<!-- 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-mod-datatsets-rarity-all-iorder-end-e2p6k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 3.2957
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 |
|---|---|---|---|
| 6.7869 | 0.32 | 500 | 5.7284 |
| 5.4579 | 0.64 | 1000 | 5.2910 |
| 5.1043 | 0.96 | 1500 | 5.0285 |
| 4.8122 | 1.29 | 2000 | 4.8804 |
| 4.6778 | 1.61 | 2500 | 4.7468 |
| 4.5698 | 1.93 | 3000 | 4.6393 |
| 4.3448 | 2.25 | 3500 | 4.5904 |
| 4.2741 | 2.57 | 4000 | 4.5200 |
| 4.2236 | 2.89 | 4500 | 4.4587 |
| 4.0238 | 3.21 | 5000 | 4.4454 |
| 3.9471 | 3.53 | 5500 | 4.4139 |
| 3.9263 | 3.86 | 6000 | 4.3783 |
| 3.762 | 4.18 | 6500 | 4.3881 |
| 3.6523 | 4.5 | 7000 | 4.3756 |
| 3.6381 | 4.82 | 7500 | 4.3591 |
| 3.551 | 5.14 | 8000 | 4.3695 |
| 3.4483 | 5.46 | 8500 | 4.3720 |
| 3.4481 | 5.78 | 9000 | 4.3706 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
