20231005-9-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: 0.5930
• Loss: 1.7283

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
2.9365	1.82	200	0.3878	2.5398
2.3968	3.64	400	0.4564	2.3602
2.2177	5.45	600	0.5127	2.2161
2.1045	7.27	800	0.5242	2.2912
2.004	9.09	1000	0.5405	1.9708
1.8877	10.91	1200	0.5758	1.7440
1.7707	12.73	1400	0.6242	1.6567
1.7869	14.55	1600	0.6283	1.5502
1.7331	16.36	1800	0.5373	1.7845
1.686	18.18	2000	0.5938	1.6903
1.6699	20.0	2200	0.5930	1.7283

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1