Upload folder using huggingface_hub

exp0_baseline/checkpoint-1/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.17.1

exp0_baseline/checkpoint-1/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

exp0_baseline/checkpoint-1/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf06f9cea89c8d9d7124c1d52bac71038ad97cd68d0c8e6ed60f7bbfcb25f80
+size 201378736

exp0_baseline/checkpoint-1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aa55dea0ca598e0bf5b442fb7f2c41ae97a63e414478868fcfe7f6d4d839642
+size 402982627

exp0_baseline/checkpoint-1/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f25a535c3b4666d82432ed14514e08df4d28f434738d10df0544ccff1f604167
+size 14645

exp0_baseline/checkpoint-1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:606cfc6388b6cf7d31d99974a689cca32d495ea107cc08ea098ddbe0845d2d35
+size 1465

exp0_baseline/checkpoint-1/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.6373677253723145,
+      "learning_rate": 0.0,
+      "loss": 1.3085,
+      "step": 1
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 3,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 690182437208064.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

exp0_baseline/checkpoint-1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc1d4d2c81fe84f834ff9f6e7f721e83167a4346e940ee66b8eced62acc15367
+size 6033

exp0_baseline/checkpoint-100/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.17.1

exp0_baseline/checkpoint-100/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

exp0_baseline/checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8209e0cbb700204af15187718e31808cf6e3166b8065c4c05ac7864dc693371
+size 201378736

exp0_baseline/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:644358c4c401fbe2649687bc34c4e1a13fecb35ca5ab401cae903e89ccd99528
+size 402982627

exp0_baseline/checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b92ede016a8dc313d233f2927862e909d5717a49b27265ddd87beb7b3aab3357
+size 14645

exp0_baseline/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c4e44404b58ce3af1b46c3d4a85a59edbbc386f340c476e894715a1199e1aed
+size 1465

