Upload folder using huggingface_hub

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed3340f42cda37489a6e5c1fe55ac4fc0b61564a13f3e573f1f356493f2c11e
+size 80755416

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/added_tokens.json

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

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1232/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1232/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1232/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efe1026bc9eacf93dcbb54fd509b6f12ce980fb23cf76981f9622d1bae4a106e
+size 80755416

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1232/added_tokens.json

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

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1232/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10ea8d4f112fbf8a1a5d0606f4e0b94eb031f4ea82169f14f99e37b4e0e27f06
+size 41136570

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1232/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:992288852f5b736717aa1b2cfff996b307660d250251aff84fe0dc606906687b
+size 14244

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1232/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:442644f04018009e339745676d855af49e719afd045348ca5915b5bd0a5436e0
+size 1064

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1232/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1232/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1232/trainer_state.json

@@ -0,0 +1,926 @@
+{
+  "best_metric": 1.765038251876831,
+  "best_model_checkpoint": "outputs-001/Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-616",
+  "epoch": 4.0,
+  "eval_steps": 10,
+  "global_step": 1232,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032467532467532464,
+      "grad_norm": 0.31557697057724,
+      "learning_rate": 0.0002,
+      "loss": 2.4028,
+      "step": 10
+    },
+    {
+      "epoch": 0.06493506493506493,
+      "grad_norm": 0.3265437185764313,
+      "learning_rate": 0.0002,
+      "loss": 2.1466,
+      "step": 20
+    },
+    {
+      "epoch": 0.09740259740259741,
+      "grad_norm": 0.3424590229988098,
+      "learning_rate": 0.0002,
+      "loss": 1.9549,
+      "step": 30
+    },
+    {
+      "epoch": 0.12987012987012986,
+      "grad_norm": 0.30609560012817383,
+      "learning_rate": 0.0002,
+      "loss": 1.8464,
+      "step": 40
+    },
+    {
+      "epoch": 0.16233766233766234,
+      "grad_norm": 0.3285873532295227,
+      "learning_rate": 0.0002,
+      "loss": 1.9203,
+      "step": 50
+    },
+    {
+      "epoch": 0.19480519480519481,
+      "grad_norm": 0.2855139374732971,
+      "learning_rate": 0.0002,
+      "loss": 1.7946,
+      "step": 60
+    },
+    {
+      "epoch": 0.22727272727272727,
+      "grad_norm": 0.283848375082016,
+      "learning_rate": 0.0002,
+      "loss": 1.7618,
+      "step": 70
+    },
+    {
+      "epoch": 0.2597402597402597,
+      "grad_norm": 0.2915274202823639,
+      "learning_rate": 0.0002,
+      "loss": 1.7875,
+      "step": 80
+    },
+    {
+      "epoch": 0.2922077922077922,
+      "grad_norm": 0.26927152276039124,
+      "learning_rate": 0.0002,
+      "loss": 1.7673,
+      "step": 90
+    },
+    {
+      "epoch": 0.3246753246753247,
+      "grad_norm": 0.29594847559928894,
+      "learning_rate": 0.0002,
+      "loss": 1.6726,
+      "step": 100
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.36750105023384094,
+      "learning_rate": 0.0002,
+      "loss": 1.7333,
+      "step": 110
+    },
+    {
+      "epoch": 0.38961038961038963,
+      "grad_norm": 0.32430270314216614,
+      "learning_rate": 0.0002,
+      "loss": 1.7772,
+      "step": 120
+    },
+    {
+      "epoch": 0.42207792207792205,
+      "grad_norm": 0.2767448127269745,
+      "learning_rate": 0.0002,
+      "loss": 1.731,
+      "step": 130
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.244296595454216,
+      "learning_rate": 0.0002,
+      "loss": 1.7604,
+      "step": 140
+    },
+    {
+      "epoch": 0.487012987012987,
+      "grad_norm": 0.25791823863983154,
+      "learning_rate": 0.0002,
+      "loss": 1.7172,
+      "step": 150
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "grad_norm": 0.25496479868888855,
+      "learning_rate": 0.0002,
+      "loss": 1.7509,
+      "step": 160
+    },
+    {
+      "epoch": 0.551948051948052,
+      "grad_norm": 0.2770450711250305,
+      "learning_rate": 0.0002,
+      "loss": 1.7328,
+      "step": 170
+    },
+    {
+      "epoch": 0.5844155844155844,
+      "grad_norm": 0.2971339821815491,
+      "learning_rate": 0.0002,
+      "loss": 1.8008,
+      "step": 180
+    },
+    {
+      "epoch": 0.6168831168831169,
+      "grad_norm": 0.3165527880191803,
+      "learning_rate": 0.0002,
+      "loss": 1.6805,
+      "step": 190
+    },
+    {
+      "epoch": 0.6493506493506493,
+      "grad_norm": 0.24732241034507751,
+      "learning_rate": 0.0002,
+      "loss": 1.732,
+      "step": 200
+    },
+    {
+      "epoch": 0.6818181818181818,
+      "grad_norm": 0.28333306312561035,
+      "learning_rate": 0.0002,
+      "loss": 1.6933,
+      "step": 210
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.24870498478412628,
+      "learning_rate": 0.0002,
+      "loss": 1.7324,
+      "step": 220
+    },
+    {
+      "epoch": 0.7467532467532467,
+      "grad_norm": 0.2484978884458542,
+      "learning_rate": 0.0002,
+      "loss": 1.7697,
+      "step": 230
+    },
+    {
+      "epoch": 0.7792207792207793,
+      "grad_norm": 0.2282458394765854,
+      "learning_rate": 0.0002,
+      "loss": 1.7624,
+      "step": 240
+    },
+    {
+      "epoch": 0.8116883116883117,
+      "grad_norm": 0.2552148699760437,
+      "learning_rate": 0.0002,
+      "loss": 1.7775,
+      "step": 250
+    },
+    {
+      "epoch": 0.8441558441558441,
+      "grad_norm": 0.25136545300483704,
+      "learning_rate": 0.0002,
+      "loss": 1.7153,
+      "step": 260
+    },
+    {
+      "epoch": 0.8766233766233766,
+      "grad_norm": 0.25096797943115234,
+      "learning_rate": 0.0002,
+      "loss": 1.7705,
+      "step": 270
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.3148603141307831,
+      "learning_rate": 0.0002,
+      "loss": 1.7842,
+      "step": 280
+    },
+    {
+      "epoch": 0.9415584415584416,
+      "grad_norm": 0.2533794343471527,
+      "learning_rate": 0.0002,
+      "loss": 1.6847,
+      "step": 290
+    },
+    {
+      "epoch": 0.974025974025974,
+      "grad_norm": 0.27348795533180237,
+      "learning_rate": 0.0002,
+      "loss": 1.7334,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.769331693649292,
+      "eval_runtime": 115.5699,
+      "eval_samples_per_second": 4.603,
+      "eval_steps_per_second": 0.58,
+      "step": 308
+    },
+    {
+      "epoch": 1.0064935064935066,
+      "grad_norm": 0.28133320808410645,
+      "learning_rate": 0.0002,
+      "loss": 1.6473,
+      "step": 310
+    },
+    {
+      "epoch": 1.0389610389610389,
+      "grad_norm": 0.2541237473487854,
+      "learning_rate": 0.0002,
+      "loss": 1.7067,
+      "step": 320
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.25699320435523987,
+      "learning_rate": 0.0002,
+      "loss": 1.7422,
+      "step": 330
+    },
+    {
+      "epoch": 1.103896103896104,
+      "grad_norm": 0.26137059926986694,
+      "learning_rate": 0.0002,
+      "loss": 1.6737,
+      "step": 340
+    },
+    {
+      "epoch": 1.1363636363636362,
+      "grad_norm": 0.2718560993671417,
+      "learning_rate": 0.0002,
+      "loss": 1.7372,
+      "step": 350
+    },
+    {
+      "epoch": 1.1688311688311688,
+      "grad_norm": 0.23400403559207916,
+      "learning_rate": 0.0002,
+      "loss": 1.6809,
+      "step": 360
+    },
+    {
+      "epoch": 1.2012987012987013,
+      "grad_norm": 0.28257420659065247,
+      "learning_rate": 0.0002,
+      "loss": 1.6892,
+      "step": 370
+    },
+    {
+      "epoch": 1.2337662337662338,
+      "grad_norm": 0.3031129240989685,
+      "learning_rate": 0.0002,
+      "loss": 1.6945,
+      "step": 380
+    },
+    {
+      "epoch": 1.2662337662337662,
+      "grad_norm": 0.3131062984466553,
+      "learning_rate": 0.0002,
+      "loss": 1.6611,
+      "step": 390
+    },
+    {
+      "epoch": 1.2987012987012987,
+      "grad_norm": 0.2594483494758606,
+      "learning_rate": 0.0002,
+      "loss": 1.6535,
+      "step": 400
+    },
+    {
+      "epoch": 1.3311688311688312,
+      "grad_norm": 0.2595517933368683,
+      "learning_rate": 0.0002,
+      "loss": 1.7275,
+      "step": 410
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.26333683729171753,
+      "learning_rate": 0.0002,
+      "loss": 1.6048,
+      "step": 420
+    },
+    {
+      "epoch": 1.396103896103896,
+      "grad_norm": 0.3051556646823883,
+      "learning_rate": 0.0002,
+      "loss": 1.8342,
+      "step": 430
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.26060932874679565,
+      "learning_rate": 0.0002,
+      "loss": 1.694,
+      "step": 440
+    },
+    {
+      "epoch": 1.4610389610389611,
+      "grad_norm": 0.282101571559906,
+      "learning_rate": 0.0002,
+      "loss": 1.6284,
+      "step": 450
+    },
+    {
+      "epoch": 1.4935064935064934,
+      "grad_norm": 0.2837599813938141,
+      "learning_rate": 0.0002,
+      "loss": 1.7301,
+      "step": 460
+    },
+    {
+      "epoch": 1.525974025974026,
+      "grad_norm": 0.2532821595668793,
+      "learning_rate": 0.0002,
+      "loss": 1.6769,
+      "step": 470
+    },
+    {
+      "epoch": 1.5584415584415585,
+      "grad_norm": 0.2448154091835022,
+      "learning_rate": 0.0002,
+      "loss": 1.6483,
+      "step": 480
+    },
+    {
+      "epoch": 1.5909090909090908,
+      "grad_norm": 0.2592053711414337,
+      "learning_rate": 0.0002,
+      "loss": 1.7212,
+      "step": 490
+    },
+    {
+      "epoch": 1.6233766233766234,
+      "grad_norm": 0.23606474697589874,
+      "learning_rate": 0.0002,
+      "loss": 1.7245,
+      "step": 500
+    },
+    {
+      "epoch": 1.655844155844156,
+      "grad_norm": 0.2693960964679718,
+      "learning_rate": 0.0002,
+      "loss": 1.7283,
+      "step": 510
+    },
+    {
+      "epoch": 1.6883116883116882,
+      "grad_norm": 0.28801923990249634,
+      "learning_rate": 0.0002,
+      "loss": 1.6573,
+      "step": 520
+    },
+    {
+      "epoch": 1.7207792207792207,
+      "grad_norm": 0.33677127957344055,
+      "learning_rate": 0.0002,
+      "loss": 1.654,
+      "step": 530
+    },
+    {
+      "epoch": 1.7532467532467533,
+      "grad_norm": 0.2794886529445648,
+      "learning_rate": 0.0002,
+      "loss": 1.7184,
+      "step": 540
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 0.2649626135826111,
+      "learning_rate": 0.0002,
+      "loss": 1.6204,
+      "step": 550
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.27729251980781555,
+      "learning_rate": 0.0002,
+      "loss": 1.7664,
+      "step": 560
+    },
+    {
+      "epoch": 1.8506493506493507,
+      "grad_norm": 0.2724396288394928,
+      "learning_rate": 0.0002,
+      "loss": 1.6099,
+      "step": 570
+    },
+    {
+      "epoch": 1.883116883116883,
+      "grad_norm": 0.25738948583602905,
+      "learning_rate": 0.0002,
+      "loss": 1.656,
+      "step": 580
+    },
+    {
+      "epoch": 1.9155844155844157,
+      "grad_norm": 0.2539234757423401,
