distilbert-base-uncased-finetuned-emotion
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: 0.1499
- F1: 0.9334
- Accuracy: 0.9335
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 | Accuracy |
---|---|---|---|---|---|
0.7725 | 1.0 | 250 | 0.2686 | 0.9184 | 0.918 |
0.2092 | 2.0 | 500 | 0.1734 | 0.9330 | 0.933 |
0.1394 | 3.0 | 750 | 0.1623 | 0.9356 | 0.935 |
0.1095 | 4.0 | 1000 | 0.1449 | 0.9368 | 0.937 |
0.0914 | 5.0 | 1250 | 0.1499 | 0.9334 | 0.9335 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 19
Finetuned from
Dataset used to train akashjoy/distilbert-base-uncased-finetuned-emotion
Evaluation results
- F1 on emotionvalidation set self-reported0.933
- Accuracy on emotionvalidation set self-reported0.933