metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: multibertfinetuned1107
results: []
multibertfinetuned1107
This model is a fine-tuned version of bert-base-multilingual-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5260
- Precision: 0.5933
- Recall: 0.4839
- F1: 0.5330
- Accuracy: 0.8502
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: 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 145 | 0.5260 | 0.5933 | 0.4839 | 0.5330 | 0.8502 |
| No log | 2.0 | 290 | 0.5357 | 0.6099 | 0.5415 | 0.5736 | 0.8604 |
| No log | 3.0 | 435 | 0.5476 | 0.6279 | 0.5795 | 0.6027 | 0.8715 |
| 0.365 | 4.0 | 580 | 0.5861 | 0.6454 | 0.6107 | 0.6276 | 0.8827 |
| 0.365 | 5.0 | 725 | 0.6235 | 0.6543 | 0.6185 | 0.6359 | 0.8804 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3