| | --- |
| | tags: |
| | - generated_from_trainer |
| | metrics: |
| | - accuracy |
| | model-index: |
| | - name: roberta-tiny-4l-10M |
| | 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. --> |
| |
|
| | # roberta-tiny-4l-10M |
| |
|
| | This model was trained from scratch on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 7.3432 |
| | - Accuracy: 0.0513 |
| |
|
| | ## 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: 0.0007 |
| | - train_batch_size: 16 |
| | - eval_batch_size: 32 |
| | - seed: 42 |
| | - gradient_accumulation_steps: 128 |
| | - total_train_batch_size: 2048 |
| | - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08 |
| | - lr_scheduler_type: cosine |
| | - lr_scheduler_warmup_steps: 50 |
| | - num_epochs: 100.0 |
| | - mixed_precision_training: Native AMP |
| |
|
| | ### Training results |
| |
|
| | | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| | |:-------------:|:-----:|:----:|:---------------:|:--------:| |
| | | 7.4785 | 4.16 | 50 | 7.3834 | 0.0514 | |
| | | 7.425 | 8.33 | 100 | 7.3559 | 0.0514 | |
| | | 7.4187 | 12.49 | 150 | 7.3517 | 0.0512 | |
| | | 7.4204 | 16.66 | 200 | 7.3440 | 0.0514 | |
| | | 7.4099 | 20.82 | 250 | 7.3454 | 0.0515 | |
| | | 7.2916 | 24.99 | 300 | 7.3442 | 0.0515 | |
| | | 7.4117 | 29.16 | 350 | 7.3440 | 0.0513 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.24.0 |
| | - Pytorch 1.11.0+cu113 |
| | - Datasets 2.6.1 |
| | - Tokenizers 0.12.1 |
| |
|
