metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: multibertfinetuned0407
results: []
multibertfinetuned0407
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: 0.4688
- Precision: 0.4879
- Recall: 0.4345
- F1: 0.4597
- Accuracy: 0.8764
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 | 131 | 0.4688 | 0.4879 | 0.4345 | 0.4597 | 0.8764 |
| No log | 2.0 | 262 | 0.5224 | 0.5400 | 0.4884 | 0.5129 | 0.8777 |
| No log | 3.0 | 393 | 0.5814 | 0.4900 | 0.4900 | 0.4900 | 0.8683 |
| 0.3219 | 4.0 | 524 | 0.6226 | 0.5125 | 0.5069 | 0.5097 | 0.8750 |
| 0.3219 | 5.0 | 655 | 0.6593 | 0.5008 | 0.4977 | 0.4992 | 0.8771 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3