| --- |
| license: mit |
| base_model: microsoft/phi-2 |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: V0410MP6 |
| 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. --> |
|
|
| # V0410MP6 |
|
|
| 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: 0.1573 |
|
|
| ## 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: 0.03 |
| - 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 | |
| |:-------------:|:-----:|:----:|:---------------:| |
| | 0.2535 | 0.18 | 20 | 0.1664 | |
| | 0.1614 | 0.36 | 40 | 0.1584 | |
| | 0.1611 | 0.54 | 60 | 0.1564 | |
| | 0.1614 | 0.73 | 80 | 0.1567 | |
| | 0.1549 | 0.91 | 100 | 0.1555 | |
| | 0.1565 | 1.09 | 120 | 0.1573 | |
| | 0.1553 | 1.27 | 140 | 0.1578 | |
| | 0.1554 | 1.45 | 160 | 0.1564 | |
| | 0.1572 | 1.63 | 180 | 0.1578 | |
| | 0.1534 | 1.81 | 200 | 0.1573 | |
| | 0.1581 | 1.99 | 220 | 0.1573 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.36.0.dev0 |
| - Pytorch 2.1.2+cu121 |
| - Datasets 2.14.6 |
| - Tokenizers 0.14.1 |
|
|
