bert_test_8

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: 0.7390
• F1: 0.8624

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 8
• 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	F1
1.5054	1.0	341	0.8553	0.7042
0.7004	2.0	682	0.5741	0.8367
0.4056	3.0	1023	0.4853	0.8504
0.2813	4.0	1364	0.4766	0.8574
0.1813	5.0	1705	0.4964	0.8536
0.1327	6.0	2046	0.5343	0.8648
0.1148	7.0	2387	0.6017	0.8723
0.0755	8.0	2728	0.6251	0.8684
0.0552	9.0	3069	0.6666	0.8624
0.0442	10.0	3410	0.6992	0.8670
0.0308	11.0	3751	0.7045	0.8705
0.0235	12.0	4092	0.7237	0.8607
0.0219	13.0	4433	0.7377	0.8596
0.0249	14.0	4774	0.7384	0.8646
0.0214	15.0	5115	0.7390	0.8624

Framework versions

• Transformers 4.27.1
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.13.3