<!-- 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-rm-2p3k-guten-rarity-all-no-cut
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3169
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 |
|---|---|---|---|
| 6.6986 | 0.29 | 500 | 5.6343 |
| 5.3344 | 0.58 | 1000 | 5.2021 |
| 4.9905 | 0.88 | 1500 | 4.9580 |
| 4.7149 | 1.17 | 2000 | 4.8044 |
| 4.5588 | 1.46 | 2500 | 4.6785 |
| 4.4525 | 1.75 | 3000 | 4.5765 |
| 4.3265 | 2.04 | 3500 | 4.4976 |
| 4.1289 | 2.34 | 4000 | 4.4494 |
| 4.1004 | 2.63 | 4500 | 4.3916 |
| 4.0707 | 2.92 | 5000 | 4.3407 |
| 3.861 | 3.21 | 5500 | 4.3344 |
| 3.7962 | 3.5 | 6000 | 4.3058 |
| 3.7897 | 3.79 | 6500 | 4.2693 |
| 3.6899 | 4.09 | 7000 | 4.2683 |
| 3.5172 | 4.38 | 7500 | 4.2615 |
| 3.5141 | 4.67 | 8000 | 4.2457 |
| 3.4965 | 4.96 | 8500 | 4.2348 |
| 3.3467 | 5.25 | 9000 | 4.2458 |
| 3.3219 | 5.55 | 9500 | 4.2465 |
| 3.3159 | 5.84 | 10000 | 4.2452 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
