gpt2_small_FR_bpe_8192_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.7071
- Accuracy: 0.4616
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 |
|---|
| 4.9232 | 1.0 | 1948 | 3.3301 | 0.3860 |
| 3.258 | 2.0 | 3896 | 3.0308 | 0.4195 |
| 3.0161 | 3.0 | 5844 | 2.9108 | 0.4339 |
| 2.8976 | 4.0 | 7792 | 2.8407 | 0.4427 |
| 2.8227 | 5.0 | 9740 | 2.7948 | 0.4491 |
| 2.7665 | 6.0 | 11688 | 2.7628 | 0.4534 |
| 2.7245 | 7.0 | 13636 | 2.7397 | 0.4569 |
| 2.6897 | 8.0 | 15584 | 2.7236 | 0.4591 |
| 2.6621 | 9.0 | 17532 | 2.7125 | 0.4608 |
| 2.6416 | 10.0 | 19480 | 2.7071 | 0.4616 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.9.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
