metadata
license: apache-2.0
base_model: google-bert/bert-base-multilingual-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: NLP_whole_dataseet_
results: []
NLP_whole_dataseet_
This model is a fine-tuned version of google-bert/bert-base-multilingual-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0925
- Accuracy: 0.9817
- Precision: 0.9797
- Recall: 0.9828
- F1: 0.9809
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.3209 | 1.0 | 55 | 0.2928 | 0.9037 | 0.9020 | 0.8929 | 0.8950 |
| 0.1962 | 2.0 | 110 | 0.1979 | 0.9450 | 0.9447 | 0.9353 | 0.9387 |
| 0.2778 | 3.0 | 165 | 0.1383 | 0.9587 | 0.9530 | 0.9627 | 0.9560 |
| 0.2216 | 4.0 | 220 | 0.1156 | 0.9679 | 0.9667 | 0.9640 | 0.9652 |
| 0.2203 | 5.0 | 275 | 0.1061 | 0.9817 | 0.9797 | 0.9828 | 0.9809 |
| 0.1948 | 6.0 | 330 | 0.0967 | 0.9817 | 0.9797 | 0.9828 | 0.9809 |
| 0.2017 | 7.0 | 385 | 0.0902 | 0.9817 | 0.9797 | 0.9828 | 0.9809 |
| 0.2384 | 8.0 | 440 | 0.0925 | 0.9817 | 0.9797 | 0.9828 | 0.9809 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1