<!-- 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. -->
OTE-domianAdaption-ABSA-MARBERT2-HARD-run1
This model is a fine-tuned version of salohnana2018/MARBERTV2-domianAdaption-OTE-ABSA-HARD-7 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1274
- Precision: 0.7517
- Recall: 0.8057
- F1: 0.7778
- Accuracy: 0.9551
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: 8
- seed: 25
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.2029 | 1.0 | 121 | 0.1193 | 0.7570 | 0.7683 | 0.7626 | 0.9538 |
0.094 | 2.0 | 242 | 0.1137 | 0.7854 | 0.7678 | 0.7765 | 0.9568 |
0.0685 | 3.0 | 363 | 0.1274 | 0.7517 | 0.8057 | 0.7778 | 0.9551 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3