|
--- |
|
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 |
|
|
