| --- |
| license: mit |
| library_name: peft |
| tags: |
| - generated_from_trainer |
| base_model: microsoft/Phi-3-mini-128k-instruct |
| model-index: |
| - name: CodePhi-3-mini-128k-instruct-appsloraN1.5k |
| 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. --> |
|
|
| # CodePhi-3-mini-128k-instruct-appsloraN1.5k |
|
|
| This model is a fine-tuned version of [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.6506 |
|
|
| ## 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: 5e-06 |
| - train_batch_size: 1 |
| - eval_batch_size: 1 |
| - seed: 42 |
| - gradient_accumulation_steps: 16 |
| - total_train_batch_size: 16 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_steps: 100 |
| - training_steps: 1500 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:------:|:----:|:---------------:| |
| | 0.5976 | 0.0667 | 100 | 0.7027 | |
| | 0.6556 | 0.1333 | 200 | 0.6810 | |
| | 0.6492 | 0.2 | 300 | 0.6706 | |
| | 0.5924 | 0.2667 | 400 | 0.6644 | |
| | 0.618 | 0.3333 | 500 | 0.6599 | |
| | 0.6025 | 0.4 | 600 | 0.6566 | |
| | 0.6049 | 0.4667 | 700 | 0.6539 | |
| | 0.5651 | 0.5333 | 800 | 0.6526 | |
| | 0.5803 | 0.6 | 900 | 0.6516 | |
| | 0.5371 | 0.6667 | 1000 | 0.6509 | |
| | 0.6274 | 0.7333 | 1100 | 0.6507 | |
| | 0.6122 | 0.8 | 1200 | 0.6506 | |
| | 0.5815 | 0.8667 | 1300 | 0.6506 | |
| | 0.6261 | 0.9333 | 1400 | 0.6505 | |
| | 0.5859 | 1.0 | 1500 | 0.6506 | |
|
|
|
|
| ### Framework versions |
|
|
| - PEFT 0.11.0 |
| - Transformers 4.40.2 |
| - Pytorch 2.3.0+cu121 |
| - Datasets 2.19.1 |
| - Tokenizers 0.19.1 |
