bert_base_for_whole_train_result_Spam-Ham_farshad_half_2_2

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0412
• Accuracy: 0.9939
• F1: 0.9941

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: 0.0001
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 64
• total_train_batch_size: 4096
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.6192	5.8501	50	0.4240	0.9057	0.9036
0.24	11.7002	100	0.0854	0.9751	0.9755
0.0403	17.5503	150	0.0386	0.9893	0.9896
0.0142	23.4004	200	0.0414	0.9904	0.9907
0.0083	29.2505	250	0.0491	0.9884	0.9887
0.0061	35.1005	300	0.0519	0.9893	0.9896
0.0047	40.9506	350	0.0558	0.9890	0.9894
0.0047	46.8007	400	0.0561	0.9887	0.9890
0.002	52.6508	450	0.0778	0.9855	0.9859
0.0029	58.5009	500	0.0541	0.9907	0.9910
0.0034	64.3510	550	0.0445	0.9910	0.9913
0.0014	70.2011	600	0.0516	0.9910	0.9913
0.0008	76.0512	650	0.0487	0.9916	0.9919
0.0012	81.9013	700	0.0508	0.9925	0.9927
0.0014	87.7514	750	0.0445	0.9925	0.9927
0.0009	93.6015	800	0.0412	0.9939	0.9941

Framework versions

• Transformers 4.40.0
• Pytorch 2.4.1+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1