gpt2_small_ZH_bpe_49152_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 5.3660
- Accuracy: 0.3007
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 |
|---|
| 7.3461 | 1.0 | 1201 | 6.5741 | 0.2603 |
| 6.4657 | 2.0 | 2402 | 6.1245 | 0.2682 |
| 6.139 | 3.0 | 3603 | 5.8858 | 0.2748 |
| 5.935 | 4.0 | 4804 | 5.7200 | 0.2818 |
| 5.6552 | 5.0 | 6005 | 5.5925 | 0.2884 |
| 5.5438 | 6.0 | 7206 | 5.5033 | 0.2933 |
| 5.4612 | 7.0 | 8407 | 5.4429 | 0.2968 |
| 5.3994 | 8.0 | 9608 | 5.4011 | 0.2989 |
| 5.3513 | 9.0 | 10809 | 5.3758 | 0.3002 |
| 5.2879 | 10.0 | 12010 | 5.3660 | 0.3007 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