exp0_baseline/checkpoint-100/trainer_state.json

@@ -0,0 +1,742 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010050251256281407,
+      "grad_norm": 1.144538164138794,
+      "learning_rate": 0.0,
+      "loss": 0.561,
+      "step": 1
+    },
+    {
+      "epoch": 0.020100502512562814,
+      "grad_norm": 1.1173577308654785,
+      "learning_rate": 5e-06,
+      "loss": 0.5438,
+      "step": 2
+    },
+    {
+      "epoch": 0.03015075376884422,
+      "grad_norm": 1.6941046714782715,
+      "learning_rate": 1e-05,
+      "loss": 0.5345,
+      "step": 3
+    },
+    {
+      "epoch": 0.04020100502512563,
+      "grad_norm": 2.2526638507843018,
+      "learning_rate": 1.5e-05,
+      "loss": 0.6601,
+      "step": 4
+    },
+    {
+      "epoch": 0.05025125628140704,
+      "grad_norm": 2.336232900619507,
+      "learning_rate": 2e-05,
+      "loss": 0.8386,
+      "step": 5
+    },
+    {
+      "epoch": 0.06030150753768844,
+      "grad_norm": 1.2247791290283203,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3448,
+      "step": 6
+    },
+    {
+      "epoch": 0.07035175879396985,
+      "grad_norm": 3.491952419281006,
+      "learning_rate": 3e-05,
+      "loss": 0.9107,
+      "step": 7
+    },
+    {
+      "epoch": 0.08040201005025126,
+      "grad_norm": 1.5285453796386719,
+      "learning_rate": 3.5e-05,
+      "loss": 0.5574,
+      "step": 8
+    },
+    {
+      "epoch": 0.09045226130653267,
+      "grad_norm": 1.9498869180679321,
+      "learning_rate": 4e-05,
+      "loss": 0.7468,
+      "step": 9
+    },
+    {
+      "epoch": 0.10050251256281408,
+      "grad_norm": 1.451749563217163,
+      "learning_rate": 4.5e-05,
+      "loss": 0.7601,
+      "step": 10
+    },
+    {
+      "epoch": 0.11055276381909548,
+      "grad_norm": 2.121290683746338,
+      "learning_rate": 5e-05,
+      "loss": 0.788,
+      "step": 11
+    },
+    {
+      "epoch": 0.12060301507537688,
+      "grad_norm": 1.173128604888916,
+      "learning_rate": 4.99847706754774e-05,
+      "loss": 0.4117,
+      "step": 12
+    },
+    {
+      "epoch": 0.1306532663316583,
+      "grad_norm": 1.4134124517440796,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.2099,
+      "step": 13
+    },
+    {
+      "epoch": 0.1407035175879397,
+      "grad_norm": 2.4718620777130127,
+      "learning_rate": 4.9863047384206835e-05,
+      "loss": 1.0762,
+      "step": 14
+    },
+    {
+      "epoch": 0.1507537688442211,
+      "grad_norm": 1.1293636560440063,
+      "learning_rate": 4.975670171853926e-05,
+      "loss": 0.338,
+      "step": 15
+    },
+    {
+      "epoch": 0.16080402010050251,
+      "grad_norm": 2.616136312484741,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 1.0328,
+      "step": 16
+    },
+    {
+      "epoch": 0.1708542713567839,
+      "grad_norm": 2.410461902618408,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.863,
+      "step": 17
+    },
+    {
+      "epoch": 0.18090452261306533,
+      "grad_norm": 2.1010797023773193,
+      "learning_rate": 4.925739315689991e-05,
+      "loss": 0.6364,
+      "step": 18
+    },
+    {
+      "epoch": 0.19095477386934673,
+      "grad_norm": 1.2987828254699707,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.4619,
+      "step": 19
+    },
+    {
+      "epoch": 0.20100502512562815,
+      "grad_norm": 1.2924538850784302,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.7118,
+      "step": 20
+    },
+    {
+      "epoch": 0.21105527638190955,
+      "grad_norm": 1.6322095394134521,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.936,
+      "step": 21
+    },
+    {
+      "epoch": 0.22110552763819097,
+      "grad_norm": 1.9164633750915527,
+      "learning_rate": 4.817959636416969e-05,
+      "loss": 0.8829,
+      "step": 22
+    },
+    {
+      "epoch": 0.23115577889447236,
+      "grad_norm": 1.2494964599609375,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.3653,
+      "step": 23
+    },
+    {
+      "epoch": 0.24120603015075376,
+      "grad_norm": 1.217826247215271,
+      "learning_rate": 4.7469851157479177e-05,
+      "loss": 0.4539,
+      "step": 24
+    },
+    {
+      "epoch": 0.25125628140703515,
+      "grad_norm": 3.2103142738342285,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.9621,
+      "step": 25
+    },
+    {
+      "epoch": 0.2613065326633166,
+      "grad_norm": 1.2653640508651733,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.448,
+      "step": 26
+    },
+    {
+      "epoch": 0.271356783919598,
+      "grad_norm": 0.9144423007965088,
+      "learning_rate": 4.620120240391065e-05,
+      "loss": 0.3957,
+      "step": 27
+    },
+    {
+      "epoch": 0.2814070351758794,
+      "grad_norm": 1.313241958618164,
+      "learning_rate": 4.572593931387604e-05,
+      "loss": 0.5468,
+      "step": 28
+    },
+    {
+      "epoch": 0.2914572864321608,
+      "grad_norm": 0.7544188499450684,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.185,
+      "step": 29
+    },
+    {
+      "epoch": 0.3015075376884422,
+      "grad_norm": 0.9644553661346436,
+      "learning_rate": 4.4700268840168045e-05,
+      "loss": 0.3864,
+      "step": 30
+    },
+    {
+      "epoch": 0.31155778894472363,
+      "grad_norm": 1.281360387802124,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.5255,
+      "step": 31
+    },
+    {
+      "epoch": 0.32160804020100503,
+      "grad_norm": 0.8318763375282288,
+      "learning_rate": 4.357862063693486e-05,
+      "loss": 0.392,
+      "step": 32
+    },
+    {
+      "epoch": 0.3316582914572864,
+      "grad_norm": 1.29972243309021,
+      "learning_rate": 4.2983495008466276e-05,
+      "loss": 0.6444,
+      "step": 33
+    },
+    {
+      "epoch": 0.3417085427135678,
+      "grad_norm": 1.3421469926834106,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 0.3876,
+      "step": 34
+    },
+    {
+      "epoch": 0.35175879396984927,
+      "grad_norm": 0.9718002676963806,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.5414,
+      "step": 35
+    },
+    {
+      "epoch": 0.36180904522613067,
+      "grad_norm": 0.9774896502494812,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 0.4928,
+      "step": 36
+    },
+    {
+      "epoch": 0.37185929648241206,
+      "grad_norm": 3.244431257247925,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 1.0665,
+      "step": 37
+    },
+    {
+      "epoch": 0.38190954773869346,
+      "grad_norm": 0.9365755319595337,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 0.3107,
+      "step": 38
+    },
+    {
+      "epoch": 0.39195979899497485,
+      "grad_norm": 1.4368454217910767,
+      "learning_rate": 3.897982258676867e-05,
+      "loss": 0.4084,
+      "step": 39
+    },
+    {
+      "epoch": 0.4020100502512563,
+      "grad_norm": 2.354626417160034,
+      "learning_rate": 3.824798160583012e-05,
+      "loss": 0.4833,
+      "step": 40
+    },
+    {
+      "epoch": 0.4120603015075377,
+      "grad_norm": 2.426787853240967,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.548,
+      "step": 41
+    },
+    {
+      "epoch": 0.4221105527638191,
+      "grad_norm": 1.3904081583023071,
+      "learning_rate": 3.673678906964727e-05,
+      "loss": 0.847,
+      "step": 42
+    },
+    {
+      "epoch": 0.4321608040201005,
+      "grad_norm": 0.8043186664581299,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 0.3826,
+      "step": 43
+    },
+    {
+      "epoch": 0.44221105527638194,
+      "grad_norm": 0.9501510858535767,
+      "learning_rate": 3.516841607689501e-05,
+      "loss": 0.2336,
+      "step": 44
+    },
+    {
+      "epoch": 0.45226130653266333,
+      "grad_norm": 2.477350950241089,
+      "learning_rate": 3.436516483539781e-05,
+      "loss": 0.8067,
+      "step": 45
+    },
+    {
+      "epoch": 0.4623115577889447,
+      "grad_norm": 1.3030426502227783,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.4237,
+      "step": 46
+    },
+    {
+      "epoch": 0.4723618090452261,
+      "grad_norm": 2.6159799098968506,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.5104,
+      "step": 47
+    },
+    {
+      "epoch": 0.4824120603015075,
+      "grad_norm": 1.256778597831726,
+      "learning_rate": 3.1890933895424976e-05,
+      "loss": 0.235,
+      "step": 48
+    },
+    {
+      "epoch": 0.49246231155778897,
+      "grad_norm": 2.076829195022583,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 0.5265,
+      "step": 49
+    },
+    {
+      "epoch": 0.5025125628140703,
+      "grad_norm": 1.3327422142028809,
+      "learning_rate": 3.0197792270443982e-05,
+      "loss": 0.5636,
+      "step": 50
+    },
+    {
+      "epoch": 0.5125628140703518,
+      "grad_norm": 1.7859450578689575,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.67,
+      "step": 51
+    },
