<!-- 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-no-cut-rerun-new-loop
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1043
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 |
|---|---|---|---|
| 6.3522 | 0.29 | 500 | 5.3397 |
| 5.0304 | 0.58 | 1000 | 4.9284 |
| 4.7066 | 0.88 | 1500 | 4.6876 |
| 4.4385 | 1.17 | 2000 | 4.5448 |
| 4.2956 | 1.46 | 2500 | 4.4290 |
| 4.192 | 1.75 | 3000 | 4.3244 |
| 4.0747 | 2.04 | 3500 | 4.2511 |
| 3.8895 | 2.33 | 4000 | 4.2067 |
| 3.865 | 2.63 | 4500 | 4.1510 |
| 3.8238 | 2.92 | 5000 | 4.1030 |
| 3.6322 | 3.21 | 5500 | 4.0978 |
| 3.5783 | 3.5 | 6000 | 4.0633 |
| 3.5675 | 3.79 | 6500 | 4.0378 |
| 3.4848 | 4.08 | 7000 | 4.0342 |
| 3.3106 | 4.38 | 7500 | 4.0309 |
| 3.3142 | 4.67 | 8000 | 4.0159 |
| 3.2988 | 4.96 | 8500 | 4.0031 |
| 3.1558 | 5.25 | 9000 | 4.0154 |
| 3.1315 | 5.54 | 9500 | 4.0143 |
| 3.1323 | 5.83 | 10000 | 4.0132 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
