<!-- 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. -->
SA-roberta-e12-w1-1.5-b16-augment
This model is a fine-tuned version of Amalq/autotrain-smm4h_large_roberta_clean-874027878 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8541
- Accuracy: 0.9188
- F1: 0.8925
- Precision: 0.8808
- Recall: 0.9045
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 12
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.3089 | 1.0 | 581 | 0.4172 | 0.9188 | 0.8889 | 0.9068 | 0.8716 |
0.1439 | 2.0 | 1162 | 0.7575 | 0.8910 | 0.8409 | 0.9217 | 0.7731 |
0.0988 | 3.0 | 1743 | 0.5909 | 0.9099 | 0.8814 | 0.8649 | 0.8985 |
0.0408 | 4.0 | 2324 | 0.6910 | 0.9099 | 0.8831 | 0.8547 | 0.9134 |
0.0225 | 5.0 | 2905 | 0.6426 | 0.9188 | 0.8922 | 0.8830 | 0.9015 |
0.0196 | 6.0 | 3486 | 0.7218 | 0.9155 | 0.8889 | 0.8711 | 0.9075 |
0.0198 | 7.0 | 4067 | 0.7932 | 0.8988 | 0.8691 | 0.8389 | 0.9015 |
0.0107 | 8.0 | 4648 | 0.7544 | 0.9155 | 0.8876 | 0.8798 | 0.8955 |
0.0036 | 9.0 | 5229 | 0.7316 | 0.9166 | 0.8889 | 0.8824 | 0.8955 |
0.0046 | 10.0 | 5810 | 0.8289 | 0.9199 | 0.8932 | 0.8879 | 0.8985 |
0.0006 | 11.0 | 6391 | 0.8285 | 0.9188 | 0.8906 | 0.8946 | 0.8866 |
0.0027 | 12.0 | 6972 | 0.8541 | 0.9188 | 0.8925 | 0.8808 | 0.9045 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3