scam-alert-bert

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

• Loss: 0.1215
• Accuracy: 0.9861
• F1: 0.9861

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: 8
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.1577	100	0.0723	0.9841	0.9841
No log	0.3155	200	0.0520	0.9900	0.9899
No log	0.4732	300	0.0825	0.9821	0.9823
No log	0.6309	400	0.0722	0.9861	0.9857
No log	0.7886	500	0.0521	0.9861	0.9859
No log	0.9464	600	0.0905	0.9761	0.9765
No log	1.1041	700	0.0675	0.9821	0.9822
No log	1.2618	800	0.0661	0.9900	0.9899
No log	1.4196	900	0.0695	0.9861	0.9861
No log	1.5773	1000	0.0780	0.9880	0.9880
No log	1.7350	1100	0.0877	0.9861	0.9858
No log	1.8927	1200	0.0714	0.9880	0.9880
No log	2.0505	1300	0.0856	0.9841	0.9841
No log	2.2082	1400	0.0930	0.9841	0.9842
No log	2.3659	1500	0.0886	0.9861	0.9860
No log	2.5237	1600	0.0982	0.9861	0.9861
No log	2.6814	1700	0.0854	0.9861	0.9860
No log	2.8391	1800	0.0949	0.9861	0.9860
No log	2.9968	1900	0.0935	0.9880	0.9880
No log	3.1546	2000	0.1004	0.9861	0.9860
No log	3.3123	2100	0.1223	0.9801	0.9803
No log	3.4700	2200	0.1146	0.9861	0.9861
No log	3.6278	2300	0.1148	0.9861	0.9861
No log	3.7855	2400	0.1074	0.9861	0.9860
No log	3.9432	2500	0.1082	0.9861	0.9860
0.0249	4.1009	2600	0.1272	0.9841	0.9842
0.0249	4.2587	2700	0.1264	0.9841	0.9842
0.0249	4.4164	2800	0.1161	0.9861	0.9861
0.0249	4.5741	2900	0.1242	0.9861	0.9861
0.0249	4.7319	3000	0.1227	0.9861	0.9861
0.0249	4.8896	3100	0.1223	0.9861	0.9861
0.0249	5.0473	3200	0.1207	0.9861	0.9861
0.0249	5.2050	3300	0.1210	0.9861	0.9861
0.0249	5.3628	3400	0.1214	0.9861	0.9861
0.0249	5.5205	3500	0.1214	0.9861	0.9861
0.0249	5.6782	3600	0.1215	0.9861	0.9861
0.0249	5.8360	3700	0.1215	0.9861	0.9861
0.0249	5.9937	3800	0.1215	0.9861	0.9861

Framework versions

• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1