【犀牛鸟实战issue】overfitting fail#107
Open
wktomo wants to merge 2 commits intoTencent-Hunyuan:mainfrom
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
任务说明：在小数据集上过模型效果不佳，在小数据集上模型能很好地解决
方案：模型会快速记住所有数据，但继续训练会导致优化器震荡，损失不降反升，从而形成“过结果效果不佳”，减少步数，增加正则化，降低学习率和提高数据增强性能，采用一下方式来检验：
1.观察训练损失：应快速恢复到接近0。
2.观察验证损失（如果有）：应快速上升（过精致的标志）。
3.生成样本：检查模型是否能完美重建训练数据。
完成修改dit_asl.yaml和train_mini_overfit.py是相应的模型权重训练和代码，提高了在迷你数据集上的过精致性能，降低了相应的损失度