<!-- 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_rarity_log_rarity_cut_19k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1132
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 |
|---|---|---|---|
| 6.3562 | 0.29 | 500 | 5.3379 |
| 5.0341 | 0.59 | 1000 | 4.9352 |
| 4.7053 | 0.88 | 1500 | 4.6936 |
| 4.4428 | 1.17 | 2000 | 4.5576 |
| 4.2966 | 1.47 | 2500 | 4.4398 |
| 4.1926 | 1.76 | 3000 | 4.3375 |
| 4.0766 | 2.05 | 3500 | 4.2600 |
| 3.892 | 2.35 | 4000 | 4.2162 |
| 3.8759 | 2.64 | 4500 | 4.1578 |
| 3.8269 | 2.93 | 5000 | 4.1082 |
| 3.6299 | 3.23 | 5500 | 4.1043 |
| 3.5924 | 3.52 | 6000 | 4.0715 |
| 3.5701 | 3.81 | 6500 | 4.0432 |
| 3.4615 | 4.11 | 7000 | 4.0445 |
| 3.3157 | 4.4 | 7500 | 4.0380 |
| 3.3114 | 4.69 | 8000 | 4.0206 |
| 3.3104 | 4.99 | 8500 | 4.0080 |
| 3.1448 | 5.28 | 9000 | 4.0219 |
| 3.1356 | 5.57 | 9500 | 4.0212 |
| 3.1365 | 5.87 | 10000 | 4.0203 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
