Duplicate from 0x1202/3db70620-2779-4f5d-8926-7b3977e4a3b9

Co-authored-by: 0x1202 <0x1202@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,165 @@
+---
+library_name: peft
+license: bigcode-openrail-m
+base_model: bigcode/starcoder2-3b
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 3db70620-2779-4f5d-8926-7b3977e4a3b9
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: lora
+base_model: bigcode/starcoder2-3b
+bf16: true
+chat_template: llama3
+data_processes: 16
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - e2f97ded3d2e7b3d_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/e2f97ded3d2e7b3d_train_data.json
+  type:
+    field_input: choices
+    field_instruction: question
+    field_output: answer
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device_map: auto
+do_eval: true
+early_stopping_patience: 5
+eval_batch_size: 2
+eval_max_new_tokens: 128
+eval_steps: 50
+eval_table_size: null
+evals_per_epoch: null
+flash_attention: true
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: 0x1202/3db70620-2779-4f5d-8926-7b3977e4a3b9
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0001
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 128
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 64
+lora_target_linear: true
+lr_scheduler: cosine
+max_grad_norm: 1.0
+max_memory:
+  0: 75GB
+max_steps: 200
+micro_batch_size: 8
+mlflow_experiment_name: /tmp/e2f97ded3d2e7b3d_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 3
+optim_args:
+  adam_beta1: 0.9
+  adam_beta2: 0.95
+  adam_epsilon: 1e-5
+optimizer: adamw_torch
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 50
+saves_per_epoch: null
+sequence_len: 1024
+special_tokens:
+  pad_token: <|endoftext|>
+strict: false
+tf32: true
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: null
+wandb_mode: online
+wandb_name: df5d8278-7744-4576-8c82-4db0b61e8a2d
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: df5d8278-7744-4576-8c82-4db0b61e8a2d
+warmup_steps: 20
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 3db70620-2779-4f5d-8926-7b3977e4a3b9
+
+This model is a fine-tuned version of [bigcode/starcoder2-3b](https://huggingface.co/bigcode/starcoder2-3b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7339
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- training_steps: 63
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 33.8017       | 0.0476 | 1    | 8.4885          |
+| 2.8421        | 2.3810 | 50   | 0.7339          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigcode/starcoder2-3b",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "c_proj",
+    "c_fc",
+    "k_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:878e793f0ca01dad51b873ff8129da8613f381f3caba5ddb173709c6b4b9601c
+size 381549290

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6f539cae862091000d8e382e8d26c2d724a267c0980007ce73051a6ed7b5d65
+size 381467712

config.json

@@ -0,0 +1,31 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "bigcode/starcoder2-3b",
+  "architectures": [
+    "Starcoder2ForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "embedding_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_size": 3072,
+  "initializer_range": 0.018042,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 16384,
+  "mlp_type": "default",
+  "model_type": "starcoder2",
+  "norm_epsilon": 1e-05,
+  "norm_type": "layer_norm",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 2,
+  "residual_dropout": 0.1,
+  "rope_scaling": null,
+  "rope_theta": 999999.4420358813,
+  "sliding_window": 4096,
+  "transformers_version": "4.46.0",
+  "use_bias": true,
+  "use_cache": false,
+  "vocab_size": 49152
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: bigcode/starcoder2-3b
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.2

last-checkpoint/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigcode/starcoder2-3b",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "c_proj",
+    "c_fc",
+    "k_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8c0d77fc68826caff6ed48bef2ede6097c0b0b2e0a3d69679e1f7840583794
+size 381467712

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f32e5d3a614001dce47d674a3a525553cfc1aaedfb453114f04d7f61fd1b28e
+size 763142410

