<!-- 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-datasets-rarity1-rerun
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 3.0263
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: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.7311 | 0.3 | 500 | 5.6497 |
| 5.3805 | 0.59 | 1000 | 5.2065 |
| 5.0306 | 0.89 | 1500 | 4.9574 |
| 4.7526 | 1.18 | 2000 | 4.8142 |
| 4.6058 | 1.48 | 2500 | 4.6885 |
| 4.4982 | 1.78 | 3000 | 4.5904 |
| 4.3593 | 2.07 | 3500 | 4.5261 |
| 4.185 | 2.37 | 4000 | 4.4783 |
| 4.154 | 2.66 | 4500 | 4.4233 |
| 4.1262 | 2.96 | 5000 | 4.3708 |
| 3.8986 | 3.26 | 5500 | 4.3804 |
| 3.8767 | 3.55 | 6000 | 4.3494 |
| 3.8605 | 3.85 | 6500 | 4.3124 |
| 3.7194 | 4.14 | 7000 | 4.3395 |
| 3.5981 | 4.44 | 7500 | 4.3194 |
| 3.5952 | 4.74 | 8000 | 4.3059 |
| 3.5511 | 5.03 | 8500 | 4.3089 |
| 3.3393 | 5.33 | 9000 | 4.3236 |
| 3.3388 | 5.62 | 9500 | 4.3220 |
| 3.3443 | 5.92 | 10000 | 4.3139 |
| 3.2213 | 6.22 | 10500 | 4.3304 |
| 3.1851 | 6.51 | 11000 | 4.3313 |
| 3.1911 | 6.81 | 11500 | 4.3317 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