+      "learning_rate": 0.0002,
+      "loss": 1.7401,
+      "step": 590
+    },
+    {
+      "epoch": 1.948051948051948,
+      "grad_norm": 0.27087679505348206,
+      "learning_rate": 0.0002,
+      "loss": 1.6833,
+      "step": 600
+    },
+    {
+      "epoch": 1.9805194805194806,
+      "grad_norm": 0.2727901041507721,
+      "learning_rate": 0.0002,
+      "loss": 1.6934,
+      "step": 610
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.765038251876831,
+      "eval_runtime": 117.4062,
+      "eval_samples_per_second": 4.531,
+      "eval_steps_per_second": 0.571,
+      "step": 616
+    },
+    {
+      "epoch": 2.012987012987013,
+      "grad_norm": 0.25380605459213257,
+      "learning_rate": 0.0002,
+      "loss": 1.6565,
+      "step": 620
+    },
+    {
+      "epoch": 2.0454545454545454,
+      "grad_norm": 0.28460997343063354,
+      "learning_rate": 0.0002,
+      "loss": 1.6043,
+      "step": 630
+    },
+    {
+      "epoch": 2.0779220779220777,
+      "grad_norm": 0.31530654430389404,
+      "learning_rate": 0.0002,
+      "loss": 1.7345,
+      "step": 640
+    },
+    {
+      "epoch": 2.1103896103896105,
+      "grad_norm": 0.30611202120780945,
+      "learning_rate": 0.0002,
+      "loss": 1.6077,
+      "step": 650
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.30674979090690613,
+      "learning_rate": 0.0002,
+      "loss": 1.6685,
+      "step": 660
+    },
+    {
+      "epoch": 2.175324675324675,
+      "grad_norm": 0.34276270866394043,
+      "learning_rate": 0.0002,
+      "loss": 1.6063,
+      "step": 670
+    },
+    {
+      "epoch": 2.207792207792208,
+      "grad_norm": 0.30068185925483704,
+      "learning_rate": 0.0002,
+      "loss": 1.6985,
+      "step": 680
+    },
+    {
+      "epoch": 2.24025974025974,
+      "grad_norm": 0.3197493851184845,
+      "learning_rate": 0.0002,
+      "loss": 1.5869,
+      "step": 690
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.3080422878265381,
+      "learning_rate": 0.0002,
+      "loss": 1.5993,
+      "step": 700
+    },
+    {
+      "epoch": 2.3051948051948052,
+      "grad_norm": 0.32039162516593933,
+      "learning_rate": 0.0002,
+      "loss": 1.634,
+      "step": 710
+    },
+    {
+      "epoch": 2.3376623376623376,
+      "grad_norm": 0.32778531312942505,
+      "learning_rate": 0.0002,
+      "loss": 1.6303,
+      "step": 720
+    },
+    {
+      "epoch": 2.3701298701298703,
+      "grad_norm": 0.31763869524002075,
+      "learning_rate": 0.0002,
+      "loss": 1.6783,
+      "step": 730
+    },
+    {
+      "epoch": 2.4025974025974026,
+      "grad_norm": 0.3438641130924225,
+      "learning_rate": 0.0002,
+      "loss": 1.5866,
+      "step": 740
+    },
+    {
+      "epoch": 2.435064935064935,
+      "grad_norm": 0.30254635214805603,
+      "learning_rate": 0.0002,
+      "loss": 1.6238,
+      "step": 750
+    },
+    {
+      "epoch": 2.4675324675324677,
+      "grad_norm": 0.3287079930305481,
+      "learning_rate": 0.0002,
+      "loss": 1.6321,
+      "step": 760
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.31394457817077637,
+      "learning_rate": 0.0002,
+      "loss": 1.6103,
+      "step": 770
+    },
+    {
+      "epoch": 2.5324675324675323,
+      "grad_norm": 0.34165051579475403,
+      "learning_rate": 0.0002,
+      "loss": 1.6384,
+      "step": 780
+    },
+    {
+      "epoch": 2.564935064935065,
+      "grad_norm": 0.3315567970275879,
+      "learning_rate": 0.0002,
+      "loss": 1.6555,
+      "step": 790
+    },
+    {
+      "epoch": 2.5974025974025974,
+      "grad_norm": 0.3183658719062805,
+      "learning_rate": 0.0002,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 2.62987012987013,
+      "grad_norm": 0.29442286491394043,
+      "learning_rate": 0.0002,
+      "loss": 1.6149,
+      "step": 810
+    },
+    {
+      "epoch": 2.6623376623376624,
+      "grad_norm": 0.3735957741737366,
+      "learning_rate": 0.0002,
+      "loss": 1.5689,
+      "step": 820
+    },
+    {
+      "epoch": 2.6948051948051948,
+      "grad_norm": 0.34174075722694397,
+      "learning_rate": 0.0002,
+      "loss": 1.6763,
+      "step": 830
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.3265220820903778,
+      "learning_rate": 0.0002,
+      "loss": 1.6333,
+      "step": 840
+    },
+    {
+      "epoch": 2.75974025974026,
+      "grad_norm": 0.3356368839740753,
+      "learning_rate": 0.0002,
+      "loss": 1.5971,
+      "step": 850
+    },
+    {
+      "epoch": 2.792207792207792,
+      "grad_norm": 0.33430132269859314,
+      "learning_rate": 0.0002,
+      "loss": 1.6042,
+      "step": 860
+    },
+    {
+      "epoch": 2.824675324675325,
+      "grad_norm": 0.28999271988868713,
+      "learning_rate": 0.0002,
+      "loss": 1.5982,
+      "step": 870
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.3253968358039856,
+      "learning_rate": 0.0002,
+      "loss": 1.6189,
+      "step": 880
+    },
+    {
+      "epoch": 2.8896103896103895,
+      "grad_norm": 0.291964054107666,
+      "learning_rate": 0.0002,
+      "loss": 1.6011,
+      "step": 890
+    },
+    {
+      "epoch": 2.9220779220779223,
+      "grad_norm": 0.32170912623405457,
+      "learning_rate": 0.0002,
+      "loss": 1.6854,
+      "step": 900
+    },
+    {
+      "epoch": 2.9545454545454546,
+      "grad_norm": 0.2738993465900421,
+      "learning_rate": 0.0002,
+      "loss": 1.7219,
+      "step": 910
+    },
+    {
+      "epoch": 2.987012987012987,
+      "grad_norm": 0.29856377840042114,
+      "learning_rate": 0.0002,
+      "loss": 1.667,
+      "step": 920
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.7705217599868774,
+      "eval_runtime": 115.3403,
+      "eval_samples_per_second": 4.612,
+      "eval_steps_per_second": 0.581,
+      "step": 924
+    },
+    {
+      "epoch": 3.0194805194805197,
+      "grad_norm": 0.3272620439529419,
+      "learning_rate": 0.0002,
+      "loss": 1.5876,
+      "step": 930
+    },
+    {
+      "epoch": 3.051948051948052,
+      "grad_norm": 0.3484354019165039,
+      "learning_rate": 0.0002,
+      "loss": 1.6262,
+      "step": 940
+    },
+    {
+      "epoch": 3.0844155844155843,
+      "grad_norm": 0.35202738642692566,
+      "learning_rate": 0.0002,
+      "loss": 1.5092,
+      "step": 950
+    },
+    {
+      "epoch": 3.116883116883117,
+      "grad_norm": 0.3635590076446533,
+      "learning_rate": 0.0002,
+      "loss": 1.5524,
+      "step": 960
+    },
+    {
+      "epoch": 3.1493506493506493,
+      "grad_norm": 0.39253556728363037,
+      "learning_rate": 0.0002,
+      "loss": 1.5169,
+      "step": 970
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "grad_norm": 0.4007384777069092,
+      "learning_rate": 0.0002,
+      "loss": 1.5001,
+      "step": 980
+    },
+    {
+      "epoch": 3.2142857142857144,
+      "grad_norm": 0.38897788524627686,
+      "learning_rate": 0.0002,
+      "loss": 1.5639,
+      "step": 990
+    },
+    {
+      "epoch": 3.2467532467532467,
+      "grad_norm": 0.38462474942207336,
+      "learning_rate": 0.0002,
+      "loss": 1.5791,
+      "step": 1000
+    },
+    {
+      "epoch": 3.279220779220779,
+      "grad_norm": 0.38225963711738586,
+      "learning_rate": 0.0002,
+      "loss": 1.4918,
+      "step": 1010
+    },
+    {
+      "epoch": 3.311688311688312,
+      "grad_norm": 0.4058142602443695,
+      "learning_rate": 0.0002,
+      "loss": 1.5094,
+      "step": 1020
+    },
+    {
+      "epoch": 3.344155844155844,
+      "grad_norm": 0.39580652117729187,
+      "learning_rate": 0.0002,
+      "loss": 1.5905,
+      "step": 1030
+    },
+    {
+      "epoch": 3.3766233766233764,
+      "grad_norm": 0.42998549342155457,
+      "learning_rate": 0.0002,
+      "loss": 1.5894,
+      "step": 1040
+    },
+    {
+      "epoch": 3.409090909090909,
+      "grad_norm": 0.3940870761871338,
+      "learning_rate": 0.0002,
+      "loss": 1.548,
+      "step": 1050
+    },
+    {
+      "epoch": 3.4415584415584415,
+      "grad_norm": 0.4069645404815674,
+      "learning_rate": 0.0002,
+      "loss": 1.6527,
+      "step": 1060
+    },
+    {
+      "epoch": 3.474025974025974,
+      "grad_norm": 0.386883407831192,
+      "learning_rate": 0.0002,
+      "loss": 1.6035,
+      "step": 1070
+    },
+    {
+      "epoch": 3.5064935064935066,
+      "grad_norm": 0.4978795051574707,
+      "learning_rate": 0.0002,
+      "loss": 1.5991,
+      "step": 1080
+    },
+    {
+      "epoch": 3.538961038961039,
+      "grad_norm": 0.4167064130306244,
+      "learning_rate": 0.0002,
+      "loss": 1.555,
+      "step": 1090
+    },
+    {
+      "epoch": 3.571428571428571,
+      "grad_norm": 0.38199925422668457,
+      "learning_rate": 0.0002,
+      "loss": 1.5393,
+      "step": 1100
+    },
+    {
+      "epoch": 3.603896103896104,
+      "grad_norm": 0.4170112609863281,
+      "learning_rate": 0.0002,
+      "loss": 1.5206,
+      "step": 1110
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 0.4023001194000244,
+      "learning_rate": 0.0002,
+      "loss": 1.5336,
+      "step": 1120
+    },
+    {
+      "epoch": 3.6688311688311686,
+      "grad_norm": 0.44960418343544006,
+      "learning_rate": 0.0002,
+      "loss": 1.5324,
+      "step": 1130
+    },
+    {
+      "epoch": 3.7012987012987013,
+      "grad_norm": 0.4334756135940552,
+      "learning_rate": 0.0002,
+      "loss": 1.5784,
+      "step": 1140
+    },
+    {
+      "epoch": 3.7337662337662336,
+      "grad_norm": 0.38534295558929443,
+      "learning_rate": 0.0002,
+      "loss": 1.5018,
+      "step": 1150
+    },
+    {
+      "epoch": 3.7662337662337664,
+      "grad_norm": 0.40537452697753906,
+      "learning_rate": 0.0002,
+      "loss": 1.6091,
+      "step": 1160
+    },
+    {
+      "epoch": 3.7987012987012987,
+      "grad_norm": 0.4050034284591675,
+      "learning_rate": 0.0002,
+      "loss": 1.5303,
+      "step": 1170
+    },
+    {
+      "epoch": 3.8311688311688314,
+      "grad_norm": 0.3953498303890228,
+      "learning_rate": 0.0002,
+      "loss": 1.5082,
+      "step": 1180
+    },
+    {
+      "epoch": 3.8636363636363638,
+      "grad_norm": 0.4208937883377075,
+      "learning_rate": 0.0002,
+      "loss": 1.5402,
+      "step": 1190
+    },
+    {
+      "epoch": 3.896103896103896,
+      "grad_norm": 0.4181132912635803,
+      "learning_rate": 0.0002,
+      "loss": 1.5657,
+      "step": 1200
+    },
+    {
+      "epoch": 3.928571428571429,
+      "grad_norm": 0.4108502268791199,
+      "learning_rate": 0.0002,
+      "loss": 1.6202,
+      "step": 1210
+    },
+    {
+      "epoch": 3.961038961038961,
+      "grad_norm": 0.3819066882133484,
+      "learning_rate": 0.0002,
+      "loss": 1.5157,
+      "step": 1220
+    },
+    {
+      "epoch": 3.9935064935064934,
+      "grad_norm": 0.3682127892971039,
+      "learning_rate": 0.0002,
+      "loss": 1.4595,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.7993888854980469,
+      "eval_runtime": 115.4041,
+      "eval_samples_per_second": 4.61,
+      "eval_steps_per_second": 0.581,
+      "step": 1232
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2464,
+  "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": 5.367319021957939e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1232/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:400ef20a202cfadecd17fb2d658472b52fb2ddded63f69b1e6150e63cfc2de96
+size 5560

