metadata
license: apache-2.0
base_model: bert-base-multilingual-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: multibertfinetuned1108
results: []
multibertfinetuned1108
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: 0.4108
- Precision: 0.7034
- Recall: 0.6951
- F1: 0.6992
- Accuracy: 0.8883
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 | 236 | 0.4646 | 0.6642 | 0.6218 | 0.6423 | 0.8693 |
| No log | 2.0 | 472 | 0.4108 | 0.7034 | 0.6951 | 0.6992 | 0.8883 |
| 0.4462 | 3.0 | 708 | 0.4471 | 0.7199 | 0.7001 | 0.7098 | 0.8924 |
| 0.4462 | 4.0 | 944 | 0.4507 | 0.7325 | 0.7477 | 0.7400 | 0.9023 |
| 0.1589 | 5.0 | 1180 | 0.4661 | 0.7406 | 0.7545 | 0.7475 | 0.9043 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3