 0.0002,
+      "loss": 1.1613,
+      "step": 250
+    },
+    {
+      "epoch": 0.16169154228855723,
+      "grad_norm": 0.20322220027446747,
+      "learning_rate": 0.0002,
+      "loss": 1.0633,
+      "step": 260
+    },
+    {
+      "epoch": 0.16791044776119404,
+      "grad_norm": 0.2053966522216797,
+      "learning_rate": 0.0002,
+      "loss": 1.1412,
+      "step": 270
+    },
+    {
+      "epoch": 0.17412935323383086,
+      "grad_norm": 0.299315869808197,
+      "learning_rate": 0.0002,
+      "loss": 1.1155,
+      "step": 280
+    },
+    {
+      "epoch": 0.18034825870646767,
+      "grad_norm": 0.19362252950668335,
+      "learning_rate": 0.0002,
+      "loss": 1.08,
+      "step": 290
+    },
+    {
+      "epoch": 0.1865671641791045,
+      "grad_norm": 0.23465056717395782,
+      "learning_rate": 0.0002,
+      "loss": 1.2717,
+      "step": 300
+    },
+    {
+      "epoch": 0.1927860696517413,
+      "grad_norm": 0.21198076009750366,
+      "learning_rate": 0.0002,
+      "loss": 1.2428,
+      "step": 310
+    },
+    {
+      "epoch": 0.19900497512437812,
+      "grad_norm": 0.23058398067951202,
+      "learning_rate": 0.0002,
+      "loss": 1.06,
+      "step": 320
+    },
+    {
+      "epoch": 0.20522388059701493,
+      "grad_norm": 0.28425389528274536,
+      "learning_rate": 0.0002,
+      "loss": 1.1131,
+      "step": 330
+    },
+    {
+      "epoch": 0.21144278606965175,
+      "grad_norm": 0.21831294894218445,
+      "learning_rate": 0.0002,
+      "loss": 1.2422,
+      "step": 340
+    },
+    {
+      "epoch": 0.21766169154228857,
+      "grad_norm": 0.20463259518146515,
+      "learning_rate": 0.0002,
+      "loss": 1.1469,
+      "step": 350
+    },
+    {
+      "epoch": 0.22388059701492538,
+      "grad_norm": 0.25539207458496094,
+      "learning_rate": 0.0002,
+      "loss": 1.2861,
+      "step": 360
+    },
+    {
+      "epoch": 0.2300995024875622,
+      "grad_norm": 0.22657011449337006,
+      "learning_rate": 0.0002,
+      "loss": 1.092,
+      "step": 370
+    },
+    {
+      "epoch": 0.236318407960199,
+      "grad_norm": 0.23945802450180054,
+      "learning_rate": 0.0002,
+      "loss": 1.1166,
+      "step": 380
+    },
+    {
+      "epoch": 0.24253731343283583,
+      "grad_norm": 0.19743943214416504,
+      "learning_rate": 0.0002,
+      "loss": 1.2688,
+      "step": 390
+    },
+    {
+      "epoch": 0.24875621890547264,
+      "grad_norm": 0.20974969863891602,
+      "learning_rate": 0.0002,
+      "loss": 1.0929,
+      "step": 400
+    },
+    {
+      "epoch": 0.25497512437810943,
+      "grad_norm": 0.20452603697776794,
+      "learning_rate": 0.0002,
+      "loss": 1.1369,
+      "step": 410
+    },
+    {
+      "epoch": 0.26119402985074625,
+      "grad_norm": 0.2160211056470871,
+      "learning_rate": 0.0002,
+      "loss": 0.9849,
+      "step": 420
+    },
+    {
+      "epoch": 0.26741293532338306,
+      "grad_norm": 0.22487811744213104,
+      "learning_rate": 0.0002,
+      "loss": 1.0582,
+      "step": 430
+    },
+    {
+      "epoch": 0.2736318407960199,
+      "grad_norm": 0.22394722700119019,
+      "learning_rate": 0.0002,
+      "loss": 0.9932,
+      "step": 440
+    },
+    {
+      "epoch": 0.2798507462686567,
+      "grad_norm": 0.18930265307426453,
+      "learning_rate": 0.0002,
+      "loss": 1.1683,
