<!-- 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. -->
augment-tweet-bert-large-e4
This model is a fine-tuned version of vinai/bertweet-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4688
- Accuracy: 0.9471
- F1: 0.8656
- Precision: 0.8224
- Recall: 0.9135
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.1265 | 1.0 | 4089 | 0.4889 | 0.9310 | 0.8304 | 0.7661 | 0.9066 |
0.0733 | 2.0 | 8178 | 0.4880 | 0.9439 | 0.8533 | 0.8322 | 0.8754 |
0.024 | 3.0 | 12267 | 0.5060 | 0.9478 | 0.8657 | 0.8312 | 0.9031 |
0.0239 | 4.0 | 16356 | 0.4688 | 0.9471 | 0.8656 | 0.8224 | 0.9135 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3