Upload folder using huggingface_hub

.ipynb_checkpoints/training_summary_iam-checkpoint.json

@@ -0,0 +1,19 @@
+{
+  "service": "IAM",
+  "epochs": 3.0,
+  "global_step": 2025,
+  "train_runtime_sec": 10042.064852237701,
+  "train_samples": 5400,
+  "eval_samples": 600,
+  "used_bitsandbytes": false,
+  "eval_metrics": {
+    "eval_loss": 0.06809257715940475,
+    "eval_runtime": 106.1734,
+    "eval_samples_per_second": 5.651,
+    "eval_steps_per_second": 0.706,
+    "eval_entropy": 0.06766340777277946,
+    "eval_num_tokens": 16535475.0,
+    "eval_mean_token_accuracy": 0.9819109582901001,
+    "epoch": 3.0
+  }
+}

README.md

@@ -0,0 +1,62 @@
+---
+base_model: bigcode/starcoder2-7b
+library_name: peft
+model_name: starcoder2_7b_lora_iam
+tags:
+- base_model:adapter:bigcode/starcoder2-7b
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for starcoder2_7b_lora_iam
+
+This model is a fine-tuned version of [bigcode/starcoder2-7b](https://huggingface.co/bigcode/starcoder2-7b).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.0
+- TRL: 0.25.1
+- Transformers: 4.57.3
+- Pytorch: 2.8.0+cu128
+- Datasets: 4.4.1
+- Tokenizers: 0.22.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigcode/starcoder2-7b",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f9a9fbadd0b35342e1993f10bde6b04ed43f8e16cbc6027b05d97c66c518dc6
+size 58754616

checkpoint-1000/README.md

@@ -0,0 +1,209 @@
+---
+base_model: bigcode/starcoder2-7b
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:bigcode/starcoder2-7b
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.0

checkpoint-1000/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigcode/starcoder2-7b",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e3cb8d4fbaa7a095b55b5c135ac12b4522be09f2a6d9e78aa916a9986ea5dd4
+size 58754616

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caae63283d10a16eea1cfb241a9775608cd96a6b92aeb1e6a2c8a4d61d76fff9
+size 117660107

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:405bb81709f17b3ac4eb03c3d986bf79a4c2b03d08f1d49fe2f55aec79a559d8
+size 14645

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b06201d9403a12d93447a0c39b7483b78fdd17e56d2db9cc8f99c3ba8cf744f1
+size 1465

