<!-- 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. -->
open_subtitles-log-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: 4.1754
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 |
---|---|---|---|
6.4321 | 0.3 | 500 | 5.3635 |
5.1155 | 0.61 | 1000 | 4.9745 |
4.7697 | 0.91 | 1500 | 4.7409 |
4.5189 | 1.22 | 2000 | 4.6014 |
4.3771 | 1.52 | 2500 | 4.4879 |
4.2813 | 1.83 | 3000 | 4.3878 |
4.1152 | 2.13 | 3500 | 4.3328 |
3.9934 | 2.44 | 4000 | 4.2727 |
3.9581 | 2.74 | 4500 | 4.2153 |
3.8771 | 3.05 | 5000 | 4.1827 |
3.6822 | 3.35 | 5500 | 4.1643 |
3.6785 | 3.66 | 6000 | 4.1326 |
3.6576 | 3.96 | 6500 | 4.0997 |
3.4438 | 4.27 | 7000 | 4.1078 |
3.4107 | 4.57 | 7500 | 4.0975 |
3.4026 | 4.88 | 8000 | 4.0827 |
3.2929 | 5.18 | 8500 | 4.0910 |
3.2304 | 5.49 | 9000 | 4.0919 |
3.2307 | 5.79 | 9500 | 4.0905 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3