<!-- 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-guten-mod-rarity-iorder-e1k-ep1k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 3.1764
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 |
|---|---|---|---|
| 6.7142 | 0.29 | 500 | 5.6402 |
| 5.3675 | 0.59 | 1000 | 5.2080 |
| 5.0162 | 0.88 | 1500 | 4.9495 |
| 4.7415 | 1.17 | 2000 | 4.7972 |
| 4.5796 | 1.47 | 2500 | 4.6741 |
| 4.4755 | 1.76 | 3000 | 4.5646 |
| 4.3352 | 2.05 | 3500 | 4.4846 |
| 4.1424 | 2.35 | 4000 | 4.4381 |
| 4.1237 | 2.64 | 4500 | 4.3785 |
| 4.0767 | 2.93 | 5000 | 4.3254 |
| 3.866 | 3.23 | 5500 | 4.3222 |
| 3.8116 | 3.52 | 6000 | 4.2890 |
| 3.8011 | 3.81 | 6500 | 4.2546 |
| 3.6876 | 4.11 | 7000 | 4.2563 |
| 3.5206 | 4.4 | 7500 | 4.2498 |
| 3.5211 | 4.69 | 8000 | 4.2322 |
| 3.5138 | 4.99 | 8500 | 4.2213 |
| 3.3361 | 5.28 | 9000 | 4.2348 |
| 3.3334 | 5.57 | 9500 | 4.2340 |
| 3.3228 | 5.87 | 10000 | 4.2330 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