+      "step": 450
+    },
+    {
+      "epoch": 0.2860696517412935,
+      "grad_norm": 0.23840737342834473,
+      "learning_rate": 0.0002,
+      "loss": 0.9753,
+      "step": 460
+    },
+    {
+      "epoch": 0.2922885572139303,
+      "grad_norm": 0.20760977268218994,
+      "learning_rate": 0.0002,
+      "loss": 1.1671,
+      "step": 470
+    },
+    {
+      "epoch": 0.29850746268656714,
+      "grad_norm": 0.22870512306690216,
+      "learning_rate": 0.0002,
+      "loss": 1.0458,
+      "step": 480
+    },
+    {
+      "epoch": 0.30472636815920395,
+      "grad_norm": 0.22682909667491913,
+      "learning_rate": 0.0002,
+      "loss": 1.0672,
+      "step": 490
+    },
+    {
+      "epoch": 0.31094527363184077,
+      "grad_norm": 0.1793045848608017,
+      "learning_rate": 0.0002,
+      "loss": 1.1414,
+      "step": 500
+    },
+    {
+      "epoch": 0.31716417910447764,
+      "grad_norm": 0.2563018798828125,
+      "learning_rate": 0.0002,
+      "loss": 1.1383,
+      "step": 510
+    },
+    {
+      "epoch": 0.32338308457711445,
+      "grad_norm": 0.22268766164779663,
+      "learning_rate": 0.0002,
+      "loss": 1.1329,
+      "step": 520
+    },
+    {
+      "epoch": 0.32960199004975127,
+      "grad_norm": 0.20912376046180725,
+      "learning_rate": 0.0002,
+      "loss": 1.0539,
+      "step": 530
+    },
+    {
+      "epoch": 0.3358208955223881,
+      "grad_norm": 0.29494908452033997,
+      "learning_rate": 0.0002,
+      "loss": 1.2096,
+      "step": 540
+    },
+    {
+      "epoch": 0.3420398009950249,
+      "grad_norm": 0.17184239625930786,
+      "learning_rate": 0.0002,
+      "loss": 1.104,
+      "step": 550
+    },
+    {
+      "epoch": 0.3482587064676617,
+      "grad_norm": 0.25503867864608765,
+      "learning_rate": 0.0002,
+      "loss": 1.2176,
+      "step": 560
+    },
+    {
+      "epoch": 0.35447761194029853,
+      "grad_norm": 0.2710067331790924,
+      "learning_rate": 0.0002,
+      "loss": 1.1762,
+      "step": 570
+    },
+    {
+      "epoch": 0.36069651741293535,
+      "grad_norm": 0.22906805574893951,
+      "learning_rate": 0.0002,
+      "loss": 1.1532,
+      "step": 580
+    },
+    {
+      "epoch": 0.36691542288557216,
+      "grad_norm": 0.22127066552639008,
+      "learning_rate": 0.0002,
+      "loss": 1.1806,
+      "step": 590
+    },
+    {
+      "epoch": 0.373134328358209,
+      "grad_norm": 0.1770811825990677,
+      "learning_rate": 0.0002,
+      "loss": 1.1221,
+      "step": 600
+    },
+    {
+      "epoch": 0.3793532338308458,
+      "grad_norm": 0.2136841118335724,
+      "learning_rate": 0.0002,
+      "loss": 1.2524,
+      "step": 610
+    },
+    {
+      "epoch": 0.3855721393034826,
+      "grad_norm": 0.1718018651008606,
+      "learning_rate": 0.0002,
+      "loss": 0.944,
+      "step": 620
+    },
+    {
+      "epoch": 0.3917910447761194,
+      "grad_norm": 0.22513172030448914,
+      "learning_rate": 0.0002,
+      "loss": 1.2148,
+      "step": 630
+    },
+    {
+      "epoch": 0.39800995024875624,
+      "grad_norm": 0.23916903138160706,
+      "learning_rate": 0.0002,
+      "loss": 1.1423,
+      "step": 640
+    },
+    {
+      "epoch": 0.40422885572139305,
+      "grad_norm": 0.21956735849380493,
+      "learning_rate": 0.0002,
+      "loss": 1.0159,
+      "step": 650