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,63 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,357 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<code_to_intermediate>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<intermediate_to_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<pr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<pr_status>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<pr_is_merged>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<pr_base>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "<pr_file>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "23": {
+      "content": "<pr_base_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24": {
+      "content": "<pr_diff>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25": {
+      "content": "<pr_diff_hunk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "26": {
+      "content": "<pr_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "27": {
+      "content": "<pr_event_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28": {
+      "content": "<pr_review>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29": {
+      "content": "<pr_review_state>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "<pr_review_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31": {
+      "content": "<pr_in_reply_to_review_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<pr_in_reply_to_comment_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "33": {
+      "content": "<pr_diff_hunk_comment_line>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "<NAME>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "<EMAIL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "<KEY>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "<PASSWORD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,234 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4814814814814814,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.805763495862484,
+      "epoch": 0.07407407407407407,
+      "grad_norm": 0.6806204319000244,
+      "learning_rate": 8.032786885245902e-05,
+      "loss": 1.5484,
+      "mean_token_accuracy": 0.6665007689595223,
+      "num_tokens": 408149.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.41144788280129435,
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.38455039262771606,
+      "learning_rate": 9.990765991730485e-05,
+      "loss": 0.3321,
+      "mean_token_accuracy": 0.9129975068569184,
+      "num_tokens": 816230.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.16323913749307395,
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.29704713821411133,
+      "learning_rate": 9.950545603782162e-05,
+      "loss": 0.1447,
+      "mean_token_accuracy": 0.9618216013908386,
+      "num_tokens": 1224471.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.1175146003998816,
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.35487300157546997,
+      "learning_rate": 9.878674879048427e-05,
+      "loss": 0.1071,
+      "mean_token_accuracy": 0.9733556269109249,
+      "num_tokens": 1632497.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.1009879010822624,
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.17419321835041046,
+      "learning_rate": 9.775613308830824e-05,
+      "loss": 0.0925,
+      "mean_token_accuracy": 0.9769376286864281,
+      "num_tokens": 2041392.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.09154447751119733,
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.20543242990970612,
+      "learning_rate": 9.642019796948866e-05,
+      "loss": 0.0836,
+      "mean_token_accuracy": 0.9787026332318782,
+      "num_tokens": 2450311.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.08632300381548702,
+      "epoch": 0.5185185185185185,
+      "grad_norm": 0.17172595858573914,
+      "learning_rate": 9.478748447168449e-05,
+      "loss": 0.0812,
+      "mean_token_accuracy": 0.9789653661847114,
+      "num_tokens": 2858744.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.08412999271415174,
