<!-- 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-seed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1201
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 |
---|---|---|---|
6.3595 | 0.29 | 500 | 5.3368 |
5.0415 | 0.58 | 1000 | 4.9326 |
4.7185 | 0.88 | 1500 | 4.6926 |
4.4523 | 1.17 | 2000 | 4.5588 |
4.3072 | 1.46 | 2500 | 4.4367 |
4.2083 | 1.75 | 3000 | 4.3335 |
4.0868 | 2.05 | 3500 | 4.2634 |
3.8988 | 2.34 | 4000 | 4.2149 |
3.8845 | 2.63 | 4500 | 4.1600 |
3.8307 | 2.92 | 5000 | 4.1128 |
3.646 | 3.22 | 5500 | 4.1082 |
3.5944 | 3.51 | 6000 | 4.0811 |
3.5769 | 3.8 | 6500 | 4.0478 |
3.487 | 4.09 | 7000 | 4.0476 |
3.3222 | 4.39 | 7500 | 4.0415 |
3.3218 | 4.68 | 8000 | 4.0281 |
3.3142 | 4.97 | 8500 | 4.0157 |
3.161 | 5.26 | 9000 | 4.0304 |
3.148 | 5.56 | 9500 | 4.0290 |
3.1368 | 5.85 | 10000 | 4.0281 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3