| --- |
| license: mit |
| base_model: microsoft/phi-2 |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: V0408MP6 |
| 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. --> |
|
|
| # V0408MP6 |
|
|
| This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.2973 |
|
|
| ## 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: 0.0003 |
| - train_batch_size: 8 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - gradient_accumulation_steps: 16 |
| - total_train_batch_size: 128 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: cosine_with_restarts |
| - lr_scheduler_warmup_steps: 20 |
| - num_epochs: 2 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:-----:|:----:|:---------------:| |
| | 6.1578 | 0.09 | 10 | 5.4708 | |
| | 5.3721 | 0.18 | 20 | 4.6279 | |
| | 3.968 | 0.27 | 30 | 3.4562 | |
| | 2.7382 | 0.36 | 40 | 2.5521 | |
| | 1.863 | 0.45 | 50 | 1.9953 | |
| | 1.3779 | 0.54 | 60 | 1.6314 | |
| | 1.0695 | 0.63 | 70 | 1.3712 | |
| | 0.8284 | 0.73 | 80 | 1.1788 | |
| | 0.6698 | 0.82 | 90 | 1.0471 | |
| | 0.5725 | 0.91 | 100 | 0.9459 | |
| | 0.4905 | 1.0 | 110 | 0.8649 | |
| | 0.961 | 1.09 | 120 | 0.5360 | |
| | 0.7176 | 1.18 | 130 | 0.4220 | |
| | 0.6284 | 1.27 | 140 | 0.3701 | |
| | 0.5176 | 1.36 | 150 | 0.3409 | |
| | 0.4973 | 1.45 | 160 | 0.3233 | |
| | 0.4747 | 1.54 | 170 | 0.3122 | |
| | 0.4566 | 1.63 | 180 | 0.3043 | |
| | 0.4338 | 1.72 | 190 | 0.3002 | |
| | 0.4333 | 1.81 | 200 | 0.2983 | |
| | 0.4315 | 1.9 | 210 | 0.2976 | |
| | 0.4348 | 1.99 | 220 | 0.2973 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.36.0.dev0 |
| - Pytorch 2.1.2+cu121 |
| - Datasets 2.14.6 |
| - Tokenizers 0.14.1 |
|
|
