CN_BERT_Digit

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: 0.0264
• F1: {'f1': 0.9936038376973816}
• Accuracy: {'accuracy': 0.9936}

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: 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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Accuracy
0.4023	0.09	1000	0.5834	{'f1': 0.7928479381443299}	{'accuracy': 0.7428}
0.269	0.18	2000	0.2556	{'f1': 0.8676012461059189}	{'accuracy': 0.881}
0.1879	0.27	3000	0.1296	{'f1': 0.9648982848025529}	{'accuracy': 0.9648}
0.142	0.36	4000	0.1022	{'f1': 0.9740272663946662}	{'accuracy': 0.9739}
0.1172	0.44	5000	0.0724	{'f1': 0.979466322785438}	{'accuracy': 0.9793}
0.1044	0.53	6000	0.1166	{'f1': 0.9756195043964828}	{'accuracy': 0.9756}
0.0948	0.62	7000	0.0538	{'f1': 0.98813441021039}	{'accuracy': 0.9881}
0.075	0.71	8000	0.0444	{'f1': 0.9892989298929893}	{'accuracy': 0.9893}
0.0667	0.8	9000	0.0427	{'f1': 0.9911168779319294}	{'accuracy': 0.9911}
0.0667	0.89	10000	0.0448	{'f1': 0.9908384783907588}	{'accuracy': 0.9908}
0.0668	0.98	11000	0.0264	{'f1': 0.9936038376973816}	{'accuracy': 0.9936}

Framework versions

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