cyan_s
cyan_s
2B的模型可以支持微调高分辨吗,尝试训练分辨率为(720, 1024)的模型,在vae阶段的x_rest = torch.nn.functional.avg_pool1d(x_rest, kernel_size=2, stride=2),会报错RuntimeError: integer out of range
`#! /bin/bash echo "RUN on $(hostname), CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES" run_cmd="PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True torchrun --standalone --nproc_per_node=8 train_video.py --base configs/test_cogvideox_5b.yaml configs/sft.yaml --seed $RANDOM" echo ${run_cmd} eval ${run_cmd} echo "DONE on `hostname`"` 启动命令应该怎样写呢? sft.yaml 跟cogvideo5b.yaml里配置需要修改么?
使用的环境如下 Package Version ------------------------ ----------- accelerate 1.6.0 aiofiles 24.1.0 aiohappyeyeballs 2.6.1 aiohttp 3.11.16 aiosignal 1.3.2 annotated-types 0.7.0 anyio 4.9.0 async-timeout 5.0.1 attrs 25.3.0 beautifulsoup4 4.13.3 certifi 2025.1.31 charset-normalizer 3.4.1 click...