gpt2_small_FR_superbpe_8192_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.5120
- Accuracy: 0.3427
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 |
|---|
| 6.196 | 1.0 | 1523 | 4.5002 | 0.2344 |
| 4.1809 | 2.0 | 3046 | 3.9973 | 0.2857 |
| 3.9696 | 3.0 | 4569 | 3.8062 | 0.3065 |
| 3.7653 | 4.0 | 6092 | 3.7039 | 0.3191 |
| 3.6894 | 5.0 | 7615 | 3.6384 | 0.3253 |
| 3.6013 | 6.0 | 9138 | 3.5913 | 0.3317 |
| 3.5558 | 7.0 | 10661 | 3.5596 | 0.3358 |
| 3.5031 | 8.0 | 12184 | 3.5352 | 0.3392 |
| 3.4755 | 9.0 | 13707 | 3.5192 | 0.3411 |
| 3.4439 | 10.0 | 15230 | 3.5120 | 0.3427 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
