<!-- 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. -->
cbt-rarity-all-end-1p4k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3077
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 |
|---|---|---|---|
| 6.705 | 0.29 | 500 | 5.6382 |
| 5.3352 | 0.58 | 1000 | 5.1973 |
| 4.9831 | 0.88 | 1500 | 4.9543 |
| 4.7098 | 1.17 | 2000 | 4.7992 |
| 4.5476 | 1.46 | 2500 | 4.6765 |
| 4.4436 | 1.75 | 3000 | 4.5667 |
| 4.3188 | 2.04 | 3500 | 4.4893 |
| 4.1169 | 2.34 | 4000 | 4.4409 |
| 4.0949 | 2.63 | 4500 | 4.3818 |
| 4.0552 | 2.92 | 5000 | 4.3294 |
| 3.8456 | 3.21 | 5500 | 4.3266 |
| 3.8001 | 3.5 | 6000 | 4.2981 |
| 3.7779 | 3.8 | 6500 | 4.2623 |
| 3.6787 | 4.09 | 7000 | 4.2611 |
| 3.5059 | 4.38 | 7500 | 4.2555 |
| 3.5038 | 4.67 | 8000 | 4.2425 |
| 3.4966 | 4.96 | 8500 | 4.2272 |
| 3.3354 | 5.26 | 9000 | 4.2411 |
| 3.3139 | 5.55 | 9500 | 4.2406 |
| 3.3086 | 5.84 | 10000 | 4.2393 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
