Upload folder using huggingface_hub

.ipynb_checkpoints/training_summary_s3-checkpoint.json

@@ -0,0 +1,19 @@
+{
+  "service": "S3",
+  "epochs": 3.0,
+  "global_step": 2025,
+  "train_runtime_sec": 9993.673266887665,
+  "train_samples": 5400,
+  "eval_samples": 600,
+  "used_bitsandbytes": false,
+  "eval_metrics": {
+    "eval_loss": 0.07721275091171265,
+    "eval_runtime": 108.6171,
+    "eval_samples_per_second": 5.524,
+    "eval_steps_per_second": 0.69,
+    "eval_entropy": 0.0753403959174951,
+    "eval_num_tokens": 16398642.0,
+    "eval_mean_token_accuracy": 0.9798894079526266,
+    "epoch": 3.0
+  }
+}

README.md

@@ -0,0 +1,62 @@
+---
+base_model: bigcode/starcoder2-7b
+library_name: peft
+model_name: starcoder2_7b_lora_s3
+tags:
+- base_model:adapter:bigcode/starcoder2-7b
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for starcoder2_7b_lora_s3
+
+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 sha256:41a51e897954eedbdc9accbe97c6f604b531441c3a49b9086cf3947d777fe3f4
+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 sha256:3819f1294660404e952a92ea82dc4672af20e1541a2fcb97261305a7cf34f27a
+size 58754616

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa3c8dd2cf965a85a521ee2c685d27fe894d91bbf461aaa36c061f8bc76f9fb5
+size 117660107

