<!-- 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-mod-formatting-rarity-no-cut
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3220
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 |
|---|---|---|---|
| 6.6963 | 0.29 | 500 | 5.6460 |
| 5.339 | 0.58 | 1000 | 5.2151 |
| 4.9881 | 0.87 | 1500 | 4.9639 |
| 4.7163 | 1.17 | 2000 | 4.8133 |
| 4.5583 | 1.46 | 2500 | 4.6867 |
| 4.4467 | 1.75 | 3000 | 4.5797 |
| 4.3262 | 2.04 | 3500 | 4.5034 |
| 4.1271 | 2.33 | 4000 | 4.4547 |
| 4.0958 | 2.62 | 4500 | 4.3996 |
| 4.0656 | 2.92 | 5000 | 4.3439 |
| 3.8593 | 3.21 | 5500 | 4.3407 |
| 3.8057 | 3.5 | 6000 | 4.3111 |
| 3.7844 | 3.79 | 6500 | 4.2748 |
| 3.684 | 4.08 | 7000 | 4.2752 |
| 3.5114 | 4.37 | 7500 | 4.2698 |
| 3.5119 | 4.66 | 8000 | 4.2560 |
| 3.498 | 4.96 | 8500 | 4.2415 |
| 3.3431 | 5.25 | 9000 | 4.2555 |
| 3.3208 | 5.54 | 9500 | 4.2541 |
| 3.3169 | 5.83 | 10000 | 4.2527 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
