metadata
license: apache-2.0
base_model: bert-base-multilingual-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: multibertfinetuned2408
results: []
multibertfinetuned2408
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: 0.3350
- Precision: 0.7395
- Recall: 0.7408
- F1: 0.7401
- Accuracy: 0.9041
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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 236 | 0.3641 | 0.6769 | 0.6472 | 0.6617 | 0.8806 |
| No log | 2.0 | 472 | 0.3733 | 0.7173 | 0.6741 | 0.6950 | 0.8906 |
| 0.429 | 3.0 | 708 | 0.3350 | 0.7395 | 0.7408 | 0.7401 | 0.9041 |
| 0.429 | 4.0 | 944 | 0.4290 | 0.7572 | 0.7279 | 0.7422 | 0.9030 |
| 0.1313 | 5.0 | 1180 | 0.4485 | 0.7432 | 0.7332 | 0.7381 | 0.9007 |
| 0.1313 | 6.0 | 1416 | 0.4799 | 0.7785 | 0.7425 | 0.7601 | 0.9100 |
| 0.0504 | 7.0 | 1652 | 0.5249 | 0.7875 | 0.7461 | 0.7662 | 0.9103 |
| 0.0504 | 8.0 | 1888 | 0.5146 | 0.7863 | 0.7513 | 0.7684 | 0.9120 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3