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f9a2d0a3b2281487aca1e6dc78688f202a90099a1190d213f79d3676dd38e6
+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": 1.7838703233003617,
+      "epoch": 0.07407407407407407,
+      "grad_norm": 2.2315239906311035,
+      "learning_rate": 8.032786885245902e-05,
+      "loss": 1.5419,
+      "mean_token_accuracy": 0.675746806114912,
+      "num_tokens": 406250.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.42496320378035307,
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.3177862763404846,
+      "learning_rate": 9.990765991730485e-05,
+      "loss": 0.3491,
+      "mean_token_accuracy": 0.9115325964987278,
+      "num_tokens": 810885.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.17912146519869565,
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.30210021138191223,
+      "learning_rate": 9.950545603782162e-05,
+      "loss": 0.1608,
+      "mean_token_accuracy": 0.9592751894891262,
+      "num_tokens": 1216948.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.13433791074901819,
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.4639471173286438,
+      "learning_rate": 9.878674879048427e-05,
+      "loss": 0.1177,
+      "mean_token_accuracy": 0.9702847249805927,
+      "num_tokens": 1623039.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.11072772483341396,
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.239689439535141,
+      "learning_rate": 9.775613308830824e-05,
+      "loss": 0.0996,
+      "mean_token_accuracy": 0.9741994588077069,
+      "num_tokens": 2029168.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.1015299869235605,
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.14000816643238068,
+      "learning_rate": 9.642019796948866e-05,
+      "loss": 0.0946,
+      "mean_token_accuracy": 0.9754497842490673,
+      "num_tokens": 2433618.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.0944658778142184,
+      "epoch": 0.5185185185185185,
+      "grad_norm": 0.2911929786205292,
+      "learning_rate": 9.478748447168449e-05,
+      "loss": 0.0888,
+      "mean_token_accuracy": 0.9764833557605743,
+      "num_tokens": 2837007.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.09286680690012872,
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.1825980246067047,
+      "learning_rate": 9.28684310265789e-05,
+      "loss": 0.0884,
+      "mean_token_accuracy": 0.9767837685346603,
+      "num_tokens": 3241067.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.09173870420083403,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.16845248639583588,
+      "learning_rate": 9.067530672382544e-05,
+      "loss": 0.0871,
+      "mean_token_accuracy": 0.9771137611567974,
+      "num_tokens": 3644774.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.08837487244978547,
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.15667857229709625,
+      "learning_rate": 8.822213287104348e-05,
+      "loss": 0.0846,
+      "mean_token_accuracy": 0.9784404304623604,
+      "num_tokens": 4050472.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.0885874280706048,
+      "epoch": 0.8148148148148148,
+      "grad_norm": 0.10147374123334885,
+      "learning_rate": 8.552459335135381e-05,
+      "loss": 0.0848,
+      "mean_token_accuracy": 0.977893346697092,
+      "num_tokens": 4453374.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.08721992008388042,
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.08062940090894699,
+      "learning_rate": 8.259993435156559e-05,
+      "loss": 0.0844,
+      "mean_token_accuracy": 0.9785151568055153,
+      "num_tokens": 4859149.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.08216898602433503,
+      "epoch": 0.9629629629629629,
+      "grad_norm": 0.1335250586271286,
+      "learning_rate": 7.946685410208296e-05,
+      "loss": 0.0798,
+      "mean_token_accuracy": 0.9796955060958862,
+      "num_tokens": 5264437.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.08460669645108282,
+      "epoch": 1.037037037037037,
+      "grad_norm": 0.0986652821302414,
+      "learning_rate": 7.614538333345735e-05,
+      "loss": 0.0822,
+      "mean_token_accuracy": 0.9785672229528427,
+      "num_tokens": 5669023.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.0850414677709341,
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.07220367342233658,
+      "learning_rate": 7.265675721386285e-05,
+      "loss": 0.0824,
+      "mean_token_accuracy": 0.9784497334063054,
+      "num_tokens": 6073001.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.08401141031645239,
+      "epoch": 1.1851851851851851,
+      "grad_norm": 0.1240311786532402,
+      "learning_rate": 6.902327958623736e-05,
+      "loss": 0.0826,
+      "mean_token_accuracy": 0.9786691051721573,
+      "num_tokens": 6478325.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.08358457050286233,
+      "epoch": 1.2592592592592593,
+      "grad_norm": 0.10120349377393723,
+      "learning_rate": 6.526818037306228e-05,
+      "loss": 0.0811,
+      "mean_token_accuracy": 0.9787746147811413,
+      "num_tokens": 6882747.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.0835177150182426,
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.10029594600200653,
+      "learning_rate": 6.14154670604355e-05,
+      "loss": 0.0818,
+      "mean_token_accuracy": 0.9788197261095047,
+      "num_tokens": 7287039.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.08201941348612309,
+      "epoch": 1.4074074074074074,
+      "grad_norm": 0.09068141877651215,
+      "learning_rate": 5.7489771210944564e-05,
+      "loss": 0.0802,
+      "mean_token_accuracy": 0.9791601756215096,
+      "num_tokens": 7692281.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.08500135038048029,
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.10811195522546768,
+      "learning_rate": 5.351619098663021e-05,
+      "loss": 0.0829,
+      "mean_token_accuracy": 0.9783452861011028,
+      "num_tokens": 8096455.0,
+      "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": 3.3821053420545024e+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 sha256:657ec4ab83e11a499cf55047de3a4140964d0c9e7020c53c70cd1720cd946db4
+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 sha256:56b88771a37e89134b0710947e99eb8547c79e6023db8800983e1c70347f3312
+size 58754616

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed200ef46871a62966796d1f87a29a942e08e8a35d87c0adc937f5eaa3f9ff67
+size 117660107

