<!-- 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_aochildes_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: 4.1487
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 |
|---|---|---|---|
| 6.3667 | 0.29 | 500 | 5.3506 |
| 5.0646 | 0.59 | 1000 | 4.9379 |
| 4.7383 | 0.88 | 1500 | 4.7025 |
| 4.478 | 1.18 | 2000 | 4.5619 |
| 4.3265 | 1.47 | 2500 | 4.4462 |
| 4.2316 | 1.77 | 3000 | 4.3544 |
| 4.1042 | 2.06 | 3500 | 4.2884 |
| 3.936 | 2.36 | 4000 | 4.2414 |
| 3.9057 | 2.65 | 4500 | 4.1840 |
| 3.8624 | 2.95 | 5000 | 4.1340 |
| 3.6568 | 3.24 | 5500 | 4.1357 |
| 3.622 | 3.54 | 6000 | 4.1047 |
| 3.6008 | 3.83 | 6500 | 4.0736 |
| 3.486 | 4.12 | 7000 | 4.0760 |
| 3.3511 | 4.42 | 7500 | 4.0744 |
| 3.3423 | 4.71 | 8000 | 4.0601 |
| 3.332 | 5.01 | 8500 | 4.0531 |
| 3.1709 | 5.3 | 9000 | 4.0641 |
| 3.1645 | 5.6 | 9500 | 4.0631 |
| 3.1651 | 5.89 | 10000 | 4.0630 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
