bert-base-uncased-amazon-massive-intent
This model is a fine-tuned version of bert-base-uncased on Amazon Massive dataset (only en-US subset). It achieves the following results on the evaluation set:
- Loss: 0.4897
- Accuracy: 0.8903
- F1: 0.8903
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 2.5862 | 1.0 | 720 | 1.0160 | 0.8096 | 0.8096 |
| 1.0591 | 2.0 | 1440 | 0.6003 | 0.8716 | 0.8716 |
| 0.4151 | 3.0 | 2160 | 0.5113 | 0.8859 | 0.8859 |
| 0.3028 | 4.0 | 2880 | 0.5030 | 0.8883 | 0.8883 |
| 0.1852 | 5.0 | 3600 | 0.4897 | 0.8903 | 0.8903 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1