gpt2_small_RU_bpe_49152_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.7435
- Accuracy: 0.4037
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 |
|---|
| 6.0741 | 1.0 | 1554 | 4.7069 | 0.3371 |
| 4.452 | 2.0 | 3108 | 4.2815 | 0.3615 |
| 4.2495 | 3.0 | 4662 | 4.0820 | 0.3754 |
| 4.0252 | 4.0 | 6216 | 3.9642 | 0.3847 |
| 3.938 | 5.0 | 7770 | 3.8836 | 0.3911 |
| 3.8264 | 6.0 | 9324 | 3.8304 | 0.3955 |
| 3.7804 | 7.0 | 10878 | 3.7928 | 0.3992 |
| 3.7116 | 8.0 | 12432 | 3.7662 | 0.4013 |
| 3.6878 | 9.0 | 13986 | 3.7494 | 0.4022 |
| 3.6472 | 10.0 | 15540 | 3.7435 | 0.4037 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.9.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
