<!-- 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
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: 0.4286
- Accuracy: 0.877
- F1: 0.8671
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: 512
- eval_batch_size: 512
- 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 | Accuracy | F1 |
---|---|---|---|---|---|
No log | 1.0 | 32 | 1.2048 | 0.5795 | 0.4541 |
No log | 2.0 | 64 | 0.8778 | 0.7085 | 0.6467 |
No log | 3.0 | 96 | 0.5991 | 0.794 | 0.7452 |
No log | 4.0 | 128 | 0.4679 | 0.866 | 0.8533 |
No log | 5.0 | 160 | 0.4286 | 0.877 | 0.8671 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3