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.1447569578886032,
+      "learning_rate": 9.28684310265789e-05,
+      "loss": 0.0805,
+      "mean_token_accuracy": 0.9786932443082332,
+      "num_tokens": 3265542.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.08065679710358381,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.19630704820156097,
+      "learning_rate": 9.067530672382544e-05,
+      "loss": 0.0773,
+      "mean_token_accuracy": 0.9797722736001014,
+      "num_tokens": 3674162.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.07874332463368773,
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.08524929732084274,
+      "learning_rate": 8.822213287104348e-05,
+      "loss": 0.0762,
+      "mean_token_accuracy": 0.9801681047677994,
+      "num_tokens": 4082734.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.07778633100911975,
+      "epoch": 0.8148148148148148,
+      "grad_norm": 0.10848797112703323,
+      "learning_rate": 8.552459335135381e-05,
+      "loss": 0.0753,
+      "mean_token_accuracy": 0.9801766823232174,
+      "num_tokens": 4491115.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.07791180345229805,
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.12547598779201508,
+      "learning_rate": 8.259993435156559e-05,
+      "loss": 0.0752,
+      "mean_token_accuracy": 0.9802092918753624,
+      "num_tokens": 4899794.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.07790746555663645,
+      "epoch": 0.9629629629629629,
+      "grad_norm": 0.0992884486913681,
+      "learning_rate": 7.946685410208296e-05,
+      "loss": 0.0759,
+      "mean_token_accuracy": 0.979848040342331,
+      "num_tokens": 5307342.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.07524958597496152,
+      "epoch": 1.037037037037037,
+      "grad_norm": 0.086652472615242,
+      "learning_rate": 7.614538333345735e-05,
+      "loss": 0.0731,
+      "mean_token_accuracy": 0.9808213406801224,
+      "num_tokens": 5716156.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.07525249728001654,
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.13188883662223816,
+      "learning_rate": 7.265675721386285e-05,
+      "loss": 0.0728,
+      "mean_token_accuracy": 0.9810096868872642,
+      "num_tokens": 6123905.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.07601501471363008,
+      "epoch": 1.1851851851851851,
+      "grad_norm": 0.0819055363535881,
+      "learning_rate": 6.902327958623736e-05,
+      "loss": 0.0736,
+      "mean_token_accuracy": 0.9805573572218418,
+      "num_tokens": 6532143.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.07429057988338172,
+      "epoch": 1.2592592592592593,
+      "grad_norm": 0.09344803541898727,
+      "learning_rate": 6.526818037306228e-05,
+      "loss": 0.0727,
+      "mean_token_accuracy": 0.9813062380254268,
+      "num_tokens": 6940424.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.07440330957062542,
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.11321987956762314,
+      "learning_rate": 6.14154670604355e-05,
+      "loss": 0.0725,
+      "mean_token_accuracy": 0.9811275874078274,
+      "num_tokens": 7348719.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.07393304943107068,
+      "epoch": 1.4074074074074074,
+      "grad_norm": 0.087185338139534,
+      "learning_rate": 5.7489771210944564e-05,
+      "loss": 0.0726,
+      "mean_token_accuracy": 0.9807305666804313,
+      "num_tokens": 7756710.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.07433672657236456,
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.10077723860740662,
+      "learning_rate": 5.351619098663021e-05,
+      "loss": 0.0726,
+      "mean_token_accuracy": 0.9807634821534157,
+      "num_tokens": 8165027.0,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2025,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.4107496965918106e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99474405bb9e12c9e6287ba75ece0944d511441013aa0f9574c0a7847af2b991
+size 6225