+    {
+      "epoch": 0.5226130653266332,
+      "grad_norm": 1.3924661874771118,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 0.6816,
+      "step": 52
+    },
+    {
+      "epoch": 0.5326633165829145,
+      "grad_norm": 1.4186939001083374,
+      "learning_rate": 2.761321158169134e-05,
+      "loss": 0.3969,
+      "step": 53
+    },
+    {
+      "epoch": 0.542713567839196,
+      "grad_norm": 2.0062601566314697,
+      "learning_rate": 2.674391184360313e-05,
+      "loss": 0.3101,
+      "step": 54
+    },
+    {
+      "epoch": 0.5527638190954773,
+      "grad_norm": 1.4015522003173828,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 0.2104,
+      "step": 55
+    },
+    {
+      "epoch": 0.5628140703517588,
+      "grad_norm": 1.5075968503952026,
+      "learning_rate": 2.5e-05,
+      "loss": 0.5247,
+      "step": 56
+    },
+    {
+      "epoch": 0.5728643216080402,
+      "grad_norm": 3.6213722229003906,
+      "learning_rate": 2.4127512582437485e-05,
+      "loss": 0.8403,
+      "step": 57
+    },
+    {
+      "epoch": 0.5829145728643216,
+      "grad_norm": 5.086165904998779,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 0.9748,
+      "step": 58
+    },
+    {
+      "epoch": 0.592964824120603,
+      "grad_norm": 0.8291557431221008,
+      "learning_rate": 2.238678841830867e-05,
+      "loss": 0.1264,
+      "step": 59
+    },
+    {
+      "epoch": 0.6030150753768844,
+      "grad_norm": 6.901468753814697,
+      "learning_rate": 2.1520672475998373e-05,
+      "loss": 1.7948,
+      "step": 60
+    },
+    {
+      "epoch": 0.6130653266331658,
+      "grad_norm": 1.2166105508804321,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.3152,
+      "step": 61
+    },
+    {
+      "epoch": 0.6231155778894473,
+      "grad_norm": 4.400286674499512,
+      "learning_rate": 1.980220772955602e-05,
+      "loss": 1.6227,
+      "step": 62
+    },
+    {
+      "epoch": 0.6331658291457286,
+      "grad_norm": 2.3584349155426025,
+      "learning_rate": 1.895195261000831e-05,
+      "loss": 0.6485,
+      "step": 63
+    },
+    {
+      "epoch": 0.6432160804020101,
+      "grad_norm": 3.535404682159424,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 1.1718,
+      "step": 64
+    },
+    {
+      "epoch": 0.6532663316582915,
+      "grad_norm": 1.4264318943023682,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.3102,
+      "step": 65
+    },
+    {
+      "epoch": 0.6633165829145728,
+      "grad_norm": 1.9855120182037354,
+      "learning_rate": 1.6449496416858284e-05,
+      "loss": 0.405,
+      "step": 66
+    },
+    {
+      "epoch": 0.6733668341708543,
+      "grad_norm": 0.8108851909637451,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 0.1325,
+      "step": 67
+    },
+    {
+      "epoch": 0.6834170854271356,
+      "grad_norm": 4.136630535125732,
+      "learning_rate": 1.4831583923104999e-05,
+      "loss": 0.968,
+      "step": 68
+    },
+    {
+      "epoch": 0.6934673366834171,
+      "grad_norm": 0.9361010789871216,
+      "learning_rate": 1.4040721330273062e-05,
+      "loss": 0.2457,
+      "step": 69
+    },
+    {
+      "epoch": 0.7035175879396985,
+      "grad_norm": 3.343045473098755,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 0.7569,
+      "step": 70
+    },
+    {
+      "epoch": 0.7135678391959799,
+      "grad_norm": 1.0723439455032349,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.1777,
+      "step": 71
+    },
+    {
+      "epoch": 0.7236180904522613,
+      "grad_norm": 1.3722829818725586,
+      "learning_rate": 1.175201839416988e-05,
+      "loss": 0.3186,
+      "step": 72
+    },
+    {
+      "epoch": 0.7336683417085427,
+      "grad_norm": 2.0538363456726074,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 0.7053,
+      "step": 73
+    },
+    {
+      "epoch": 0.7437185929648241,
+      "grad_norm": 1.7194602489471436,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 0.4186,
+      "step": 74
+    },
+    {
+      "epoch": 0.7537688442211056,
+      "grad_norm": 1.9144634008407593,
+      "learning_rate": 9.608463116858542e-06,
+      "loss": 0.4359,
+      "step": 75
+    },
+    {
+      "epoch": 0.7638190954773869,
+      "grad_norm": 1.8238540887832642,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.3578,
+      "step": 76
+    },
+    {
+      "epoch": 0.7738693467336684,
+      "grad_norm": 1.620219349861145,
+      "learning_rate": 8.271734841028553e-06,
+      "loss": 0.6803,
+      "step": 77
+    },
+    {
+      "epoch": 0.7839195979899497,
+      "grad_norm": 1.2236140966415405,
+      "learning_rate": 7.633540738525066e-06,
+      "loss": 0.285,
+      "step": 78
+    },
+    {
+      "epoch": 0.7939698492462312,
+      "grad_norm": 2.433211326599121,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 0.3922,
+      "step": 79
+    },
+    {
+      "epoch": 0.8040201005025126,
+      "grad_norm": 1.6254342794418335,
+      "learning_rate": 6.421379363065142e-06,
+      "loss": 0.6371,
+      "step": 80
+    },
+    {
+      "epoch": 0.8140703517587939,
+      "grad_norm": 0.95794677734375,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.4203,
+      "step": 81
+    },
+    {
+      "epoch": 0.8241206030150754,
+      "grad_norm": 2.8286194801330566,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 0.7793,
+      "step": 82
+    },
+    {
+      "epoch": 0.8341708542713567,
+      "grad_norm": 2.440025806427002,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.7263,
+      "step": 83
+    },
+    {
+      "epoch": 0.8442211055276382,
+      "grad_norm": 2.440507173538208,
+      "learning_rate": 4.274060686123959e-06,
+      "loss": 0.4484,
+      "step": 84
+    },
+    {
+      "epoch": 0.8542713567839196,
+      "grad_norm": 1.1934988498687744,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.2335,
+      "step": 85
+    },
+    {
+      "epoch": 0.864321608040201,
+      "grad_norm": 1.1017628908157349,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.3244,
+      "step": 86
+    },
+    {
+      "epoch": 0.8743718592964824,
+      "grad_norm": 1.3522121906280518,
+      "learning_rate": 2.9263101785268254e-06,
+      "loss": 0.3025,
+      "step": 87
+    },
+    {
+      "epoch": 0.8844221105527639,
+      "grad_norm": 1.3555244207382202,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 0.2563,
+      "step": 88
+    },
+    {
+      "epoch": 0.8944723618090452,
+      "grad_norm": 1.7802023887634277,
+      "learning_rate": 2.1613635589349756e-06,
+      "loss": 0.8291,
+      "step": 89
+    },
+    {
+      "epoch": 0.9045226130653267,
+      "grad_norm": 1.5431946516036987,
+      "learning_rate": 1.8204036358303173e-06,
+      "loss": 0.496,
+      "step": 90
+    },
+    {
+      "epoch": 0.914572864321608,
+      "grad_norm": 3.552048444747925,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.6235,
+      "step": 91
+    },
+    {
+      "epoch": 0.9246231155778895,
+      "grad_norm": 1.6633059978485107,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.3562,
+      "step": 92
+    },
+    {
+      "epoch": 0.9346733668341709,
+      "grad_norm": 1.6059434413909912,
+      "learning_rate": 9.684576015420278e-07,
+      "loss": 0.5505,
+      "step": 93
+    },
+    {
+      "epoch": 0.9447236180904522,
+      "grad_norm": 1.9522382020950317,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 0.3748,
+      "step": 94
+    },
+    {
+      "epoch": 0.9547738693467337,
+      "grad_norm": 3.010096788406372,
+      "learning_rate": 5.463099816548579e-07,
+      "loss": 0.6046,
+      "step": 95
+    },
+    {
+      "epoch": 0.964824120603015,
+      "grad_norm": 2.7505385875701904,
+      "learning_rate": 3.7980617469479953e-07,
+      "loss": 0.8919,
+      "step": 96
+    },
+    {
+      "epoch": 0.9748743718592965,
+      "grad_norm": 1.0584425926208496,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.3999,
+      "step": 97
+    },
+    {
+      "epoch": 0.9849246231155779,
+      "grad_norm": 1.4713913202285767,
+      "learning_rate": 1.3695261579316777e-07,
+      "loss": 0.4368,
+      "step": 98
+    },
+    {
+      "epoch": 0.9949748743718593,
+      "grad_norm": 1.4613982439041138,
+      "learning_rate": 6.089874350439506e-08,
+      "loss": 0.3824,
+      "step": 99
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7810527086257935,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 0.1018,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.45845267176628113,
+      "eval_runtime": 85.8607,
+      "eval_samples_per_second": 3.494,
+      "eval_steps_per_second": 1.747,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 33,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.867315250220237e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

