<!-- 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-rarity-cut-seed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1224
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 |
|---|---|---|---|
| 6.3514 | 0.29 | 500 | 5.3501 |
| 5.045 | 0.59 | 1000 | 4.9290 |
| 4.7213 | 0.88 | 1500 | 4.6893 |
| 4.4515 | 1.17 | 2000 | 4.5504 |
| 4.3046 | 1.46 | 2500 | 4.4356 |
| 4.1974 | 1.76 | 3000 | 4.3392 |
| 4.0962 | 2.05 | 3500 | 4.2626 |
| 3.8992 | 2.34 | 4000 | 4.2172 |
| 3.8818 | 2.63 | 4500 | 4.1666 |
| 3.8397 | 2.93 | 5000 | 4.1141 |
| 3.6504 | 3.22 | 5500 | 4.1101 |
| 3.5971 | 3.51 | 6000 | 4.0814 |
| 3.5789 | 3.8 | 6500 | 4.0525 |
| 3.4848 | 4.1 | 7000 | 4.0495 |
| 3.326 | 4.39 | 7500 | 4.0447 |
| 3.3224 | 4.68 | 8000 | 4.0311 |
| 3.3133 | 4.97 | 8500 | 4.0196 |
| 3.1639 | 5.27 | 9000 | 4.0325 |
| 3.1433 | 5.56 | 9500 | 4.0317 |
| 3.1391 | 5.85 | 10000 | 4.0309 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
