<!-- 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_0529
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: 0.1485
- Accuracy: 0.9375
- F1: 0.9378
- Precision: 0.9124
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 |
---|---|---|---|---|---|---|
0.8109 | 1.0 | 250 | 0.2686 | 0.913 | 0.9111 | 0.8958 |
0.2078 | 2.0 | 500 | 0.1663 | 0.931 | 0.9309 | 0.9148 |
0.1383 | 3.0 | 750 | 0.1562 | 0.9365 | 0.9366 | 0.9170 |
0.114 | 4.0 | 1000 | 0.1485 | 0.9375 | 0.9378 | 0.9124 |
Framework versions
- Transformers 4.27.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3