bert-030724-dataset

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: 0.0347
• F1: 0.9668
• Roc Auc: 0.9811
• Accuracy: 0.8713

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: 0.001
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 35

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
No log	1.0	31	0.2372	0.4911	0.6721	0.0175
No log	2.0	62	0.1959	0.6542	0.7889	0.1053
No log	3.0	93	0.1550	0.7549	0.8454	0.1637
No log	4.0	124	0.1180	0.8135	0.8806	0.3275
No log	5.0	155	0.0916	0.8616	0.9024	0.4386
No log	6.0	186	0.0794	0.8895	0.9347	0.5146
No log	7.0	217	0.0652	0.9091	0.9423	0.6082
No log	8.0	248	0.0577	0.9280	0.9590	0.6959
No log	9.0	279	0.0512	0.9408	0.9594	0.7485
No log	10.0	310	0.0492	0.9432	0.9636	0.7485
No log	11.0	341	0.0482	0.9394	0.9615	0.7544
No log	12.0	372	0.0452	0.9467	0.9641	0.7719
No log	13.0	403	0.0424	0.9579	0.9704	0.8246
No log	14.0	434	0.0366	0.9573	0.9735	0.8304
No log	15.0	465	0.0413	0.9543	0.9777	0.7953
No log	16.0	496	0.0384	0.9593	0.9761	0.8304
0.0787	17.0	527	0.0352	0.9622	0.9789	0.8596
0.0787	18.0	558	0.0329	0.9656	0.9778	0.8655
0.0787	19.0	589	0.0351	0.9647	0.9769	0.8655
0.0787	20.0	620	0.0362	0.9601	0.9754	0.8363
0.0787	21.0	651	0.0347	0.9668	0.9811	0.8713
0.0787	22.0	682	0.0355	0.9641	0.9799	0.8596
0.0787	23.0	713	0.0351	0.9639	0.9775	0.8596
0.0787	24.0	744	0.0381	0.9629	0.9766	0.8538
0.0787	25.0	775	0.0376	0.9639	0.9775	0.8596
0.0787	26.0	806	0.0356	0.9639	0.9783	0.8596
0.0787	27.0	837	0.0359	0.9639	0.9775	0.8596
0.0787	28.0	868	0.0354	0.9630	0.9774	0.8596
0.0787	29.0	899	0.0356	0.9630	0.9782	0.8596
0.0787	30.0	930	0.0366	0.9648	0.9785	0.8655
0.0787	31.0	961	0.0357	0.9630	0.9774	0.8596
0.0787	32.0	992	0.0370	0.9630	0.9782	0.8538
0.0043	33.0	1023	0.0363	0.9639	0.9783	0.8596
0.0043	34.0	1054	0.0362	0.9639	0.9783	0.8596
0.0043	35.0	1085	0.0362	0.9639	0.9783	0.8596

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0
• Datasets 2.18.0
• Tokenizers 0.15.2