<!-- 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-english-sentweet-derogatory
This model is a fine-tuned version of bhadresh-savani/distilbert-base-uncased-emotion on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8426
- Accuracy: 0.7917
- Precision: 0.8038
- Recall: 0.8018
- F1: 0.7916
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
No log | 1.0 | 81 | 0.4182 | 0.8194 | 0.8363 | 0.8314 | 0.8193 |
No log | 2.0 | 162 | 0.4585 | 0.8125 | 0.8394 | 0.8273 | 0.8119 |
No log | 3.0 | 243 | 0.4828 | 0.8125 | 0.8394 | 0.8273 | 0.8119 |
No log | 4.0 | 324 | 0.5100 | 0.8125 | 0.8198 | 0.8207 | 0.8125 |
No log | 5.0 | 405 | 0.7268 | 0.8021 | 0.8029 | 0.8061 | 0.8017 |
No log | 6.0 | 486 | 0.8426 | 0.7917 | 0.8038 | 0.8018 | 0.7916 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.1+cu117
- Datasets 2.6.1
- Tokenizers 0.11.0