<!-- 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. -->
miniLm-tuned-emotion
This model is a fine-tuned version of microsoft/MiniLm-L12-H384-uncased on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.1777
- F1: 0.9384
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: 64
- eval_batch_size: 64
- 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 | F1 |
---|---|---|---|---|
0.0968 | 1.0 | 250 | 0.1843 | 0.9323 |
0.0798 | 2.0 | 500 | 0.1784 | 0.9380 |
0.0698 | 3.0 | 750 | 0.2012 | 0.9380 |
0.0639 | 4.0 | 1000 | 0.1847 | 0.9420 |
0.0593 | 5.0 | 1250 | 0.1777 | 0.9384 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3