gpt2_medium_ZH_bpe_32768_parallel3_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.7870
- Accuracy: 0.3681
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: 64
- eval_batch_size: 64
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 128
- total_eval_batch_size: 128
- 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 |
|---|
| 4.2866 | 1.0 | 22680 | 4.2187 | 0.3189 |
| 4.0787 | 2.0 | 45360 | 4.0402 | 0.3368 |
| 3.9649 | 3.0 | 68040 | 3.9566 | 0.3451 |
| 3.8912 | 4.0 | 90720 | 3.9052 | 0.3517 |
| 3.8295 | 5.0 | 113400 | 3.8694 | 0.3550 |
| 3.7774 | 6.0 | 136080 | 3.8416 | 0.3596 |
| 3.728 | 7.0 | 158760 | 3.8210 | 0.3624 |
| 3.685 | 8.0 | 181440 | 3.8046 | 0.3648 |
| 3.6395 | 9.0 | 204120 | 3.7923 | 0.3672 |
| 3.5987 | 10.0 | 226800 | 3.7870 | 0.3681 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
