20231005-4-bert-base-multilingual-cased-new

This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Accuracy: 0.5955
• Loss: 1.5685

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
2.869	1.82	200	0.4070	2.4909
2.334	3.64	400	0.5118	2.2459
2.194	5.45	600	0.5283	2.1484
2.0426	7.27	800	0.5064	2.1731
1.9618	9.09	1000	0.5344	1.8738
1.8369	10.91	1200	0.5702	1.8349
1.8272	12.73	1400	0.5374	1.8769
1.7237	14.55	1600	0.6121	1.5797
1.7028	16.36	1800	0.5843	1.6272
1.6908	18.18	2000	0.6414	1.5303
1.6235	20.0	2200	0.5955	1.5685

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.0