SimCSE

SimCSE copied to clipboard

Question: When inference hint:newly initialized: ['bert.pooler.dense.weight', 'bert.pooler.dense.bias']

1

I used the latest release of the version, and use the `run_sup_example.sh` to train my datasets. But when I used SimCSE to load the model I got this hint: Use...

zhiqiangohuo

How can I tell if the model is converging or not, and is the value of the loss function indicative? I trained on my own dataset and the loss of...

Jessica-jia

wget: Command not found

3

I'm trying to train SimCSE in a virtual environment (w/ python 3.7.0) I tried to run the download_wiki.sh file, but I got an error message saying "/Users/davidsun/Downloads/SimCSE/data/download_wiki.sh: line 1: wget:...

sundavid2002

Issue w/ batch shape

2

I am trying to run SimCSE evaluation on a virtual environment w/ python 3.8.6 & the following packages: transformers==4.2.1 scipy==1.5.4 datasets==1.2.1 pandas==1.1.5 scikit-learn==0.24.0 prettytable==2.1.0 gradio torch setuptools==49.3.0 I tried running...

sundavid2002

How do I use SimCSE on my own dataset?

1

I'm doing search task and the pre-training model I'm using is RoBerta Base. I would like to join SimCSE on this basis, how to use SimCSE on my own data...

skye95git

encode method generate diff vector output

1

So, encode method in tool.py may generate diff results after each run. add model.eval() may solve the problem. also adding a vector saving and reloading function may by helpful

mingyao743

when I run the train.py get the warning .

xxllp

The command is exactly as the following example, only the model_name_or_path is changed ```shell python evaluation.py \ --model_name_or_path princeton-nlp/sup-simcse-bert-base-uncased \ --pooler cls \ --task_set sts \ --mode test ``` The...

Moximixi

setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (750,) + inhomogeneous part.

1

报错：setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (750,) + inhomogeneous part.

JYru

AttributeError: 'OurTrainingArguments' object has no attribute 'distributed_state'

1

'OurTrainingArguments' object has no attribute 'distributed_state' File "/public/duzx/project/Path2Vec/SimCSE/train.py", line 548, in main trainer = CLTrainer( File "/public/duzx/project/Path2Vec/SimCSE/train.py", line 600, in main() AttributeError: 'OurTrainingArguments' object has no attribute 'distributed_state'

zongxindu