+    },
+    {
+      "epoch": 0.41044776119402987,
+      "grad_norm": 0.2406178116798401,
+      "learning_rate": 0.0002,
+      "loss": 1.1582,
+      "step": 660
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.19150735437870026,
+      "learning_rate": 0.0002,
+      "loss": 1.0568,
+      "step": 670
+    },
+    {
+      "epoch": 0.4228855721393035,
+      "grad_norm": 0.2316412329673767,
+      "learning_rate": 0.0002,
+      "loss": 1.0864,
+      "step": 680
+    },
+    {
+      "epoch": 0.4291044776119403,
+      "grad_norm": 0.21616971492767334,
+      "learning_rate": 0.0002,
+      "loss": 1.2746,
+      "step": 690
+    },
+    {
+      "epoch": 0.43532338308457713,
+      "grad_norm": 0.1868504136800766,
+      "learning_rate": 0.0002,
+      "loss": 1.168,
+      "step": 700
+    },
+    {
+      "epoch": 0.44154228855721395,
+      "grad_norm": 0.19621914625167847,
+      "learning_rate": 0.0002,
+      "loss": 1.1566,
+      "step": 710
+    },
+    {
+      "epoch": 0.44776119402985076,
+      "grad_norm": 0.20955324172973633,
+      "learning_rate": 0.0002,
+      "loss": 1.1196,
+      "step": 720
+    },
+    {
+      "epoch": 0.4539800995024876,
+      "grad_norm": 0.20259015262126923,
+      "learning_rate": 0.0002,
+      "loss": 1.0708,
+      "step": 730
+    },
+    {
+      "epoch": 0.4601990049751244,
+      "grad_norm": 0.20897835493087769,
+      "learning_rate": 0.0002,
+      "loss": 1.1795,
+      "step": 740
+    },
+    {
+      "epoch": 0.4664179104477612,
+      "grad_norm": 0.19419585168361664,
+      "learning_rate": 0.0002,
+      "loss": 1.0217,
+      "step": 750
+    },
+    {
+      "epoch": 0.472636815920398,
+      "grad_norm": 0.28699710965156555,
+      "learning_rate": 0.0002,
+      "loss": 1.0922,
+      "step": 760
+    },
+    {
+      "epoch": 0.47885572139303484,
+      "grad_norm": 0.20983494818210602,
+      "learning_rate": 0.0002,
+      "loss": 1.1587,
+      "step": 770
+    },
+    {
+      "epoch": 0.48507462686567165,
+      "grad_norm": 0.2040906548500061,
+      "learning_rate": 0.0002,
+      "loss": 1.1692,
+      "step": 780
+    },
+    {
+      "epoch": 0.49129353233830847,
+      "grad_norm": 0.20985379815101624,
+      "learning_rate": 0.0002,
+      "loss": 1.0823,
+      "step": 790
+    },
+    {
+      "epoch": 0.4975124378109453,
+      "grad_norm": 0.17362040281295776,
+      "learning_rate": 0.0002,
+      "loss": 1.0732,
+      "step": 800
+    },
+    {
+      "epoch": 0.503731343283582,
+      "grad_norm": 0.20593293011188507,
+      "learning_rate": 0.0002,
+      "loss": 1.1948,
+      "step": 810
+    },
+    {
+      "epoch": 0.5099502487562189,
+      "grad_norm": 0.22094237804412842,
+      "learning_rate": 0.0002,
+      "loss": 1.1767,
+      "step": 820
+    },
+    {
+      "epoch": 0.5161691542288557,
+      "grad_norm": 0.19221271574497223,
+      "learning_rate": 0.0002,
+      "loss": 1.0262,
+      "step": 830
+    },
+    {
+      "epoch": 0.5223880597014925,
+      "grad_norm": 0.26233774423599243,
+      "learning_rate": 0.0002,
+      "loss": 1.0891,
+      "step": 840
+    },
+    {
+      "epoch": 0.5286069651741293,
+      "grad_norm": 0.2587118148803711,
+      "learning_rate": 0.0002,
+      "loss": 1.0409,
+      "step": 850
+    },
+    {
+      "epoch": 0.5348258706467661,
