Shufflewave
Shufflewave
How do you think I should adjust my training strategy?
> i think the epoch num is tooooo big, my model is also a little bit overfitting after full finetune in 20k data and 2 epoch(batch 4 ), and the...
> loss显著降低之后 聚类性能会有明显提升吗
@Yunfan-Li
> 请问 你的实验中5000到1000epoch loss能降低多少
@Yunfan-Li
@czczup 请大佬帮忙看一下
> 在InternVL-Chat-V1-2-Plus中我们用的格式是这样： > > ``` > { > "id": 0, > "image": "images/5.png", > "conversations": [ > { > "from": "human", > "value": "\nPlease provide the bounding box coordinate of...
> 我们的v1.2-plus使用的中文数据中有一些构造的负样本，是这样的格式： > > ``` > {"image": "train2017/000000179725.jpg", "conversations": [{"from": "human", "value": "\n这是哪个旅游景点？"}, {"from": "gpt", "value": "这张图片可能并非拍摄的旅游景点，而是其他场景。"}], "id": 6076} > {"image": "train2017/000000000384.jpg", "conversations": [{"from": "human", "value": "\n图片中的人物是谁？"}, {"from": "gpt", "value":...
@czczup 感谢 请问可以在训练过程中，验证一下验证集上的指标吗