<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bnc_spoken-gutenberg_fixed-not-mixed-rarity-seed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1290
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: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.3575 | 0.29 | 500 | 5.3508 |
| 5.0454 | 0.59 | 1000 | 4.9293 |
| 4.7215 | 0.88 | 1500 | 4.6988 |
| 4.4664 | 1.17 | 2000 | 4.5559 |
| 4.3196 | 1.46 | 2500 | 4.4411 |
| 4.2129 | 1.76 | 3000 | 4.3422 |
| 4.0849 | 2.05 | 3500 | 4.2688 |
| 3.9127 | 2.34 | 4000 | 4.2228 |
| 3.8846 | 2.63 | 4500 | 4.1692 |
| 3.8456 | 2.93 | 5000 | 4.1214 |
| 3.6549 | 3.22 | 5500 | 4.1186 |
| 3.6084 | 3.51 | 6000 | 4.0832 |
| 3.5865 | 3.8 | 6500 | 4.0558 |
| 3.4886 | 4.1 | 7000 | 4.0536 |
| 3.3352 | 4.39 | 7500 | 4.0479 |
| 3.3306 | 4.68 | 8000 | 4.0346 |
| 3.3197 | 4.97 | 8500 | 4.0253 |
| 3.1677 | 5.27 | 9000 | 4.0370 |
| 3.1535 | 5.56 | 9500 | 4.0357 |
| 3.1531 | 5.85 | 10000 | 4.0352 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
