gpt2_small_FR_bpe_65536_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.9833
- Accuracy: 0.4420
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|
| 5.3077 | 1.0 | 1749 | 3.5483 | 0.3941 |
| 3.4441 | 2.0 | 3498 | 3.3016 | 0.4122 |
| 3.2499 | 3.0 | 5247 | 3.1905 | 0.4209 |
| 3.1792 | 4.0 | 6996 | 3.1208 | 0.4263 |
| 3.0847 | 5.0 | 8745 | 3.0727 | 0.4312 |
| 3.0221 | 6.0 | 10494 | 3.0381 | 0.4348 |
| 2.9736 | 7.0 | 12243 | 3.0154 | 0.4377 |
| 2.9461 | 8.0 | 13992 | 2.9981 | 0.4396 |
| 2.9079 | 9.0 | 15741 | 2.9872 | 0.4413 |
| 2.8871 | 10.0 | 17490 | 2.9833 | 0.4420 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
