metadata
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: M12-BERT-SIMILIARITY
results: []
M12-BERT-SIMILIARITY
This model is a fine-tuned version of aubmindlab/bert-base-arabertv2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2225
- Accuracy: 0.9344
- Precision: 0.8927
- Recall: 0.9873
- F1: 0.9377
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.2303 | 1.0 | 49975 | 0.2080 | 0.9372 | 0.9036 | 0.9787 | 0.9397 |
| 0.2109 | 2.0 | 99950 | 0.2342 | 0.9337 | 0.8952 | 0.9825 | 0.9368 |
| 0.203 | 3.0 | 149925 | 0.2192 | 0.9375 | 0.9070 | 0.9749 | 0.9397 |
| 0.1962 | 4.0 | 199900 | 0.2225 | 0.9344 | 0.8927 | 0.9873 | 0.9377 |
Framework versions
- Transformers 4.21.3
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1