metadata
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: fine-tuned-marBERT_latest
results: []
fine-tuned-marBERT_latest
This model is a fine-tuned version of UBC-NLP/MARBERTv2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1243
- Accuracy: 0.9712
- Precision: 0.9730
- Recall: 0.9836
- F1: 0.9783
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 |
|---|---|---|---|---|---|---|---|
| 0.1558 | 1.0 | 56232 | 0.1159 | 0.9693 | 0.9734 | 0.9802 | 0.9768 |
| 0.1245 | 2.0 | 112464 | 0.1427 | 0.9696 | 0.9724 | 0.9817 | 0.9770 |
| 0.1061 | 3.0 | 168696 | 0.1262 | 0.9716 | 0.9760 | 0.9810 | 0.9785 |
| 0.0925 | 4.0 | 224928 | 0.1243 | 0.9712 | 0.9730 | 0.9836 | 0.9783 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1