checkpoint-1500/README.md

@@ -0,0 +1,209 @@
+---
+base_model: bigcode/starcoder2-7b
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:bigcode/starcoder2-7b
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.0

checkpoint-1500/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigcode/starcoder2-7b",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51440351365e4163d078c6553c2ce5af93f0ee4fd98568324dea27cbfa4f81ad
+size 58754616

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec49af2f6ddb12761771490bd6bb517536c4a3fb21021f57c9c104e2230df302
+size 117660107

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:519d2868f3fe16de7c023a3db67a6535bad4a88579318ddd99606f1ecc8e7cec
+size 14645

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b10d09adf0489af5dc688ca572941043ef06e06d7551388176d2e6574474a5a
+size 1465

checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,63 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,357 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<code_to_intermediate>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<intermediate_to_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<pr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<pr_status>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<pr_is_merged>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<pr_base>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "<pr_file>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "23": {
+      "content": "<pr_base_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24": {
+      "content": "<pr_diff>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25": {
+      "content": "<pr_diff_hunk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "26": {
+      "content": "<pr_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "27": {
+      "content": "<pr_event_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28": {
+      "content": "<pr_review>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29": {
+      "content": "<pr_review_state>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "<pr_review_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31": {
+      "content": "<pr_in_reply_to_review_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<pr_in_reply_to_comment_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "33": {
+      "content": "<pr_diff_hunk_comment_line>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "<NAME>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "<EMAIL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "<KEY>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "<PASSWORD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,334 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.2222222222222223,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.805763495862484,
+      "epoch": 0.07407407407407407,
+      "grad_norm": 0.6806204319000244,
+      "learning_rate": 8.032786885245902e-05,
+      "loss": 1.5484,
+      "mean_token_accuracy": 0.6665007689595223,
+      "num_tokens": 408149.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.41144788280129435,
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.38455039262771606,
+      "learning_rate": 9.990765991730485e-05,
+      "loss": 0.3321,
+      "mean_token_accuracy": 0.9129975068569184,
+      "num_tokens": 816230.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.16323913749307395,
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.29704713821411133,
+      "learning_rate": 9.950545603782162e-05,
+      "loss": 0.1447,
+      "mean_token_accuracy": 0.9618216013908386,
+      "num_tokens": 1224471.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.1175146003998816,
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.35487300157546997,
+      "learning_rate": 9.878674879048427e-05,
+      "loss": 0.1071,
+      "mean_token_accuracy": 0.9733556269109249,
+      "num_tokens": 1632497.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.1009879010822624,
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.17419321835041046,
+      "learning_rate": 9.775613308830824e-05,
+      "loss": 0.0925,
+      "mean_token_accuracy": 0.9769376286864281,
+      "num_tokens": 2041392.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.09154447751119733,
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.20543242990970612,
+      "learning_rate": 9.642019796948866e-05,
+      "loss": 0.0836,
+      "mean_token_accuracy": 0.9787026332318782,
+      "num_tokens": 2450311.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.08632300381548702,
+      "epoch": 0.5185185185185185,
+      "grad_norm": 0.17172595858573914,
+      "learning_rate": 9.478748447168449e-05,
+      "loss": 0.0812,
+      "mean_token_accuracy": 0.9789653661847114,
+      "num_tokens": 2858744.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.08412999271415174,
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.1447569578886032,
+      "learning_rate": 9.28684310265789e-05,
+      "loss": 0.0805,
+      "mean_token_accuracy": 0.9786932443082332,
+      "num_tokens": 3265542.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.08065679710358381,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.19630704820156097,
+      "learning_rate": 9.067530672382544e-05,
+      "loss": 0.0773,
+      "mean_token_accuracy": 0.9797722736001014,
+      "num_tokens": 3674162.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.07874332463368773,
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.08524929732084274,
+      "learning_rate": 8.822213287104348e-05,
+      "loss": 0.0762,
+      "mean_token_accuracy": 0.9801681047677994,
+      "num_tokens": 4082734.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.07778633100911975,
+      "epoch": 0.8148148148148148,
+      "grad_norm": 0.10848797112703323,
+      "learning_rate": 8.552459335135381e-05,
+      "loss": 0.0753,
