distilbert-base-uncased-distilled-clinc
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: 0.3033
- Accuracy: 0.9442
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: 48
- eval_batch_size: 48
- 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 |
---|---|---|---|---|
2.6145 | 1.0 | 318 | 1.8929 | 0.7213 |
1.4633 | 2.0 | 636 | 0.9656 | 0.8677 |
0.7728 | 3.0 | 954 | 0.5575 | 0.9103 |
0.4641 | 4.0 | 1272 | 0.4082 | 0.9306 |
0.3342 | 5.0 | 1590 | 0.3504 | 0.9371 |
0.2786 | 6.0 | 1908 | 0.3256 | 0.9432 |
0.2514 | 7.0 | 2226 | 0.3150 | 0.9435 |
0.2365 | 8.0 | 2544 | 0.3096 | 0.9413 |
0.2275 | 9.0 | 2862 | 0.3055 | 0.9445 |
0.224 | 10.0 | 3180 | 0.3033 | 0.9442 |
Framework versions
- Transformers 4.36.2
- Pytorch 1.13.1+cu116
- Datasets 2.16.2.dev0
- Tokenizers 0.15.0
- Downloads last month
- 5