exp0_baseline/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eea06f89c6a9f3345ae45b085ca42903e4044f47016fd3035bff387ef5774f26
+size 6033

exp0_baseline/checkpoint-33/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.17.1

exp0_baseline/checkpoint-33/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

exp0_baseline/checkpoint-33/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e22fb03e7642a23c3093ca2e1365d1d7ca5a08fc84f13f3860912ab1d8384c
+size 201378736

exp0_baseline/checkpoint-33/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5a7a46a4e2ed346bac46b5b5c1431282688ae8e0f2f57f7c74ff06985e2d109
+size 402982627

exp0_baseline/checkpoint-33/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4370640aed47e1cfe501e222405e6de0a6701dc2554814f30a0ec4610f4a16b
+size 14645

exp0_baseline/checkpoint-33/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b360cc37b95be8398ac4635eb61f23915865018f0c39c4789e480a08ead764a
+size 1465

exp0_baseline/checkpoint-33/trainer_state.json

@@ -0,0 +1,265 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3316582914572864,
+  "eval_steps": 100,
+  "global_step": 33,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010050251256281407,
+      "grad_norm": 1.144538164138794,
+      "learning_rate": 0.0,
+      "loss": 0.561,
+      "step": 1
+    },
+    {
+      "epoch": 0.020100502512562814,
+      "grad_norm": 1.1173577308654785,
+      "learning_rate": 5e-06,
+      "loss": 0.5438,
+      "step": 2
+    },
+    {
+      "epoch": 0.03015075376884422,
+      "grad_norm": 1.6941046714782715,
+      "learning_rate": 1e-05,
+      "loss": 0.5345,
+      "step": 3
+    },
+    {
+      "epoch": 0.04020100502512563,
+      "grad_norm": 2.2526638507843018,
+      "learning_rate": 1.5e-05,
+      "loss": 0.6601,
+      "step": 4
+    },
+    {
+      "epoch": 0.05025125628140704,
+      "grad_norm": 2.336232900619507,
+      "learning_rate": 2e-05,
+      "loss": 0.8386,
+      "step": 5
+    },
+    {
+      "epoch": 0.06030150753768844,
+      "grad_norm": 1.2247791290283203,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3448,
+      "step": 6
+    },
+    {
+      "epoch": 0.07035175879396985,
+      "grad_norm": 3.491952419281006,
+      "learning_rate": 3e-05,
+      "loss": 0.9107,
+      "step": 7
+    },
+    {
+      "epoch": 0.08040201005025126,
+      "grad_norm": 1.5285453796386719,
+      "learning_rate": 3.5e-05,
+      "loss": 0.5574,
+      "step": 8
+    },
+    {
+      "epoch": 0.09045226130653267,
+      "grad_norm": 1.9498869180679321,
+      "learning_rate": 4e-05,
+      "loss": 0.7468,
+      "step": 9
+    },
+    {
+      "epoch": 0.10050251256281408,
+      "grad_norm": 1.451749563217163,
+      "learning_rate": 4.5e-05,
+      "loss": 0.7601,
+      "step": 10
+    },
+    {
+      "epoch": 0.11055276381909548,
+      "grad_norm": 2.121290683746338,
+      "learning_rate": 5e-05,
+      "loss": 0.788,
+      "step": 11
+    },
+    {
+      "epoch": 0.12060301507537688,
+      "grad_norm": 1.173128604888916,
+      "learning_rate": 4.99847706754774e-05,
+      "loss": 0.4117,
+      "step": 12
+    },
+    {
+      "epoch": 0.1306532663316583,
+      "grad_norm": 1.4134124517440796,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.2099,
+      "step": 13
+    },
+    {
+      "epoch": 0.1407035175879397,
+      "grad_norm": 2.4718620777130127,
+      "learning_rate": 4.9863047384206835e-05,
+      "loss": 1.0762,
+      "step": 14
+    },
+    {
+      "epoch": 0.1507537688442211,
+      "grad_norm": 1.1293636560440063,
+      "learning_rate": 4.975670171853926e-05,
+      "loss": 0.338,
+      "step": 15
+    },
+    {
+      "epoch": 0.16080402010050251,
+      "grad_norm": 2.616136312484741,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 1.0328,
+      "step": 16
+    },
+    {
+      "epoch": 0.1708542713567839,
+      "grad_norm": 2.410461902618408,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.863,
+      "step": 17
+    },
+    {
+      "epoch": 0.18090452261306533,
+      "grad_norm": 2.1010797023773193,
+      "learning_rate": 4.925739315689991e-05,
+      "loss": 0.6364,
+      "step": 18
+    },
+    {
+      "epoch": 0.19095477386934673,
+      "grad_norm": 1.2987828254699707,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.4619,
+      "step": 19
+    },
+    {
+      "epoch": 0.20100502512562815,
+      "grad_norm": 1.2924538850784302,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.7118,
+      "step": 20
+    },
+    {
+      "epoch": 0.21105527638190955,
+      "grad_norm": 1.6322095394134521,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.936,
+      "step": 21
+    },
+    {
+      "epoch": 0.22110552763819097,
+      "grad_norm": 1.9164633750915527,
+      "learning_rate": 4.817959636416969e-05,
+      "loss": 0.8829,
+      "step": 22
+    },
+    {
+      "epoch": 0.23115577889447236,
+      "grad_norm": 1.2494964599609375,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.3653,
+      "step": 23
+    },
+    {
+      "epoch": 0.24120603015075376,
+      "grad_norm": 1.217826247215271,
+      "learning_rate": 4.7469851157479177e-05,
+      "loss": 0.4539,
+      "step": 24
+    },
+    {
+      "epoch": 0.25125628140703515,
+      "grad_norm": 3.2103142738342285,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.9621,
+      "step": 25
+    },
+    {
+      "epoch": 0.2613065326633166,
+      "grad_norm": 1.2653640508651733,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.448,
+      "step": 26
+    },
+    {
+      "epoch": 0.271356783919598,
+      "grad_norm": 0.9144423007965088,
+      "learning_rate": 4.620120240391065e-05,
+      "loss": 0.3957,
+      "step": 27
+    },
+    {
+      "epoch": 0.2814070351758794,
+      "grad_norm": 1.313241958618164,
+      "learning_rate": 4.572593931387604e-05,
+      "loss": 0.5468,
+      "step": 28
+    },
+    {
+      "epoch": 0.2914572864321608,
+      "grad_norm": 0.7544188499450684,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.185,
+      "step": 29
+    },
+    {
+      "epoch": 0.3015075376884422,
+      "grad_norm": 0.9644553661346436,
+      "learning_rate": 4.4700268840168045e-05,
+      "loss": 0.3864,
+      "step": 30
+    },
+    {
+      "epoch": 0.31155778894472363,
+      "grad_norm": 1.281360387802124,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.5255,
+      "step": 31
+    },
+    {
+      "epoch": 0.32160804020100503,
+      "grad_norm": 0.8318763375282288,
+      "learning_rate": 4.357862063693486e-05,
+      "loss": 0.392,
+      "step": 32
+    },
+    {
+      "epoch": 0.3316582914572864,
+      "grad_norm": 1.29972243309021,
+      "learning_rate": 4.2983495008466276e-05,
+      "loss": 0.6444,
+      "step": 33
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 33,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.277602042786611e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

exp0_baseline/checkpoint-33/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eea06f89c6a9f3345ae45b085ca42903e4044f47016fd3035bff387ef5774f26
+size 6033

exp0_baseline/checkpoint-66/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.17.1

exp0_baseline/checkpoint-66/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

exp0_baseline/checkpoint-66/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0346072ab4d7bbd9a9afd5b3644913d57eaf8efea013486bb1c3d484b0dad19e
+size 201378736

exp0_baseline/checkpoint-66/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:073c8f4dc8278d37d2225d3a83ee995296494429a086dfb5f194e151354389fa
+size 402982627

exp0_baseline/checkpoint-66/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe8399edd28ccffb95622add1833ade04c0b6c9ff41375a11d9923ffa06e322
+size 14645

exp0_baseline/checkpoint-66/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2fd2e1422c94e485a1f77b0038f8f0bc12efa27617f0f3dbfaf4b9a3fd1fd59
+size 1465