+      "mean_token_accuracy": 0.9801766823232174,
+      "num_tokens": 4491115.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.07791180345229805,
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.12547598779201508,
+      "learning_rate": 8.259993435156559e-05,
+      "loss": 0.0752,
+      "mean_token_accuracy": 0.9802092918753624,
+      "num_tokens": 4899794.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.07790746555663645,
+      "epoch": 0.9629629629629629,
+      "grad_norm": 0.0992884486913681,
+      "learning_rate": 7.946685410208296e-05,
+      "loss": 0.0759,
+      "mean_token_accuracy": 0.979848040342331,
+      "num_tokens": 5307342.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.07524958597496152,
+      "epoch": 1.037037037037037,
+      "grad_norm": 0.086652472615242,
+      "learning_rate": 7.614538333345735e-05,
+      "loss": 0.0731,
+      "mean_token_accuracy": 0.9808213406801224,
+      "num_tokens": 5716156.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.07525249728001654,
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.13188883662223816,
+      "learning_rate": 7.265675721386285e-05,
+      "loss": 0.0728,
+      "mean_token_accuracy": 0.9810096868872642,
+      "num_tokens": 6123905.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.07601501471363008,
+      "epoch": 1.1851851851851851,
+      "grad_norm": 0.0819055363535881,
+      "learning_rate": 6.902327958623736e-05,
+      "loss": 0.0736,
+      "mean_token_accuracy": 0.9805573572218418,
+      "num_tokens": 6532143.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.07429057988338172,
+      "epoch": 1.2592592592592593,
+      "grad_norm": 0.09344803541898727,
+      "learning_rate": 6.526818037306228e-05,
+      "loss": 0.0727,
+      "mean_token_accuracy": 0.9813062380254268,
+      "num_tokens": 6940424.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.07440330957062542,
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.11321987956762314,
+      "learning_rate": 6.14154670604355e-05,
+      "loss": 0.0725,
+      "mean_token_accuracy": 0.9811275874078274,
+      "num_tokens": 7348719.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.07393304943107068,
+      "epoch": 1.4074074074074074,
+      "grad_norm": 0.087185338139534,
+      "learning_rate": 5.7489771210944564e-05,
+      "loss": 0.0726,
+      "mean_token_accuracy": 0.9807305666804313,
+      "num_tokens": 7756710.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.07433672657236456,
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.10077723860740662,
+      "learning_rate": 5.351619098663021e-05,
+      "loss": 0.0726,
+      "mean_token_accuracy": 0.9807634821534157,
+      "num_tokens": 8165027.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.07262381819076837,
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.05774468928575516,
+      "learning_rate": 4.952013068883795e-05,
+      "loss": 0.0717,
+      "mean_token_accuracy": 0.9813279174268246,
+      "num_tokens": 8573428.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.07313465082086623,
+      "epoch": 1.6296296296296298,
+      "grad_norm": 0.156134694814682,
+      "learning_rate": 4.5527138340828776e-05,
+      "loss": 0.0717,
+      "mean_token_accuracy": 0.9811334984004497,
+      "num_tokens": 8981661.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.07226949028670787,
+      "epoch": 1.7037037037037037,
+      "grad_norm": 0.060666773468256,
+      "learning_rate": 4.156274235153189e-05,
+      "loss": 0.071,
+      "mean_token_accuracy": 0.9813579262793064,
+      "num_tokens": 9390026.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.07272680706344545,
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.10639354586601257,
+      "learning_rate": 3.765228830469794e-05,
+      "loss": 0.0711,
+      "mean_token_accuracy": 0.981099860817194,
+      "num_tokens": 9798433.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.07212639102712273,
+      "epoch": 1.8518518518518519,
+      "grad_norm": 0.06637933105230331,
+      "learning_rate": 3.3820776916908857e-05,
+      "loss": 0.0711,
+      "mean_token_accuracy": 0.9812221045792103,
+      "num_tokens": 10206854.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.07320461552590132,
+      "epoch": 1.925925925925926,
+      "grad_norm": 0.10055620223283768,
+      "learning_rate": 3.0092704200428058e-05,
+      "loss": 0.0719,
+      "mean_token_accuracy": 0.9807316599786282,
+      "num_tokens": 10615186.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.07290558220818638,
+      "epoch": 2.0,
+      "grad_norm": 0.0677887499332428,
+      "learning_rate": 2.649190485277792e-05,
+      "loss": 0.0718,
+      "mean_token_accuracy": 0.9811730526387692,
+      "num_tokens": 11023650.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.07251124914735556,
+      "epoch": 2.074074074074074,
+      "grad_norm": 0.11045810580253601,
+      "learning_rate": 2.3041399874302905e-05,
+      "loss": 0.0709,
+      "mean_token_accuracy": 0.9809805656969547,
+      "num_tokens": 11430802.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.07181317125447094,
+      "epoch": 2.148148148148148,
+      "grad_norm": 0.07149960100650787,
+      "learning_rate": 1.976324938794482e-05,
+      "loss": 0.0708,
+      "mean_token_accuracy": 0.9813783176243305,
+      "num_tokens": 11839809.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.0717768538929522,
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.05869750306010246,
+      "learning_rate": 1.667841160219835e-05,
+      "loss": 0.0707,
+      "mean_token_accuracy": 0.9814658354222775,
+      "num_tokens": 12248612.0,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2025,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.1165721390352794e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99474405bb9e12c9e6287ba75ece0944d511441013aa0f9574c0a7847af2b991
+size 6225

