<!-- 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. -->
cbt_rarity-all-p5k-guten-rarity-all-mixed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3120
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 |
|---|---|---|---|
| 6.7048 | 0.29 | 500 | 5.6337 |
| 5.3413 | 0.58 | 1000 | 5.2097 |
| 4.9978 | 0.88 | 1500 | 4.9513 |
| 4.7156 | 1.17 | 2000 | 4.8019 |
| 4.5648 | 1.46 | 2500 | 4.6789 |
| 4.4578 | 1.75 | 3000 | 4.5759 |
| 4.3353 | 2.04 | 3500 | 4.4930 |
| 4.1339 | 2.33 | 4000 | 4.4498 |
| 4.1084 | 2.63 | 4500 | 4.3924 |
| 4.0661 | 2.92 | 5000 | 4.3386 |
| 3.8655 | 3.21 | 5500 | 4.3300 |
| 3.8072 | 3.5 | 6000 | 4.2981 |
| 3.7854 | 3.79 | 6500 | 4.2698 |
| 3.703 | 4.08 | 7000 | 4.2625 |
| 3.5143 | 4.38 | 7500 | 4.2608 |
| 3.5218 | 4.67 | 8000 | 4.2455 |
| 3.5048 | 4.96 | 8500 | 4.2308 |
| 3.3509 | 5.25 | 9000 | 4.2436 |
| 3.3237 | 5.54 | 9500 | 4.2428 |
| 3.3261 | 5.83 | 10000 | 4.2418 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