exp0_baseline/checkpoint-66/trainer_state.json

@@ -0,0 +1,496 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6633165829145728,
+  "eval_steps": 100,
+  "global_step": 66,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010050251256281407,
+      "grad_norm": 1.144538164138794,
+      "learning_rate": 0.0,
+      "loss": 0.561,
+      "step": 1
+    },
+    {
+      "epoch": 0.020100502512562814,
+      "grad_norm": 1.1173577308654785,
+      "learning_rate": 5e-06,
+      "loss": 0.5438,
+      "step": 2
+    },
+    {
+      "epoch": 0.03015075376884422,
+      "grad_norm": 1.6941046714782715,
+      "learning_rate": 1e-05,
+      "loss": 0.5345,
+      "step": 3
+    },
+    {
+      "epoch": 0.04020100502512563,
+      "grad_norm": 2.2526638507843018,
+      "learning_rate": 1.5e-05,
+      "loss": 0.6601,
+      "step": 4
+    },
+    {
+      "epoch": 0.05025125628140704,
+      "grad_norm": 2.336232900619507,
+      "learning_rate": 2e-05,
+      "loss": 0.8386,
+      "step": 5
+    },
+    {
+      "epoch": 0.06030150753768844,
+      "grad_norm": 1.2247791290283203,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3448,
+      "step": 6
+    },
+    {
+      "epoch": 0.07035175879396985,
+      "grad_norm": 3.491952419281006,
+      "learning_rate": 3e-05,
+      "loss": 0.9107,
+      "step": 7
+    },
+    {
+      "epoch": 0.08040201005025126,
+      "grad_norm": 1.5285453796386719,
+      "learning_rate": 3.5e-05,
+      "loss": 0.5574,
+      "step": 8
+    },
+    {
+      "epoch": 0.09045226130653267,
+      "grad_norm": 1.9498869180679321,
+      "learning_rate": 4e-05,
+      "loss": 0.7468,
+      "step": 9
+    },
+    {
+      "epoch": 0.10050251256281408,
+      "grad_norm": 1.451749563217163,
+      "learning_rate": 4.5e-05,
+      "loss": 0.7601,
+      "step": 10
+    },
+    {
+      "epoch": 0.11055276381909548,
+      "grad_norm": 2.121290683746338,
+      "learning_rate": 5e-05,
+      "loss": 0.788,
+      "step": 11
+    },
+    {
+      "epoch": 0.12060301507537688,
+      "grad_norm": 1.173128604888916,
+      "learning_rate": 4.99847706754774e-05,
+      "loss": 0.4117,
+      "step": 12
+    },
+    {
+      "epoch": 0.1306532663316583,
+      "grad_norm": 1.4134124517440796,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.2099,
+      "step": 13
+    },
+    {
+      "epoch": 0.1407035175879397,
+      "grad_norm": 2.4718620777130127,
+      "learning_rate": 4.9863047384206835e-05,
+      "loss": 1.0762,
+      "step": 14
+    },
+    {
+      "epoch": 0.1507537688442211,
+      "grad_norm": 1.1293636560440063,
+      "learning_rate": 4.975670171853926e-05,
+      "loss": 0.338,
+      "step": 15
+    },
+    {
+      "epoch": 0.16080402010050251,
+      "grad_norm": 2.616136312484741,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 1.0328,
+      "step": 16
+    },
+    {
+      "epoch": 0.1708542713567839,
+      "grad_norm": 2.410461902618408,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.863,
+      "step": 17
+    },
+    {
+      "epoch": 0.18090452261306533,
+      "grad_norm": 2.1010797023773193,
+      "learning_rate": 4.925739315689991e-05,
+      "loss": 0.6364,
+      "step": 18
+    },
+    {
+      "epoch": 0.19095477386934673,
+      "grad_norm": 1.2987828254699707,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.4619,
+      "step": 19
+    },
+    {
+      "epoch": 0.20100502512562815,
+      "grad_norm": 1.2924538850784302,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.7118,
+      "step": 20
+    },
+    {
+      "epoch": 0.21105527638190955,
+      "grad_norm": 1.6322095394134521,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.936,
+      "step": 21
+    },
+    {
+      "epoch": 0.22110552763819097,
+      "grad_norm": 1.9164633750915527,
+      "learning_rate": 4.817959636416969e-05,
+      "loss": 0.8829,
+      "step": 22
+    },
+    {
+      "epoch": 0.23115577889447236,
+      "grad_norm": 1.2494964599609375,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.3653,
+      "step": 23
+    },
+    {
+      "epoch": 0.24120603015075376,
+      "grad_norm": 1.217826247215271,
+      "learning_rate": 4.7469851157479177e-05,
+      "loss": 0.4539,
+      "step": 24
+    },
+    {
+      "epoch": 0.25125628140703515,
+      "grad_norm": 3.2103142738342285,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.9621,
+      "step": 25
+    },
+    {
+      "epoch": 0.2613065326633166,
+      "grad_norm": 1.2653640508651733,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.448,
+      "step": 26
+    },
+    {
+      "epoch": 0.271356783919598,
+      "grad_norm": 0.9144423007965088,
+      "learning_rate": 4.620120240391065e-05,
+      "loss": 0.3957,
+      "step": 27
+    },
+    {
+      "epoch": 0.2814070351758794,
+      "grad_norm": 1.313241958618164,
+      "learning_rate": 4.572593931387604e-05,
+      "loss": 0.5468,
+      "step": 28
+    },
+    {
+      "epoch": 0.2914572864321608,
+      "grad_norm": 0.7544188499450684,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.185,
+      "step": 29
+    },
+    {
+      "epoch": 0.3015075376884422,
+      "grad_norm": 0.9644553661346436,
+      "learning_rate": 4.4700268840168045e-05,
+      "loss": 0.3864,
+      "step": 30
+    },
+    {
+      "epoch": 0.31155778894472363,
+      "grad_norm": 1.281360387802124,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.5255,
+      "step": 31
+    },
+    {
+      "epoch": 0.32160804020100503,
+      "grad_norm": 0.8318763375282288,
+      "learning_rate": 4.357862063693486e-05,
+      "loss": 0.392,
+      "step": 32
+    },
+    {
+      "epoch": 0.3316582914572864,
+      "grad_norm": 1.29972243309021,
+      "learning_rate": 4.2983495008466276e-05,
+      "loss": 0.6444,
+      "step": 33
+    },
+    {
+      "epoch": 0.3417085427135678,
+      "grad_norm": 1.3421469926834106,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 0.3876,
+      "step": 34
+    },
+    {
+      "epoch": 0.35175879396984927,
+      "grad_norm": 0.9718002676963806,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.5414,
+      "step": 35
+    },
+    {
+      "epoch": 0.36180904522613067,
+      "grad_norm": 0.9774896502494812,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 0.4928,
+      "step": 36
+    },
+    {
+      "epoch": 0.37185929648241206,
+      "grad_norm": 3.244431257247925,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 1.0665,
+      "step": 37
+    },
+    {
+      "epoch": 0.38190954773869346,
+      "grad_norm": 0.9365755319595337,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 0.3107,
+      "step": 38
+    },
+    {
+      "epoch": 0.39195979899497485,
+      "grad_norm": 1.4368454217910767,
+      "learning_rate": 3.897982258676867e-05,
+      "loss": 0.4084,
+      "step": 39
+    },
+    {
+      "epoch": 0.4020100502512563,
+      "grad_norm": 2.354626417160034,
+      "learning_rate": 3.824798160583012e-05,
+      "loss": 0.4833,
+      "step": 40
+    },
+    {
+      "epoch": 0.4120603015075377,
+      "grad_norm": 2.426787853240967,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.548,
+      "step": 41
+    },
+    {
+      "epoch": 0.4221105527638191,
+      "grad_norm": 1.3904081583023071,
+      "learning_rate": 3.673678906964727e-05,
+      "loss": 0.847,
+      "step": 42
+    },
+    {
+      "epoch": 0.4321608040201005,
+      "grad_norm": 0.8043186664581299,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 0.3826,
+      "step": 43
+    },
+    {
+      "epoch": 0.44221105527638194,
+      "grad_norm": 0.9501510858535767,
+      "learning_rate": 3.516841607689501e-05,
+      "loss": 0.2336,
+      "step": 44
+    },
+    {
+      "epoch": 0.45226130653266333,
+      "grad_norm": 2.477350950241089,
+      "learning_rate": 3.436516483539781e-05,
+      "loss": 0.8067,
+      "step": 45
+    },
+    {
+      "epoch": 0.4623115577889447,
+      "grad_norm": 1.3030426502227783,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.4237,
+      "step": 46
+    },
+    {
+      "epoch": 0.4723618090452261,
+      "grad_norm": 2.6159799098968506,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.5104,
+      "step": 47
+    },
+    {
+      "epoch": 0.4824120603015075,
+      "grad_norm": 1.256778597831726,
+      "learning_rate": 3.1890933895424976e-05,
+      "loss": 0.235,
+      "step": 48
+    },
+    {
+      "epoch": 0.49246231155778897,
+      "grad_norm": 2.076829195022583,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 0.5265,
+      "step": 49
+    },
+    {
+      "epoch": 0.5025125628140703,
+      "grad_norm": 1.3327422142028809,
+      "learning_rate": 3.0197792270443982e-05,
+      "loss": 0.5636,
+      "step": 50
+    },
+    {
+      "epoch": 0.5125628140703518,
+      "grad_norm": 1.7859450578689575,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.67,
+      "step": 51
+    },
+    {
+      "epoch": 0.5226130653266332,
+      "grad_norm": 1.3924661874771118,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 0.6816,
+      "step": 52
+    },
+    {
+      "epoch": 0.5326633165829145,
+      "grad_norm": 1.4186939001083374,
+      "learning_rate": 2.761321158169134e-05,
+      "loss": 0.3969,
+      "step": 53
+    },
+    {
+      "epoch": 0.542713567839196,
+      "grad_norm": 2.0062601566314697,
+      "learning_rate": 2.674391184360313e-05,
+      "loss": 0.3101,
+      "step": 54
+    },
+    {
+      "epoch": 0.5527638190954773,
+      "grad_norm": 1.4015522003173828,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 0.2104,
+      "step": 55
+    },
+    {
+      "epoch": 0.5628140703517588,
+      "grad_norm": 1.5075968503952026,
+      "learning_rate": 2.5e-05,
+      "loss": 0.5247,
+      "step": 56
+    },
+    {
+      "epoch": 0.5728643216080402,
+      "grad_norm": 3.6213722229003906,
+      "learning_rate": 2.4127512582437485e-05,
+      "loss": 0.8403,
+      "step": 57
+    },
+    {
+      "epoch": 0.5829145728643216,
+      "grad_norm": 5.086165904998779,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 0.9748,
+      "step": 58
+    },
+    {
+      "epoch": 0.592964824120603,
+      "grad_norm": 0.8291557431221008,
+      "learning_rate": 2.238678841830867e-05,
+      "loss": 0.1264,
+      "step": 59
+    },
+    {
+      "epoch": 0.6030150753768844,
+      "grad_norm": 6.901468753814697,
+      "learning_rate": 2.1520672475998373e-05,
+      "loss": 1.7948,
+      "step": 60
+    },
+    {
+      "epoch": 0.6130653266331658,
+      "grad_norm": 1.2166105508804321,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.3152,
+      "step": 61
+    },
+    {
+      "epoch": 0.6231155778894473,
+      "grad_norm": 4.400286674499512,
+      "learning_rate": 1.980220772955602e-05,
+      "loss": 1.6227,
+      "step": 62
+    },
+    {
+      "epoch": 0.6331658291457286,
+      "grad_norm": 2.3584349155426025,
+      "learning_rate": 1.895195261000831e-05,
+      "loss": 0.6485,
+      "step": 63
+    },
+    {
+      "epoch": 0.6432160804020101,
+      "grad_norm": 3.535404682159424,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 1.1718,
+      "step": 64
+    },
+    {
+      "epoch": 0.6532663316582915,
+      "grad_norm": 1.4264318943023682,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.3102,
+      "step": 65
+    },
+    {
+      "epoch": 0.6633165829145728,
+      "grad_norm": 1.9855120182037354,
+      "learning_rate": 1.6449496416858284e-05,
+      "loss": 0.405,
+      "step": 66
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 33,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.555204085573222e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