checkpoint-2000/README.md

@@ -0,0 +1,209 @@
+---
+base_model: bigcode/starcoder2-7b
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:bigcode/starcoder2-7b
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.0

checkpoint-2000/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigcode/starcoder2-7b",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53788087d95ab47ebd4d9d954a183a37247ae189fa7fe014e4d2b77153e50819
+size 58754616

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a6b49f0449304a1a162741c5817dd937ed429729770ff1c516073c81d70ef17
+size 117660107

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:334838e136c1a65b2f6261b884ef1f869ed891021ed06ed0a4c6c7f127147cfa
+size 14645

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:591d55d90adc2dbaeabd46529428d7ba9aa1ba92348998be2f0a794eeb555bea
+size 1465

checkpoint-2000/special_tokens_map.json

@@ -0,0 +1,63 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,357 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<code_to_intermediate>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<intermediate_to_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<pr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<pr_status>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<pr_is_merged>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<pr_base>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "<pr_file>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "23": {
+      "content": "<pr_base_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24": {
+      "content": "<pr_diff>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25": {
+      "content": "<pr_diff_hunk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "26": {
+      "content": "<pr_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "27": {
+      "content": "<pr_event_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28": {
+      "content": "<pr_review>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29": {
+      "content": "<pr_review_state>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "<pr_review_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31": {
+      "content": "<pr_in_reply_to_review_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<pr_in_reply_to_comment_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "33": {
+      "content": "<pr_diff_hunk_comment_line>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "<NAME>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "<EMAIL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "<KEY>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "<PASSWORD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.962962962962963,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.805763495862484,
+      "epoch": 0.07407407407407407,
+      "grad_norm": 0.6806204319000244,
+      "learning_rate": 8.032786885245902e-05,
+      "loss": 1.5484,
+      "mean_token_accuracy": 0.6665007689595223,
+      "num_tokens": 408149.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.41144788280129435,
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.38455039262771606,
+      "learning_rate": 9.990765991730485e-05,
+      "loss": 0.3321,
+      "mean_token_accuracy": 0.9129975068569184,
+      "num_tokens": 816230.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.16323913749307395,
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.29704713821411133,
+      "learning_rate": 9.950545603782162e-05,
+      "loss": 0.1447,
+      "mean_token_accuracy": 0.9618216013908386,
+      "num_tokens": 1224471.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.1175146003998816,
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.35487300157546997,
+      "learning_rate": 9.878674879048427e-05,
+      "loss": 0.1071,
+      "mean_token_accuracy": 0.9733556269109249,
+      "num_tokens": 1632497.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.1009879010822624,
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.17419321835041046,
+      "learning_rate": 9.775613308830824e-05,
+      "loss": 0.0925,
+      "mean_token_accuracy": 0.9769376286864281,
+      "num_tokens": 2041392.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.09154447751119733,
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.20543242990970612,
+      "learning_rate": 9.642019796948866e-05,
+      "loss": 0.0836,
+      "mean_token_accuracy": 0.9787026332318782,
+      "num_tokens": 2450311.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.08632300381548702,
+      "epoch": 0.5185185185185185,
+      "grad_norm": 0.17172595858573914,
+      "learning_rate": 9.478748447168449e-05,
+      "loss": 0.0812,
+      "mean_token_accuracy": 0.9789653661847114,
+      "num_tokens": 2858744.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.08412999271415174,
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.1447569578886032,
+      "learning_rate": 9.28684310265789e-05,
+      "loss": 0.0805,
+      "mean_token_accuracy": 0.9786932443082332,
+      "num_tokens": 3265542.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.08065679710358381,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.19630704820156097,
+      "learning_rate": 9.067530672382544e-05,
