<!-- 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. -->
gpt2-finetuned-seinfeld
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.0471
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
3.3835 | 0.99 | 26 | 3.2201 |
3.316 | 1.99 | 52 | 3.1480 |
3.2054 | 2.99 | 78 | 3.1031 |
3.1206 | 3.99 | 104 | 3.0799 |
3.0525 | 4.99 | 130 | 3.0655 |
2.9891 | 5.99 | 156 | 3.0589 |
2.9358 | 6.99 | 182 | 3.0504 |
2.8765 | 7.99 | 208 | 3.0493 |
2.8189 | 8.99 | 234 | 3.0497 |
2.7579 | 9.99 | 260 | 3.0471 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2