bert-base-uncased-finetuned-emotion
This model is a fine-tuned version of bert-base-uncased on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.3648
- Accuracy: 0.9405
- F1: 0.9404
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: 15
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
0.0177 | 1.0 | 250 | 0.3372 | 0.933 | 0.9331 |
0.0149 | 2.0 | 500 | 0.3434 | 0.9385 | 0.9386 |
0.012 | 3.0 | 750 | 0.3878 | 0.9355 | 0.9353 |
0.0135 | 4.0 | 1000 | 0.3981 | 0.938 | 0.9371 |
0.0088 | 5.0 | 1250 | 0.3695 | 0.94 | 0.9400 |
0.0112 | 6.0 | 1500 | 0.4133 | 0.933 | 0.9334 |
0.0105 | 7.0 | 1750 | 0.3733 | 0.937 | 0.9370 |
0.0117 | 8.0 | 2000 | 0.3625 | 0.938 | 0.9381 |
0.0126 | 9.0 | 2250 | 0.3539 | 0.9405 | 0.9405 |
0.0095 | 10.0 | 2500 | 0.3963 | 0.9315 | 0.9318 |
0.0088 | 11.0 | 2750 | 0.3692 | 0.9355 | 0.9353 |
0.0072 | 12.0 | 3000 | 0.3646 | 0.9385 | 0.9385 |
0.0064 | 13.0 | 3250 | 0.3630 | 0.9375 | 0.9373 |
0.0052 | 14.0 | 3500 | 0.3659 | 0.9405 | 0.9403 |
0.005 | 15.0 | 3750 | 0.3648 | 0.9405 | 0.9404 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 15
Dataset used to train Gridflow/bert-base-uncased-finetuned-emotion
Evaluation results
- Accuracy on emotionvalidation set self-reported0.941
- F1 on emotionvalidation set self-reported0.940