<!-- 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_guten_mod_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: 4.1142
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 |
|---|---|---|---|
| 6.3334 | 0.29 | 500 | 5.3349 |
| 5.0261 | 0.58 | 1000 | 4.9336 |
| 4.7154 | 0.88 | 1500 | 4.6955 |
| 4.4459 | 1.17 | 2000 | 4.5492 |
| 4.3091 | 1.46 | 2500 | 4.4363 |
| 4.1996 | 1.75 | 3000 | 4.3329 |
| 4.0845 | 2.04 | 3500 | 4.2614 |
| 3.9009 | 2.34 | 4000 | 4.2199 |
| 3.8804 | 2.63 | 4500 | 4.1658 |
| 3.8367 | 2.92 | 5000 | 4.1110 |
| 3.6506 | 3.21 | 5500 | 4.1057 |
| 3.5925 | 3.5 | 6000 | 4.0814 |
| 3.5792 | 3.8 | 6500 | 4.0465 |
| 3.4905 | 4.09 | 7000 | 4.0440 |
| 3.3328 | 4.38 | 7500 | 4.0390 |
| 3.3201 | 4.67 | 8000 | 4.0244 |
| 3.3132 | 4.96 | 8500 | 4.0109 |
| 3.1672 | 5.26 | 9000 | 4.0239 |
| 3.1467 | 5.55 | 9500 | 4.0233 |
| 3.142 | 5.84 | 10000 | 4.0223 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
