<!-- 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-finetuned-emotion-lr-2e-05-wd-0001
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: 0.3670
- Accuracy: 0.896
- F1: 0.8929
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.0933 | 1.0 | 125 | 0.5691 | 0.8335 | 0.8121 |
| 0.4488 | 2.0 | 250 | 0.3670 | 0.896 | 0.8929 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.10.0
- Datasets 2.6.1
- Tokenizers 0.13.1
