gpt2_small_DE_bpe_12310_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.1999
- Accuracy: 0.4174
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 |
|---|
| 5.4654 | 1.0 | 1746 | 3.9950 | 0.3349 |
| 3.8405 | 2.0 | 3492 | 3.6137 | 0.3685 |
| 3.5601 | 3.0 | 5238 | 3.4620 | 0.3848 |
| 3.4726 | 4.0 | 6984 | 3.3698 | 0.3963 |
| 3.3554 | 5.0 | 8730 | 3.3118 | 0.4027 |
| 3.2812 | 6.0 | 10476 | 3.2687 | 0.4075 |
| 3.2279 | 7.0 | 12222 | 3.2384 | 0.4119 |
| 3.1962 | 8.0 | 13968 | 3.2198 | 0.4145 |
| 3.1561 | 9.0 | 15714 | 3.2062 | 0.4167 |
| 3.1313 | 10.0 | 17460 | 3.1999 | 0.4174 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
