<!-- 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. -->
bert-tomi
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: 0.5795
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|
| No log | 1.0 | 20 | 1.4813 |
| No log | 2.0 | 40 | 0.8226 |
| No log | 3.0 | 60 | 0.8029 |
| No log | 4.0 | 80 | 0.7540 |
| No log | 5.0 | 100 | 0.6975 |
| No log | 6.0 | 120 | 0.6551 |
| No log | 7.0 | 140 | 0.5427 |
| No log | 8.0 | 160 | 0.6468 |
| No log | 9.0 | 180 | 0.5132 |
| No log | 10.0 | 200 | 0.5187 |
| No log | 11.0 | 220 | 0.4608 |
| No log | 12.0 | 240 | 0.4695 |
| No log | 13.0 | 260 | 0.5127 |
| No log | 14.0 | 280 | 0.4852 |
| No log | 15.0 | 300 | 0.9083 |
| No log | 16.0 | 320 | 0.6483 |
| No log | 17.0 | 340 | 0.5506 |
| No log | 18.0 | 360 | 0.5809 |
| No log | 19.0 | 380 | 0.5848 |
| No log | 20.0 | 400 | 0.5795 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
