ossp-reverse-v0_3
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5481
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: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2235 | 0.2 | 10000 | 1.0768 |
| 0.8477 | 0.39 | 20000 | 0.7847 |
| 0.7494 | 0.59 | 30000 | 0.7090 |
| 0.6854 | 0.79 | 40000 | 0.6623 |
| 0.6673 | 0.98 | 50000 | 0.6288 |
| 0.6002 | 1.18 | 60000 | 0.6092 |
| 0.5839 | 1.38 | 70000 | 0.5894 |
| 0.5642 | 1.57 | 80000 | 0.5731 |
| 0.5564 | 1.77 | 90000 | 0.5572 |
| 0.5496 | 1.97 | 100000 | 0.5481 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Tokenizers 0.13.3