<!-- 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. -->
distilbert-emotion-intent
This model is a fine-tuned version of distilbert-base-uncased on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.1989
- Accuracy: 0.937
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 |
---|---|---|---|---|
0.3939 | 1.0 | 1000 | 0.2123 | 0.9285 |
0.1539 | 2.0 | 2000 | 0.1635 | 0.936 |
0.1213 | 3.0 | 3000 | 0.1820 | 0.931 |
0.1016 | 4.0 | 4000 | 0.1989 | 0.937 |
0.0713 | 5.0 | 5000 | 0.2681 | 0.935 |
0.0462 | 6.0 | 6000 | 0.3034 | 0.9365 |
0.027 | 7.0 | 7000 | 0.3538 | 0.937 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1