<!-- 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. -->
aochildes-guten-fixed-rarity-mixed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1290
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 |
|---|---|---|---|
| 6.365 | 0.29 | 500 | 5.3433 |
| 5.0504 | 0.59 | 1000 | 4.9338 |
| 4.72 | 0.88 | 1500 | 4.6948 |
| 4.4681 | 1.17 | 2000 | 4.5525 |
| 4.3117 | 1.47 | 2500 | 4.4371 |
| 4.2069 | 1.76 | 3000 | 4.3333 |
| 4.0872 | 2.05 | 3500 | 4.2616 |
| 3.9143 | 2.35 | 4000 | 4.2156 |
| 3.88 | 2.64 | 4500 | 4.1594 |
| 3.8477 | 2.93 | 5000 | 4.1171 |
| 3.6334 | 3.23 | 5500 | 4.1165 |
| 3.607 | 3.52 | 6000 | 4.0836 |
| 3.5905 | 3.81 | 6500 | 4.0549 |
| 3.4793 | 4.11 | 7000 | 4.0555 |
| 3.3298 | 4.4 | 7500 | 4.0536 |
| 3.3312 | 4.69 | 8000 | 4.0366 |
| 3.3098 | 4.99 | 8500 | 4.0267 |
| 3.1519 | 5.28 | 9000 | 4.0423 |
| 3.1522 | 5.57 | 9500 | 4.0401 |
| 3.1459 | 5.87 | 10000 | 4.0393 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