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1e439f3761d3e161b20f0488023b41b1aff5abd6b74f408a263c3c7a2a0e7f
+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": 1.7838703233003617,
+      "epoch": 0.07407407407407407,
+      "grad_norm": 2.2315239906311035,
+      "learning_rate": 8.032786885245902e-05,
+      "loss": 1.5419,
+      "mean_token_accuracy": 0.675746806114912,
+      "num_tokens": 406250.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.42496320378035307,
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.3177862763404846,
+      "learning_rate": 9.990765991730485e-05,
+      "loss": 0.3491,
+      "mean_token_accuracy": 0.9115325964987278,
+      "num_tokens": 810885.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.17912146519869565,
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.30210021138191223,
+      "learning_rate": 9.950545603782162e-05,
+      "loss": 0.1608,
+      "mean_token_accuracy": 0.9592751894891262,
+      "num_tokens": 1216948.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.13433791074901819,
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.4639471173286438,
+      "learning_rate": 9.878674879048427e-05,
+      "loss": 0.1177,
+      "mean_token_accuracy": 0.9702847249805927,
+      "num_tokens": 1623039.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.11072772483341396,
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.239689439535141,
+      "learning_rate": 9.775613308830824e-05,
+      "loss": 0.0996,
+      "mean_token_accuracy": 0.9741994588077069,
+      "num_tokens": 2029168.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.1015299869235605,
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.14000816643238068,
+      "learning_rate": 9.642019796948866e-05,
+      "loss": 0.0946,
+      "mean_token_accuracy": 0.9754497842490673,
+      "num_tokens": 2433618.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.0944658778142184,
+      "epoch": 0.5185185185185185,
+      "grad_norm": 0.2911929786205292,
+      "learning_rate": 9.478748447168449e-05,
+      "loss": 0.0888,
+      "mean_token_accuracy": 0.9764833557605743,
+      "num_tokens": 2837007.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.09286680690012872,
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.1825980246067047,
+      "learning_rate": 9.28684310265789e-05,
+      "loss": 0.0884,
+      "mean_token_accuracy": 0.9767837685346603,
+      "num_tokens": 3241067.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.09173870420083403,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.16845248639583588,
+      "learning_rate": 9.067530672382544e-05,
+      "loss": 0.0871,
+      "mean_token_accuracy": 0.9771137611567974,
+      "num_tokens": 3644774.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.08837487244978547,
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.15667857229709625,
+      "learning_rate": 8.822213287104348e-05,
+      "loss": 0.0846,
+      "mean_token_accuracy": 0.9784404304623604,
+      "num_tokens": 4050472.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.0885874280706048,
+      "epoch": 0.8148148148148148,
+      "grad_norm": 0.10147374123334885,
+      "learning_rate": 8.552459335135381e-05,
+      "loss": 0.0848,
+      "mean_token_accuracy": 0.977893346697092,
+      "num_tokens": 4453374.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.08721992008388042,
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.08062940090894699,
+      "learning_rate": 8.259993435156559e-05,
+      "loss": 0.0844,
+      "mean_token_accuracy": 0.9785151568055153,
+      "num_tokens": 4859149.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.08216898602433503,
+      "epoch": 0.9629629629629629,
+      "grad_norm": 0.1335250586271286,
+      "learning_rate": 7.946685410208296e-05,
+      "loss": 0.0798,
+      "mean_token_accuracy": 0.9796955060958862,
+      "num_tokens": 5264437.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.08460669645108282,
+      "epoch": 1.037037037037037,
+      "grad_norm": 0.0986652821302414,
+      "learning_rate": 7.614538333345735e-05,
+      "loss": 0.0822,
+      "mean_token_accuracy": 0.9785672229528427,
+      "num_tokens": 5669023.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.0850414677709341,
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.07220367342233658,
+      "learning_rate": 7.265675721386285e-05,
+      "loss": 0.0824,
+      "mean_token_accuracy": 0.9784497334063054,
+      "num_tokens": 6073001.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.08401141031645239,
+      "epoch": 1.1851851851851851,
+      "grad_norm": 0.1240311786532402,
