<!-- 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. -->
rarity-guten-end-19k-cbt-p5k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3181
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 |
|---|---|---|---|
| 6.7036 | 0.29 | 500 | 5.6394 |
| 5.3354 | 0.59 | 1000 | 5.2009 |
| 4.9887 | 0.88 | 1500 | 4.9557 |
| 4.73 | 1.18 | 2000 | 4.8094 |
| 4.562 | 1.47 | 2500 | 4.6910 |
| 4.4541 | 1.77 | 3000 | 4.5849 |
| 4.3232 | 2.06 | 3500 | 4.5048 |
| 4.1357 | 2.36 | 4000 | 4.4546 |
| 4.116 | 2.65 | 4500 | 4.3942 |
| 4.0689 | 2.95 | 5000 | 4.3395 |
| 3.8466 | 3.24 | 5500 | 4.3376 |
| 3.8118 | 3.54 | 6000 | 4.3041 |
| 3.7934 | 3.83 | 6500 | 4.2713 |
| 3.6709 | 4.13 | 7000 | 4.2708 |
| 3.5286 | 4.42 | 7500 | 4.2653 |
| 3.517 | 4.72 | 8000 | 4.2466 |
| 3.5028 | 5.01 | 8500 | 4.2425 |
| 3.3328 | 5.31 | 9000 | 4.2491 |
| 3.3321 | 5.6 | 9500 | 4.2479 |
| 3.3329 | 5.9 | 10000 | 4.2468 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
