Closed ilingen closed 1 year ago
Hi,
Please make sure you have converted the model format per README's instruction before you use evaluation.py
.
Hi, I have got the 75.7% spearman correlation by setting different random seeds and I have checked my previous resutls and found that different random seed had a large impact on the performance. I am going to close this issue and thanks for your reply.
When I train my simcse model by using run_unsup_example.sh, I got the best result as follows:
But when I run evaluate.py to test my trained model, it's eval_avg_sts score is only 0.7490, which is 2 points gap. I think it is an unacceptable loss. BTW, I also run
, and get eval_avg_sts score is 76.25, same as the paper reported. So I wonder why my train result and evaluate result differ a lot.