+      "grad_norm": 0.2248653620481491,
+      "learning_rate": 0.0002,
+      "loss": 1.1459,
+      "step": 860
+    },
+    {
+      "epoch": 0.5410447761194029,
+      "grad_norm": 0.210169717669487,
+      "learning_rate": 0.0002,
+      "loss": 1.2886,
+      "step": 870
+    },
+    {
+      "epoch": 0.5472636815920398,
+      "grad_norm": 0.19172827899456024,
+      "learning_rate": 0.0002,
+      "loss": 1.08,
+      "step": 880
+    },
+    {
+      "epoch": 0.5534825870646766,
+      "grad_norm": 0.23246489465236664,
+      "learning_rate": 0.0002,
+      "loss": 1.1021,
+      "step": 890
+    },
+    {
+      "epoch": 0.5597014925373134,
+      "grad_norm": 0.21363039314746857,
+      "learning_rate": 0.0002,
+      "loss": 1.2078,
+      "step": 900
+    },
+    {
+      "epoch": 0.5659203980099502,
+      "grad_norm": 0.24523669481277466,
+      "learning_rate": 0.0002,
+      "loss": 1.0479,
+      "step": 910
+    },
+    {
+      "epoch": 0.572139303482587,
+      "grad_norm": 0.18214288353919983,
+      "learning_rate": 0.0002,
+      "loss": 1.0124,
+      "step": 920
+    },
+    {
+      "epoch": 0.5783582089552238,
+      "grad_norm": 0.31379181146621704,
+      "learning_rate": 0.0002,
+      "loss": 1.1764,
+      "step": 930
+    },
+    {
+      "epoch": 0.5845771144278606,
+      "grad_norm": 0.34351202845573425,
+      "learning_rate": 0.0002,
+      "loss": 1.0157,
+      "step": 940
+    },
+    {
+      "epoch": 0.5907960199004975,
+      "grad_norm": 0.24276268482208252,
+      "learning_rate": 0.0002,
+      "loss": 1.1093,
+      "step": 950
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 0.18730808794498444,
+      "learning_rate": 0.0002,
+      "loss": 1.1167,
+      "step": 960
+    },
+    {
+      "epoch": 0.6032338308457711,
+      "grad_norm": 0.1846453845500946,
+      "learning_rate": 0.0002,
+      "loss": 1.165,
+      "step": 970
+    },
+    {
+      "epoch": 0.6094527363184079,
+      "grad_norm": 0.1947498768568039,
+      "learning_rate": 0.0002,
+      "loss": 1.1531,
+      "step": 980
+    },
+    {
+      "epoch": 0.6156716417910447,
+      "grad_norm": 0.23108096420764923,
+      "learning_rate": 0.0002,
+      "loss": 1.1547,
+      "step": 990
+    },
+    {
+      "epoch": 0.6218905472636815,
+      "grad_norm": 0.3734484314918518,
+      "learning_rate": 0.0002,
+      "loss": 1.0631,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6281094527363185,
+      "grad_norm": 0.1858675479888916,
+      "learning_rate": 0.0002,
+      "loss": 1.1,
+      "step": 1010
+    },
+    {
+      "epoch": 0.6343283582089553,
+      "grad_norm": 0.19122643768787384,
+      "learning_rate": 0.0002,
+      "loss": 1.1602,
+      "step": 1020
+    },
+    {
+      "epoch": 0.6405472636815921,
+      "grad_norm": 0.2099395990371704,
+      "learning_rate": 0.0002,
+      "loss": 1.2074,
+      "step": 1030
+    },
+    {
+      "epoch": 0.6467661691542289,
+      "grad_norm": 0.20726917684078217,
+      "learning_rate": 0.0002,
+      "loss": 1.1463,
+      "step": 1040
+    },
+    {
+      "epoch": 0.6529850746268657,
+      "grad_norm": 0.20917607843875885,
+      "learning_rate": 0.0002,
+      "loss": 1.1062,
+      "step": 1050
+    },
+    {
+      "epoch": 0.6592039800995025,
+      "grad_norm": 0.22000652551651,
