metadata
license: apache-2.0
base_model: google-bert/bert-base-multilingual-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: sentiment_bert
results: []
sentiment_bert
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: 0.7469
- Accuracy: 0.6802
- F1: 0.6332
- Precision: 0.6152
- Recall: 0.6942
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.7975 | 1.0 | 94 | 0.9153 | 0.4158 | 0.4603 | 0.5512 | 0.5862 |
0.7765 | 2.0 | 188 | 0.8220 | 0.6583 | 0.6023 | 0.5894 | 0.6461 |
0.71 | 3.0 | 282 | 0.8345 | 0.6062 | 0.5908 | 0.5955 | 0.6858 |
0.6439 | 4.0 | 376 | 0.7753 | 0.6568 | 0.6241 | 0.6133 | 0.7010 |
0.6623 | 5.0 | 470 | 0.7469 | 0.6802 | 0.6332 | 0.6152 | 0.6942 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1