+      "learning_rate": 6.902327958623736e-05,
+      "loss": 0.0826,
+      "mean_token_accuracy": 0.9786691051721573,
+      "num_tokens": 6478325.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.08358457050286233,
+      "epoch": 1.2592592592592593,
+      "grad_norm": 0.10120349377393723,
+      "learning_rate": 6.526818037306228e-05,
+      "loss": 0.0811,
+      "mean_token_accuracy": 0.9787746147811413,
+      "num_tokens": 6882747.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.0835177150182426,
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.10029594600200653,
+      "learning_rate": 6.14154670604355e-05,
+      "loss": 0.0818,
+      "mean_token_accuracy": 0.9788197261095047,
+      "num_tokens": 7287039.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.08201941348612309,
+      "epoch": 1.4074074074074074,
+      "grad_norm": 0.09068141877651215,
+      "learning_rate": 5.7489771210944564e-05,
+      "loss": 0.0802,
+      "mean_token_accuracy": 0.9791601756215096,
+      "num_tokens": 7692281.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.08500135038048029,
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.10811195522546768,
+      "learning_rate": 5.351619098663021e-05,
+      "loss": 0.0829,
+      "mean_token_accuracy": 0.9783452861011028,
+      "num_tokens": 8096455.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.08261076767928899,
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.07817448675632477,
+      "learning_rate": 4.952013068883795e-05,
+      "loss": 0.0807,
+      "mean_token_accuracy": 0.9787566863000393,
+      "num_tokens": 8501481.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.08088674335740506,
+      "epoch": 1.6296296296296298,
+      "grad_norm": 0.0741722360253334,
+      "learning_rate": 4.5527138340828776e-05,
+      "loss": 0.0794,
+      "mean_token_accuracy": 0.9796176181733608,
+      "num_tokens": 8907814.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.08092430792748928,
+      "epoch": 1.7037037037037037,
+      "grad_norm": 0.0863470658659935,
+      "learning_rate": 4.156274235153189e-05,
+      "loss": 0.0792,
+      "mean_token_accuracy": 0.9792905601859093,
+      "num_tokens": 9312142.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.07963837143965065,
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.10823621600866318,
+      "learning_rate": 3.765228830469794e-05,
+      "loss": 0.0791,
+      "mean_token_accuracy": 0.9794147987663746,
+      "num_tokens": 9716258.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.08162923349067569,
+      "epoch": 1.8518518518518519,
+      "grad_norm": 0.1495106816291809,
+      "learning_rate": 3.3820776916908857e-05,
+      "loss": 0.0801,
+      "mean_token_accuracy": 0.9793653392791748,
+      "num_tokens": 10121713.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.08032218031585217,
+      "epoch": 1.925925925925926,
+      "grad_norm": 0.08044654875993729,
+      "learning_rate": 3.0092704200428058e-05,
+      "loss": 0.079,
+      "mean_token_accuracy": 0.9795299915969372,
+      "num_tokens": 10526002.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.07872624884359539,
+      "epoch": 2.0,
+      "grad_norm": 0.07752422988414764,
+      "learning_rate": 2.649190485277792e-05,
+      "loss": 0.0775,
+      "mean_token_accuracy": 0.980090646147728,
+      "num_tokens": 10932428.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.08063295830972493,
+      "epoch": 2.074074074074074,
+      "grad_norm": 0.09133461862802505,
+      "learning_rate": 2.3041399874302905e-05,
+      "loss": 0.0793,
+      "mean_token_accuracy": 0.9794050461053848,
+      "num_tokens": 11337209.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.08033578357659281,
+      "epoch": 2.148148148148148,
+      "grad_norm": 0.06361774355173111,
+      "learning_rate": 1.976324938794482e-05,
+      "loss": 0.0792,
+      "mean_token_accuracy": 0.9797105365991592,
+      "num_tokens": 11741968.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.07973854598589242,
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.09148402512073517,
+      "learning_rate": 1.667841160219835e-05,
+      "loss": 0.0778,
+      "mean_token_accuracy": 0.9796544459462165,
+      "num_tokens": 12147108.0,
+      "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": 5.074171209166602e+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 sha256:657ec4ab83e11a499cf55047de3a4140964d0c9e7020c53c70cd1720cd946db4
+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 sha256:397cac0081d5eb1d3be72c214ff0f92c16732d8dab595a1895ea1bf939b3d629
+size 58754616