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1540/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1540/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1540/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c20caa5cba21d78192c88ac405b7fa17c83b8c8b74478b34be2c10ae8e3b93
+size 80755416

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1540/added_tokens.json

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

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1540/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e008fcbf38c46b144c32a85e36ed6e77b6e9977fc344ed9a6fd749701dcb2cc
+size 41136570

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1540/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7ae3bcad17c4053a3962711420dfba382500eac28a2b91c8ec3a7b526e06803
+size 14244

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1540/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b08ad7b1bf73e40d77d05150187e25e652c4e26a62272f7d02f7aff7ac9d96
+size 1064

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1540/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1540/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1540/trainer_state.json

@@ -0,0 +1,1151 @@
+{
+  "best_metric": 1.765038251876831,
+  "best_model_checkpoint": "outputs-001/Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-616",
+  "epoch": 5.0,
+  "eval_steps": 10,
+  "global_step": 1540,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032467532467532464,
+      "grad_norm": 0.31557697057724,
+      "learning_rate": 0.0002,
+      "loss": 2.4028,
+      "step": 10
+    },
+    {
+      "epoch": 0.06493506493506493,
+      "grad_norm": 0.3265437185764313,
+      "learning_rate": 0.0002,
+      "loss": 2.1466,
+      "step": 20
+    },
+    {
+      "epoch": 0.09740259740259741,
+      "grad_norm": 0.3424590229988098,
+      "learning_rate": 0.0002,
+      "loss": 1.9549,
+      "step": 30
+    },
+    {
+      "epoch": 0.12987012987012986,
+      "grad_norm": 0.30609560012817383,
+      "learning_rate": 0.0002,
+      "loss": 1.8464,
+      "step": 40
+    },
+    {
+      "epoch": 0.16233766233766234,
+      "grad_norm": 0.3285873532295227,
+      "learning_rate": 0.0002,
+      "loss": 1.9203,
+      "step": 50
+    },
+    {
+      "epoch": 0.19480519480519481,
+      "grad_norm": 0.2855139374732971,
+      "learning_rate": 0.0002,
+      "loss": 1.7946,
+      "step": 60
+    },
+    {
+      "epoch": 0.22727272727272727,
+      "grad_norm": 0.283848375082016,
+      "learning_rate": 0.0002,
+      "loss": 1.7618,
+      "step": 70
+    },
+    {
+      "epoch": 0.2597402597402597,
+      "grad_norm": 0.2915274202823639,
+      "learning_rate": 0.0002,
+      "loss": 1.7875,
+      "step": 80
+    },
+    {
+      "epoch": 0.2922077922077922,
+      "grad_norm": 0.26927152276039124,
+      "learning_rate": 0.0002,
+      "loss": 1.7673,
+      "step": 90
+    },
+    {
+      "epoch": 0.3246753246753247,
+      "grad_norm": 0.29594847559928894,
+      "learning_rate": 0.0002,
+      "loss": 1.6726,
+      "step": 100
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.36750105023384094,
+      "learning_rate": 0.0002,
+      "loss": 1.7333,
+      "step": 110
+    },
+    {
+      "epoch": 0.38961038961038963,
+      "grad_norm": 0.32430270314216614,
+      "learning_rate": 0.0002,
+      "loss": 1.7772,
+      "step": 120
+    },
+    {
+      "epoch": 0.42207792207792205,
+      "grad_norm": 0.2767448127269745,
+      "learning_rate": 0.0002,
+      "loss": 1.731,
+      "step": 130
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.244296595454216,
+      "learning_rate": 0.0002,
+      "loss": 1.7604,
+      "step": 140
+    },
+    {
+      "epoch": 0.487012987012987,
+      "grad_norm": 0.25791823863983154,
+      "learning_rate": 0.0002,
+      "loss": 1.7172,
+      "step": 150
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "grad_norm": 0.25496479868888855,
+      "learning_rate": 0.0002,
+      "loss": 1.7509,
+      "step": 160
+    },
+    {
+      "epoch": 0.551948051948052,
+      "grad_norm": 0.2770450711250305,
+      "learning_rate": 0.0002,
+      "loss": 1.7328,
+      "step": 170
+    },
+    {
+      "epoch": 0.5844155844155844,
+      "grad_norm": 0.2971339821815491,
+      "learning_rate": 0.0002,
+      "loss": 1.8008,
+      "step": 180
+    },
+    {
+      "epoch": 0.6168831168831169,
+      "grad_norm": 0.3165527880191803,
+      "learning_rate": 0.0002,
+      "loss": 1.6805,
+      "step": 190
+    },
+    {
+      "epoch": 0.6493506493506493,
+      "grad_norm": 0.24732241034507751,
+      "learning_rate": 0.0002,
+      "loss": 1.732,
+      "step": 200
+    },
+    {
+      "epoch": 0.6818181818181818,
+      "grad_norm": 0.28333306312561035,
+      "learning_rate": 0.0002,
+      "loss": 1.6933,
+      "step": 210
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.24870498478412628,
+      "learning_rate": 0.0002,
+      "loss": 1.7324,
+      "step": 220
+    },
+    {
+      "epoch": 0.7467532467532467,
+      "grad_norm": 0.2484978884458542,
+      "learning_rate": 0.0002,
+      "loss": 1.7697,
+      "step": 230
+    },
+    {
+      "epoch": 0.7792207792207793,
+      "grad_norm": 0.2282458394765854,
+      "learning_rate": 0.0002,
+      "loss": 1.7624,
+      "step": 240
+    },
+    {
+      "epoch": 0.8116883116883117,
+      "grad_norm": 0.2552148699760437,
+      "learning_rate": 0.0002,
+      "loss": 1.7775,
+      "step": 250
+    },
+    {
+      "epoch": 0.8441558441558441,
+      "grad_norm": 0.25136545300483704,
+      "learning_rate": 0.0002,
+      "loss": 1.7153,
+      "step": 260
+    },
+    {
+      "epoch": 0.8766233766233766,
+      "grad_norm": 0.25096797943115234,
+      "learning_rate": 0.0002,
+      "loss": 1.7705,
+      "step": 270
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.3148603141307831,
+      "learning_rate": 0.0002,
+      "loss": 1.7842,
+      "step": 280
+    },
+    {
+      "epoch": 0.9415584415584416,
+      "grad_norm": 0.2533794343471527,
+      "learning_rate": 0.0002,
+      "loss": 1.6847,
+      "step": 290
+    },
+    {
+      "epoch": 0.974025974025974,
+      "grad_norm": 0.27348795533180237,
+      "learning_rate": 0.0002,
+      "loss": 1.7334,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.769331693649292,
+      "eval_runtime": 115.5699,
+      "eval_samples_per_second": 4.603,
+      "eval_steps_per_second": 0.58,
+      "step": 308
+    },
+    {
+      "epoch": 1.0064935064935066,
+      "grad_norm": 0.28133320808410645,
+      "learning_rate": 0.0002,
+      "loss": 1.6473,
+      "step": 310
+    },
+    {
+      "epoch": 1.0389610389610389,
+      "grad_norm": 0.2541237473487854,
+      "learning_rate": 0.0002,
+      "loss": 1.7067,
+      "step": 320
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.25699320435523987,
+      "learning_rate": 0.0002,
+      "loss": 1.7422,
+      "step": 330
+    },
+    {
+      "epoch": 1.103896103896104,
+      "grad_norm": 0.26137059926986694,
+      "learning_rate": 0.0002,
+      "loss": 1.6737,
+      "step": 340
+    },
+    {
+      "epoch": 1.1363636363636362,
+      "grad_norm": 0.2718560993671417,
+      "learning_rate": 0.0002,
+      "loss": 1.7372,
+      "step": 350
+    },
+    {
+      "epoch": 1.1688311688311688,
+      "grad_norm": 0.23400403559207916,
+      "learning_rate": 0.0002,
+      "loss": 1.6809,
+      "step": 360
+    },
+    {
+      "epoch": 1.2012987012987013,
+      "grad_norm": 0.28257420659065247,
+      "learning_rate": 0.0002,
+      "loss": 1.6892,
+      "step": 370
+    },
+    {
+      "epoch": 1.2337662337662338,
+      "grad_norm": 0.3031129240989685,
+      "learning_rate": 0.0002,
+      "loss": 1.6945,
+      "step": 380
+    },
+    {
+      "epoch": 1.2662337662337662,
+      "grad_norm": 0.3131062984466553,
+      "learning_rate": 0.0002,
+      "loss": 1.6611,
+      "step": 390
+    },
+    {
+      "epoch": 1.2987012987012987,
+      "grad_norm": 0.2594483494758606,
+      "learning_rate": 0.0002,
+      "loss": 1.6535,
+      "step": 400
+    },
+    {
+      "epoch": 1.3311688311688312,
+      "grad_norm": 0.2595517933368683,
+      "learning_rate": 0.0002,
+      "loss": 1.7275,
+      "step": 410
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.26333683729171753,
+      "learning_rate": 0.0002,
+      "loss": 1.6048,
+      "step": 420
+    },
+    {
+      "epoch": 1.396103896103896,
+      "grad_norm": 0.3051556646823883,
+      "learning_rate": 0.0002,
+      "loss": 1.8342,
+      "step": 430
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.26060932874679565,
+      "learning_rate": 0.0002,
+      "loss": 1.694,
+      "step": 440
+    },
+    {
+      "epoch": 1.4610389610389611,
+      "grad_norm": 0.282101571559906,
+      "learning_rate": 0.0002,
+      "loss": 1.6284,
+      "step": 450
+    },
+    {
+      "epoch": 1.4935064935064934,
+      "grad_norm": 0.2837599813938141,
+      "learning_rate": 0.0002,
+      "loss": 1.7301,
+      "step": 460
+    },
+    {
+      "epoch": 1.525974025974026,
+      "grad_norm": 0.2532821595668793,
+      "learning_rate": 0.0002,
+      "loss": 1.6769,
+      "step": 470
+    },
+    {
