bert_base_for_whole_train_result_Spam-Ham_farshad_half_4_4

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: 0.0516
• Accuracy: 0.9913
• F1: 0.9916

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
0.662	5.8501	50	0.3620	0.8785	0.8798
0.2015	11.7002	100	0.1009	0.9751	0.9757
0.0614	17.5503	150	0.0566	0.9826	0.9830
0.021	23.4004	200	0.0501	0.9843	0.9847
0.0109	29.2505	250	0.0504	0.9872	0.9876
0.0071	35.1005	300	0.0761	0.9826	0.9830
0.0052	40.9506	350	0.0853	0.9823	0.9827
0.0047	46.8007	400	0.0481	0.9907	0.9910
0.0033	52.6508	450	0.0550	0.9893	0.9896
0.0026	58.5009	500	0.0648	0.9855	0.9859
0.003	64.3510	550	0.0470	0.9901	0.9904
0.0015	70.2011	600	0.0450	0.9922	0.9924
0.0016	76.0512	650	0.0619	0.9884	0.9887
0.0013	81.9013	700	0.0382	0.9930	0.9933
0.0022	87.7514	750	0.0364	0.9930	0.9933
0.0011	93.6015	800	0.0516	0.9913	0.9916

Framework versions

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