distilbert-base-uncased-finetunded-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: 0.1584
- Accuracuy: 0.9365
- F1: 0.9365
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracuy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 250 | 0.2735 | 0.9155 | 0.9134 |
| No log | 2.0 | 500 | 0.1727 | 0.932 | 0.9321 |
| No log | 3.0 | 750 | 0.1584 | 0.9365 | 0.9365 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1