<!-- 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_cbt_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: 4.1218
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 |
|---|---|---|---|
| 6.366 | 0.29 | 500 | 5.3305 |
| 5.0478 | 0.59 | 1000 | 4.9325 |
| 4.7159 | 0.88 | 1500 | 4.6882 |
| 4.4541 | 1.17 | 2000 | 4.5478 |
| 4.3142 | 1.46 | 2500 | 4.4363 |
| 4.2068 | 1.76 | 3000 | 4.3334 |
| 4.0948 | 2.05 | 3500 | 4.2611 |
| 3.9065 | 2.34 | 4000 | 4.2156 |
| 3.8793 | 2.63 | 4500 | 4.1613 |
| 3.8461 | 2.93 | 5000 | 4.1146 |
| 3.6533 | 3.22 | 5500 | 4.1112 |
| 3.5945 | 3.51 | 6000 | 4.0788 |
| 3.5863 | 3.81 | 6500 | 4.0459 |
| 3.4902 | 4.1 | 7000 | 4.0491 |
| 3.3324 | 4.39 | 7500 | 4.0429 |
| 3.3243 | 4.68 | 8000 | 4.0290 |
| 3.3156 | 4.98 | 8500 | 4.0193 |
| 3.1646 | 5.27 | 9000 | 4.0316 |
| 3.1471 | 5.56 | 9500 | 4.0313 |
| 3.1498 | 5.85 | 10000 | 4.0303 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
