gpt2_small_EN_bpe_100000_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.2764
- Accuracy: 0.4161
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 |
|---|
| 5.5559 | 1.0 | 1746 | 3.8054 | 0.3709 |
| 3.7075 | 2.0 | 3492 | 3.5672 | 0.3883 |
| 3.5182 | 3.0 | 5238 | 3.4628 | 0.3980 |
| 3.4499 | 4.0 | 6984 | 3.3983 | 0.4033 |
| 3.3575 | 5.0 | 8730 | 3.3543 | 0.4079 |
| 3.2971 | 6.0 | 10476 | 3.3247 | 0.4101 |
| 3.2491 | 7.0 | 12222 | 3.3038 | 0.4127 |
| 3.2197 | 8.0 | 13968 | 3.2887 | 0.4145 |
| 3.1841 | 9.0 | 15714 | 3.2801 | 0.4156 |
| 3.162 | 10.0 | 17460 | 3.2764 | 0.4161 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