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2669227e8cf84bfa0341ef1f0aaeb18ec95cc3e598892a80acdc1939b1c78722
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:badf8dd7fd843c03f3dfa379f5a62cbdac918ff18b84343f94ed7c04cd128a3f
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,70 @@
+{
+  "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
+  },
+  "pad_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
+  }
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,358 @@
+{
+  "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|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,499 @@
+{
+  "best_metric": 0.7339180707931519,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 3.0,
+  "eval_steps": 50,
+  "global_step": 63,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 70.61749267578125,
+      "learning_rate": 5e-06,
+      "loss": 33.8017,
+      "step": 1
+    },
+    {
+      "epoch": 0.047619047619047616,
+      "eval_loss": 8.488510131835938,
+      "eval_runtime": 1.5143,
+      "eval_samples_per_second": 23.774,
+      "eval_steps_per_second": 11.887,
+      "step": 1
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 89.3288345336914,
+      "learning_rate": 1e-05,
+      "loss": 36.8574,
+      "step": 2
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 80.17635345458984,
+      "learning_rate": 1.5e-05,
+      "loss": 37.14,
+      "step": 3
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 75.35139465332031,
+      "learning_rate": 2e-05,
+      "loss": 35.5743,
+      "step": 4
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 80.63961791992188,
+      "learning_rate": 2.5e-05,
+      "loss": 35.1564,
+      "step": 5
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 75.4241943359375,
+      "learning_rate": 3e-05,
+      "loss": 30.6528,
+      "step": 6
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 73.1867446899414,
+      "learning_rate": 3.5e-05,
+      "loss": 27.3585,
+      "step": 7
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 66.09611511230469,
+      "learning_rate": 4e-05,
+      "loss": 20.9346,
+      "step": 8
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 61.280120849609375,
+      "learning_rate": 4.5e-05,
+      "loss": 16.2169,
+      "step": 9
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 44.32679748535156,
+      "learning_rate": 5e-05,
+      "loss": 12.3205,
+      "step": 10
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 51.232906341552734,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.1753,
+      "step": 11
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 53.598365783691406,
+      "learning_rate": 6e-05,
+      "loss": 9.5126,
+      "step": 12
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "grad_norm": 49.24958419799805,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 6.3121,
+      "step": 13
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 36.19329833984375,
+      "learning_rate": 7e-05,
+      "loss": 4.8738,
+      "step": 14
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 25.576393127441406,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 4.6295,
+      "step": 15
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 39.14617919921875,
+      "learning_rate": 8e-05,
+      "loss": 3.8308,
+      "step": 16
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 28.955108642578125,
+      "learning_rate": 8.5e-05,
+      "loss": 3.9269,
+      "step": 17
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 33.5592155456543,
+      "learning_rate": 9e-05,
+      "loss": 4.2107,
+      "step": 18
+    },
+    {
+      "epoch": 0.9047619047619048,
+      "grad_norm": 29.655385971069336,
+      "learning_rate": 9.5e-05,
+      "loss": 3.5708,
+      "step": 19
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 26.0640811920166,
+      "learning_rate": 0.0001,
+      "loss": 3.4429,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 38.40494918823242,
+      "learning_rate": 9.986661418317759e-05,
+      "loss": 3.5586,
+      "step": 21
+    },
+    {
+      "epoch": 1.0476190476190477,
+      "grad_norm": 14.375667572021484,
+      "learning_rate": 9.946716840375551e-05,
+      "loss": 3.3643,
+      "step": 22
+    },
+    {
+      "epoch": 1.0952380952380953,
+      "grad_norm": 25.285995483398438,
+      "learning_rate": 9.880379387779637e-05,
+      "loss": 3.4791,
+      "step": 23
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 11.269182205200195,
+      "learning_rate": 9.78800299954203e-05,
+      "loss": 2.9826,
+      "step": 24
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 15.11327838897705,
+      "learning_rate": 9.67008054366274e-05,
+      "loss": 3.1094,
+      "step": 25
+    },
+    {
+      "epoch": 1.2380952380952381,
+      "grad_norm": 16.692920684814453,
+      "learning_rate": 9.527241187465734e-05,
+      "loss": 2.9784,
+      "step": 26
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 36.734500885009766,
+      "learning_rate": 9.360247040719039e-05,
+      "loss": 3.5783,
+      "step": 27
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 14.008699417114258,
+      "learning_rate": 9.16998908944939e-05,
+      "loss": 2.9826,
+      "step": 28
+    },
+    {
+      "epoch": 1.380952380952381,
+      "grad_norm": 11.462227821350098,
+      "learning_rate": 8.957482442146272e-05,
+      "loss": 3.0921,
+      "step": 29
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 13.71957015991211,
+      "learning_rate": 8.72386091371891e-05,
+      "loss": 3.3794,
+      "step": 30
+    },
+    {
+      "epoch": 1.4761904761904763,
+      "grad_norm": 4.488590240478516,
+      "learning_rate": 8.47037097610317e-05,
+      "loss": 2.7482,
+      "step": 31
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": 9.806519508361816,
+      "learning_rate": 8.198365107794457e-05,
+      "loss": 2.7917,
+      "step": 32
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 19.80751609802246,
