| --- |
| library_name: transformers |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: sI_b256 |
| 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. --> |
|
|
| # sI_b256 |
| |
| This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 3.1416 |
| |
| ## 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: 0.0035355339059327372 |
| - train_batch_size: 256 |
| - eval_batch_size: 256 |
| - seed: 42 |
| - gradient_accumulation_steps: 8 |
| - total_train_batch_size: 2048 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_steps: 1000 |
| - num_epochs: 1 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:------:|:-----:|:---------------:| |
| | 3.9254 | 0.1718 | 5000 | 3.5494 | |
| | 3.5128 | 0.3435 | 10000 | 3.4209 | |
| | 3.4093 | 0.5153 | 15000 | 3.3317 | |
| | 3.3189 | 0.6871 | 20000 | 3.2404 | |
| | 3.2233 | 0.8588 | 25000 | 3.1416 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.45.0.dev0 |
| - Pytorch 2.4.1+cu124 |
| - Datasets 3.0.0 |
| - Tokenizers 0.19.1 |
| |
