<!-- 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-guten-rarity-iroder-est-rarity-all-5k-2p5k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 3.1825
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 |
|---|---|---|---|
| 6.7149 | 0.3 | 500 | 5.6379 |
| 5.3626 | 0.59 | 1000 | 5.2053 |
| 5.0103 | 0.89 | 1500 | 4.9561 |
| 4.7374 | 1.18 | 2000 | 4.8042 |
| 4.5794 | 1.48 | 2500 | 4.6786 |
| 4.4756 | 1.77 | 3000 | 4.5728 |
| 4.3345 | 2.07 | 3500 | 4.4966 |
| 4.1538 | 2.36 | 4000 | 4.4468 |
| 4.1275 | 2.66 | 4500 | 4.3875 |
| 4.0815 | 2.95 | 5000 | 4.3316 |
| 3.8534 | 3.25 | 5500 | 4.3293 |
| 3.8151 | 3.54 | 6000 | 4.2939 |
| 3.8069 | 3.84 | 6500 | 4.2572 |
| 3.6706 | 4.13 | 7000 | 4.2627 |
| 3.5322 | 4.43 | 7500 | 4.2534 |
| 3.5274 | 4.73 | 8000 | 4.2397 |
| 3.4978 | 5.02 | 8500 | 4.2343 |
| 3.3402 | 5.32 | 9000 | 4.2407 |
| 3.3342 | 5.61 | 9500 | 4.2388 |
| 3.3308 | 5.91 | 10000 | 4.2382 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
