gpt2_medium_ZH_bpe_65536_parallel3-100_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.4299
- Accuracy: 0.3240
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 |
|---|
| 5.4852 | 1.0 | 5523 | 5.2515 | 0.2615 |
| 4.9222 | 2.0 | 11046 | 4.8275 | 0.2878 |
| 4.7037 | 3.0 | 16569 | 4.6563 | 0.2997 |
| 4.5377 | 4.0 | 22092 | 4.5611 | 0.3085 |
| 4.4214 | 5.0 | 27615 | 4.5023 | 0.3137 |
| 4.3173 | 6.0 | 33138 | 4.4674 | 0.3171 |
| 4.2303 | 7.0 | 38661 | 4.4464 | 0.3198 |
| 4.1511 | 8.0 | 44184 | 4.4369 | 0.3220 |
| 4.0822 | 9.0 | 49707 | 4.4309 | 0.3232 |
| 4.0256 | 10.0 | 55230 | 4.4299 | 0.3240 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