+      "epoch": 1.5584415584415585,
+      "grad_norm": 0.2448154091835022,
+      "learning_rate": 0.0002,
+      "loss": 1.6483,
+      "step": 480
+    },
+    {
+      "epoch": 1.5909090909090908,
+      "grad_norm": 0.2592053711414337,
+      "learning_rate": 0.0002,
+      "loss": 1.7212,
+      "step": 490
+    },
+    {
+      "epoch": 1.6233766233766234,
+      "grad_norm": 0.23606474697589874,
+      "learning_rate": 0.0002,
+      "loss": 1.7245,
+      "step": 500
+    },
+    {
+      "epoch": 1.655844155844156,
+      "grad_norm": 0.2693960964679718,
+      "learning_rate": 0.0002,
+      "loss": 1.7283,
+      "step": 510
+    },
+    {
+      "epoch": 1.6883116883116882,
+      "grad_norm": 0.28801923990249634,
+      "learning_rate": 0.0002,
+      "loss": 1.6573,
+      "step": 520
+    },
+    {
+      "epoch": 1.7207792207792207,
+      "grad_norm": 0.33677127957344055,
+      "learning_rate": 0.0002,
+      "loss": 1.654,
+      "step": 530
+    },
+    {
+      "epoch": 1.7532467532467533,
+      "grad_norm": 0.2794886529445648,
+      "learning_rate": 0.0002,
+      "loss": 1.7184,
+      "step": 540
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 0.2649626135826111,
+      "learning_rate": 0.0002,
+      "loss": 1.6204,
+      "step": 550
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.27729251980781555,
+      "learning_rate": 0.0002,
+      "loss": 1.7664,
+      "step": 560
+    },
+    {
+      "epoch": 1.8506493506493507,
+      "grad_norm": 0.2724396288394928,
+      "learning_rate": 0.0002,
+      "loss": 1.6099,
+      "step": 570
+    },
+    {
+      "epoch": 1.883116883116883,
+      "grad_norm": 0.25738948583602905,
+      "learning_rate": 0.0002,
+      "loss": 1.656,
+      "step": 580
+    },
+    {
+      "epoch": 1.9155844155844157,
+      "grad_norm": 0.2539234757423401,
+      "learning_rate": 0.0002,
+      "loss": 1.7401,
+      "step": 590
+    },
+    {
+      "epoch": 1.948051948051948,
+      "grad_norm": 0.27087679505348206,
+      "learning_rate": 0.0002,
+      "loss": 1.6833,
+      "step": 600
+    },
+    {
+      "epoch": 1.9805194805194806,
+      "grad_norm": 0.2727901041507721,
+      "learning_rate": 0.0002,
+      "loss": 1.6934,
+      "step": 610
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.765038251876831,
+      "eval_runtime": 117.4062,
+      "eval_samples_per_second": 4.531,
+      "eval_steps_per_second": 0.571,
+      "step": 616
+    },
+    {
+      "epoch": 2.012987012987013,
+      "grad_norm": 0.25380605459213257,
+      "learning_rate": 0.0002,
+      "loss": 1.6565,
+      "step": 620
+    },
+    {
+      "epoch": 2.0454545454545454,
+      "grad_norm": 0.28460997343063354,
+      "learning_rate": 0.0002,
+      "loss": 1.6043,
+      "step": 630
+    },
+    {
+      "epoch": 2.0779220779220777,
+      "grad_norm": 0.31530654430389404,
+      "learning_rate": 0.0002,
+      "loss": 1.7345,
+      "step": 640
+    },
+    {
+      "epoch": 2.1103896103896105,
+      "grad_norm": 0.30611202120780945,
+      "learning_rate": 0.0002,
+      "loss": 1.6077,
+      "step": 650
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.30674979090690613,
+      "learning_rate": 0.0002,
+      "loss": 1.6685,
+      "step": 660
+    },
+    {
+      "epoch": 2.175324675324675,
+      "grad_norm": 0.34276270866394043,
+      "learning_rate": 0.0002,
+      "loss": 1.6063,
+      "step": 670
+    },
+    {
+      "epoch": 2.207792207792208,
+      "grad_norm": 0.30068185925483704,
+      "learning_rate": 0.0002,
+      "loss": 1.6985,
+      "step": 680
+    },
+    {
+      "epoch": 2.24025974025974,
+      "grad_norm": 0.3197493851184845,
+      "learning_rate": 0.0002,
+      "loss": 1.5869,
+      "step": 690
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.3080422878265381,
+      "learning_rate": 0.0002,
+      "loss": 1.5993,
+      "step": 700
+    },
+    {
+      "epoch": 2.3051948051948052,
+      "grad_norm": 0.32039162516593933,
+      "learning_rate": 0.0002,
+      "loss": 1.634,
+      "step": 710
+    },
+    {
+      "epoch": 2.3376623376623376,
+      "grad_norm": 0.32778531312942505,
+      "learning_rate": 0.0002,
+      "loss": 1.6303,
+      "step": 720
+    },
+    {
+      "epoch": 2.3701298701298703,
+      "grad_norm": 0.31763869524002075,
+      "learning_rate": 0.0002,
+      "loss": 1.6783,
+      "step": 730
+    },
+    {
+      "epoch": 2.4025974025974026,
+      "grad_norm": 0.3438641130924225,
+      "learning_rate": 0.0002,
+      "loss": 1.5866,
+      "step": 740
+    },
+    {
+      "epoch": 2.435064935064935,
+      "grad_norm": 0.30254635214805603,
+      "learning_rate": 0.0002,
+      "loss": 1.6238,
+      "step": 750
+    },
+    {
+      "epoch": 2.4675324675324677,
+      "grad_norm": 0.3287079930305481,
+      "learning_rate": 0.0002,
+      "loss": 1.6321,
+      "step": 760
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.31394457817077637,
+      "learning_rate": 0.0002,
+      "loss": 1.6103,
+      "step": 770
+    },
+    {
+      "epoch": 2.5324675324675323,
+      "grad_norm": 0.34165051579475403,
+      "learning_rate": 0.0002,
+      "loss": 1.6384,
+      "step": 780
+    },
+    {
+      "epoch": 2.564935064935065,
+      "grad_norm": 0.3315567970275879,
+      "learning_rate": 0.0002,
+      "loss": 1.6555,
+      "step": 790
+    },
+    {
+      "epoch": 2.5974025974025974,
+      "grad_norm": 0.3183658719062805,
+      "learning_rate": 0.0002,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 2.62987012987013,
+      "grad_norm": 0.29442286491394043,
+      "learning_rate": 0.0002,
+      "loss": 1.6149,
+      "step": 810
+    },
+    {
+      "epoch": 2.6623376623376624,
+      "grad_norm": 0.3735957741737366,
+      "learning_rate": 0.0002,
+      "loss": 1.5689,
+      "step": 820
+    },
+    {
+      "epoch": 2.6948051948051948,
+      "grad_norm": 0.34174075722694397,
+      "learning_rate": 0.0002,
+      "loss": 1.6763,
+      "step": 830
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.3265220820903778,
+      "learning_rate": 0.0002,
+      "loss": 1.6333,
+      "step": 840
+    },
+    {
+      "epoch": 2.75974025974026,
+      "grad_norm": 0.3356368839740753,
+      "learning_rate": 0.0002,
+      "loss": 1.5971,
+      "step": 850
+    },
+    {
+      "epoch": 2.792207792207792,
+      "grad_norm": 0.33430132269859314,
+      "learning_rate": 0.0002,
+      "loss": 1.6042,
+      "step": 860
+    },
+    {
+      "epoch": 2.824675324675325,
+      "grad_norm": 0.28999271988868713,
+      "learning_rate": 0.0002,
+      "loss": 1.5982,
+      "step": 870
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.3253968358039856,
+      "learning_rate": 0.0002,
+      "loss": 1.6189,
+      "step": 880
+    },
+    {
+      "epoch": 2.8896103896103895,
+      "grad_norm": 0.291964054107666,
+      "learning_rate": 0.0002,
+      "loss": 1.6011,
+      "step": 890
+    },
+    {
+      "epoch": 2.9220779220779223,
+      "grad_norm": 0.32170912623405457,
+      "learning_rate": 0.0002,
+      "loss": 1.6854,
+      "step": 900
+    },
+    {
+      "epoch": 2.9545454545454546,
+      "grad_norm": 0.2738993465900421,
+      "learning_rate": 0.0002,
+      "loss": 1.7219,
+      "step": 910
+    },
+    {
+      "epoch": 2.987012987012987,
+      "grad_norm": 0.29856377840042114,
+      "learning_rate": 0.0002,
+      "loss": 1.667,
+      "step": 920
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.7705217599868774,
+      "eval_runtime": 115.3403,
+      "eval_samples_per_second": 4.612,
+      "eval_steps_per_second": 0.581,
+      "step": 924
+    },
+    {
+      "epoch": 3.0194805194805197,
+      "grad_norm": 0.3272620439529419,
+      "learning_rate": 0.0002,
+      "loss": 1.5876,
+      "step": 930
+    },
+    {
+      "epoch": 3.051948051948052,
+      "grad_norm": 0.3484354019165039,
+      "learning_rate": 0.0002,
+      "loss": 1.6262,
+      "step": 940
+    },
+    {
+      "epoch": 3.0844155844155843,
+      "grad_norm": 0.35202738642692566,
+      "learning_rate": 0.0002,
+      "loss": 1.5092,
+      "step": 950
+    },
+    {
+      "epoch": 3.116883116883117,
+      "grad_norm": 0.3635590076446533,
+      "learning_rate": 0.0002,
+      "loss": 1.5524,
+      "step": 960
+    },
+    {
+      "epoch": 3.1493506493506493,
+      "grad_norm": 0.39253556728363037,
+      "learning_rate": 0.0002,
+      "loss": 1.5169,
+      "step": 970
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "grad_norm": 0.4007384777069092,
+      "learning_rate": 0.0002,
+      "loss": 1.5001,
+      "step": 980
+    },
+    {
+      "epoch": 3.2142857142857144,
+      "grad_norm": 0.38897788524627686,
+      "learning_rate": 0.0002,
+      "loss": 1.5639,
+      "step": 990
+    },
+    {
+      "epoch": 3.2467532467532467,
+      "grad_norm": 0.38462474942207336,
+      "learning_rate": 0.0002,
+      "loss": 1.5791,
+      "step": 1000
+    },
+    {
+      "epoch": 3.279220779220779,
+      "grad_norm": 0.38225963711738586,
+      "learning_rate": 0.0002,
+      "loss": 1.4918,
+      "step": 1010
+    },
+    {
+      "epoch": 3.311688311688312,
+      "grad_norm": 0.4058142602443695,
+      "learning_rate": 0.0002,