exp0_baseline/checkpoint-66/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eea06f89c6a9f3345ae45b085ca42903e4044f47016fd3035bff387ef5774f26
+size 6033

exp0_baseline/checkpoint-99/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.17.1

exp0_baseline/checkpoint-99/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

exp0_baseline/checkpoint-99/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea1a4945e24e24fe59703e6682e385bd4872796f62a1512b92dbd3c243a4db8
+size 201378736

exp0_baseline/checkpoint-99/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48cffc2fd316bc098cfc6ef453f9b26c302bfcc79ef1d3863ad61734bb3d2170
+size 402982627

exp0_baseline/checkpoint-99/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b293338027ef39107c758bc2300d51015b6a878a9f0e09fe1822d419dcbb163e
+size 14645

exp0_baseline/checkpoint-99/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba8e76678603d3d1769a2ed6315c7bfd1edb3a261c537a3ff7c1689618cf725
+size 1465

exp0_baseline/checkpoint-99/trainer_state.json

@@ -0,0 +1,727 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9949748743718593,
+  "eval_steps": 100,
+  "global_step": 99,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010050251256281407,
+      "grad_norm": 1.144538164138794,
+      "learning_rate": 0.0,
+      "loss": 0.561,
+      "step": 1
+    },
+    {
+      "epoch": 0.020100502512562814,
+      "grad_norm": 1.1173577308654785,
+      "learning_rate": 5e-06,
+      "loss": 0.5438,
+      "step": 2
+    },
+    {
+      "epoch": 0.03015075376884422,
+      "grad_norm": 1.6941046714782715,
+      "learning_rate": 1e-05,
+      "loss": 0.5345,
+      "step": 3
+    },
+    {
+      "epoch": 0.04020100502512563,
+      "grad_norm": 2.2526638507843018,
+      "learning_rate": 1.5e-05,
+      "loss": 0.6601,
+      "step": 4
+    },
+    {
+      "epoch": 0.05025125628140704,
+      "grad_norm": 2.336232900619507,
+      "learning_rate": 2e-05,
+      "loss": 0.8386,
+      "step": 5
+    },
+    {
+      "epoch": 0.06030150753768844,
+      "grad_norm": 1.2247791290283203,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3448,
+      "step": 6
+    },
+    {
+      "epoch": 0.07035175879396985,
+      "grad_norm": 3.491952419281006,
+      "learning_rate": 3e-05,
+      "loss": 0.9107,
+      "step": 7
+    },
+    {
+      "epoch": 0.08040201005025126,
+      "grad_norm": 1.5285453796386719,
+      "learning_rate": 3.5e-05,
+      "loss": 0.5574,
+      "step": 8
+    },
+    {
+      "epoch": 0.09045226130653267,
+      "grad_norm": 1.9498869180679321,
+      "learning_rate": 4e-05,
+      "loss": 0.7468,
+      "step": 9
+    },
+    {
+      "epoch": 0.10050251256281408,
+      "grad_norm": 1.451749563217163,
+      "learning_rate": 4.5e-05,
+      "loss": 0.7601,
+      "step": 10
+    },
+    {
+      "epoch": 0.11055276381909548,
+      "grad_norm": 2.121290683746338,
+      "learning_rate": 5e-05,
+      "loss": 0.788,
+      "step": 11
+    },
+    {
+      "epoch": 0.12060301507537688,
+      "grad_norm": 1.173128604888916,
+      "learning_rate": 4.99847706754774e-05,
+      "loss": 0.4117,
+      "step": 12
+    },
+    {
+      "epoch": 0.1306532663316583,
+      "grad_norm": 1.4134124517440796,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.2099,
+      "step": 13
+    },
+    {
+      "epoch": 0.1407035175879397,
+      "grad_norm": 2.4718620777130127,
+      "learning_rate": 4.9863047384206835e-05,
+      "loss": 1.0762,
+      "step": 14
+    },
+    {
+      "epoch": 0.1507537688442211,
+      "grad_norm": 1.1293636560440063,
+      "learning_rate": 4.975670171853926e-05,
+      "loss": 0.338,
+      "step": 15
+    },
+    {
+      "epoch": 0.16080402010050251,
+      "grad_norm": 2.616136312484741,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 1.0328,
+      "step": 16
+    },
+    {
+      "epoch": 0.1708542713567839,
+      "grad_norm": 2.410461902618408,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.863,
+      "step": 17
+    },
+    {
+      "epoch": 0.18090452261306533,
+      "grad_norm": 2.1010797023773193,
+      "learning_rate": 4.925739315689991e-05,
+      "loss": 0.6364,
+      "step": 18
+    },
+    {
+      "epoch": 0.19095477386934673,
+      "grad_norm": 1.2987828254699707,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.4619,
+      "step": 19
+    },
+    {
+      "epoch": 0.20100502512562815,
+      "grad_norm": 1.2924538850784302,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.7118,
+      "step": 20
+    },
+    {
+      "epoch": 0.21105527638190955,
+      "grad_norm": 1.6322095394134521,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.936,
+      "step": 21
+    },
+    {
+      "epoch": 0.22110552763819097,
+      "grad_norm": 1.9164633750915527,
+      "learning_rate": 4.817959636416969e-05,
+      "loss": 0.8829,
+      "step": 22
+    },
+    {
+      "epoch": 0.23115577889447236,
+      "grad_norm": 1.2494964599609375,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.3653,
+      "step": 23
+    },
+    {
+      "epoch": 0.24120603015075376,
+      "grad_norm": 1.217826247215271,
+      "learning_rate": 4.7469851157479177e-05,
+      "loss": 0.4539,
+      "step": 24
+    },
+    {
+      "epoch": 0.25125628140703515,
+      "grad_norm": 3.2103142738342285,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.9621,
+      "step": 25
+    },
+    {
+      "epoch": 0.2613065326633166,
+      "grad_norm": 1.2653640508651733,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.448,
+      "step": 26
+    },
+    {
+      "epoch": 0.271356783919598,
+      "grad_norm": 0.9144423007965088,
+      "learning_rate": 4.620120240391065e-05,
+      "loss": 0.3957,
+      "step": 27
+    },
+    {
+      "epoch": 0.2814070351758794,
+      "grad_norm": 1.313241958618164,
+      "learning_rate": 4.572593931387604e-05,
+      "loss": 0.5468,
+      "step": 28
+    },
+    {
+      "epoch": 0.2914572864321608,
+      "grad_norm": 0.7544188499450684,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.185,
+      "step": 29
+    },
+    {
+      "epoch": 0.3015075376884422,
+      "grad_norm": 0.9644553661346436,
+      "learning_rate": 4.4700268840168045e-05,
+      "loss": 0.3864,
+      "step": 30
+    },
+    {
+      "epoch": 0.31155778894472363,
+      "grad_norm": 1.281360387802124,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.5255,
+      "step": 31
+    },
+    {
+      "epoch": 0.32160804020100503,
+      "grad_norm": 0.8318763375282288,
+      "learning_rate": 4.357862063693486e-05,
+      "loss": 0.392,
+      "step": 32
