<!-- 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-cbt-rarity-all-4p5k-p3k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 3.1891
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 |
---|---|---|---|
6.7192 | 0.29 | 500 | 5.6402 |
5.37 | 0.58 | 1000 | 5.2012 |
5.0291 | 0.88 | 1500 | 4.9442 |
4.7507 | 1.17 | 2000 | 4.7965 |
4.5833 | 1.46 | 2500 | 4.6742 |
4.4772 | 1.75 | 3000 | 4.5664 |
4.3569 | 2.04 | 3500 | 4.4890 |
4.1616 | 2.34 | 4000 | 4.4396 |
4.1266 | 2.63 | 4500 | 4.3837 |
4.0807 | 2.92 | 5000 | 4.3330 |
3.8821 | 3.21 | 5500 | 4.3276 |
3.8204 | 3.5 | 6000 | 4.2971 |
3.8083 | 3.8 | 6500 | 4.2614 |
3.712 | 4.09 | 7000 | 4.2583 |
3.5343 | 4.38 | 7500 | 4.2532 |
3.5334 | 4.67 | 8000 | 4.2382 |
3.5216 | 4.96 | 8500 | 4.2254 |
3.3634 | 5.26 | 9000 | 4.2379 |
3.3443 | 5.55 | 9500 | 4.2367 |
3.3402 | 5.84 | 10000 | 4.2359 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3