gpt2_small_RU_bpe_65536_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.8071
- Accuracy: 0.4025
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 |
|---|
| 6.1489 | 1.0 | 1527 | 4.7391 | 0.3425 |
| 4.4852 | 2.0 | 3054 | 4.3308 | 0.3627 |
| 4.2914 | 3.0 | 4581 | 4.1418 | 0.3750 |
| 4.079 | 4.0 | 6108 | 4.0240 | 0.3843 |
| 3.991 | 5.0 | 7635 | 3.9461 | 0.3905 |
| 3.8831 | 6.0 | 9162 | 3.8923 | 0.3948 |
| 3.8325 | 7.0 | 10689 | 3.8554 | 0.3977 |
| 3.7688 | 8.0 | 12216 | 3.8296 | 0.4004 |
| 3.7396 | 9.0 | 13743 | 3.8137 | 0.4019 |
| 3.7054 | 10.0 | 15270 | 3.8071 | 0.4025 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.9.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