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e65bf91b718e195707355230914b6e83c2c07fcb92116140289de0c84d091aa
+size 117660107

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:384f2918d61093e6ba761dd995ebbef670fa56d5a54fbbab20ee05f73eb2d6df
+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": 1.7838703233003617,
+      "epoch": 0.07407407407407407,
+      "grad_norm": 2.2315239906311035,
+      "learning_rate": 8.032786885245902e-05,
+      "loss": 1.5419,
+      "mean_token_accuracy": 0.675746806114912,
+      "num_tokens": 406250.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.42496320378035307,
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.3177862763404846,
+      "learning_rate": 9.990765991730485e-05,
+      "loss": 0.3491,
+      "mean_token_accuracy": 0.9115325964987278,
+      "num_tokens": 810885.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.17912146519869565,
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.30210021138191223,
+      "learning_rate": 9.950545603782162e-05,
+      "loss": 0.1608,
+      "mean_token_accuracy": 0.9592751894891262,
+      "num_tokens": 1216948.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.13433791074901819,
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.4639471173286438,
+      "learning_rate": 9.878674879048427e-05,
+      "loss": 0.1177,
+      "mean_token_accuracy": 0.9702847249805927,
+      "num_tokens": 1623039.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.11072772483341396,
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.239689439535141,
+      "learning_rate": 9.775613308830824e-05,
+      "loss": 0.0996,
+      "mean_token_accuracy": 0.9741994588077069,
+      "num_tokens": 2029168.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.1015299869235605,
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.14000816643238068,
+      "learning_rate": 9.642019796948866e-05,
+      "loss": 0.0946,
+      "mean_token_accuracy": 0.9754497842490673,
+      "num_tokens": 2433618.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.0944658778142184,
+      "epoch": 0.5185185185185185,
+      "grad_norm": 0.2911929786205292,
+      "learning_rate": 9.478748447168449e-05,
+      "loss": 0.0888,
+      "mean_token_accuracy": 0.9764833557605743,
+      "num_tokens": 2837007.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.09286680690012872,
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.1825980246067047,
+      "learning_rate": 9.28684310265789e-05,
+      "loss": 0.0884,
+      "mean_token_accuracy": 0.9767837685346603,
+      "num_tokens": 3241067.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.09173870420083403,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.16845248639583588,
+      "learning_rate": 9.067530672382544e-05,
+      "loss": 0.0871,
+      "mean_token_accuracy": 0.9771137611567974,
+      "num_tokens": 3644774.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.08837487244978547,
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.15667857229709625,
+      "learning_rate": 8.822213287104348e-05,
+      "loss": 0.0846,
+      "mean_token_accuracy": 0.9784404304623604,
+      "num_tokens": 4050472.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.0885874280706048,
+      "epoch": 0.8148148148148148,
+      "grad_norm": 0.10147374123334885,
+      "learning_rate": 8.552459335135381e-05,
+      "loss": 0.0848,
+      "mean_token_accuracy": 0.977893346697092,
+      "num_tokens": 4453374.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.08721992008388042,
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.08062940090894699,
+      "learning_rate": 8.259993435156559e-05,
+      "loss": 0.0844,
+      "mean_token_accuracy": 0.9785151568055153,
+      "num_tokens": 4859149.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.08216898602433503,
+      "epoch": 0.9629629629629629,
+      "grad_norm": 0.1335250586271286,
+      "learning_rate": 7.946685410208296e-05,
+      "loss": 0.0798,
+      "mean_token_accuracy": 0.9796955060958862,
+      "num_tokens": 5264437.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.08460669645108282,
+      "epoch": 1.037037037037037,
+      "grad_norm": 0.0986652821302414,
+      "learning_rate": 7.614538333345735e-05,
