<!-- 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 None dataset. It achieves the following results on the evaluation set:
- Loss: 2.5264
- Accuracy: 0.7647
- F1: 0.7451
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 14
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
5.0618 | 1.0 | 250 | 4.7750 | 0.1961 | 0.0788 |
4.437 | 2.0 | 500 | 4.2650 | 0.2353 | 0.1158 |
3.8364 | 3.0 | 750 | 3.8796 | 0.2745 | 0.1819 |
3.3633 | 4.0 | 1000 | 3.6106 | 0.4510 | 0.3610 |
2.9623 | 5.0 | 1250 | 3.3625 | 0.4902 | 0.4224 |
2.6293 | 6.0 | 1500 | 3.1718 | 0.6078 | 0.5468 |
2.3484 | 7.0 | 1750 | 3.0107 | 0.6471 | 0.6078 |
2.1081 | 8.0 | 2000 | 2.8755 | 0.7255 | 0.6948 |
1.9214 | 9.0 | 2250 | 2.7750 | 0.7255 | 0.6948 |
1.7762 | 10.0 | 2500 | 2.6882 | 0.7255 | 0.6948 |
1.6532 | 11.0 | 2750 | 2.6092 | 0.7647 | 0.7438 |
1.5627 | 12.0 | 3000 | 2.5639 | 0.7647 | 0.7451 |
1.488 | 13.0 | 3250 | 2.5370 | 0.7647 | 0.7451 |
1.4596 | 14.0 | 3500 | 2.5264 | 0.7647 | 0.7451 |
Framework versions
- Transformers 4.16.2
- Pytorch 2.0.1+cu118
- Datasets 1.16.1
- Tokenizers 0.13.3