+      "loss": 0.0773,
+      "mean_token_accuracy": 0.9797722736001014,
+      "num_tokens": 3674162.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.07874332463368773,
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.08524929732084274,
+      "learning_rate": 8.822213287104348e-05,
+      "loss": 0.0762,
+      "mean_token_accuracy": 0.9801681047677994,
+      "num_tokens": 4082734.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.07778633100911975,
+      "epoch": 0.8148148148148148,
+      "grad_norm": 0.10848797112703323,
+      "learning_rate": 8.552459335135381e-05,
+      "loss": 0.0753,
+      "mean_token_accuracy": 0.9801766823232174,
+      "num_tokens": 4491115.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.07791180345229805,
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.12547598779201508,
+      "learning_rate": 8.259993435156559e-05,
+      "loss": 0.0752,
+      "mean_token_accuracy": 0.9802092918753624,
+      "num_tokens": 4899794.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.07790746555663645,
+      "epoch": 0.9629629629629629,
+      "grad_norm": 0.0992884486913681,
+      "learning_rate": 7.946685410208296e-05,
+      "loss": 0.0759,
+      "mean_token_accuracy": 0.979848040342331,
+      "num_tokens": 5307342.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.07524958597496152,
+      "epoch": 1.037037037037037,
+      "grad_norm": 0.086652472615242,
+      "learning_rate": 7.614538333345735e-05,
+      "loss": 0.0731,
+      "mean_token_accuracy": 0.9808213406801224,
+      "num_tokens": 5716156.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.07525249728001654,
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.13188883662223816,
+      "learning_rate": 7.265675721386285e-05,
+      "loss": 0.0728,
+      "mean_token_accuracy": 0.9810096868872642,
+      "num_tokens": 6123905.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.07601501471363008,
+      "epoch": 1.1851851851851851,
+      "grad_norm": 0.0819055363535881,
+      "learning_rate": 6.902327958623736e-05,
+      "loss": 0.0736,
+      "mean_token_accuracy": 0.9805573572218418,
+      "num_tokens": 6532143.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.07429057988338172,
+      "epoch": 1.2592592592592593,
+      "grad_norm": 0.09344803541898727,
+      "learning_rate": 6.526818037306228e-05,
+      "loss": 0.0727,
+      "mean_token_accuracy": 0.9813062380254268,
+      "num_tokens": 6940424.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.07440330957062542,
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.11321987956762314,
+      "learning_rate": 6.14154670604355e-05,
+      "loss": 0.0725,
+      "mean_token_accuracy": 0.9811275874078274,
+      "num_tokens": 7348719.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.07393304943107068,
+      "epoch": 1.4074074074074074,
+      "grad_norm": 0.087185338139534,
+      "learning_rate": 5.7489771210944564e-05,
+      "loss": 0.0726,
+      "mean_token_accuracy": 0.9807305666804313,
+      "num_tokens": 7756710.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.07433672657236456,
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.10077723860740662,
+      "learning_rate": 5.351619098663021e-05,
+      "loss": 0.0726,
+      "mean_token_accuracy": 0.9807634821534157,
+      "num_tokens": 8165027.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.07262381819076837,
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.05774468928575516,
+      "learning_rate": 4.952013068883795e-05,
+      "loss": 0.0717,
+      "mean_token_accuracy": 0.9813279174268246,
+      "num_tokens": 8573428.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.07313465082086623,
+      "epoch": 1.6296296296296298,
+      "grad_norm": 0.156134694814682,
+      "learning_rate": 4.5527138340828776e-05,
+      "loss": 0.0717,
+      "mean_token_accuracy": 0.9811334984004497,
+      "num_tokens": 8981661.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.07226949028670787,
+      "epoch": 1.7037037037037037,
+      "grad_norm": 0.060666773468256,
+      "learning_rate": 4.156274235153189e-05,
+      "loss": 0.071,
+      "mean_token_accuracy": 0.9813579262793064,
+      "num_tokens": 9390026.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.07272680706344545,
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.10639354586601257,
+      "learning_rate": 3.765228830469794e-05,
+      "loss": 0.0711,
+      "mean_token_accuracy": 0.981099860817194,
+      "num_tokens": 9798433.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.07212639102712273,
+      "epoch": 1.8518518518518519,
+      "grad_norm": 0.06637933105230331,
+      "learning_rate": 3.3820776916908857e-05,
+      "loss": 0.0711,
+      "mean_token_accuracy": 0.9812221045792103,
+      "num_tokens": 10206854.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.07320461552590132,
+      "epoch": 1.925925925925926,
+      "grad_norm": 0.10055620223283768,
+      "learning_rate": 3.0092704200428058e-05,
+      "loss": 0.0719,
+      "mean_token_accuracy": 0.9807316599786282,
+      "num_tokens": 10615186.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.07290558220818638,
+      "epoch": 2.0,