+      "loss": 0.0822,
+      "mean_token_accuracy": 0.9785672229528427,
+      "num_tokens": 5669023.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.0850414677709341,
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.07220367342233658,
+      "learning_rate": 7.265675721386285e-05,
+      "loss": 0.0824,
+      "mean_token_accuracy": 0.9784497334063054,
+      "num_tokens": 6073001.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.08401141031645239,
+      "epoch": 1.1851851851851851,
+      "grad_norm": 0.1240311786532402,
+      "learning_rate": 6.902327958623736e-05,
+      "loss": 0.0826,
+      "mean_token_accuracy": 0.9786691051721573,
+      "num_tokens": 6478325.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.08358457050286233,
+      "epoch": 1.2592592592592593,
+      "grad_norm": 0.10120349377393723,
+      "learning_rate": 6.526818037306228e-05,
+      "loss": 0.0811,
+      "mean_token_accuracy": 0.9787746147811413,
+      "num_tokens": 6882747.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.0835177150182426,
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.10029594600200653,
+      "learning_rate": 6.14154670604355e-05,
+      "loss": 0.0818,
+      "mean_token_accuracy": 0.9788197261095047,
+      "num_tokens": 7287039.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.08201941348612309,
+      "epoch": 1.4074074074074074,
+      "grad_norm": 0.09068141877651215,
+      "learning_rate": 5.7489771210944564e-05,
+      "loss": 0.0802,
+      "mean_token_accuracy": 0.9791601756215096,
+      "num_tokens": 7692281.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.08500135038048029,
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.10811195522546768,
+      "learning_rate": 5.351619098663021e-05,
+      "loss": 0.0829,
+      "mean_token_accuracy": 0.9783452861011028,
+      "num_tokens": 8096455.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.08261076767928899,
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.07817448675632477,
+      "learning_rate": 4.952013068883795e-05,
+      "loss": 0.0807,
+      "mean_token_accuracy": 0.9787566863000393,
+      "num_tokens": 8501481.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.08088674335740506,
+      "epoch": 1.6296296296296298,
+      "grad_norm": 0.0741722360253334,
+      "learning_rate": 4.5527138340828776e-05,
+      "loss": 0.0794,
+      "mean_token_accuracy": 0.9796176181733608,
+      "num_tokens": 8907814.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.08092430792748928,
+      "epoch": 1.7037037037037037,
+      "grad_norm": 0.0863470658659935,
+      "learning_rate": 4.156274235153189e-05,
+      "loss": 0.0792,
+      "mean_token_accuracy": 0.9792905601859093,
+      "num_tokens": 9312142.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.07963837143965065,
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.10823621600866318,
+      "learning_rate": 3.765228830469794e-05,
+      "loss": 0.0791,
+      "mean_token_accuracy": 0.9794147987663746,
+      "num_tokens": 9716258.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.08162923349067569,
+      "epoch": 1.8518518518518519,
+      "grad_norm": 0.1495106816291809,
+      "learning_rate": 3.3820776916908857e-05,
+      "loss": 0.0801,
+      "mean_token_accuracy": 0.9793653392791748,
+      "num_tokens": 10121713.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.08032218031585217,
+      "epoch": 1.925925925925926,
+      "grad_norm": 0.08044654875993729,
+      "learning_rate": 3.0092704200428058e-05,
+      "loss": 0.079,
+      "mean_token_accuracy": 0.9795299915969372,
+      "num_tokens": 10526002.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.07872624884359539,
+      "epoch": 2.0,
+      "grad_norm": 0.07752422988414764,
+      "learning_rate": 2.649190485277792e-05,
+      "loss": 0.0775,
+      "mean_token_accuracy": 0.980090646147728,
+      "num_tokens": 10932428.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.08063295830972493,
+      "epoch": 2.074074074074074,
+      "grad_norm": 0.09133461862802505,
+      "learning_rate": 2.3041399874302905e-05,
+      "loss": 0.0793,
+      "mean_token_accuracy": 0.9794050461053848,
+      "num_tokens": 11337209.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.08033578357659281,