+      "learning_rate": 7.909294577789766e-05,
+      "loss": 3.4169,
+      "step": 33
+    },
+    {
+      "epoch": 1.619047619047619,
+      "grad_norm": 14.619462966918945,
+      "learning_rate": 7.604701702439651e-05,
+      "loss": 3.326,
+      "step": 34
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 16.35366439819336,
+      "learning_rate": 7.286211616523193e-05,
+      "loss": 3.2313,
+      "step": 35
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 6.2724609375,
+      "learning_rate": 6.95552360245078e-05,
+      "loss": 2.8079,
+      "step": 36
+    },
+    {
+      "epoch": 1.7619047619047619,
+      "grad_norm": 10.460845947265625,
+      "learning_rate": 6.614402023857232e-05,
+      "loss": 2.9459,
+      "step": 37
+    },
+    {
+      "epoch": 1.8095238095238095,
+      "grad_norm": 9.461526870727539,
+      "learning_rate": 6.264666911958404e-05,
+      "loss": 2.9598,
+      "step": 38
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 7.6167097091674805,
+      "learning_rate": 5.908184254897182e-05,
+      "loss": 2.9533,
+      "step": 39
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 9.928021430969238,
+      "learning_rate": 5.546856041889373e-05,
+      "loss": 2.9279,
+      "step": 40
+    },
+    {
+      "epoch": 1.9523809523809523,
+      "grad_norm": 5.470791339874268,
+      "learning_rate": 5.182610115288295e-05,
+      "loss": 2.9515,
+      "step": 41
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.028589725494385,
+      "learning_rate": 4.817389884711705e-05,
+      "loss": 3.0166,
+      "step": 42
+    },
+    {
+      "epoch": 2.0476190476190474,
+      "grad_norm": 5.838282585144043,
+      "learning_rate": 4.4531439581106295e-05,
+      "loss": 2.8832,
+      "step": 43
+    },
+    {
+      "epoch": 2.0952380952380953,
+      "grad_norm": 7.127386093139648,
+      "learning_rate": 4.0918157451028185e-05,
+      "loss": 2.9343,
+      "step": 44
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 5.750761985778809,
+      "learning_rate": 3.735333088041596e-05,
+      "loss": 2.8033,
+      "step": 45
+    },
+    {
+      "epoch": 2.1904761904761907,
+      "grad_norm": 7.080549240112305,
+      "learning_rate": 3.38559797614277e-05,
+      "loss": 2.6489,
+      "step": 46
+    },
+    {
+      "epoch": 2.238095238095238,
+      "grad_norm": 3.680392265319824,
+      "learning_rate": 3.0444763975492208e-05,
+      "loss": 2.7227,
+      "step": 47
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 4.481716632843018,
+      "learning_rate": 2.7137883834768073e-05,
+      "loss": 2.8145,
+      "step": 48
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 10.20344352722168,
+      "learning_rate": 2.3952982975603496e-05,
+      "loss": 3.0544,
+      "step": 49
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 6.239677906036377,
+      "learning_rate": 2.090705422210237e-05,
+      "loss": 2.8421,
+      "step": 50
+    },
+    {
+      "epoch": 2.380952380952381,
+      "eval_loss": 0.7339180707931519,
+      "eval_runtime": 1.53,
+      "eval_samples_per_second": 23.53,
+      "eval_steps_per_second": 11.765,
+      "step": 50
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 5.302610874176025,
+      "learning_rate": 1.801634892205545e-05,
+      "loss": 2.907,
+      "step": 51
+    },
+    {
+      "epoch": 2.4761904761904763,
+      "grad_norm": 3.535484790802002,
+      "learning_rate": 1.5296290238968303e-05,
+      "loss": 2.816,
+      "step": 52
+    },
+    {
+      "epoch": 2.5238095238095237,
+      "grad_norm": 2.9045586585998535,
+      "learning_rate": 1.2761390862810907e-05,
+      "loss": 2.8551,
+      "step": 53
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 5.55578088760376,
+      "learning_rate": 1.0425175578537299e-05,
+      "loss": 2.7582,
+      "step": 54
+    },
+    {
+      "epoch": 2.619047619047619,
+      "grad_norm": 7.579736232757568,
+      "learning_rate": 8.30010910550611e-06,
+      "loss": 2.8881,
+      "step": 55
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 4.39998722076416,
+      "learning_rate": 6.397529592809614e-06,
+      "loss": 2.7402,
+      "step": 56
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 8.276344299316406,
+      "learning_rate": 4.727588125342669e-06,
+      "loss": 2.7021,
+      "step": 57
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 4.667769908905029,
+      "learning_rate": 3.299194563372604e-06,
+      "loss": 2.9088,
+      "step": 58
+    },
+    {
+      "epoch": 2.8095238095238093,
+      "grad_norm": 4.007717132568359,
+      "learning_rate": 2.1199700045797077e-06,
+      "loss": 2.8541,
+      "step": 59
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 6.375820636749268,
+      "learning_rate": 1.196206122203647e-06,
+      "loss": 2.864,
+      "step": 60
+    },
+    {
+      "epoch": 2.9047619047619047,
+      "grad_norm": 4.68563175201416,
+      "learning_rate": 5.328315962444874e-07,
+      "loss": 2.8855,
+      "step": 61
+    },
+    {
+      "epoch": 2.9523809523809526,
+      "grad_norm": 4.791390895843506,
+      "learning_rate": 1.333858168224178e-07,
+      "loss": 2.7794,
+      "step": 62
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 7.031291484832764,
+      "learning_rate": 0.0,
+      "loss": 2.8601,
+      "step": 63
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 63,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.673626526089216e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d98d215f1060c6ed2da7a4041c1e7b594a546aca545ecb16a3a6a2d9f5879f7d
+size 6840

special_tokens_map.json

@@ -0,0 +1,70 @@
+{
+  "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
+  },
+  "pad_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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,358 @@
+{
+  "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|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d98d215f1060c6ed2da7a4041c1e7b594a546aca545ecb16a3a6a2d9f5879f7d
+size 6840