+    },
+    {
+      "epoch": 0.3316582914572864,
+      "grad_norm": 1.29972243309021,
+      "learning_rate": 4.2983495008466276e-05,
+      "loss": 0.6444,
+      "step": 33
+    },
+    {
+      "epoch": 0.3417085427135678,
+      "grad_norm": 1.3421469926834106,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 0.3876,
+      "step": 34
+    },
+    {
+      "epoch": 0.35175879396984927,
+      "grad_norm": 0.9718002676963806,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.5414,
+      "step": 35
+    },
+    {
+      "epoch": 0.36180904522613067,
+      "grad_norm": 0.9774896502494812,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 0.4928,
+      "step": 36
+    },
+    {
+      "epoch": 0.37185929648241206,
+      "grad_norm": 3.244431257247925,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 1.0665,
+      "step": 37
+    },
+    {
+      "epoch": 0.38190954773869346,
+      "grad_norm": 0.9365755319595337,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 0.3107,
+      "step": 38
+    },
+    {
+      "epoch": 0.39195979899497485,
+      "grad_norm": 1.4368454217910767,
+      "learning_rate": 3.897982258676867e-05,
+      "loss": 0.4084,
+      "step": 39
+    },
+    {
+      "epoch": 0.4020100502512563,
+      "grad_norm": 2.354626417160034,
+      "learning_rate": 3.824798160583012e-05,
+      "loss": 0.4833,
+      "step": 40
+    },
+    {
+      "epoch": 0.4120603015075377,
+      "grad_norm": 2.426787853240967,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.548,
+      "step": 41
+    },
+    {
+      "epoch": 0.4221105527638191,
+      "grad_norm": 1.3904081583023071,
+      "learning_rate": 3.673678906964727e-05,
+      "loss": 0.847,
+      "step": 42
+    },
+    {
+      "epoch": 0.4321608040201005,
+      "grad_norm": 0.8043186664581299,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 0.3826,
+      "step": 43
+    },
+    {
+      "epoch": 0.44221105527638194,
+      "grad_norm": 0.9501510858535767,
+      "learning_rate": 3.516841607689501e-05,
+      "loss": 0.2336,
+      "step": 44
+    },
+    {
+      "epoch": 0.45226130653266333,
+      "grad_norm": 2.477350950241089,
+      "learning_rate": 3.436516483539781e-05,
+      "loss": 0.8067,
+      "step": 45
+    },
+    {
+      "epoch": 0.4623115577889447,
+      "grad_norm": 1.3030426502227783,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.4237,
+      "step": 46
+    },
+    {
+      "epoch": 0.4723618090452261,
+      "grad_norm": 2.6159799098968506,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.5104,
+      "step": 47
+    },
+    {
+      "epoch": 0.4824120603015075,
+      "grad_norm": 1.256778597831726,
+      "learning_rate": 3.1890933895424976e-05,
+      "loss": 0.235,
+      "step": 48
+    },
+    {
+      "epoch": 0.49246231155778897,
+      "grad_norm": 2.076829195022583,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 0.5265,
+      "step": 49
+    },
+    {
+      "epoch": 0.5025125628140703,
+      "grad_norm": 1.3327422142028809,
+      "learning_rate": 3.0197792270443982e-05,
+      "loss": 0.5636,
+      "step": 50
+    },
+    {
+      "epoch": 0.5125628140703518,
+      "grad_norm": 1.7859450578689575,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.67,
+      "step": 51
+    },
+    {
+      "epoch": 0.5226130653266332,
+      "grad_norm": 1.3924661874771118,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 0.6816,
+      "step": 52
+    },
+    {
+      "epoch": 0.5326633165829145,
+      "grad_norm": 1.4186939001083374,
+      "learning_rate": 2.761321158169134e-05,
+      "loss": 0.3969,
+      "step": 53
+    },
+    {
+      "epoch": 0.542713567839196,
+      "grad_norm": 2.0062601566314697,
+      "learning_rate": 2.674391184360313e-05,
+      "loss": 0.3101,
+      "step": 54
+    },
+    {
+      "epoch": 0.5527638190954773,
+      "grad_norm": 1.4015522003173828,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 0.2104,
+      "step": 55
+    },
+    {
+      "epoch": 0.5628140703517588,
+      "grad_norm": 1.5075968503952026,
+      "learning_rate": 2.5e-05,
+      "loss": 0.5247,
+      "step": 56
+    },
+    {
+      "epoch": 0.5728643216080402,
+      "grad_norm": 3.6213722229003906,
+      "learning_rate": 2.4127512582437485e-05,
+      "loss": 0.8403,
+      "step": 57
+    },
+    {
+      "epoch": 0.5829145728643216,
+      "grad_norm": 5.086165904998779,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 0.9748,
+      "step": 58
+    },
+    {
+      "epoch": 0.592964824120603,
+      "grad_norm": 0.8291557431221008,
+      "learning_rate": 2.238678841830867e-05,
+      "loss": 0.1264,
+      "step": 59
+    },
+    {
+      "epoch": 0.6030150753768844,
+      "grad_norm": 6.901468753814697,
+      "learning_rate": 2.1520672475998373e-05,
+      "loss": 1.7948,
+      "step": 60
+    },
+    {
+      "epoch": 0.6130653266331658,
+      "grad_norm": 1.2166105508804321,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.3152,
+      "step": 61
+    },
+    {
+      "epoch": 0.6231155778894473,
+      "grad_norm": 4.400286674499512,
+      "learning_rate": 1.980220772955602e-05,
+      "loss": 1.6227,
+      "step": 62
+    },
+    {
+      "epoch": 0.6331658291457286,
+      "grad_norm": 2.3584349155426025,
+      "learning_rate": 1.895195261000831e-05,
+      "loss": 0.6485,
+      "step": 63
+    },
+    {
+      "epoch": 0.6432160804020101,
+      "grad_norm": 3.535404682159424,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 1.1718,
+      "step": 64
+    },
+    {
+      "epoch": 0.6532663316582915,
+      "grad_norm": 1.4264318943023682,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.3102,
+      "step": 65
+    },
+    {
+      "epoch": 0.6633165829145728,
+      "grad_norm": 1.9855120182037354,
+      "learning_rate": 1.6449496416858284e-05,
+      "loss": 0.405,
+      "step": 66
+    },
+    {
+      "epoch": 0.6733668341708543,
+      "grad_norm": 0.8108851909637451,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 0.1325,
+      "step": 67
+    },
+    {
+      "epoch": 0.6834170854271356,
+      "grad_norm": 4.136630535125732,
+      "learning_rate": 1.4831583923104999e-05,
+      "loss": 0.968,
+      "step": 68
+    },
+    {
+      "epoch": 0.6934673366834171,
+      "grad_norm": 0.9361010789871216,
+      "learning_rate": 1.4040721330273062e-05,
+      "loss": 0.2457,
+      "step": 69
+    },
+    {
+      "epoch": 0.7035175879396985,
+      "grad_norm": 3.343045473098755,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 0.7569,
+      "step": 70
+    },
+    {
