Performance of fine-tuned Gemma (500 samples) across ten runs.
收藏数据链接:
官方服务:
资源简介:
Metrics include mean, standard deviation (SD), and 95% confidence interval (CI) using the t-distribution. For sentiment analysis and news categorization, the metric is macro-F1. For sarcasm detection, F1-score is used.
创建时间:
2025-10-08



