microsoft-resnet-50-english-sentweet-derogatory
This model is a fine-tuned version of nlptown/bert-base-multilingual-uncased-sentiment on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3923
- Accuracy: 0.8229
- Precision: 0.8388
- Recall: 0.8345
- F1: 0.8228
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 | 1.4751 | 0.8021 | 0.8101 | 0.8105 | 0.8021 |
| No log | 2.0 | 162 | 1.2925 | 0.8021 | 0.8086 | 0.8098 | 0.8021 |
| No log | 3.0 | 243 | 1.4240 | 0.8090 | 0.8268 | 0.8212 | 0.8088 |
| No log | 4.0 | 324 | 1.3803 | 0.8125 | 0.8214 | 0.8214 | 0.8125 |
| No log | 5.0 | 405 | 1.3698 | 0.8090 | 0.8187 | 0.8183 | 0.8090 |
| No log | 6.0 | 486 | 1.3923 | 0.8229 | 0.8388 | 0.8345 | 0.8228 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.1+cu117
- Datasets 2.6.1
- Tokenizers 0.11.0