+      "loss": 1.5094,
+      "step": 1020
+    },
+    {
+      "epoch": 3.344155844155844,
+      "grad_norm": 0.39580652117729187,
+      "learning_rate": 0.0002,
+      "loss": 1.5905,
+      "step": 1030
+    },
+    {
+      "epoch": 3.3766233766233764,
+      "grad_norm": 0.42998549342155457,
+      "learning_rate": 0.0002,
+      "loss": 1.5894,
+      "step": 1040
+    },
+    {
+      "epoch": 3.409090909090909,
+      "grad_norm": 0.3940870761871338,
+      "learning_rate": 0.0002,
+      "loss": 1.548,
+      "step": 1050
+    },
+    {
+      "epoch": 3.4415584415584415,
+      "grad_norm": 0.4069645404815674,
+      "learning_rate": 0.0002,
+      "loss": 1.6527,
+      "step": 1060
+    },
+    {
+      "epoch": 3.474025974025974,
+      "grad_norm": 0.386883407831192,
+      "learning_rate": 0.0002,
+      "loss": 1.6035,
+      "step": 1070
+    },
+    {
+      "epoch": 3.5064935064935066,
+      "grad_norm": 0.4978795051574707,
+      "learning_rate": 0.0002,
+      "loss": 1.5991,
+      "step": 1080
+    },
+    {
+      "epoch": 3.538961038961039,
+      "grad_norm": 0.4167064130306244,
+      "learning_rate": 0.0002,
+      "loss": 1.555,
+      "step": 1090
+    },
+    {
+      "epoch": 3.571428571428571,
+      "grad_norm": 0.38199925422668457,
+      "learning_rate": 0.0002,
+      "loss": 1.5393,
+      "step": 1100
+    },
+    {
+      "epoch": 3.603896103896104,
+      "grad_norm": 0.4170112609863281,
+      "learning_rate": 0.0002,
+      "loss": 1.5206,
+      "step": 1110
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 0.4023001194000244,
+      "learning_rate": 0.0002,
+      "loss": 1.5336,
+      "step": 1120
+    },
+    {
+      "epoch": 3.6688311688311686,
+      "grad_norm": 0.44960418343544006,
+      "learning_rate": 0.0002,
+      "loss": 1.5324,
+      "step": 1130
+    },
+    {
+      "epoch": 3.7012987012987013,
+      "grad_norm": 0.4334756135940552,
+      "learning_rate": 0.0002,
+      "loss": 1.5784,
+      "step": 1140
+    },
+    {
+      "epoch": 3.7337662337662336,
+      "grad_norm": 0.38534295558929443,
+      "learning_rate": 0.0002,
+      "loss": 1.5018,
+      "step": 1150
+    },
+    {
+      "epoch": 3.7662337662337664,
+      "grad_norm": 0.40537452697753906,
+      "learning_rate": 0.0002,
+      "loss": 1.6091,
+      "step": 1160
+    },
+    {
+      "epoch": 3.7987012987012987,
+      "grad_norm": 0.4050034284591675,
+      "learning_rate": 0.0002,
+      "loss": 1.5303,
+      "step": 1170
+    },
+    {
+      "epoch": 3.8311688311688314,
+      "grad_norm": 0.3953498303890228,
+      "learning_rate": 0.0002,
+      "loss": 1.5082,
+      "step": 1180
+    },
+    {
+      "epoch": 3.8636363636363638,
+      "grad_norm": 0.4208937883377075,
+      "learning_rate": 0.0002,
+      "loss": 1.5402,
+      "step": 1190
+    },
+    {
+      "epoch": 3.896103896103896,
+      "grad_norm": 0.4181132912635803,
+      "learning_rate": 0.0002,
+      "loss": 1.5657,
+      "step": 1200
+    },
+    {
+      "epoch": 3.928571428571429,
+      "grad_norm": 0.4108502268791199,
+      "learning_rate": 0.0002,
+      "loss": 1.6202,
+      "step": 1210
+    },
+    {
+      "epoch": 3.961038961038961,
+      "grad_norm": 0.3819066882133484,
+      "learning_rate": 0.0002,
+      "loss": 1.5157,
+      "step": 1220
+    },
+    {
+      "epoch": 3.9935064935064934,
+      "grad_norm": 0.3682127892971039,
+      "learning_rate": 0.0002,
+      "loss": 1.4595,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.7993888854980469,
+      "eval_runtime": 115.4041,
+      "eval_samples_per_second": 4.61,
+      "eval_steps_per_second": 0.581,
+      "step": 1232
+    },
+    {
+      "epoch": 4.025974025974026,
+      "grad_norm": 0.446053683757782,
+      "learning_rate": 0.0002,
+      "loss": 1.4387,
+      "step": 1240
+    },
+    {
+      "epoch": 4.058441558441558,
+      "grad_norm": 0.45109686255455017,
+      "learning_rate": 0.0002,
+      "loss": 1.4896,
+      "step": 1250
+    },
+    {
+      "epoch": 4.090909090909091,
+      "grad_norm": 0.48673322796821594,
+      "learning_rate": 0.0002,
+      "loss": 1.4838,
+      "step": 1260
+    },
+    {
+      "epoch": 4.123376623376624,
+      "grad_norm": 0.46708911657333374,
+      "learning_rate": 0.0002,
+      "loss": 1.4905,
+      "step": 1270
+    },
+    {
+      "epoch": 4.1558441558441555,
+      "grad_norm": 0.5715873837471008,
+      "learning_rate": 0.0002,
+      "loss": 1.4315,
+      "step": 1280
+    },
+    {
+      "epoch": 4.188311688311688,
+      "grad_norm": 0.5619666576385498,
+      "learning_rate": 0.0002,
+      "loss": 1.4223,
+      "step": 1290
+    },
+    {
+      "epoch": 4.220779220779221,
+      "grad_norm": 0.5654240250587463,
+      "learning_rate": 0.0002,
+      "loss": 1.4439,
+      "step": 1300
+    },
+    {
+      "epoch": 4.253246753246753,
+      "grad_norm": 0.597672700881958,
+      "learning_rate": 0.0002,
+      "loss": 1.4349,
+      "step": 1310
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 0.5012733936309814,
+      "learning_rate": 0.0002,
+      "loss": 1.4762,
+      "step": 1320
+    },
+    {
+      "epoch": 4.318181818181818,
+      "grad_norm": 0.5443211793899536,
+      "learning_rate": 0.0002,
+      "loss": 1.431,
+      "step": 1330
+    },
+    {
+      "epoch": 4.35064935064935,
+      "grad_norm": 0.5234072208404541,
+      "learning_rate": 0.0002,
+      "loss": 1.513,
+      "step": 1340
+    },
+    {
+      "epoch": 4.383116883116883,
+      "grad_norm": 0.5355457067489624,
+      "learning_rate": 0.0002,
+      "loss": 1.4977,
+      "step": 1350
+    },
+    {
+      "epoch": 4.415584415584416,
+      "grad_norm": 0.5286158919334412,
+      "learning_rate": 0.0002,
+      "loss": 1.4997,
+      "step": 1360
+    },
+    {
+      "epoch": 4.448051948051948,
+      "grad_norm": 0.5439335107803345,
+      "learning_rate": 0.0002,
+      "loss": 1.4659,
+      "step": 1370
+    },
+    {
+      "epoch": 4.48051948051948,
+      "grad_norm": 0.48760029673576355,
+      "learning_rate": 0.0002,
+      "loss": 1.432,
+      "step": 1380
+    },
+    {
+      "epoch": 4.512987012987013,
+      "grad_norm": 0.5220261216163635,
+      "learning_rate": 0.0002,
+      "loss": 1.482,
+      "step": 1390
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 0.5583887100219727,
+      "learning_rate": 0.0002,
+      "loss": 1.4622,
+      "step": 1400
+    },
+    {
+      "epoch": 4.577922077922078,
+      "grad_norm": 0.5749692320823669,
+      "learning_rate": 0.0002,
+      "loss": 1.4822,
+      "step": 1410
+    },
+    {
+      "epoch": 4.6103896103896105,
+      "grad_norm": 0.5173711180686951,
+      "learning_rate": 0.0002,
+      "loss": 1.4512,
+      "step": 1420
+    },
+    {
+      "epoch": 4.642857142857143,
+      "grad_norm": 0.47573772072792053,
+      "learning_rate": 0.0002,
+      "loss": 1.4657,
+      "step": 1430
+    },
+    {
+      "epoch": 4.675324675324675,
+      "grad_norm": 0.5032379031181335,
+      "learning_rate": 0.0002,
+      "loss": 1.3951,
+      "step": 1440
+    },
+    {
+      "epoch": 4.707792207792208,
+      "grad_norm": 0.5489498972892761,
+      "learning_rate": 0.0002,
+      "loss": 1.3851,
+      "step": 1450
+    },
+    {
+      "epoch": 4.740259740259741,
+      "grad_norm": 0.45405253767967224,
+      "learning_rate": 0.0002,
+      "loss": 1.4318,
+      "step": 1460
+    },
+    {
+      "epoch": 4.7727272727272725,
+      "grad_norm": 0.5374584197998047,
+      "learning_rate": 0.0002,
+      "loss": 1.4504,
+      "step": 1470
+    },
+    {
+      "epoch": 4.805194805194805,
+      "grad_norm": 0.5726877450942993,
+      "learning_rate": 0.0002,
+      "loss": 1.4764,
+      "step": 1480
+    },
+    {
+      "epoch": 4.837662337662338,
+      "grad_norm": 0.5010805130004883,
+      "learning_rate": 0.0002,
+      "loss": 1.4387,
+      "step": 1490
+    },
+    {
+      "epoch": 4.87012987012987,
+      "grad_norm": 0.5171884298324585,
+      "learning_rate": 0.0002,
+      "loss": 1.427,
+      "step": 1500
+    },
+    {
+      "epoch": 4.902597402597403,
+      "grad_norm": 0.5789468884468079,
+      "learning_rate": 0.0002,
+      "loss": 1.4507,
+      "step": 1510
+    },
+    {
+      "epoch": 4.935064935064935,
+      "grad_norm": 0.4989932179450989,
+      "learning_rate": 0.0002,
+      "loss": 1.4341,
+      "step": 1520
+    },
+    {
+      "epoch": 4.967532467532467,
+      "grad_norm": 0.5641090869903564,
+      "learning_rate": 0.0002,
+      "loss": 1.5556,
+      "step": 1530
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.5337041020393372,
+      "learning_rate": 0.0002,
+      "loss": 1.4618,
+      "step": 1540
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.8461486101150513,
+      "eval_runtime": 115.277,
+      "eval_samples_per_second": 4.615,
+      "eval_steps_per_second": 0.581,
+      "step": 1540
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2464,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.709148777447424e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1540/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:400ef20a202cfadecd17fb2d658472b52fb2ddded63f69b1e6150e63cfc2de96
+size 5560

