electra-base-discriminator-english-sentweet-targeted-insult
This model is a fine-tuned version of google/electra-base-discriminator on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6952
- Accuracy: 0.7986
- Precision: 0.8114
- Recall: 0.8083
- F1: 0.7985
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 | 0.4782 | 0.7917 | 0.8182 | 0.8054 | 0.7908 |
| No log | 2.0 | 162 | 0.5122 | 0.7882 | 0.8188 | 0.8029 | 0.7871 |
| No log | 3.0 | 243 | 0.4836 | 0.8056 | 0.8300 | 0.8187 | 0.8050 |
| No log | 4.0 | 324 | 0.5253 | 0.7604 | 0.7582 | 0.7578 | 0.7580 |
| No log | 5.0 | 405 | 0.6095 | 0.7951 | 0.8035 | 0.8031 | 0.7951 |
| No log | 6.0 | 486 | 0.6952 | 0.7986 | 0.8114 | 0.8083 | 0.7985 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.1+cu117
- Datasets 2.6.1
- Tokenizers 0.11.0