ArBERT-finetuned-CrossVal-fnd
This model is a fine-tuned version of UBC-NLP/ARBERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2055
- Macro F1: 0.9125
- Accuracy: 0.9154
- Precision: 0.9132
- Recall: 0.9117
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: 8
- eval_batch_size: 8
- seed: 123
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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 | Macro F1 | Accuracy | Precision | Recall |
---|---|---|---|---|---|---|---|
0.3468 | 1.0 | 1597 | 0.2055 | 0.9125 | 0.9154 | 0.9132 | 0.9117 |
0.2241 | 2.0 | 3194 | 0.2280 | 0.9088 | 0.9115 | 0.9079 | 0.9098 |
0.1555 | 3.0 | 4791 | 0.3194 | 0.9085 | 0.9114 | 0.9083 | 0.9088 |
0.1022 | 4.0 | 6388 | 0.4153 | 0.9073 | 0.9105 | 0.9083 | 0.9064 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.