princeton-nlp / SimCSE

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
MIT License
3.4k stars 512 forks source link

error when training run_unsup_example.sh #58

Closed mode007 closed 3 years ago

mode007 commented 3 years ago

When i run run_unsup_example.sh, an error happend: 6%|████████▎ | 125/1954 [01:30<17:25, 1.75it/s]Traceback (most recent call last): File "train.py", line 584, in main() File "train.py", line 548, in main train_result = trainer.train(model_path=model_path) File "/home/yutianyao/whoiswho/train_simcse/simcse/trainers.py", line 507, in train self._maybe_log_save_evaluate(tr_loss, model, trial, epoch) File "/root/anaconda3/envs/myven/lib/python3.7/site-packages/transformers/trainer.py", line 1004, in _maybe_log_save_evaluate metrics = self.evaluate() File "/home/yutianyao/whoiswho/train_simcse/simcse/trainers.py", line 129, in evaluate results = se.eval(tasks) File "./SentEval/senteval/engine.py", line 59, in eval self.results = {x: self.eval(x) for x in name} File "./SentEval/senteval/engine.py", line 59, in self.results = {x: self.eval(x) for x in name} File "./SentEval/senteval/engine.py", line 85, in eval self.evaluation = STSBenchmarkEval(tpath + '/downstream/STS/STSBenchmark', seed=self.params.seed) File "./SentEval/senteval/sts.py", line 165, in init train = self.loadFile(os.path.join(task_path, 'sts-train.csv')) File "./SentEval/senteval/sts.py", line 173, in loadFile with io.open(fpath, 'r', encoding='utf-8') as f: FileNotFoundError: [Errno 2] No such file or directory: './SentEval/data/downstream/STS/STSBenchmark/sts-train.csv'

Could you please tell me why? thank you!

mode007 commented 3 years ago

I solved it! sorry, because i I didn't download eval/data