CHENS
CHENS
> Yes, just as TFA , seed 0 actually is manually sampled. Thus, it always has the best result. What does seed0 mean? In http://dl.yf.io/fs-det/datasets/vocsplit/, there no seed0 folder.
  In Table1, the performance on 10-shot is 61.4 while in Table2, the result is 63.4 and the average over 10 random seeds is 59.7. These results are confusing.
 I use your base model and train it 'Stage 2: Fine-tune for novel data' with 4 gpus, but the results are much lower than the reported. I use the...
If cross-entropy and SCL(supervised contrastive learning) are regarded as a multi-task task, which means that the network is in the form of a backbone and multiple branches, what will be...
 The results on CUB dataset are lower than your results, but the seen result is exactly the same as your seen result. But I have not...
Me too! After I finetune 7B, the model I got is three bin files, but what you release is two bin files. The files I get from finetune are all...
` chosen_trunc_rewards = chosen_rewards[i, div_index:end_index] # shape 69 rejected_trunc_rewards = rejected_rewards[i, div_index:end_index] # shape 69 loss = -torch.nn.functional.logsigmoid(chosen_trunc_rewards - rejected_trunc_rewards).mean()` 请教一个问题。RM模型计算loss的时候，应该是sentence级别或者sequence级别去计算sigmoid loss吧？因为逻辑上是要求某个sentence的回答比另一个sentence的回答的分数高。但是实现的时候，是token级别的去计算sigmoid loss，然后取mean了。不知道是我哪里理解有问题呢？谢谢
Hi, @Xenovortex . Have you reproduced supervised NIN? I have reproduced supervised NIN as the paper setting, which is 88.23 in my experimental results, but the result of the paper...
> Yes, I did reproduced the supervised NIN. With my code (https://github.com/Xenovortex/Implementation-FeatureLearningRotNet), I achieved slightly lower accuracy than in the paper but pretty close: > > Total Accuracy: 91.39 %...