kambert

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: 0.0973
• F1: 0.9263
• Roc Auc: 0.9558
• Accuracy: 0.9263

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: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
No log	1.0	68	0.3104	0.5522	0.6926	0.3895
No log	2.0	136	0.1786	0.8701	0.9000	0.8105
No log	3.0	204	0.1377	0.9043	0.9389	0.8947
No log	4.0	272	0.1141	0.9101	0.9442	0.9053
No log	5.0	340	0.1051	0.9053	0.9432	0.9053
No log	6.0	408	0.0973	0.9263	0.9558	0.9263
No log	7.0	476	0.0943	0.9263	0.9558	0.9263
0.1513	8.0	544	0.0949	0.9263	0.9558	0.9263
0.1513	9.0	612	0.0946	0.9263	0.9558	0.9263
0.1513	10.0	680	0.0947	0.9263	0.9558	0.9263

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1