DarrenWang

3d segmentation submission failed

3

hi, I tried to submit my 3d segmentation result to the server many times, but it always shows that 'You have no submissions.' on the submission page, could you do...

why class number of waymo dataset is 23?

1

I noticed that you set 0 as ignore label in cross entropy loss but no in lovasz loss, the reason is?

[BUG]: fp32 param and grad have different shape torch.Size([5064704]) vs torch.Size([128000]) when use lora_rank=4 at stage 1

6

### 🐛 Describe the bug Traceback (most recent call last): File "train_sft.py", line 175, in train(args) File "train_sft.py", line 146, in train train(args) File "train_sft.py", line 146, in train trainer.fit(logger=logger,...

请问二次训练是在什么样的硬件上训练时长是多少呢

### Is there an existing issue for this? - [X] I have searched the existing issues ### Current Behavior 这个函数的作用是在input_ids前面加两个特殊的token，微调训练时一定要加上这个吗，作用是什么 ### Expected Behavior no ### Steps To Reproduce no ###...

[BUG] pull了最新的14b模型相同的代码微调后loss相对之前的高了不少，请问是做了什么改动吗

3

### 是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this? - [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions ### 该问题是否在FAQ中有解答？ | Is there an...

hi, could you send me a token so I can try it? thanks a lot.

error in compiling syntaxnet model branch "documents-from-tensor"

2

Hi, when I compile syntaxnet model branch "documents-from-tensor", error occurs as follow: ERROR: /home/darren.wy/.cache/bazel/_bazel_darren.wy/ac581bc1223ed80290130d37625e326f/external/org_tensorflow/tensorflow/contrib/quantization/kernels/BUILD:86:1: C++ compilation of rule '@org_tensorflow//tensorflow/contrib/quantization/kernels:_quantized_kernels.so' failed: gcc failed: error executing command /usr/bin/gcc -U_FORTIFY_SOURCE '-D_FORTIFY_SOURCE=1' -fstack-protector -Wall...

如题

Hi, when I use zero3 to train model, but occurs ```Invalidate trace cache @ step 0: expected module 0, but got module 6```, anyone who knows the reason.