<!-- 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-base-Massive-intent
This model is a fine-tuned version of bert-base-uncased on the massive dataset. It achieves the following results on the evaluation set:
- Loss: 0.6707
- Accuracy: 0.8859
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 33
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6844 | 1.0 | 720 | 0.7190 | 0.8387 |
| 0.4713 | 2.0 | 1440 | 0.5449 | 0.8726 |
| 0.2459 | 3.0 | 2160 | 0.5893 | 0.8790 |
| 0.1469 | 4.0 | 2880 | 0.6631 | 0.8795 |
| 0.0874 | 5.0 | 3600 | 0.6707 | 0.8859 |
| 0.0507 | 6.0 | 4320 | 0.7189 | 0.8844 |
| 0.0344 | 7.0 | 5040 | 0.7480 | 0.8854 |
| 0.0225 | 8.0 | 5760 | 0.7956 | 0.8844 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1
