<!-- 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-p8k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3054
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 |
|---|---|---|---|
| 6.694 | 0.29 | 500 | 5.6309 |
| 5.3347 | 0.58 | 1000 | 5.2043 |
| 4.9965 | 0.88 | 1500 | 4.9539 |
| 4.7114 | 1.17 | 2000 | 4.8013 |
| 4.5591 | 1.46 | 2500 | 4.6788 |
| 4.4472 | 1.75 | 3000 | 4.5686 |
| 4.3225 | 2.04 | 3500 | 4.4859 |
| 4.1246 | 2.33 | 4000 | 4.4444 |
| 4.0984 | 2.63 | 4500 | 4.3849 |
| 4.0541 | 2.92 | 5000 | 4.3333 |
| 3.8498 | 3.21 | 5500 | 4.3250 |
| 3.7946 | 3.5 | 6000 | 4.2926 |
| 3.7818 | 3.79 | 6500 | 4.2596 |
| 3.6918 | 4.08 | 7000 | 4.2579 |
| 3.5071 | 4.38 | 7500 | 4.2527 |
| 3.5112 | 4.67 | 8000 | 4.2387 |
| 3.4937 | 4.96 | 8500 | 4.2265 |
| 3.3413 | 5.25 | 9000 | 4.2384 |
| 3.3145 | 5.54 | 9500 | 4.2374 |
| 3.3183 | 5.83 | 10000 | 4.2366 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
