Closed Humble2967738843 closed 4 months ago
The file in the folder is just the Toy Example. You need to download the whole datasets. (links are provided in the README)
Oh sorry, thank you. I thought this dataset was a combination of validation and testing datasets...
github_projects/DiffuSeq_v2/DiffuSeq/diffusion_models/diffuseq_cc_h128_lr0.0001_t2000_sqrt_lossaware_seed102_learned_mask_fp16_denoise_0.5_reproduce20240419-12:55:19/training_args.json
Creating model and diffusion...
########## 0
The parameter count is 91225402
reload the random embeddings Embedding(30522, 128)
Sampling...on test
############################## Loading text data... ############################## Loading dataset cc from github_projects/DiffuSeq_v2/DiffuSeq/datasets/CommonsenseConversation...
Loading form the TEST set...
Traceback (most recent call last): File "sample_seq2seq_dpmSolver.py", line 223, in
main()
File "sample_seq2seq_dpmSolver.py", line 87, in main
data_valid = load_data_text(
File "github_projects/DiffuSeq_v2/DiffuSeq/diffuseq/text_datasets.py", line 45, in load_data_text
training_data = get_corpus(data_args, seq_len, split=split, loaded_vocab=loaded_vocab)
File "github_projects/DiffuSeq_v2/DiffuSeq/diffuseq/text_datasets.py", line 238, in get_corpus
with open(path, 'r') as f_reader:
FileNotFoundError: [Errno 2] No such file or directory: 'github_projects/DiffuSeq_v2/DiffuSeq/datasets/CommonsenseConversation/test.jsonl'