+      "epoch": 0.7135678391959799,
+      "grad_norm": 1.0723439455032349,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.1777,
+      "step": 71
+    },
+    {
+      "epoch": 0.7236180904522613,
+      "grad_norm": 1.3722829818725586,
+      "learning_rate": 1.175201839416988e-05,
+      "loss": 0.3186,
+      "step": 72
+    },
+    {
+      "epoch": 0.7336683417085427,
+      "grad_norm": 2.0538363456726074,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 0.7053,
+      "step": 73
+    },
+    {
+      "epoch": 0.7437185929648241,
+      "grad_norm": 1.7194602489471436,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 0.4186,
+      "step": 74
+    },
+    {
+      "epoch": 0.7537688442211056,
+      "grad_norm": 1.9144634008407593,
+      "learning_rate": 9.608463116858542e-06,
+      "loss": 0.4359,
+      "step": 75
+    },
+    {
+      "epoch": 0.7638190954773869,
+      "grad_norm": 1.8238540887832642,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.3578,
+      "step": 76
+    },
+    {
+      "epoch": 0.7738693467336684,
+      "grad_norm": 1.620219349861145,
+      "learning_rate": 8.271734841028553e-06,
+      "loss": 0.6803,
+      "step": 77
+    },
+    {
+      "epoch": 0.7839195979899497,
+      "grad_norm": 1.2236140966415405,
+      "learning_rate": 7.633540738525066e-06,
+      "loss": 0.285,
+      "step": 78
+    },
+    {
+      "epoch": 0.7939698492462312,
+      "grad_norm": 2.433211326599121,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 0.3922,
+      "step": 79
+    },
+    {
+      "epoch": 0.8040201005025126,
+      "grad_norm": 1.6254342794418335,
+      "learning_rate": 6.421379363065142e-06,
+      "loss": 0.6371,
+      "step": 80
+    },
+    {
+      "epoch": 0.8140703517587939,
+      "grad_norm": 0.95794677734375,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.4203,
+      "step": 81
+    },
+    {
+      "epoch": 0.8241206030150754,
+      "grad_norm": 2.8286194801330566,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 0.7793,
+      "step": 82
+    },
+    {
+      "epoch": 0.8341708542713567,
+      "grad_norm": 2.440025806427002,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.7263,
+      "step": 83
+    },
+    {
+      "epoch": 0.8442211055276382,
+      "grad_norm": 2.440507173538208,
+      "learning_rate": 4.274060686123959e-06,
+      "loss": 0.4484,
+      "step": 84
+    },
+    {
+      "epoch": 0.8542713567839196,
+      "grad_norm": 1.1934988498687744,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.2335,
+      "step": 85
+    },
+    {
+      "epoch": 0.864321608040201,
+      "grad_norm": 1.1017628908157349,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.3244,
+      "step": 86
+    },
+    {
+      "epoch": 0.8743718592964824,
+      "grad_norm": 1.3522121906280518,
+      "learning_rate": 2.9263101785268254e-06,
+      "loss": 0.3025,
+      "step": 87
+    },
+    {
+      "epoch": 0.8844221105527639,
+      "grad_norm": 1.3555244207382202,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 0.2563,
+      "step": 88
+    },
+    {
+      "epoch": 0.8944723618090452,
+      "grad_norm": 1.7802023887634277,
+      "learning_rate": 2.1613635589349756e-06,
+      "loss": 0.8291,
+      "step": 89
+    },
+    {
+      "epoch": 0.9045226130653267,
+      "grad_norm": 1.5431946516036987,
+      "learning_rate": 1.8204036358303173e-06,
+      "loss": 0.496,
+      "step": 90
+    },
+    {
+      "epoch": 0.914572864321608,
+      "grad_norm": 3.552048444747925,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.6235,
+      "step": 91
+    },
+    {
+      "epoch": 0.9246231155778895,
+      "grad_norm": 1.6633059978485107,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.3562,
+      "step": 92
+    },
+    {
+      "epoch": 0.9346733668341709,
+      "grad_norm": 1.6059434413909912,
+      "learning_rate": 9.684576015420278e-07,
+      "loss": 0.5505,
+      "step": 93
+    },
+    {
+      "epoch": 0.9447236180904522,
+      "grad_norm": 1.9522382020950317,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 0.3748,
+      "step": 94
+    },
+    {
+      "epoch": 0.9547738693467337,
+      "grad_norm": 3.010096788406372,
+      "learning_rate": 5.463099816548579e-07,
+      "loss": 0.6046,
+      "step": 95
+    },
+    {
+      "epoch": 0.964824120603015,
+      "grad_norm": 2.7505385875701904,
+      "learning_rate": 3.7980617469479953e-07,
+      "loss": 0.8919,
+      "step": 96
+    },
+    {
+      "epoch": 0.9748743718592965,
+      "grad_norm": 1.0584425926208496,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.3999,
+      "step": 97
+    },
+    {
+      "epoch": 0.9849246231155779,
+      "grad_norm": 1.4713913202285767,
+      "learning_rate": 1.3695261579316777e-07,
+      "loss": 0.4368,
+      "step": 98
+    },
+    {
+      "epoch": 0.9949748743718593,
+      "grad_norm": 1.4613982439041138,
+      "learning_rate": 6.089874350439506e-08,
+      "loss": 0.3824,
+      "step": 99
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 33,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.832806128359834e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

exp0_baseline/checkpoint-99/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eea06f89c6a9f3345ae45b085ca42903e4044f47016fd3035bff387ef5774f26
+size 6033

exp0_baseline/final_model/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.17.1

exp0_baseline/final_model/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

exp0_baseline/final_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8209e0cbb700204af15187718e31808cf6e3166b8065c4c05ac7864dc693371
+size 201378736

exp0_baseline/final_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eea06f89c6a9f3345ae45b085ca42903e4044f47016fd3035bff387ef5774f26
+size 6033

exp1_signal_c_100/checkpoint-100/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.17.1

exp1_signal_c_100/checkpoint-100/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

exp1_signal_c_100/checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d06d5d1fb081e5847792d8a5a3630488d31de5ea5b5f3835e79c4ec1c3f5e65
+size 201378736

exp1_signal_c_100/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a81531c61562ce6bf2f54003446cd3bb82829259c65125b09eb2259404ce87b
+size 402982627

exp1_signal_c_100/checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b92ede016a8dc313d233f2927862e909d5717a49b27265ddd87beb7b3aab3357
+size 14645

exp1_signal_c_100/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c4e44404b58ce3af1b46c3d4a85a59edbbc386f340c476e894715a1199e1aed
+size 1465