NLP-HIBA_DisTEMIST_fine_tuned_bert-base-multilingual-cased

This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2057
• Precision: 0.6288
• Recall: 0.5579
• F1: 0.5912
• Accuracy: 0.9555

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	71	0.1547	0.5048	0.3774	0.4319	0.9430
No log	2.0	142	0.1542	0.5965	0.4071	0.4839	0.9495
No log	3.0	213	0.1369	0.5519	0.5160	0.5334	0.9516
No log	4.0	284	0.1435	0.5622	0.4989	0.5287	0.9512
No log	5.0	355	0.1542	0.5920	0.5575	0.5742	0.9536
No log	6.0	426	0.1625	0.6069	0.5663	0.5859	0.9546
No log	7.0	497	0.1779	0.5936	0.5830	0.5883	0.9526
0.0978	8.0	568	0.1827	0.6035	0.5784	0.5907	0.9546
0.0978	9.0	639	0.2026	0.6121	0.5685	0.5895	0.9546
0.0978	10.0	710	0.2057	0.6288	0.5579	0.5912	0.9555

Framework versions

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