CN_RoBERTa_Dig

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

• Loss: 0.0130
• F1: {'f1': 0.9967980788473083}
• Accuracy: {'accuracy': 0.9968}

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
0.4103	0.09	1000	0.3527	{'f1': 0.8274601063829787}	{'accuracy': 0.7924}
0.2856	0.18	2000	0.2321	{'f1': 0.9308926367749896}	{'accuracy': 0.9328}
0.2036	0.27	3000	0.0932	{'f1': 0.975979268414233}	{'accuracy': 0.9759}
0.1441	0.36	4000	0.0455	{'f1': 0.9877477836437892}	{'accuracy': 0.9877}
0.0973	0.44	5000	0.0518	{'f1': 0.9883963106218387}	{'accuracy': 0.9883}
0.0827	0.53	6000	0.0334	{'f1': 0.9924045572656407}	{'accuracy': 0.9924}
0.0723	0.62	7000	0.0398	{'f1': 0.9914581449100593}	{'accuracy': 0.9915}
0.0603	0.71	8000	0.0216	{'f1': 0.9947195377104713}	{'accuracy': 0.9947}
0.044	0.8	9000	0.0285	{'f1': 0.9932122180075863}	{'accuracy': 0.9932}
0.0476	0.89	10000	0.0138	{'f1': 0.9964021587047771}	{'accuracy': 0.9964}
0.0392	0.98	11000	0.0130	{'f1': 0.9967980788473083}	{'accuracy': 0.9968}

Framework versions

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