<!-- 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-miss-cbt-seed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1336
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 |
|---|---|---|---|
| 6.3272 | 0.31 | 500 | 5.3559 |
| 5.0184 | 0.61 | 1000 | 4.9377 |
| 4.6905 | 0.92 | 1500 | 4.7047 |
| 4.4183 | 1.22 | 2000 | 4.5602 |
| 4.2842 | 1.53 | 2500 | 4.4477 |
| 4.1746 | 1.83 | 3000 | 4.3341 |
| 4.0002 | 2.14 | 3500 | 4.2774 |
| 3.8776 | 2.44 | 4000 | 4.2189 |
| 3.8524 | 2.75 | 4500 | 4.1618 |
| 3.7691 | 3.05 | 5000 | 4.1277 |
| 3.575 | 3.36 | 5500 | 4.1122 |
| 3.5747 | 3.66 | 6000 | 4.0774 |
| 3.548 | 3.97 | 6500 | 4.0453 |
| 3.3299 | 4.27 | 7000 | 4.0648 |
| 3.2994 | 4.58 | 7500 | 4.0483 |
| 3.2955 | 4.88 | 8000 | 4.0332 |
| 3.1853 | 5.19 | 8500 | 4.0422 |
| 3.1201 | 5.49 | 9000 | 4.0422 |
| 3.1215 | 5.8 | 9500 | 4.0409 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
