gpt2_medium_EN_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: 2.8759
- Accuracy: 0.4636
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 |
|---|
| 3.4023 | 1.0 | 7940 | 3.2790 | 0.4149 |
| 3.1435 | 2.0 | 15880 | 3.0874 | 0.4339 |
| 3.0117 | 3.0 | 23820 | 2.9995 | 0.4440 |
| 2.9171 | 4.0 | 31760 | 2.9478 | 0.4507 |
| 2.8422 | 5.0 | 39700 | 2.9148 | 0.4541 |
| 2.7751 | 6.0 | 47640 | 2.8962 | 0.4571 |
| 2.7136 | 7.0 | 55580 | 2.8819 | 0.4605 |
| 2.6605 | 8.0 | 63520 | 2.8788 | 0.4616 |
| 2.6104 | 9.0 | 71460 | 2.8754 | 0.4628 |
| 2.5681 | 10.0 | 79400 | 2.8759 | 0.4636 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
