gpt2_small_AR_superbpe_7909_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.0837
- Accuracy: 0.2909
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 |
|---|
| 6.6569 | 1.0 | 1593 | 5.1133 | 0.2006 |
| 4.824 | 2.0 | 3186 | 4.6008 | 0.2401 |
| 4.6007 | 3.0 | 4779 | 4.4009 | 0.2581 |
| 4.3745 | 4.0 | 6372 | 4.2926 | 0.2682 |
| 4.2992 | 5.0 | 7965 | 4.2214 | 0.2756 |
| 4.1889 | 6.0 | 9558 | 4.1694 | 0.2806 |
| 4.123 | 7.0 | 11151 | 4.1346 | 0.2855 |
| 4.083 | 8.0 | 12744 | 4.1081 | 0.2875 |
| 4.0394 | 9.0 | 14337 | 4.0919 | 0.2897 |
| 4.0185 | 10.0 | 15930 | 4.0837 | 0.2909 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
