metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: BERT_AA_IMDB_Top100_WithoutOOC_082023_MultilingualBertBase
results: []
BERT_AA_IMDB_Top100_WithoutOOC_082023_MultilingualBertBase
This model is a fine-tuned version of bert-base-multilingual-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2350
- Accuracy: 0.7903
- F1: 0.7935
- Precision: 0.8003
- Recall: 0.7903
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: 2e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 1.7616 | 1.0 | 2884 | 1.4266 | 0.6849 | 0.6789 | 0.7161 | 0.6849 |
| 1.088 | 2.0 | 5768 | 1.0637 | 0.7519 | 0.7542 | 0.7731 | 0.7519 |
| 0.6829 | 3.0 | 8652 | 0.9868 | 0.7681 | 0.7692 | 0.7808 | 0.7681 |
| 0.4706 | 4.0 | 11536 | 0.9578 | 0.7814 | 0.7828 | 0.7910 | 0.7814 |
| 0.2697 | 5.0 | 14420 | 1.0124 | 0.7810 | 0.7839 | 0.7946 | 0.7810 |
| 0.1534 | 6.0 | 17304 | 1.0703 | 0.7876 | 0.7890 | 0.7954 | 0.7876 |
| 0.0788 | 7.0 | 20188 | 1.1626 | 0.7836 | 0.7878 | 0.7988 | 0.7836 |
| 0.0375 | 8.0 | 23072 | 1.2020 | 0.7887 | 0.7925 | 0.8029 | 0.7887 |
| 0.0283 | 9.0 | 25956 | 1.2304 | 0.7886 | 0.7928 | 0.8015 | 0.7886 |
| 0.0114 | 10.0 | 28840 | 1.2350 | 0.7903 | 0.7935 | 0.8003 | 0.7903 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.8.0
- Datasets 2.10.1
- Tokenizers 0.13.2