for_classification

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

• Loss: 0.2366
• Accuracy: 0.9189
• F1: 0.9415

模型實作

from transformers import pipeline

id2_label = {'LABEL_0':"負評",'LABEL_1':"正評"}
pipe = pipeline('text-classification', model="roberthsu2003/for_classification")

sen="服務人員都很親切"
print(sen,id2_label[pipe(sen)[0]['label']])

sen1="服務人員都不親切"
print(sen1,id2_label[pipe(sen1)[0]['label']])

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: 64
• eval_batch_size: 128
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.2886	1.0	110	0.2269	0.9009	0.9272
0.1799	2.0	220	0.2218	0.9112	0.9356
0.1395	3.0	330	0.2366	0.9189	0.9415

Framework versions

• Transformers 4.50.0
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1