gpt2_small_TR_unigram_4271_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.2933
- Accuracy: 0.3869
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 |
|---|
| 5.5649 | 1.0 | 1746 | 4.1129 | 0.2897 |
| 3.94 | 2.0 | 3492 | 3.7047 | 0.3370 |
| 3.6507 | 3.0 | 5238 | 3.5531 | 0.3532 |
| 3.5634 | 4.0 | 6984 | 3.4653 | 0.3641 |
| 3.4511 | 5.0 | 8730 | 3.4081 | 0.3718 |
| 3.3819 | 6.0 | 10476 | 3.3671 | 0.3768 |
| 3.3289 | 7.0 | 12222 | 3.3387 | 0.3795 |
| 3.2969 | 8.0 | 13968 | 3.3160 | 0.3834 |
| 3.2567 | 9.0 | 15714 | 3.3005 | 0.3855 |
| 3.2306 | 10.0 | 17460 | 3.2933 | 0.3869 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
