20231005-6-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: 0.6122
• Loss: 1.7100

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
2.8657	1.82	200	0.4491	2.2492
2.3762	3.64	400	0.4819	2.3058
2.1854	5.45	600	0.5117	2.1061
2.0751	7.27	800	0.5574	1.9374
1.9179	9.09	1000	0.5319	2.0854
1.8486	10.91	1200	0.5840	1.9498
1.786	12.73	1400	0.5547	1.9965
1.7243	14.55	1600	0.5922	1.7396
1.6937	16.36	1800	0.6345	1.6550
1.6508	18.18	2000	0.6297	1.5891
1.6364	20.0	2200	0.6122	1.7100

Framework versions

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