| --- |
| base_model: microsoft/Phi-3-mini-128k-instruct |
| library_name: peft |
| license: mit |
| tags: |
| - trl |
| - sft |
| - generated_from_trainer |
| model-index: |
| - name: phi-3-mini-LoRA |
| 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/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/dohyung97022/phi3-128k-finetuning-v5/runs/tfd16g9i) |
| # phi-3-mini-LoRA |
|
|
| 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: 0.9261 |
|
|
| ## 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: 1 |
| - eval_batch_size: 1 |
| - seed: 42 |
| - gradient_accumulation_steps: 4 |
| - total_train_batch_size: 4 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_ratio: 0.1 |
| - num_epochs: 4 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:------:|:----:|:---------------:| |
| | 1.0422 | 0.6024 | 100 | 0.9495 | |
| | 0.8992 | 1.2048 | 200 | 0.9344 | |
| | 0.8815 | 1.8072 | 300 | 0.9300 | |
| | 0.8884 | 2.4096 | 400 | 0.9286 | |
| | 0.8645 | 3.0120 | 500 | 0.9257 | |
| | 0.8637 | 3.6145 | 600 | 0.9261 | |
|
|
|
|
| ### Framework versions |
|
|
| - PEFT 0.11.1 |
| - Transformers 4.42.4 |
| - Pytorch 2.3.0+cu121 |
| - Datasets 2.20.0 |
| - Tokenizers 0.19.1 |
