<!-- 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-concat-all-mod-datasets1-rarity-all-iorder-end-c2p6k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3830
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 |
|---|---|---|---|
| 6.784 | 0.32 | 500 | 5.6510 |
| 5.4458 | 0.63 | 1000 | 5.2234 |
| 5.0999 | 0.95 | 1500 | 4.9802 |
| 4.8039 | 1.26 | 2000 | 4.8338 |
| 4.6712 | 1.58 | 2500 | 4.7110 |
| 4.5643 | 1.89 | 3000 | 4.5978 |
| 4.3499 | 2.21 | 3500 | 4.5524 |
| 4.2538 | 2.52 | 4000 | 4.4816 |
| 4.2202 | 2.84 | 4500 | 4.4235 |
| 4.0629 | 3.15 | 5000 | 4.4144 |
| 3.9341 | 3.47 | 5500 | 4.3803 |
| 3.9186 | 3.78 | 6000 | 4.3457 |
| 3.8084 | 4.1 | 6500 | 4.3452 |
| 3.6343 | 4.41 | 7000 | 4.3378 |
| 3.6317 | 4.73 | 7500 | 4.3197 |
| 3.5947 | 5.04 | 8000 | 4.3232 |
| 3.4369 | 5.36 | 8500 | 4.3272 |
| 3.434 | 5.67 | 9000 | 4.3271 |
| 3.4327 | 5.99 | 9500 | 4.3265 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
