gpt2_small_AR_unigram_81920_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.6617
- Accuracy: 0.3306
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 |
|---|
| 7.0135 | 1.0 | 1373 | 5.7032 | 0.2801 |
| 5.6948 | 2.0 | 2746 | 5.2143 | 0.3027 |
| 5.1229 | 3.0 | 4119 | 5.0044 | 0.3132 |
| 4.9822 | 4.0 | 5492 | 4.8840 | 0.3172 |
| 4.885 | 5.0 | 6865 | 4.8039 | 0.3221 |
| 4.7415 | 6.0 | 8238 | 4.7471 | 0.3254 |
| 4.6878 | 7.0 | 9611 | 4.7092 | 0.3268 |
| 4.6484 | 8.0 | 10984 | 4.6841 | 0.3285 |
| 4.5797 | 9.0 | 12357 | 4.6681 | 0.3299 |
| 4.5598 | 10.0 | 13730 | 4.6617 | 0.3306 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
