<!-- 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. -->
children_stories-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: 4.0996
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 |
---|---|---|---|
6.3312 | 0.29 | 500 | 5.3354 |
5.0371 | 0.58 | 1000 | 4.9186 |
4.6965 | 0.87 | 1500 | 4.6883 |
4.4447 | 1.16 | 2000 | 4.5459 |
4.2947 | 1.46 | 2500 | 4.4323 |
4.1916 | 1.75 | 3000 | 4.3253 |
4.0754 | 2.04 | 3500 | 4.2524 |
3.886 | 2.33 | 4000 | 4.2091 |
3.8693 | 2.62 | 4500 | 4.1548 |
3.8235 | 2.91 | 5000 | 4.1078 |
3.6423 | 3.2 | 5500 | 4.0967 |
3.5745 | 3.49 | 6000 | 4.0700 |
3.5702 | 3.78 | 6500 | 4.0351 |
3.489 | 4.07 | 7000 | 4.0307 |
3.3135 | 4.37 | 7500 | 4.0300 |
3.3057 | 4.66 | 8000 | 4.0129 |
3.294 | 4.95 | 8500 | 4.0020 |
3.151 | 5.24 | 9000 | 4.0121 |
3.1315 | 5.53 | 9500 | 4.0117 |
3.127 | 5.82 | 10000 | 4.0105 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3