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1848/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1848/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1848/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee4a45a06a92a40832e61ee4af2f3cebbb78b31bd260ddb1919fd0a38d55842d
+size 80755416

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1848/added_tokens.json

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

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1848/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:569a7ca48f48fc2921f255ffdf6f77a8321d2e1c1ad3c393d8252611cf945831
+size 41136570

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1848/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf0f7412c501d21ce2aa7a592a81eaf6381cb90a6824a8eec7b74be9e2203cc
+size 14244

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1848/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30fcae4a89d4c234120b0406d6521923488e077e6c4aa142e4c91c84ecd612c3
+size 1064

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1848/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1848/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1848/trainer_state.json

@@ -0,0 +1,1369 @@
+{
+  "best_metric": 1.765038251876831,
+  "best_model_checkpoint": "outputs-001/Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-616",
+  "epoch": 6.0,
+  "eval_steps": 10,
+  "global_step": 1848,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032467532467532464,
+      "grad_norm": 0.31557697057724,
+      "learning_rate": 0.0002,
+      "loss": 2.4028,
+      "step": 10
+    },
+    {
+      "epoch": 0.06493506493506493,
+      "grad_norm": 0.3265437185764313,
+      "learning_rate": 0.0002,
+      "loss": 2.1466,
+      "step": 20
+    },
+    {
+      "epoch": 0.09740259740259741,
+      "grad_norm": 0.3424590229988098,
+      "learning_rate": 0.0002,
+      "loss": 1.9549,
+      "step": 30
+    },
+    {
+      "epoch": 0.12987012987012986,
+      "grad_norm": 0.30609560012817383,
+      "learning_rate": 0.0002,
+      "loss": 1.8464,
+      "step": 40
+    },
+    {
+      "epoch": 0.16233766233766234,
+      "grad_norm": 0.3285873532295227,
+      "learning_rate": 0.0002,
+      "loss": 1.9203,
+      "step": 50
+    },
+    {
+      "epoch": 0.19480519480519481,
+      "grad_norm": 0.2855139374732971,
+      "learning_rate": 0.0002,
+      "loss": 1.7946,
+      "step": 60
+    },
+    {
+      "epoch": 0.22727272727272727,
+      "grad_norm": 0.283848375082016,
+      "learning_rate": 0.0002,
+      "loss": 1.7618,
+      "step": 70
+    },
+    {
+      "epoch": 0.2597402597402597,
+      "grad_norm": 0.2915274202823639,
+      "learning_rate": 0.0002,
+      "loss": 1.7875,
+      "step": 80
+    },
+    {
+      "epoch": 0.2922077922077922,
+      "grad_norm": 0.26927152276039124,
+      "learning_rate": 0.0002,
+      "loss": 1.7673,
+      "step": 90
+    },
+    {
+      "epoch": 0.3246753246753247,
+      "grad_norm": 0.29594847559928894,
+      "learning_rate": 0.0002,
+      "loss": 1.6726,
+      "step": 100
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.36750105023384094,
+      "learning_rate": 0.0002,
+      "loss": 1.7333,
+      "step": 110
+    },
+    {
+      "epoch": 0.38961038961038963,
+      "grad_norm": 0.32430270314216614,
+      "learning_rate": 0.0002,
+      "loss": 1.7772,
+      "step": 120
+    },
+    {
+      "epoch": 0.42207792207792205,
+      "grad_norm": 0.2767448127269745,
+      "learning_rate": 0.0002,
+      "loss": 1.731,
+      "step": 130
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.244296595454216,
+      "learning_rate": 0.0002,
+      "loss": 1.7604,
+      "step": 140
+    },
+    {
+      "epoch": 0.487012987012987,
+      "grad_norm": 0.25791823863983154,
+      "learning_rate": 0.0002,
+      "loss": 1.7172,
+      "step": 150
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "grad_norm": 0.25496479868888855,
+      "learning_rate": 0.0002,
+      "loss": 1.7509,
+      "step": 160
+    },
+    {
+      "epoch": 0.551948051948052,
+      "grad_norm": 0.2770450711250305,
+      "learning_rate": 0.0002,
+      "loss": 1.7328,
+      "step": 170
+    },
+    {
+      "epoch": 0.5844155844155844,
+      "grad_norm": 0.2971339821815491,
+      "learning_rate": 0.0002,
+      "loss": 1.8008,
+      "step": 180
+    },
+    {
+      "epoch": 0.6168831168831169,
+      "grad_norm": 0.3165527880191803,
+      "learning_rate": 0.0002,
+      "loss": 1.6805,
+      "step": 190
+    },
+    {
+      "epoch": 0.6493506493506493,
+      "grad_norm": 0.24732241034507751,
+      "learning_rate": 0.0002,
+      "loss": 1.732,
+      "step": 200
+    },
+    {
+      "epoch": 0.6818181818181818,
+      "grad_norm": 0.28333306312561035,
+      "learning_rate": 0.0002,
+      "loss": 1.6933,
+      "step": 210
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.24870498478412628,
+      "learning_rate": 0.0002,
+      "loss": 1.7324,
+      "step": 220
+    },
+    {
+      "epoch": 0.7467532467532467,
+      "grad_norm": 0.2484978884458542,
+      "learning_rate": 0.0002,
+      "loss": 1.7697,
+      "step": 230
+    },
+    {
+      "epoch": 0.7792207792207793,
+      "grad_norm": 0.2282458394765854,
+      "learning_rate": 0.0002,
+      "loss": 1.7624,
+      "step": 240
+    },
+    {
+      "epoch": 0.8116883116883117,
+      "grad_norm": 0.2552148699760437,
+      "learning_rate": 0.0002,
+      "loss": 1.7775,
+      "step": 250
+    },
+    {
+      "epoch": 0.8441558441558441,
+      "grad_norm": 0.25136545300483704,
+      "learning_rate": 0.0002,
+      "loss": 1.7153,
+      "step": 260
+    },
+    {
+      "epoch": 0.8766233766233766,
+      "grad_norm": 0.25096797943115234,
+      "learning_rate": 0.0002,
+      "loss": 1.7705,
+      "step": 270
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.3148603141307831,
+      "learning_rate": 0.0002,
+      "loss": 1.7842,
+      "step": 280
+    },
+    {
+      "epoch": 0.9415584415584416,
+      "grad_norm": 0.2533794343471527,
+      "learning_rate": 0.0002,
+      "loss": 1.6847,
+      "step": 290
+    },
+    {
+      "epoch": 0.974025974025974,
+      "grad_norm": 0.27348795533180237,
+      "learning_rate": 0.0002,
+      "loss": 1.7334,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.769331693649292,
+      "eval_runtime": 115.5699,
+      "eval_samples_per_second": 4.603,
+      "eval_steps_per_second": 0.58,
+      "step": 308
+    },
+    {
+      "epoch": 1.0064935064935066,
+      "grad_norm": 0.28133320808410645,
+      "learning_rate": 0.0002,
+      "loss": 1.6473,
+      "step": 310
+    },
+    {
+      "epoch": 1.0389610389610389,
+      "grad_norm": 0.2541237473487854,
+      "learning_rate": 0.0002,
+      "loss": 1.7067,
+      "step": 320
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.25699320435523987,
+      "learning_rate": 0.0002,
+      "loss": 1.7422,
+      "step": 330
+    },
+    {
+      "epoch": 1.103896103896104,
+      "grad_norm": 0.26137059926986694,
+      "learning_rate": 0.0002,
+      "loss": 1.6737,
+      "step": 340
+    },
+    {
+      "epoch": 1.1363636363636362,
+      "grad_norm": 0.2718560993671417,
+      "learning_rate": 0.0002,
+      "loss": 1.7372,
+      "step": 350
+    },
+    {
+      "epoch": 1.1688311688311688,
+      "grad_norm": 0.23400403559207916,
+      "learning_rate": 0.0002,
+      "loss": 1.6809,
+      "step": 360
+    },
+    {
+      "epoch": 1.2012987012987013,
+      "grad_norm": 0.28257420659065247,
+      "learning_rate": 0.0002,
+      "loss": 1.6892,
+      "step": 370
+    },
+    {
+      "epoch": 1.2337662337662338,
+      "grad_norm": 0.3031129240989685,
+      "learning_rate": 0.0002,
+      "loss": 1.6945,
+      "step": 380
+    },
+    {
+      "epoch": 1.2662337662337662,
+      "grad_norm": 0.3131062984466553,
+      "learning_rate": 0.0002,
+      "loss": 1.6611,
+      "step": 390
+    },
+    {
+      "epoch": 1.2987012987012987,
+      "grad_norm": 0.2594483494758606,
+      "learning_rate": 0.0002,
+      "loss": 1.6535,
+      "step": 400
+    },
+    {
+      "epoch": 1.3311688311688312,
+      "grad_norm": 0.2595517933368683,
+      "learning_rate": 0.0002,
+      "loss": 1.7275,
+      "step": 410
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.26333683729171753,
+      "learning_rate": 0.0002,
+      "loss": 1.6048,
+      "step": 420
+    },
+    {
+      "epoch": 1.396103896103896,
+      "grad_norm": 0.3051556646823883,
+      "learning_rate": 0.0002,
+      "loss": 1.8342,
+      "step": 430
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.26060932874679565,
+      "learning_rate": 0.0002,
+      "loss": 1.694,
+      "step": 440
+    },
+    {
+      "epoch": 1.4610389610389611,
+      "grad_norm": 0.282101571559906,
+      "learning_rate": 0.0002,
+      "loss": 1.6284,
+      "step": 450
+    },
+    {
+      "epoch": 1.4935064935064934,
+      "grad_norm": 0.2837599813938141,
+      "learning_rate": 0.0002,
+      "loss": 1.7301,
+      "step": 460
+    },
+    {
+      "epoch": 1.525974025974026,
+      "grad_norm": 0.2532821595668793,
+      "learning_rate": 0.0002,
+      "loss": 1.6769,
+      "step": 470
+    },
+    {
+      "epoch": 1.5584415584415585,
+      "grad_norm": 0.2448154091835022,
+      "learning_rate": 0.0002,
+      "loss": 1.6483,
+      "step": 480
+    },
+    {
+      "epoch": 1.5909090909090908,
+      "grad_norm": 0.2592053711414337,
+      "learning_rate": 0.0002,
+      "loss": 1.7212,
+      "step": 490
+    },
+    {
+      "epoch": 1.6233766233766234,
+      "grad_norm": 0.23606474697589874,
+      "learning_rate": 0.0002,
+      "loss": 1.7245,
+      "step": 500
+    },
+    {
+      "epoch": 1.655844155844156,
+      "grad_norm": 0.2693960964679718,
+      "learning_rate": 0.0002,
+      "loss": 1.7283,
+      "step": 510
+    },
+    {
+      "epoch": 1.6883116883116882,
+      "grad_norm": 0.28801923990249634,
+      "learning_rate": 0.0002,
+      "loss": 1.6573,
+      "step": 520
+    },
+    {
+      "epoch": 1.7207792207792207,
+      "grad_norm": 0.33677127957344055,
+      "learning_rate": 0.0002,
+      "loss": 1.654,
+      "step": 530
+    },
+    {
+      "epoch": 1.7532467532467533,
+      "grad_norm": 0.2794886529445648,
+      "learning_rate": 0.0002,
+      "loss": 1.7184,
+      "step": 540
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 0.2649626135826111,
+      "learning_rate": 0.0002,
+      "loss": 1.6204,
+      "step": 550
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.27729251980781555,
+      "learning_rate": 0.0002,
+      "loss": 1.7664,
+      "step": 560
+    },
+    {
+      "epoch": 1.8506493506493507,
+      "grad_norm": 0.2724396288394928,
+      "learning_rate": 0.0002,
+      "loss": 1.6099,
+      "step": 570
+    },
+    {
+      "epoch": 1.883116883116883,
+      "grad_norm": 0.25738948583602905,
+      "learning_rate": 0.0002,
+      "loss": 1.656,
+      "step": 580
+    },
+    {
+      "epoch": 1.9155844155844157,
+      "grad_norm": 0.2539234757423401,
+      "learning_rate": 0.0002,
