<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
multibertfinetuned0906
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: 0.4599
- Precision: 0.7258
- Recall: 0.7077
- F1: 0.7166
- Accuracy: 0.9235
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 290 | 0.3998 | 0.7001 | 0.6635 | 0.6813 | 0.9163 |
0.105 | 2.0 | 580 | 0.3746 | 0.7303 | 0.7018 | 0.7157 | 0.9235 |
0.105 | 3.0 | 870 | 0.3891 | 0.725 | 0.7047 | 0.7147 | 0.9257 |
0.0655 | 4.0 | 1160 | 0.4368 | 0.7173 | 0.6951 | 0.7061 | 0.9227 |
0.0655 | 5.0 | 1450 | 0.4576 | 0.7279 | 0.7091 | 0.7184 | 0.9235 |
0.0323 | 6.0 | 1740 | 0.4599 | 0.7258 | 0.7077 | 0.7166 | 0.9235 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3