<!-- 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-children-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: 4.3041
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 |
---|---|---|---|
6.6911 | 0.29 | 500 | 5.6297 |
5.3391 | 0.58 | 1000 | 5.1981 |
4.9881 | 0.87 | 1500 | 4.9521 |
4.7132 | 1.16 | 2000 | 4.7947 |
4.5556 | 1.46 | 2500 | 4.6743 |
4.4441 | 1.75 | 3000 | 4.5685 |
4.3241 | 2.04 | 3500 | 4.4891 |
4.1211 | 2.33 | 4000 | 4.4398 |
4.0983 | 2.62 | 4500 | 4.3846 |
4.0564 | 2.91 | 5000 | 4.3257 |
3.8632 | 3.2 | 5500 | 4.3216 |
3.7913 | 3.49 | 6000 | 4.2901 |
3.7794 | 3.78 | 6500 | 4.2588 |
3.693 | 4.07 | 7000 | 4.2573 |
3.508 | 4.37 | 7500 | 4.2534 |
3.5022 | 4.66 | 8000 | 4.2377 |
3.4941 | 4.95 | 8500 | 4.2240 |
3.341 | 5.24 | 9000 | 4.2355 |
3.3176 | 5.53 | 9500 | 4.2352 |
3.3059 | 5.82 | 10000 | 4.2347 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3