<!-- 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. -->
all-base-rarity-all-cbt-rarity-all-p8k-iorder-est-5p5k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3333
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 |
---|---|---|---|
6.7559 | 0.31 | 500 | 5.6511 |
5.4062 | 0.63 | 1000 | 5.2172 |
5.0687 | 0.94 | 1500 | 4.9678 |
4.7662 | 1.25 | 2000 | 4.8187 |
4.628 | 1.57 | 2500 | 4.6878 |
4.5225 | 1.88 | 3000 | 4.5768 |
4.3098 | 2.19 | 3500 | 4.5210 |
4.2125 | 2.51 | 4000 | 4.4508 |
4.1764 | 2.82 | 4500 | 4.3910 |
4.0275 | 3.13 | 5000 | 4.3703 |
3.8912 | 3.45 | 5500 | 4.3383 |
3.8735 | 3.76 | 6000 | 4.3003 |
3.7925 | 4.07 | 6500 | 4.2941 |
3.5917 | 4.39 | 7000 | 4.2879 |
3.5908 | 4.7 | 7500 | 4.2713 |
3.577 | 5.01 | 8000 | 4.2617 |
3.4004 | 5.33 | 8500 | 4.2710 |
3.3993 | 5.64 | 9000 | 4.2699 |
3.3898 | 5.95 | 9500 | 4.2692 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3