+      "learning_rate": 0.0002,
+      "loss": 1.1452,
+      "step": 1060
+    },
+    {
+      "epoch": 0.6654228855721394,
+      "grad_norm": 0.20291198790073395,
+      "learning_rate": 0.0002,
+      "loss": 1.0574,
+      "step": 1070
+    },
+    {
+      "epoch": 0.6716417910447762,
+      "grad_norm": 0.24871645867824554,
+      "learning_rate": 0.0002,
+      "loss": 1.1736,
+      "step": 1080
+    },
+    {
+      "epoch": 0.677860696517413,
+      "grad_norm": 0.19254647195339203,
+      "learning_rate": 0.0002,
+      "loss": 1.07,
+      "step": 1090
+    },
+    {
+      "epoch": 0.6840796019900498,
+      "grad_norm": 0.24950885772705078,
+      "learning_rate": 0.0002,
+      "loss": 1.1889,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6902985074626866,
+      "grad_norm": 0.21884030103683472,
+      "learning_rate": 0.0002,
+      "loss": 1.1291,
+      "step": 1110
+    },
+    {
+      "epoch": 0.6965174129353234,
+      "grad_norm": 0.1705121546983719,
+      "learning_rate": 0.0002,
+      "loss": 1.1391,
+      "step": 1120
+    },
+    {
+      "epoch": 0.7027363184079602,
+      "grad_norm": 0.18771620094776154,
+      "learning_rate": 0.0002,
+      "loss": 1.2353,
+      "step": 1130
+    },
+    {
+      "epoch": 0.7089552238805971,
+      "grad_norm": 0.2052127718925476,
+      "learning_rate": 0.0002,
+      "loss": 1.0902,
+      "step": 1140
+    },
+    {
+      "epoch": 0.7151741293532339,
+      "grad_norm": 0.26393118500709534,
+      "learning_rate": 0.0002,
+      "loss": 1.1253,
+      "step": 1150
+    },
+    {
+      "epoch": 0.7213930348258707,
+      "grad_norm": 0.18015135824680328,
+      "learning_rate": 0.0002,
+      "loss": 1.1012,
+      "step": 1160
+    },
+    {
+      "epoch": 0.7276119402985075,
+      "grad_norm": 0.2660037577152252,
+      "learning_rate": 0.0002,
+      "loss": 1.1228,
+      "step": 1170
+    },
+    {
+      "epoch": 0.7338308457711443,
+      "grad_norm": 0.30652812123298645,
+      "learning_rate": 0.0002,
+      "loss": 1.0486,
+      "step": 1180
+    },
+    {
+      "epoch": 0.7400497512437811,
+      "grad_norm": 0.19333289563655853,
+      "learning_rate": 0.0002,
+      "loss": 1.0657,
+      "step": 1190
+    },
+    {
+      "epoch": 0.746268656716418,
+      "grad_norm": 0.23530776798725128,
+      "learning_rate": 0.0002,
+      "loss": 1.1681,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7524875621890548,
+      "grad_norm": 0.21188388764858246,
+      "learning_rate": 0.0002,
+      "loss": 1.0912,
+      "step": 1210
+    },
+    {
+      "epoch": 0.7587064676616916,
+      "grad_norm": 0.2162955403327942,
+      "learning_rate": 0.0002,
+      "loss": 0.9928,
+      "step": 1220
+    },
+    {
+      "epoch": 0.7649253731343284,
+      "grad_norm": 0.2244316190481186,
+      "learning_rate": 0.0002,
+      "loss": 0.991,
+      "step": 1230
+    },
+    {
+      "epoch": 0.7711442786069652,
+      "grad_norm": 0.24604550004005432,
+      "learning_rate": 0.0002,
+      "loss": 1.0239,
+      "step": 1240
+    },
+    {
+      "epoch": 0.777363184079602,
+      "grad_norm": 0.24209164083003998,
+      "learning_rate": 0.0002,
+      "loss": 1.1732,
+      "step": 1250
+    },
+    {
+      "epoch": 0.7835820895522388,
+      "grad_norm": 0.19271963834762573,
+      "learning_rate": 0.0002,
