<!-- 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. -->
concat-cl-rarity-all-base-rarity-all-iorder-5p5k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.7611
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: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.5939 | 0.05 | 500 | 5.7911 |
| 5.3314 | 0.11 | 1000 | 5.3918 |
| 4.9794 | 0.16 | 1500 | 5.1739 |
| 4.7558 | 0.21 | 2000 | 5.0572 |
| 4.5948 | 0.26 | 2500 | 4.9703 |
| 4.4717 | 0.32 | 3000 | 4.9111 |
| 4.3542 | 0.37 | 3500 | 4.8589 |
| 4.2537 | 0.42 | 4000 | 4.8299 |
| 4.1629 | 0.48 | 4500 | 4.7936 |
| 4.0724 | 0.53 | 5000 | 4.7776 |
| 3.9856 | 0.58 | 5500 | 4.7594 |
| 3.8979 | 0.63 | 6000 | 4.7457 |
| 3.8286 | 0.69 | 6500 | 4.7269 |
| 3.7589 | 0.74 | 7000 | 4.7128 |
| 3.7037 | 0.79 | 7500 | 4.7066 |
| 3.6596 | 0.85 | 8000 | 4.7021 |
| 3.6308 | 0.9 | 8500 | 4.6989 |
| 3.6143 | 0.95 | 9000 | 4.6964 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
