bert_base_for_whole_train_result_Spam-Ham_farshad_2_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: 0.0514
• 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
0.6568	2.9250	50	0.3947	0.8794	0.8753
0.2182	5.8501	100	0.0878	0.9724	0.9730
0.0482	8.7751	150	0.0529	0.9794	0.9799
0.0196	11.7002	200	0.0434	0.9855	0.9859
0.0112	14.6252	250	0.0342	0.9898	0.9902
0.0067	17.5503	300	0.0452	0.9887	0.9890
0.0049	20.4753	350	0.0447	0.9898	0.9902
0.0035	23.4004	400	0.0491	0.9896	0.9899
0.0039	26.3254	450	0.0577	0.9849	0.9853
0.0018	29.2505	500	0.0525	0.9893	0.9896
0.0023	32.1755	550	0.0378	0.9925	0.9927
0.0017	35.1005	600	0.0462	0.9910	0.9914
0.0023	38.0256	650	0.0525	0.9884	0.9887
0.0015	40.9506	700	0.0550	0.9890	0.9893
0.0017	43.8757	750	0.0421	0.9925	0.9927
0.0019	46.8007	800	0.0466	0.9907	0.9910
0.0013	49.7258	850	0.0575	0.9896	0.9898
0.0014	52.6508	900	0.0396	0.9939	0.9941
0.0007	55.5759	950	0.0512	0.9916	0.9918
0.0006	58.5009	1000	0.0416	0.9945	0.9947
0.0006	61.4260	1050	0.0506	0.9919	0.9921
0.0007	64.3510	1100	0.0467	0.9933	0.9935
0.0005	67.2761	1150	0.0590	0.9907	0.9910
0.0011	70.2011	1200	0.0462	0.9916	0.9918
0.0006	73.1261	1250	0.0513	0.9925	0.9927
0.0008	76.0512	1300	0.0507	0.9916	0.9918
0.0005	78.9762	1350	0.0430	0.9939	0.9941
0.0004	81.9013	1400	0.0461	0.9927	0.9930
0.0004	84.8263	1450	0.0488	0.9919	0.9922
0.0003	87.7514	1500	0.0514	0.9913	0.9916

Framework versions

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