| --- |
| license: mit |
| base_model: microsoft/phi-2 |
| tags: |
| - generated_from_trainer |
| datasets: |
| - mc4 |
| model-index: |
| - name: laft_tha_phi |
| 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. --> |
|
|
| # laft_tha_phi |
|
|
| This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the mc4 th dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.8405 |
|
|
| ## 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: 1 |
| - eval_batch_size: 1 |
| - seed: 42 |
| - distributed_type: multi-GPU |
| - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05 |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_steps: 2000 |
| - num_epochs: 6.0 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:-----:|:------:|:---------------:| |
| | 0.8258 | 1.0 | 24415 | 0.9875 | |
| | 1.4555 | 2.0 | 48830 | 0.9360 | |
| | 0.1738 | 3.0 | 73245 | 0.8877 | |
| | 0.7233 | 4.0 | 97660 | 0.8167 | |
| | 0.5537 | 5.0 | 122075 | 0.7832 | |
| | 0.3837 | 6.0 | 146490 | 0.8405 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.44.0 |
| - Pytorch 2.4.0+cu121 |
| - Datasets 2.20.0 |
| - Tokenizers 0.19.1 |
|
|
