<!-- 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-bnc-rarity-12k-1p5k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 3.1872
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 |
|---|---|---|---|
| 6.7337 | 0.29 | 500 | 5.6373 |
| 5.3734 | 0.59 | 1000 | 5.1990 |
| 5.0255 | 0.88 | 1500 | 4.9588 |
| 4.7542 | 1.18 | 2000 | 4.7996 |
| 4.593 | 1.47 | 2500 | 4.6785 |
| 4.4842 | 1.76 | 3000 | 4.5724 |
| 4.353 | 2.06 | 3500 | 4.4943 |
| 4.1666 | 2.35 | 4000 | 4.4439 |
| 4.1294 | 2.65 | 4500 | 4.3928 |
| 4.0879 | 2.94 | 5000 | 4.3360 |
| 3.8794 | 3.23 | 5500 | 4.3322 |
| 3.8264 | 3.53 | 6000 | 4.3009 |
| 3.8139 | 3.82 | 6500 | 4.2684 |
| 3.6919 | 4.12 | 7000 | 4.2740 |
| 3.542 | 4.41 | 7500 | 4.2658 |
| 3.5326 | 4.7 | 8000 | 4.2494 |
| 3.5195 | 5.0 | 8500 | 4.2370 |
| 3.3414 | 5.29 | 9000 | 4.2524 |
| 3.3457 | 5.58 | 9500 | 4.2512 |
| 3.3385 | 5.88 | 10000 | 4.2500 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
