bert-f1-durga-muhammad-c

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

• Loss: 0.0001
• Accuracy: 1.0
• Precision: 1.0
• Recall: 1.0
• F1: 1.0

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: 24
• eval_batch_size: 24
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.0245	1.0	42	0.0241	0.995	0.995	0.995	0.995
0.0032	2.0	84	0.0081	0.999	0.999	0.999	0.999
0.0011	3.0	126	0.0075	0.999	0.999	0.999	0.999
0.0008	4.0	168	0.0068	0.999	0.999	0.999	0.999
0.0006	5.0	210	0.0078	0.999	0.999	0.999	0.999
0.0012	6.0	252	0.0063	0.999	0.999	0.999	0.999
0.0022	7.0	294	0.0015	1.0	1.0	1.0	1.0
0.0004	8.0	336	0.0031	0.999	0.999	0.999	0.999
0.0003	9.0	378	0.0002	1.0	1.0	1.0	1.0
0.0002	10.0	420	0.0002	1.0	1.0	1.0	1.0
0.0002	11.0	462	0.0001	1.0	1.0	1.0	1.0
0.0002	12.0	504	0.0001	1.0	1.0	1.0	1.0
0.0002	13.0	546	0.0001	1.0	1.0	1.0	1.0
0.0001	14.0	588	0.0001	1.0	1.0	1.0	1.0
0.0001	15.0	630	0.0001	1.0	1.0	1.0	1.0
0.0001	16.0	672	0.0001	1.0	1.0	1.0	1.0
0.0001	17.0	714	0.0001	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1