20231005-1-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: 0.6240
• Loss: 1.6828

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
2.9403	1.82	200	0.4411	2.4884
2.4143	3.64	400	0.4908	2.1693
2.1466	5.45	600	0.5377	1.9990
2.0429	7.27	800	0.5424	2.1102
1.9514	9.09	1000	0.5680	1.8748
1.8498	10.91	1200	0.5826	1.8680
1.8097	12.73	1400	0.5960	1.8489
1.737	14.55	1600	0.6364	1.6621
1.7203	16.36	1800	0.6298	1.6846
1.6172	18.18	2000	0.6527	1.5969
1.6564	20.0	2200	0.6240	1.6828

Framework versions

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