<!-- 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. -->
guten-raqrity-log-rarity-no-cut
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1129
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 |
|---|---|---|---|
| 6.3432 | 0.29 | 500 | 5.3400 |
| 5.0375 | 0.58 | 1000 | 4.9224 |
| 4.7018 | 0.87 | 1500 | 4.6880 |
| 4.4418 | 1.16 | 2000 | 4.5537 |
| 4.3059 | 1.46 | 2500 | 4.4374 |
| 4.1943 | 1.75 | 3000 | 4.3310 |
| 4.084 | 2.04 | 3500 | 4.2580 |
| 3.8919 | 2.33 | 4000 | 4.2195 |
| 3.8697 | 2.62 | 4500 | 4.1600 |
| 3.8291 | 2.91 | 5000 | 4.1122 |
| 3.6488 | 3.2 | 5500 | 4.1011 |
| 3.5862 | 3.49 | 6000 | 4.0753 |
| 3.5729 | 3.79 | 6500 | 4.0437 |
| 3.4885 | 4.08 | 7000 | 4.0376 |
| 3.3164 | 4.37 | 7500 | 4.0371 |
| 3.3169 | 4.66 | 8000 | 4.0220 |
| 3.3017 | 4.95 | 8500 | 4.0090 |
| 3.1581 | 5.24 | 9000 | 4.0217 |
| 3.1392 | 5.53 | 9500 | 4.0204 |
| 3.1322 | 5.82 | 10000 | 4.0196 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