+      "loss": 1.1368,
+      "step": 1260
+    },
+    {
+      "epoch": 0.7898009950248757,
+      "grad_norm": 0.28388479351997375,
+      "learning_rate": 0.0002,
+      "loss": 1.0423,
+      "step": 1270
+    },
+    {
+      "epoch": 0.7960199004975125,
+      "grad_norm": 0.3417700231075287,
+      "learning_rate": 0.0002,
+      "loss": 1.213,
+      "step": 1280
+    },
+    {
+      "epoch": 0.8022388059701493,
+      "grad_norm": 0.22656400501728058,
+      "learning_rate": 0.0002,
+      "loss": 1.075,
+      "step": 1290
+    },
+    {
+      "epoch": 0.8084577114427861,
+      "grad_norm": 0.21172961592674255,
+      "learning_rate": 0.0002,
+      "loss": 1.2326,
+      "step": 1300
+    },
+    {
+      "epoch": 0.8146766169154229,
+      "grad_norm": 0.2140684574842453,
+      "learning_rate": 0.0002,
+      "loss": 0.9925,
+      "step": 1310
+    },
+    {
+      "epoch": 0.8208955223880597,
+      "grad_norm": 0.24036948382854462,
+      "learning_rate": 0.0002,
+      "loss": 1.0776,
+      "step": 1320
+    },
+    {
+      "epoch": 0.8271144278606966,
+      "grad_norm": 0.25161686539649963,
+      "learning_rate": 0.0002,
+      "loss": 1.2241,
+      "step": 1330
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.2122456133365631,
+      "learning_rate": 0.0002,
+      "loss": 1.0513,
+      "step": 1340
+    },
+    {
+      "epoch": 0.8395522388059702,
+      "grad_norm": 0.2035810351371765,
+      "learning_rate": 0.0002,
+      "loss": 1.0153,
+      "step": 1350
+    },
+    {
+      "epoch": 0.845771144278607,
+      "grad_norm": 0.2636254131793976,
+      "learning_rate": 0.0002,
+      "loss": 1.0601,
+      "step": 1360
+    },
+    {
+      "epoch": 0.8519900497512438,
+      "grad_norm": 0.22904661297798157,
+      "learning_rate": 0.0002,
+      "loss": 1.1656,
+      "step": 1370
+    },
+    {
+      "epoch": 0.8582089552238806,
+      "grad_norm": 0.2617220878601074,
+      "learning_rate": 0.0002,
+      "loss": 1.2156,
+      "step": 1380
+    },
+    {
+      "epoch": 0.8644278606965174,
+      "grad_norm": 0.25202617049217224,
+      "learning_rate": 0.0002,
+      "loss": 1.0568,
+      "step": 1390
+    },
+    {
+      "epoch": 0.8706467661691543,
+      "grad_norm": 0.23861873149871826,
+      "learning_rate": 0.0002,
+      "loss": 1.0909,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8768656716417911,
+      "grad_norm": 0.22162985801696777,
+      "learning_rate": 0.0002,
+      "loss": 1.3063,
+      "step": 1410
+    },
+    {
+      "epoch": 0.8830845771144279,
+      "grad_norm": 0.23491384088993073,
+      "learning_rate": 0.0002,
+      "loss": 1.2873,
+      "step": 1420
+    },
+    {
+      "epoch": 0.8893034825870647,
+      "grad_norm": 0.1919153481721878,
+      "learning_rate": 0.0002,
+      "loss": 1.1478,
+      "step": 1430
+    },
+    {
+      "epoch": 0.8955223880597015,
+      "grad_norm": 0.23028430342674255,
+      "learning_rate": 0.0002,
+      "loss": 1.3066,
+      "step": 1440
+    },
+    {
+      "epoch": 0.9017412935323383,
+      "grad_norm": 0.1966322958469391,
+      "learning_rate": 0.0002,
+      "loss": 1.1629,
+      "step": 1450
+    },
+    {
+      "epoch": 0.9079601990049752,
+      "grad_norm": 0.16606393456459045,
+      "learning_rate": 0.0002,
+      "loss": 1.2253,
