<!-- 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-dp-cl-rarity-11-135k-mod-datasets-rarity1-root3
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.7616
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: 1
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
6.7003 | 0.05 | 500 | 5.8421 |
5.4077 | 0.1 | 1000 | 5.4379 |
5.0667 | 0.15 | 1500 | 5.2282 |
4.8285 | 0.2 | 2000 | 5.0890 |
4.6639 | 0.25 | 2500 | 4.9968 |
4.5282 | 0.29 | 3000 | 4.9414 |
4.4194 | 0.34 | 3500 | 4.8843 |
4.3138 | 0.39 | 4000 | 4.8436 |
4.2135 | 0.44 | 4500 | 4.8229 |
4.1242 | 0.49 | 5000 | 4.7947 |
4.0388 | 0.54 | 5500 | 4.7670 |
3.952 | 0.59 | 6000 | 4.7585 |
3.8701 | 0.64 | 6500 | 4.7431 |
3.8026 | 0.69 | 7000 | 4.7273 |
3.7345 | 0.74 | 7500 | 4.7219 |
3.6661 | 0.79 | 8000 | 4.7135 |
3.6259 | 0.84 | 8500 | 4.7072 |
3.5927 | 0.88 | 9000 | 4.7052 |
3.5699 | 0.93 | 9500 | 4.7025 |
3.5638 | 0.98 | 10000 | 4.7018 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3