20231005-2-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: 0.6479
• Loss: 1.6281

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
2.8918	1.82	200	0.4038	2.4903
2.3882	3.64	400	0.4978	2.2096
2.1785	5.45	600	0.4934	1.9995
2.0686	7.27	800	0.5386	2.0103
1.9575	9.09	1000	0.5243	2.1245
1.8828	10.91	1200	0.5932	1.7872
1.8112	12.73	1400	0.6204	1.4894
1.7449	14.55	1600	0.5978	1.7968
1.6916	16.36	1800	0.6253	1.6254
1.6763	18.18	2000	0.6377	1.4638
1.6459	20.0	2200	0.6479	1.6281

Framework versions

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