20231005-8-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: 0.6178
• Loss: 1.5315

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
2.9965	1.82	200	0.4212	2.5494
2.5203	3.64	400	0.4747	2.4152
2.3137	5.45	600	0.4965	1.9514
2.1441	7.27	800	0.5762	1.9575
2.0708	9.09	1000	0.5794	1.7864
2.0004	10.91	1200	0.5336	1.9741
1.9093	12.73	1400	0.6217	1.7001
1.8906	14.55	1600	0.5589	1.8629
1.7744	16.36	1800	0.5996	1.5749
1.7698	18.18	2000	0.6288	1.6576
1.7274	20.0	2200	0.6178	1.5315

Framework versions

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