<!-- 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. -->
distilbert-base-uncased-finetuned-himani_auto-text-gen
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.7913
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: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.8212 | 1.0 | 30 | 2.9480 |
| 4.0493 | 2.0 | 60 | 1.9459 |
| 3.5449 | 3.0 | 90 | 3.1831 |
| 3.6318 | 4.0 | 120 | 4.5427 |
| 3.4761 | 5.0 | 150 | 4.6722 |
| 2.9815 | 6.0 | 180 | 5.4563 |
| 3.1247 | 7.0 | 210 | 3.6281 |
| 2.9715 | 8.0 | 240 | 4.5996 |
| 2.8263 | 9.0 | 270 | 3.7812 |
| 2.3001 | 10.0 | 300 | 4.1159 |
| 2.656 | 11.0 | 330 | 4.0686 |
| 2.5122 | 12.0 | 360 | 3.4073 |
| 1.8478 | 13.0 | 390 | 3.1591 |
| 2.5157 | 14.0 | 420 | 3.4517 |
| 2.0329 | 15.0 | 450 | 2.5513 |
| 2.2727 | 16.0 | 480 | 3.1985 |
| 1.591 | 17.0 | 510 | 2.7810 |
| 1.81 | 18.0 | 540 | 4.5671 |
| 2.0059 | 19.0 | 570 | 2.9868 |
| 1.8184 | 20.0 | 600 | 5.4829 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.2
- Tokenizers 0.13.3