+      "step": 1460
+    },
+    {
+      "epoch": 0.914179104477612,
+      "grad_norm": 0.2936268150806427,
+      "learning_rate": 0.0002,
+      "loss": 1.2855,
+      "step": 1470
+    },
+    {
+      "epoch": 0.9203980099502488,
+      "grad_norm": 0.20130130648612976,
+      "learning_rate": 0.0002,
+      "loss": 1.1301,
+      "step": 1480
+    },
+    {
+      "epoch": 0.9266169154228856,
+      "grad_norm": 0.30875328183174133,
+      "learning_rate": 0.0002,
+      "loss": 1.0549,
+      "step": 1490
+    },
+    {
+      "epoch": 0.9328358208955224,
+      "grad_norm": 0.2345164269208908,
+      "learning_rate": 0.0002,
+      "loss": 1.063,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9390547263681592,
+      "grad_norm": 0.18518008291721344,
+      "learning_rate": 0.0002,
+      "loss": 1.1084,
+      "step": 1510
+    },
+    {
+      "epoch": 0.945273631840796,
+      "grad_norm": 0.1648719161748886,
+      "learning_rate": 0.0002,
+      "loss": 1.1137,
+      "step": 1520
+    },
+    {
+      "epoch": 0.9514925373134329,
+      "grad_norm": 0.19943983852863312,
+      "learning_rate": 0.0002,
+      "loss": 1.0943,
+      "step": 1530
+    },
+    {
+      "epoch": 0.9577114427860697,
+      "grad_norm": 0.20847691595554352,
+      "learning_rate": 0.0002,
+      "loss": 1.1104,
+      "step": 1540
+    },
+    {
+      "epoch": 0.9639303482587065,
+      "grad_norm": 0.2128416895866394,
+      "learning_rate": 0.0002,
+      "loss": 1.0223,
+      "step": 1550
+    },
+    {
+      "epoch": 0.9701492537313433,
+      "grad_norm": 0.18023279309272766,
+      "learning_rate": 0.0002,
+      "loss": 1.1459,
+      "step": 1560
+    },
+    {
+      "epoch": 0.9763681592039801,
+      "grad_norm": 0.22048872709274292,
+      "learning_rate": 0.0002,
+      "loss": 1.1323,
+      "step": 1570
+    },
+    {
+      "epoch": 0.9825870646766169,
+      "grad_norm": 0.2871592342853546,
+      "learning_rate": 0.0002,
+      "loss": 1.2514,
+      "step": 1580
+    },
+    {
+      "epoch": 0.9888059701492538,
+      "grad_norm": 0.5251742601394653,
+      "learning_rate": 0.0002,
+      "loss": 1.2233,
+      "step": 1590
+    },
+    {
+      "epoch": 0.9950248756218906,
+      "grad_norm": 0.21216285228729248,
+      "learning_rate": 0.0002,
+      "loss": 1.076,
+      "step": 1600
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.123377799987793,
+      "eval_runtime": 85.7655,
+      "eval_samples_per_second": 5.34,
+      "eval_steps_per_second": 0.676,
+      "step": 1608
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 12864,
+  "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": 7.005396905282765e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-1608/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d275255dce8376488e75407256065fb6f35be7731d4937a9fd7ad6e8036803
+size 5560

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-3216/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-3216/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-3216/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:754869148598515a055923668008e9e2abd38129ff2cd1b45061871e3e32fcae
+size 80755416

Qwen2-7B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-9809-sd-1/checkpoint-3216/added_tokens.json

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