20231005-10-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: 0.5619
• Loss: 1.7791

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
3.0157	1.82	200	0.4232	2.6671
2.5352	3.64	400	0.4476	2.6419
2.3183	5.45	600	0.5189	2.3181
2.1379	7.27	800	0.5192	2.0600
2.0734	9.09	1000	0.4961	2.1997
1.9287	10.91	1200	0.5075	2.1356
1.8827	12.73	1400	0.5405	2.0868
1.8261	14.55	1600	0.5490	1.9918
1.7685	16.36	1800	0.5917	1.8753
1.7322	18.18	2000	0.5789	1.8090
1.6964	20.0	2200	0.5619	1.7791

Framework versions

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