+      "loss": 1.7401,
+      "step": 590
+    },
+    {
+      "epoch": 1.948051948051948,
+      "grad_norm": 0.27087679505348206,
+      "learning_rate": 0.0002,
+      "loss": 1.6833,
+      "step": 600
+    },
+    {
+      "epoch": 1.9805194805194806,
+      "grad_norm": 0.2727901041507721,
+      "learning_rate": 0.0002,
+      "loss": 1.6934,
+      "step": 610
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.765038251876831,
+      "eval_runtime": 117.4062,
+      "eval_samples_per_second": 4.531,
+      "eval_steps_per_second": 0.571,
+      "step": 616
+    },
+    {
+      "epoch": 2.012987012987013,
+      "grad_norm": 0.25380605459213257,
+      "learning_rate": 0.0002,
+      "loss": 1.6565,
+      "step": 620
+    },
+    {
+      "epoch": 2.0454545454545454,
+      "grad_norm": 0.28460997343063354,
+      "learning_rate": 0.0002,
+      "loss": 1.6043,
+      "step": 630
+    },
+    {
+      "epoch": 2.0779220779220777,
+      "grad_norm": 0.31530654430389404,
+      "learning_rate": 0.0002,
+      "loss": 1.7345,
+      "step": 640
+    },
+    {
+      "epoch": 2.1103896103896105,
+      "grad_norm": 0.30611202120780945,
+      "learning_rate": 0.0002,
+      "loss": 1.6077,
+      "step": 650
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.30674979090690613,
+      "learning_rate": 0.0002,
+      "loss": 1.6685,
+      "step": 660
+    },
+    {
+      "epoch": 2.175324675324675,
+      "grad_norm": 0.34276270866394043,
+      "learning_rate": 0.0002,
+      "loss": 1.6063,
+      "step": 670
+    },
+    {
+      "epoch": 2.207792207792208,
+      "grad_norm": 0.30068185925483704,
+      "learning_rate": 0.0002,
+      "loss": 1.6985,
+      "step": 680
+    },
+    {
+      "epoch": 2.24025974025974,
+      "grad_norm": 0.3197493851184845,
+      "learning_rate": 0.0002,
+      "loss": 1.5869,
+      "step": 690
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.3080422878265381,
+      "learning_rate": 0.0002,
+      "loss": 1.5993,
+      "step": 700
+    },
+    {
+      "epoch": 2.3051948051948052,
+      "grad_norm": 0.32039162516593933,
+      "learning_rate": 0.0002,
+      "loss": 1.634,
+      "step": 710
+    },
+    {
+      "epoch": 2.3376623376623376,
+      "grad_norm": 0.32778531312942505,
+      "learning_rate": 0.0002,
+      "loss": 1.6303,
+      "step": 720
+    },
+    {
+      "epoch": 2.3701298701298703,
+      "grad_norm": 0.31763869524002075,
+      "learning_rate": 0.0002,
+      "loss": 1.6783,
+      "step": 730
+    },
+    {
+      "epoch": 2.4025974025974026,
+      "grad_norm": 0.3438641130924225,
+      "learning_rate": 0.0002,
+      "loss": 1.5866,
+      "step": 740
+    },
+    {
+      "epoch": 2.435064935064935,
+      "grad_norm": 0.30254635214805603,
+      "learning_rate": 0.0002,
+      "loss": 1.6238,
+      "step": 750
+    },
+    {
+      "epoch": 2.4675324675324677,
+      "grad_norm": 0.3287079930305481,
+      "learning_rate": 0.0002,
+      "loss": 1.6321,
+      "step": 760
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.31394457817077637,
+      "learning_rate": 0.0002,
+      "loss": 1.6103,
+      "step": 770
+    },
+    {
+      "epoch": 2.5324675324675323,
+      "grad_norm": 0.34165051579475403,
+      "learning_rate": 0.0002,
+      "loss": 1.6384,
+      "step": 780
+    },
+    {
+      "epoch": 2.564935064935065,
+      "grad_norm": 0.3315567970275879,
+      "learning_rate": 0.0002,
+      "loss": 1.6555,
+      "step": 790
+    },
+    {
+      "epoch": 2.5974025974025974,
+      "grad_norm": 0.3183658719062805,
+      "learning_rate": 0.0002,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 2.62987012987013,
+      "grad_norm": 0.29442286491394043,
+      "learning_rate": 0.0002,
+      "loss": 1.6149,
+      "step": 810
+    },
+    {
+      "epoch": 2.6623376623376624,
+      "grad_norm": 0.3735957741737366,
+      "learning_rate": 0.0002,
+      "loss": 1.5689,
+      "step": 820
+    },
+    {
+      "epoch": 2.6948051948051948,
+      "grad_norm": 0.34174075722694397,
+      "learning_rate": 0.0002,
+      "loss": 1.6763,
+      "step": 830
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.3265220820903778,
+      "learning_rate": 0.0002,
+      "loss": 1.6333,
+      "step": 840
+    },
+    {
+      "epoch": 2.75974025974026,
+      "grad_norm": 0.3356368839740753,
+      "learning_rate": 0.0002,
+      "loss": 1.5971,
+      "step": 850
+    },
+    {
+      "epoch": 2.792207792207792,
+      "grad_norm": 0.33430132269859314,
+      "learning_rate": 0.0002,
+      "loss": 1.6042,
+      "step": 860
+    },
+    {
+      "epoch": 2.824675324675325,
+      "grad_norm": 0.28999271988868713,
+      "learning_rate": 0.0002,
+      "loss": 1.5982,
+      "step": 870
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.3253968358039856,
+      "learning_rate": 0.0002,
+      "loss": 1.6189,
+      "step": 880
+    },
+    {
+      "epoch": 2.8896103896103895,
+      "grad_norm": 0.291964054107666,
+      "learning_rate": 0.0002,
+      "loss": 1.6011,
+      "step": 890
+    },
+    {
+      "epoch": 2.9220779220779223,
+      "grad_norm": 0.32170912623405457,
+      "learning_rate": 0.0002,
+      "loss": 1.6854,
+      "step": 900
+    },
+    {
+      "epoch": 2.9545454545454546,
+      "grad_norm": 0.2738993465900421,
+      "learning_rate": 0.0002,
+      "loss": 1.7219,
+      "step": 910
+    },
+    {
+      "epoch": 2.987012987012987,
+      "grad_norm": 0.29856377840042114,
+      "learning_rate": 0.0002,
+      "loss": 1.667,
+      "step": 920
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.7705217599868774,
+      "eval_runtime": 115.3403,
+      "eval_samples_per_second": 4.612,
+      "eval_steps_per_second": 0.581,
+      "step": 924
+    },
+    {
+      "epoch": 3.0194805194805197,
+      "grad_norm": 0.3272620439529419,
+      "learning_rate": 0.0002,
+      "loss": 1.5876,
+      "step": 930
+    },
+    {
+      "epoch": 3.051948051948052,
+      "grad_norm": 0.3484354019165039,
+      "learning_rate": 0.0002,
+      "loss": 1.6262,
+      "step": 940
+    },
+    {
+      "epoch": 3.0844155844155843,
+      "grad_norm": 0.35202738642692566,
+      "learning_rate": 0.0002,
+      "loss": 1.5092,
+      "step": 950
+    },
+    {
+      "epoch": 3.116883116883117,
+      "grad_norm": 0.3635590076446533,
+      "learning_rate": 0.0002,
+      "loss": 1.5524,
+      "step": 960
+    },
+    {
+      "epoch": 3.1493506493506493,
+      "grad_norm": 0.39253556728363037,
+      "learning_rate": 0.0002,
+      "loss": 1.5169,
+      "step": 970
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "grad_norm": 0.4007384777069092,
+      "learning_rate": 0.0002,
+      "loss": 1.5001,
+      "step": 980
+    },
+    {
+      "epoch": 3.2142857142857144,
+      "grad_norm": 0.38897788524627686,
+      "learning_rate": 0.0002,
+      "loss": 1.5639,
+      "step": 990
+    },
+    {
+      "epoch": 3.2467532467532467,
+      "grad_norm": 0.38462474942207336,
+      "learning_rate": 0.0002,
+      "loss": 1.5791,
+      "step": 1000
+    },
+    {
+      "epoch": 3.279220779220779,
+      "grad_norm": 0.38225963711738586,
+      "learning_rate": 0.0002,
+      "loss": 1.4918,
+      "step": 1010
+    },
+    {
+      "epoch": 3.311688311688312,
+      "grad_norm": 0.4058142602443695,
+      "learning_rate": 0.0002,
+      "loss": 1.5094,
+      "step": 1020
+    },
+    {
+      "epoch": 3.344155844155844,
+      "grad_norm": 0.39580652117729187,
+      "learning_rate": 0.0002,
+      "loss": 1.5905,
+      "step": 1030
+    },
+    {
+      "epoch": 3.3766233766233764,
+      "grad_norm": 0.42998549342155457,
+      "learning_rate": 0.0002,
+      "loss": 1.5894,
+      "step": 1040
+    },
+    {
+      "epoch": 3.409090909090909,
+      "grad_norm": 0.3940870761871338,
+      "learning_rate": 0.0002,
+      "loss": 1.548,
+      "step": 1050
+    },
+    {
+      "epoch": 3.4415584415584415,
+      "grad_norm": 0.4069645404815674,
+      "learning_rate": 0.0002,
+      "loss": 1.6527,
+      "step": 1060
+    },
+    {
+      "epoch": 3.474025974025974,
+      "grad_norm": 0.386883407831192,
+      "learning_rate": 0.0002,
+      "loss": 1.6035,
+      "step": 1070
+    },
+    {
+      "epoch": 3.5064935064935066,
+      "grad_norm": 0.4978795051574707,
+      "learning_rate": 0.0002,
+      "loss": 1.5991,
+      "step": 1080
+    },
+    {
+      "epoch": 3.538961038961039,
+      "grad_norm": 0.4167064130306244,
+      "learning_rate": 0.0002,
+      "loss": 1.555,
+      "step": 1090
+    },
+    {
+      "epoch": 3.571428571428571,
+      "grad_norm": 0.38199925422668457,
+      "learning_rate": 0.0002,
+      "loss": 1.5393,
+      "step": 1100
+    },
+    {
+      "epoch": 3.603896103896104,
+      "grad_norm": 0.4170112609863281,
+      "learning_rate": 0.0002,
+      "loss": 1.5206,
+      "step": 1110
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 0.4023001194000244,
+      "learning_rate": 0.0002,
+      "loss": 1.5336,
+      "step": 1120
+    },
+    {
+      "epoch": 3.6688311688311686,
+      "grad_norm": 0.44960418343544006,
+      "learning_rate": 0.0002,
+      "loss": 1.5324,
+      "step": 1130
+    },
+    {
+      "epoch": 3.7012987012987013,
+      "grad_norm": 0.4334756135940552,
+      "learning_rate": 0.0002,
+      "loss": 1.5784,
+      "step": 1140
+    },
+    {
+      "epoch": 3.7337662337662336,
+      "grad_norm": 0.38534295558929443,
+      "learning_rate": 0.0002,
+      "loss": 1.5018,
+      "step": 1150
+    },
+    {
+      "epoch": 3.7662337662337664,
+      "grad_norm": 0.40537452697753906,
+      "learning_rate": 0.0002,
+      "loss": 1.6091,
+      "step": 1160
+    },
+    {
+      "epoch": 3.7987012987012987,
+      "grad_norm": 0.4050034284591675,
+      "learning_rate": 0.0002,
+      "loss": 1.5303,
+      "step": 1170
+    },
+    {
+      "epoch": 3.8311688311688314,
+      "grad_norm": 0.3953498303890228,
+      "learning_rate": 0.0002,
+      "loss": 1.5082,
+      "step": 1180
+    },
+    {
+      "epoch": 3.8636363636363638,
+      "grad_norm": 0.4208937883377075,
+      "learning_rate": 0.0002,
+      "loss": 1.5402,
+      "step": 1190
+    },
+    {
+      "epoch": 3.896103896103896,
+      "grad_norm": 0.4181132912635803,
+      "learning_rate": 0.0002,
+      "loss": 1.5657,
+      "step": 1200
+    },
+    {
+      "epoch": 3.928571428571429,
+      "grad_norm": 0.4108502268791199,
+      "learning_rate": 0.0002,
+      "loss": 1.6202,
+      "step": 1210
+    },
+    {
+      "epoch": 3.961038961038961,
+      "grad_norm": 0.3819066882133484,
+      "learning_rate": 0.0002,
+      "loss": 1.5157,
+      "step": 1220
+    },
+    {
+      "epoch": 3.9935064935064934,
+      "grad_norm": 0.3682127892971039,
+      "learning_rate": 0.0002,
+      "loss": 1.4595,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.7993888854980469,
+      "eval_runtime": 115.4041,
+      "eval_samples_per_second": 4.61,
+      "eval_steps_per_second": 0.581,
+      "step": 1232
+    },
+    {
+      "epoch": 4.025974025974026,
