verizon_model1

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

• Loss: 0.0242
• Accuracy: 1.0
• F1: 1.0

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.458	1.0	8	1.1774	0.7451	0.6817
1.1574	2.0	16	0.8376	0.7843	0.6934
0.8281	3.0	24	0.6155	0.8627	0.8055
0.6272	4.0	32	0.4462	0.8824	0.8493
0.4532	5.0	40	0.3344	0.9216	0.9111
0.3607	6.0	48	0.2535	1.0	1.0
0.2153	7.0	56	0.1961	0.9804	0.9800
0.1704	8.0	64	0.1489	1.0	1.0
0.1238	9.0	72	0.1116	1.0	1.0
0.0998	10.0	80	0.0841	1.0	1.0
0.097	11.0	88	0.0642	1.0	1.0
0.0751	12.0	96	0.0510	1.0	1.0
0.0583	13.0	104	0.0421	1.0	1.0
0.0422	14.0	112	0.0350	1.0	1.0
0.037	15.0	120	0.0307	1.0	1.0
0.0354	16.0	128	0.0282	1.0	1.0
0.0336	17.0	136	0.0265	1.0	1.0
0.0316	18.0	144	0.0252	1.0	1.0
0.0341	19.0	152	0.0244	1.0	1.0
0.027	20.0	160	0.0242	1.0	1.0

Framework versions

• Transformers 4.16.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2