“From the Related Work section (best guess): Stochastic Weight Averaging (Izmailov et al 2018) https://arxiv.org/abs/1803.05407 Latest Weight Averaging (Kaddour 2022) https://arxiv.org/abs/2209.14981 Latest Weight Averaging? (Sanyal et al 2023) https://arxiv.org/abs/2311.16294 Cyclic Learning Rates (Portes et al 2022) https://arxiv.org/abs/2206.00832 …”
按年被提到
20222022 · 1 次2026
Stop Wasting My Time! Saving Days of ImageNet and BERT Training with Latest Weight Averaging
Jean Kaddour · 2022
被提及 · 2 人首次 2022-10-02 · 最近 2024-04-06
2不同的人
2活跃月份
2讨论串
8被引(OpenAlex)
arXiv 摘要(候选层不写导读)
Training vision or language models on large datasets can take days, if not weeks. We show that averaging the weights of the k latest checkpoints, each collected at the end of an epoch, can speed up the training progression in terms of loss and accuracy by dozens of epochs, corresponding to time savings up to ~68 and ~30 GPU hours when training a ResNet50 on ImageNet and RoBERTa-Base model on WikiText-103, respectively. We also provide the code and model checkpoint trajectory to reproduce the results and facilitate research on reusing historical weights for faster convergence.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及评论JieJie · 2024-04
被提交为 story · 1 次
- Saving Days of ImageNet and Bert Training with Latest Weight Averaging ↗belter · 2022-10-02 · 2 分