+      "grad_norm": 0.446053683757782,
+      "learning_rate": 0.0002,
+      "loss": 1.4387,
+      "step": 1240
+    },
+    {
+      "epoch": 4.058441558441558,
+      "grad_norm": 0.45109686255455017,
+      "learning_rate": 0.0002,
+      "loss": 1.4896,
+      "step": 1250
+    },
+    {
+      "epoch": 4.090909090909091,
+      "grad_norm": 0.48673322796821594,
+      "learning_rate": 0.0002,
+      "loss": 1.4838,
+      "step": 1260
+    },
+    {
+      "epoch": 4.123376623376624,
+      "grad_norm": 0.46708911657333374,
+      "learning_rate": 0.0002,
+      "loss": 1.4905,
+      "step": 1270
+    },
+    {
+      "epoch": 4.1558441558441555,
+      "grad_norm": 0.5715873837471008,
+      "learning_rate": 0.0002,
+      "loss": 1.4315,
+      "step": 1280
+    },
+    {
+      "epoch": 4.188311688311688,
+      "grad_norm": 0.5619666576385498,
+      "learning_rate": 0.0002,
+      "loss": 1.4223,
+      "step": 1290
+    },
+    {
+      "epoch": 4.220779220779221,
+      "grad_norm": 0.5654240250587463,
+      "learning_rate": 0.0002,
+      "loss": 1.4439,
+      "step": 1300
+    },
+    {
+      "epoch": 4.253246753246753,
+      "grad_norm": 0.597672700881958,
+      "learning_rate": 0.0002,
+      "loss": 1.4349,
+      "step": 1310
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 0.5012733936309814,
+      "learning_rate": 0.0002,
+      "loss": 1.4762,
+      "step": 1320
+    },
+    {
+      "epoch": 4.318181818181818,
+      "grad_norm": 0.5443211793899536,
+      "learning_rate": 0.0002,
+      "loss": 1.431,
+      "step": 1330
+    },
+    {
+      "epoch": 4.35064935064935,
+      "grad_norm": 0.5234072208404541,
+      "learning_rate": 0.0002,
+      "loss": 1.513,
+      "step": 1340
+    },
+    {
+      "epoch": 4.383116883116883,
+      "grad_norm": 0.5355457067489624,
+      "learning_rate": 0.0002,
+      "loss": 1.4977,
+      "step": 1350
+    },
+    {
+      "epoch": 4.415584415584416,
+      "grad_norm": 0.5286158919334412,
+      "learning_rate": 0.0002,
+      "loss": 1.4997,
+      "step": 1360
+    },
+    {
+      "epoch": 4.448051948051948,
+      "grad_norm": 0.5439335107803345,
+      "learning_rate": 0.0002,
+      "loss": 1.4659,
+      "step": 1370
+    },
+    {
+      "epoch": 4.48051948051948,
+      "grad_norm": 0.48760029673576355,
+      "learning_rate": 0.0002,
+      "loss": 1.432,
+      "step": 1380
+    },
+    {
+      "epoch": 4.512987012987013,
+      "grad_norm": 0.5220261216163635,
+      "learning_rate": 0.0002,
+      "loss": 1.482,
+      "step": 1390
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 0.5583887100219727,
+      "learning_rate": 0.0002,
+      "loss": 1.4622,
+      "step": 1400
+    },
+    {
+      "epoch": 4.577922077922078,
+      "grad_norm": 0.5749692320823669,
+      "learning_rate": 0.0002,
+      "loss": 1.4822,
+      "step": 1410
+    },
+    {
+      "epoch": 4.6103896103896105,
+      "grad_norm": 0.5173711180686951,
+      "learning_rate": 0.0002,
+      "loss": 1.4512,
+      "step": 1420
+    },
+    {
+      "epoch": 4.642857142857143,
+      "grad_norm": 0.47573772072792053,
+      "learning_rate": 0.0002,
+      "loss": 1.4657,
+      "step": 1430
+    },
+    {
+      "epoch": 4.675324675324675,
+      "grad_norm": 0.5032379031181335,
+      "learning_rate": 0.0002,
+      "loss": 1.3951,
+      "step": 1440
+    },
+    {
+      "epoch": 4.707792207792208,
+      "grad_norm": 0.5489498972892761,
+      "learning_rate": 0.0002,
+      "loss": 1.3851,
+      "step": 1450
+    },
+    {
+      "epoch": 4.740259740259741,
+      "grad_norm": 0.45405253767967224,
+      "learning_rate": 0.0002,
+      "loss": 1.4318,
+      "step": 1460
+    },
+    {
+      "epoch": 4.7727272727272725,
+      "grad_norm": 0.5374584197998047,
+      "learning_rate": 0.0002,
+      "loss": 1.4504,
+      "step": 1470
+    },
+    {
+      "epoch": 4.805194805194805,
+      "grad_norm": 0.5726877450942993,
+      "learning_rate": 0.0002,
+      "loss": 1.4764,
+      "step": 1480
+    },
+    {
+      "epoch": 4.837662337662338,
+      "grad_norm": 0.5010805130004883,
+      "learning_rate": 0.0002,
+      "loss": 1.4387,
+      "step": 1490
+    },
+    {
+      "epoch": 4.87012987012987,
+      "grad_norm": 0.5171884298324585,
+      "learning_rate": 0.0002,
+      "loss": 1.427,
+      "step": 1500
+    },
+    {
+      "epoch": 4.902597402597403,
+      "grad_norm": 0.5789468884468079,
+      "learning_rate": 0.0002,
+      "loss": 1.4507,
+      "step": 1510
+    },
+    {
+      "epoch": 4.935064935064935,
+      "grad_norm": 0.4989932179450989,
+      "learning_rate": 0.0002,
+      "loss": 1.4341,
+      "step": 1520
+    },
+    {
+      "epoch": 4.967532467532467,
+      "grad_norm": 0.5641090869903564,
+      "learning_rate": 0.0002,
+      "loss": 1.5556,
+      "step": 1530
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.5337041020393372,
+      "learning_rate": 0.0002,
+      "loss": 1.4618,
+      "step": 1540
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.8461486101150513,
+      "eval_runtime": 115.277,
+      "eval_samples_per_second": 4.615,
+      "eval_steps_per_second": 0.581,
+      "step": 1540
+    },
+    {
+      "epoch": 5.032467532467533,
+      "grad_norm": 0.9605194926261902,
+      "learning_rate": 0.0002,
+      "loss": 1.3205,
+      "step": 1550
+    },
+    {
+      "epoch": 5.064935064935065,
+      "grad_norm": 0.6274206042289734,
+      "learning_rate": 0.0002,
+      "loss": 1.3339,
+      "step": 1560
+    },
+    {
+      "epoch": 5.097402597402597,
+      "grad_norm": 0.6573551297187805,
+      "learning_rate": 0.0002,
+      "loss": 1.2737,
+      "step": 1570
+    },
+    {
+      "epoch": 5.12987012987013,
+      "grad_norm": 0.7081370949745178,
+      "learning_rate": 0.0002,
+      "loss": 1.4036,
+      "step": 1580
+    },
+    {
+      "epoch": 5.162337662337662,
+      "grad_norm": 0.7647580504417419,
+      "learning_rate": 0.0002,
+      "loss": 1.3609,
+      "step": 1590
+    },
+    {
+      "epoch": 5.194805194805195,
+      "grad_norm": 0.6994581818580627,
+      "learning_rate": 0.0002,
+      "loss": 1.3455,
+      "step": 1600
+    },
+    {
+      "epoch": 5.2272727272727275,
+      "grad_norm": 0.7378994226455688,
+      "learning_rate": 0.0002,
+      "loss": 1.2874,
+      "step": 1610
+    },
+    {
+      "epoch": 5.259740259740259,
+      "grad_norm": 0.714074432849884,
+      "learning_rate": 0.0002,
+      "loss": 1.2868,
+      "step": 1620
+    },
+    {
+      "epoch": 5.292207792207792,
+      "grad_norm": 0.7327056527137756,
+      "learning_rate": 0.0002,
+      "loss": 1.3336,
+      "step": 1630
+    },
+    {
+      "epoch": 5.324675324675325,
+      "grad_norm": 0.7495806813240051,
+      "learning_rate": 0.0002,
+      "loss": 1.2988,
+      "step": 1640
+    },
+    {
+      "epoch": 5.357142857142857,
+      "grad_norm": 0.6599726676940918,
+      "learning_rate": 0.0002,
+      "loss": 1.3469,
+      "step": 1650
+    },
+    {
+      "epoch": 5.3896103896103895,
+      "grad_norm": 0.7198082804679871,
+      "learning_rate": 0.0002,
+      "loss": 1.3071,
+      "step": 1660
+    },
+    {
+      "epoch": 5.422077922077922,
+      "grad_norm": 0.626568615436554,
+      "learning_rate": 0.0002,
+      "loss": 1.322,
+      "step": 1670
+    },
+    {
+      "epoch": 5.454545454545454,
+      "grad_norm": 0.9457268714904785,
+      "learning_rate": 0.0002,
+      "loss": 1.3557,
+      "step": 1680
+    },
+    {
+      "epoch": 5.487012987012987,
+      "grad_norm": 0.6491796374320984,
+      "learning_rate": 0.0002,
+      "loss": 1.3625,
+      "step": 1690
+    },
+    {
+      "epoch": 5.51948051948052,
+      "grad_norm": 0.6802761554718018,
+      "learning_rate": 0.0002,
+      "loss": 1.3357,
+      "step": 1700
+    },
+    {
+      "epoch": 5.551948051948052,
+      "grad_norm": 0.8260579705238342,
+      "learning_rate": 0.0002,
+      "loss": 1.4207,
+      "step": 1710
+    },
+    {
+      "epoch": 5.584415584415584,
+      "grad_norm": 0.6188812851905823,
+      "learning_rate": 0.0002,
+      "loss": 1.3702,
+      "step": 1720
+    },
+    {
+      "epoch": 5.616883116883117,
+      "grad_norm": 0.7274051308631897,
+      "learning_rate": 0.0002,
+      "loss": 1.3587,
+      "step": 1730
+    },
+    {
+      "epoch": 5.64935064935065,
+      "grad_norm": 0.635021984577179,
+      "learning_rate": 0.0002,
+      "loss": 1.3843,
+      "step": 1740
+    },
+    {
+      "epoch": 5.681818181818182,
+      "grad_norm": 0.7513797283172607,
+      "learning_rate": 0.0002,
+      "loss": 1.366,
+      "step": 1750
+    },
+    {
+      "epoch": 5.714285714285714,
+      "grad_norm": 0.6351640820503235,
+      "learning_rate": 0.0002,
+      "loss": 1.2785,
+      "step": 1760
+    },
+    {
+      "epoch": 5.746753246753247,
+      "grad_norm": 0.776997447013855,
+      "learning_rate": 0.0002,
+      "loss": 1.4055,
+      "step": 1770
+    },
+    {
+      "epoch": 5.779220779220779,
+      "grad_norm": 0.6774960160255432,
+      "learning_rate": 0.0002,
+      "loss": 1.4416,
+      "step": 1780
+    },
+    {
+      "epoch": 5.811688311688312,
+      "grad_norm": 0.7220422625541687,
+      "learning_rate": 0.0002,
+      "loss": 1.3096,
+      "step": 1790
+    },
+    {
+      "epoch": 5.8441558441558445,
+      "grad_norm": 0.6656085848808289,
+      "learning_rate": 0.0002,
+      "loss": 1.3325,
+      "step": 1800
+    },
+    {
+      "epoch": 5.876623376623376,
+      "grad_norm": 0.6828312277793884,
+      "learning_rate": 0.0002,
+      "loss": 1.3594,
+      "step": 1810
+    },
+    {
+      "epoch": 5.909090909090909,
+      "grad_norm": 0.649799108505249,
+      "learning_rate": 0.0002,
+      "loss": 1.4054,
+      "step": 1820
+    },
+    {
+      "epoch": 5.941558441558442,
+      "grad_norm": 0.6278491020202637,
+      "learning_rate": 0.0002,
+      "loss": 1.4273,
+      "step": 1830
+    },
+    {
+      "epoch": 5.974025974025974,
+      "grad_norm": 0.6418891549110413,
+      "learning_rate": 0.0002,
+      "loss": 1.4321,
+      "step": 1840
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.9093387126922607,
+      "eval_runtime": 119.2556,
+      "eval_samples_per_second": 4.461,
+      "eval_steps_per_second": 0.562,
+      "step": 1848
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2464,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.050978532936909e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-1848/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:400ef20a202cfadecd17fb2d658472b52fb2ddded63f69b1e6150e63cfc2de96
+size 5560

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-2156/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-2156/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-2156/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44184a28c8a5a0bed8ef1c8ab116390389ae78ab1f9f26233aa78f6e1d76b4fe
+size 80755416

Qwen2-7B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1405-sd-42/checkpoint-2156/added_tokens.json

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