<!-- 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-rarity-all-guten-2p5k-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: 4.3195
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 |
|---|---|---|---|
| 6.6858 | 0.29 | 500 | 5.6433 |
| 5.3511 | 0.59 | 1000 | 5.2111 |
| 4.9925 | 0.88 | 1500 | 4.9524 |
| 4.7238 | 1.17 | 2000 | 4.8079 |
| 4.5666 | 1.47 | 2500 | 4.6856 |
| 4.453 | 1.76 | 3000 | 4.5716 |
| 4.3289 | 2.06 | 3500 | 4.5002 |
| 4.137 | 2.35 | 4000 | 4.4482 |
| 4.1124 | 2.64 | 4500 | 4.3913 |
| 4.0636 | 2.94 | 5000 | 4.3336 |
| 3.852 | 3.23 | 5500 | 4.3341 |
| 3.8135 | 3.52 | 6000 | 4.3033 |
| 3.7914 | 3.82 | 6500 | 4.2691 |
| 3.6733 | 4.11 | 7000 | 4.2704 |
| 3.5243 | 4.4 | 7500 | 4.2640 |
| 3.5183 | 4.7 | 8000 | 4.2479 |
| 3.5042 | 4.99 | 8500 | 4.2351 |
| 3.3345 | 5.28 | 9000 | 4.2497 |
| 3.3242 | 5.58 | 9500 | 4.2486 |
| 3.3254 | 5.87 | 10000 | 4.2476 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
