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: 0.2237
- Accuracy: 0.9275
- F1: 0.9274
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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.8643 | 1.0 | 250 | 0.3324 | 0.9065 | 0.9025 |
| 0.2589 | 2.0 | 500 | 0.2237 | 0.9275 | 0.9274 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.11.0+cu113
- Datasets 1.16.1
- Tokenizers 0.10.3
- Downloads last month
- 116
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Dataset used to train armandnlp/distilbert-base-uncased-finetuned-emotion
Evaluation results
- Accuracy on emotionself-reported0.927
- F1 on emotionself-reported0.927
- Accuracy on emotiontest set self-reported0.919
- Precision Macro on emotiontest set self-reported0.888
- Precision Micro on emotiontest set self-reported0.919
- Precision Weighted on emotiontest set self-reported0.919
- Recall Macro on emotiontest set self-reported0.858
- Recall Micro on emotiontest set self-reported0.919
- Recall Weighted on emotiontest set self-reported0.919
- F1 Macro on emotiontest set self-reported0.868