<!-- 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-base-uncased_emotion_ft_0416
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: 0.1481
- Accuracy: 0.9385
- F1: 0.9387
- Precision: 0.9103
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: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision |
---|---|---|---|---|---|---|
0.7769 | 1.0 | 250 | 0.2467 | 0.9205 | 0.9196 | 0.8974 |
0.2029 | 2.0 | 500 | 0.1649 | 0.9325 | 0.9321 | 0.9162 |
0.1382 | 3.0 | 750 | 0.1523 | 0.935 | 0.9355 | 0.9023 |
0.1121 | 4.0 | 1000 | 0.1481 | 0.9385 | 0.9387 | 0.9103 |
Framework versions
- Transformers 4.27.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3