meshed-memory-transformer
meshed-memory-transformer copied to clipboard
Cannot reproduce the results during RL training stage
Thanks for your work. We are using fixed seeds of these and the result is reproducible for each run until the RL part. Specifically, the results from the XE training stage are reproducible but results are not reproducible from the RL training stage. Is there any way to make the results of the RL stage reproducible?
seed = 1234 random.seed(seed) torch.manual_seed(seed) np.random.seed(seed) torch.cuda.manual_seed_all(seed) os.environ['PYTHONHASHSEED'] = str(seed) torch.backends.cudnn.deterministic = True torch.backends.cudnn.benchmark = False
I met the problem at Switching to RL part . It reports that AssertionError : assert(gts.keys() == res.keys()) and OSError: [WinError 1455] 页面文件太小,无法完成操作。 How do you solve it? Does it because of the lack of my graphics card memory?