+      "epoch": 2.148148148148148,
+      "grad_norm": 0.06361774355173111,
+      "learning_rate": 1.976324938794482e-05,
+      "loss": 0.0792,
+      "mean_token_accuracy": 0.9797105365991592,
+      "num_tokens": 11741968.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.07973854598589242,
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.09148402512073517,
+      "learning_rate": 1.667841160219835e-05,
+      "loss": 0.0778,
+      "mean_token_accuracy": 0.9796544459462165,
+      "num_tokens": 12147108.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.07991634771227836,
+      "epoch": 2.2962962962962963,
+      "grad_norm": 0.058334823697805405,
+      "learning_rate": 1.3806608818939203e-05,
+      "loss": 0.0787,
+      "mean_token_accuracy": 0.9793905445933342,
+      "num_tokens": 12551885.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.07991615429520607,
+      "epoch": 2.3703703703703702,
+      "grad_norm": 0.07122901827096939,
+      "learning_rate": 1.1166201342777438e-05,
+      "loss": 0.0785,
+      "mean_token_accuracy": 0.979671506434679,
+      "num_tokens": 12956475.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.07969259418547153,
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.11193029582500458,
+      "learning_rate": 8.774070098071668e-06,
+      "loss": 0.0787,
+      "mean_token_accuracy": 0.979515576660633,
+      "num_tokens": 13362716.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.08067716302350164,
+      "epoch": 2.5185185185185186,
+      "grad_norm": 0.09012539684772491,
+      "learning_rate": 6.645508704069003e-06,
+      "loss": 0.0802,
+      "mean_token_accuracy": 0.9791687172651291,
+      "num_tokens": 13766986.0,
+      "step": 1700
+    },
+    {
+      "entropy": 0.07974634082056582,
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.09309827536344528,
+      "learning_rate": 4.794125698167262e-06,
+      "loss": 0.0787,
+      "mean_token_accuracy": 0.9794514080882073,
+      "num_tokens": 14171018.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.08121541824191808,
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.06920253485441208,
+      "learning_rate": 3.231757532415458e-06,
+      "loss": 0.0794,
+      "mean_token_accuracy": 0.9792174778878688,
+      "num_tokens": 14575902.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.07990395256318152,
+      "epoch": 2.7407407407407405,
+      "grad_norm": 0.05824149027466774,
+      "learning_rate": 1.9683928994924385e-06,
+      "loss": 0.0781,
+      "mean_token_accuracy": 0.9798404219746589,
+      "num_tokens": 14980838.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.08023261365480722,
+      "epoch": 2.814814814814815,
+      "grad_norm": 0.08101186901330948,
+      "learning_rate": 1.0121088719706296e-06,
+      "loss": 0.0795,
+      "mean_token_accuracy": 0.9791903717815876,
+      "num_tokens": 15385944.0,
+      "step": 1900
+    },
+    {
+      "entropy": 0.08040859408676625,
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.07091067731380463,
+      "learning_rate": 3.6901926314575894e-07,
+      "loss": 0.0797,
+      "mean_token_accuracy": 0.9792876356840133,
+      "num_tokens": 15791071.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.0779489404708147,
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.05987590551376343,
+      "learning_rate": 4.323553957759629e-08,
+      "loss": 0.0778,
+      "mean_token_accuracy": 0.9800369493663311,
+      "num_tokens": 16196052.0,
+      "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": 6.765523181366723e+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 sha256:657ec4ab83e11a499cf55047de3a4140964d0c9e7020c53c70cd1720cd946db4
+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 sha256:41a51e897954eedbdc9accbe97c6f604b531441c3a49b9086cf3947d777fe3f4
+size 58754616

checkpoint-2025/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9a22e53409fcd33edd489cecacf9f2894a1cf4fbde961fcee2dcc0cdcd5330e
+size 117660107

checkpoint-2025/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f35edb3c58982b0cb4bd8e4dc876872617db7f923a0e3cfd584597c20bf97e2b
+size 14645

checkpoint-2025/scheduler.pt

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