whatsapp-group-classifierv2

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4619
• Accuracy: 0.8283
• Precision: 0.8483
• Recall: 0.8347
• F1: 0.8407

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: 4e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.9676	1.0	513	0.7151	0.7322	0.7315	0.7148	0.7182
0.6846	2.0	1026	0.5747	0.7741	0.7918	0.7716	0.7732
0.5657	3.0	1539	0.5265	0.7946	0.8224	0.7882	0.7983
0.5294	4.0	2052	0.4870	0.8059	0.8260	0.8084	0.8163
0.4941	5.0	2565	0.4787	0.8102	0.8326	0.8122	0.8210
0.4956	6.0	3078	0.4796	0.8156	0.8363	0.8183	0.8252
0.4701	7.0	3591	0.4812	0.8146	0.8370	0.8165	0.8230
0.4521	8.0	4104	0.4738	0.8220	0.8398	0.8287	0.8336
0.444	9.0	4617	0.4664	0.8195	0.8412	0.8240	0.8313
0.4336	10.0	5130	0.4682	0.8244	0.8445	0.8311	0.8370
0.4345	11.0	5643	0.4653	0.8229	0.8446	0.8285	0.8351
0.4275	12.0	6156	0.4619	0.8254	0.8463	0.8322	0.8382
0.4155	13.0	6669	0.4620	0.8288	0.8487	0.8356	0.8414
0.4179	14.0	7182	0.4624	0.8283	0.8485	0.8354	0.8412
0.4078	15.0	7695	0.4619	0.8283	0.8483	0.8347	0.8407

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0