+      "grad_norm": 0.0677887499332428,
+      "learning_rate": 2.649190485277792e-05,
+      "loss": 0.0718,
+      "mean_token_accuracy": 0.9811730526387692,
+      "num_tokens": 11023650.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.07251124914735556,
+      "epoch": 2.074074074074074,
+      "grad_norm": 0.11045810580253601,
+      "learning_rate": 2.3041399874302905e-05,
+      "loss": 0.0709,
+      "mean_token_accuracy": 0.9809805656969547,
+      "num_tokens": 11430802.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.07181317125447094,
+      "epoch": 2.148148148148148,
+      "grad_norm": 0.07149960100650787,
+      "learning_rate": 1.976324938794482e-05,
+      "loss": 0.0708,
+      "mean_token_accuracy": 0.9813783176243305,
+      "num_tokens": 11839809.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.0717768538929522,
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.05869750306010246,
+      "learning_rate": 1.667841160219835e-05,
+      "loss": 0.0707,
+      "mean_token_accuracy": 0.9814658354222775,
+      "num_tokens": 12248612.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.0715598820708692,
+      "epoch": 2.2962962962962963,
+      "grad_norm": 0.08496281504631042,
+      "learning_rate": 1.3806608818939203e-05,
+      "loss": 0.0705,
+      "mean_token_accuracy": 0.9812778060138225,
+      "num_tokens": 12657077.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.07179237512871622,
+      "epoch": 2.3703703703703702,
+      "grad_norm": 0.06790705770254135,
+      "learning_rate": 1.1166201342777438e-05,
+      "loss": 0.0709,
+      "mean_token_accuracy": 0.9812556092441082,
+      "num_tokens": 13064930.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.0720329173374921,
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.06569824367761612,
+      "learning_rate": 8.774070098071668e-06,
+      "loss": 0.0711,
+      "mean_token_accuracy": 0.9811322076618672,
+      "num_tokens": 13472953.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.07238605052232742,
+      "epoch": 2.5185185185185186,
+      "grad_norm": 0.05740037187933922,
+      "learning_rate": 6.645508704069003e-06,
+      "loss": 0.0712,
+      "mean_token_accuracy": 0.9810698322951794,
+      "num_tokens": 13881339.0,
+      "step": 1700
+    },
+    {
+      "entropy": 0.07082363245077432,
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.06362631171941757,
+      "learning_rate": 4.794125698167262e-06,
+      "loss": 0.0703,
+      "mean_token_accuracy": 0.9813959409296512,
+      "num_tokens": 14289567.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.07266209500841797,
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.05623815581202507,
+      "learning_rate": 3.231757532415458e-06,
+      "loss": 0.0714,
+      "mean_token_accuracy": 0.9809911704063415,
+      "num_tokens": 14697205.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.07201593144796789,
+      "epoch": 2.7407407407407405,
+      "grad_norm": 0.05804692208766937,
+      "learning_rate": 1.9683928994924385e-06,
+      "loss": 0.071,
+      "mean_token_accuracy": 0.9810844567418099,
+      "num_tokens": 15105573.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.07237200179137289,
+      "epoch": 2.814814814814815,
+      "grad_norm": 0.07103168219327927,
+      "learning_rate": 1.0121088719706296e-06,
+      "loss": 0.0715,
+      "mean_token_accuracy": 0.9812616856396198,
+      "num_tokens": 15514180.0,
+      "step": 1900
+    },
+    {
+      "entropy": 0.07117950812913477,
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.062420960515737534,
+      "learning_rate": 3.6901926314575894e-07,
+      "loss": 0.0703,
+      "mean_token_accuracy": 0.981419977247715,
+      "num_tokens": 15922315.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.07066867646761238,
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.05154326930642128,
+      "learning_rate": 4.323553957759629e-08,
+      "loss": 0.07,
+      "mean_token_accuracy": 0.9817947860062123,
+      "num_tokens": 16331178.0,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2025,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.821968917982372e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99474405bb9e12c9e6287ba75ece0944d511441013aa0f9574c0a7847af2b991
+size 6225

checkpoint-2025/README.md

@@ -0,0 +1,209 @@
+---
+base_model: bigcode/starcoder2-7b
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:bigcode/starcoder2-7b
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.0

checkpoint-2025/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigcode/starcoder2-7b",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-2025/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f9a9fbadd0b35342e1993f10bde6b04ed43f8e16cbc6027b05d97c66c518dc6
+size 58754616

checkpoint-2025/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:310e3145759ebef6398ac4a4c3b94099f6f222a086adee3c58729b9361c6f49e
+size 117660107

checkpoint-2025/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a039ed66a9d266986e1f0e98befe7f1d8ca1c98ad6639ae7472d051bd9603c69
+size 14645

checkpoint-2025/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e77c94e08fe995eb38321a73baf050cd174cc938ef4133784c892be1db9c05
+size 1465