<!-- 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-all-mod-aochildes-rarity-all-30k-3k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 3.0554
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: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.787 | 0.32 | 500 | 5.8319 |
| 5.4867 | 0.65 | 1000 | 5.4639 |
| 5.1388 | 0.97 | 1500 | 5.2444 |
| 4.8676 | 1.3 | 2000 | 5.1700 |
| 4.7551 | 1.62 | 2500 | 5.0582 |
| 4.6549 | 1.95 | 3000 | 4.9945 |
| 4.4476 | 2.27 | 3500 | 4.9966 |
| 4.4081 | 2.6 | 4000 | 4.9368 |
| 4.3708 | 2.92 | 4500 | 4.9070 |
| 4.1704 | 3.25 | 5000 | 4.9144 |
| 4.1343 | 3.57 | 5500 | 4.8945 |
| 4.1237 | 3.9 | 6000 | 4.8582 |
| 3.9238 | 4.22 | 6500 | 4.8881 |
| 3.8703 | 4.55 | 7000 | 4.8883 |
| 3.8693 | 4.87 | 7500 | 4.8628 |
| 3.6914 | 5.19 | 8000 | 4.9088 |
| 3.6022 | 5.52 | 8500 | 4.9100 |
| 3.6033 | 5.84 | 9000 | 4.9048 |
| 3.476 | 6.17 | 9500 | 4.9392 |
| 3.3693 | 6.49 | 10000 | 4.9473 |
| 3.3744 | 6.82 | 10500 | 4.9551 |
| 3.3104 | 7.14 | 11000 | 4.9658 |
| 3.2401 | 7.47 | 11500 | 4.9706 |
| 3.2421 | 7.79 | 12000 | 4.9727 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
