full-review-clf

作者 justina · 下载 0 · 点赞 0 · 更新 2023-11-03

generated_from_trainer

full-review-clf

This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-sentiment-latest on justina/yelp-boba-reviews dataset.

It achieves the following results on the evaluation set:

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:

Training results

Training Loss Epoch Step Validation Loss F1 Macro Aucpr Macro Accuracy
0.723 0.43 500 0.7576 0.5979 0.6652 0.6831
0.7307 0.87 1000 0.6862 0.6368 0.6752 0.7185
0.5828 1.3 1500 0.7398 0.6439 0.6661 0.7255
0.6236 1.73 2000 0.7878 0.6212 0.6690 0.7069
0.3739 2.16 2500 0.8138 0.6447 0.6752 0.7170
0.4235 2.6 3000 0.8048 0.6490 0.6673 0.7255
0.3684 3.03 3500 0.9615 0.6483 0.6715 0.7205
0.3243 3.46 4000 1.0931 0.6432 0.6632 0.7235

Framework versions