<!-- 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-cbt-rarity-iorder-2k-p3k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 3.1774
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 |
|---|---|---|---|
| 6.7131 | 0.29 | 500 | 5.6430 |
| 5.375 | 0.58 | 1000 | 5.1968 |
| 5.0193 | 0.87 | 1500 | 4.9479 |
| 4.7453 | 1.17 | 2000 | 4.7999 |
| 4.5773 | 1.46 | 2500 | 4.6700 |
| 4.4741 | 1.75 | 3000 | 4.5630 |
| 4.3595 | 2.04 | 3500 | 4.4810 |
| 4.147 | 2.33 | 4000 | 4.4299 |
| 4.1212 | 2.62 | 4500 | 4.3779 |
| 4.0799 | 2.91 | 5000 | 4.3250 |
| 3.8841 | 3.21 | 5500 | 4.3160 |
| 3.8202 | 3.5 | 6000 | 4.2871 |
| 3.7956 | 3.79 | 6500 | 4.2533 |
| 3.7127 | 4.08 | 7000 | 4.2505 |
| 3.5311 | 4.37 | 7500 | 4.2459 |
| 3.5233 | 4.66 | 8000 | 4.2311 |
| 3.5046 | 4.95 | 8500 | 4.2175 |
| 3.3596 | 5.24 | 9000 | 4.2289 |
| 3.3317 | 5.54 | 9500 | 4.2278 |
| 3.331 | 5.83 | 10000 | 4.2271 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
