google-electra-base-discriminator-english-sentweet-sentiment
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: 0.5459
- Accuracy: 0.8194
- Precision: 0.8367
- Recall: 0.8273
- F1: 0.8189
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 | 0.4708 | 0.7847 | 0.8008 | 0.7924 | 0.7841 |
| No log | 2.0 | 162 | 0.4815 | 0.8090 | 0.8346 | 0.8185 | 0.8078 |
| No log | 3.0 | 243 | 0.4717 | 0.8160 | 0.8448 | 0.8260 | 0.8146 |
| No log | 4.0 | 324 | 0.4291 | 0.8229 | 0.8351 | 0.8296 | 0.8227 |
| No log | 5.0 | 405 | 0.4318 | 0.8090 | 0.8099 | 0.8113 | 0.8089 |
| No log | 6.0 | 486 | 0.5459 | 0.8194 | 0.8367 | 0.8273 | 0.8189 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.1+cu117
- Datasets 2.6.1
- Tokenizers 0.11.0