<!-- 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. -->
bnc-rarity-no-cut-rerun-new-loop
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1195
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 |
---|---|---|---|
6.3551 | 0.29 | 500 | 5.3418 |
5.0486 | 0.58 | 1000 | 4.9250 |
4.7195 | 0.88 | 1500 | 4.6902 |
4.4505 | 1.17 | 2000 | 4.5554 |
4.3122 | 1.46 | 2500 | 4.4397 |
4.2086 | 1.75 | 3000 | 4.3377 |
4.0988 | 2.05 | 3500 | 4.2667 |
3.9066 | 2.34 | 4000 | 4.2201 |
3.8832 | 2.63 | 4500 | 4.1674 |
3.8411 | 2.92 | 5000 | 4.1144 |
3.6573 | 3.22 | 5500 | 4.1102 |
3.6052 | 3.51 | 6000 | 4.0806 |
3.5785 | 3.8 | 6500 | 4.0520 |
3.4876 | 4.09 | 7000 | 4.0516 |
3.3346 | 4.39 | 7500 | 4.0438 |
3.3193 | 4.68 | 8000 | 4.0291 |
3.315 | 4.97 | 8500 | 4.0162 |
3.1611 | 5.26 | 9000 | 4.0307 |
3.1496 | 5.56 | 9500 | 4.0291 |
3.147 | 5.85 | 10000 | 4.0281 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3