<!-- 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. -->
demo_model
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3071
- Accuracy: 0.9556
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.2576 | 1.0 | 4298 | 0.2377 | 0.9363 |
0.1865 | 2.0 | 8596 | 0.2192 | 0.9463 |
0.1306 | 3.0 | 12894 | 0.2071 | 0.9525 |
0.0954 | 4.0 | 17192 | 0.2278 | 0.9522 |
0.0734 | 5.0 | 21490 | 0.2453 | 0.9534 |
0.0568 | 6.0 | 25788 | 0.2612 | 0.9541 |
0.0427 | 7.0 | 30086 | 0.2736 | 0.9567 |
0.0332 | 8.0 | 34384 | 0.2861 | 0.9559 |
0.0296 | 9.0 | 38682 | 0.3014 | 0.9552 |
0.0198 | 10.0 | 42980 | 0.3071 | 0.9556 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3