<!-- 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-gutenberg_fixed-notm-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: 4.1452
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: 128
- eval_batch_size: 128
- 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 |
---|---|---|---|
6.2287 | 0.59 | 500 | 5.1296 |
4.7894 | 1.17 | 1000 | 4.6882 |
4.4055 | 1.76 | 1500 | 4.4303 |
4.1038 | 2.34 | 2000 | 4.2799 |
3.9529 | 2.93 | 2500 | 4.1705 |
3.7134 | 3.52 | 3000 | 4.1288 |
3.6138 | 4.1 | 3500 | 4.0921 |
3.4188 | 4.69 | 4000 | 4.0665 |
3.3146 | 5.28 | 4500 | 4.0712 |
3.2243 | 5.86 | 5000 | 4.0652 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3