Mahshid Hosseini

Hi. Thanks for the great repo. When fine-tuning bert on SNLI task using the commands in the `Fine-tuning Models` section, one file `SNLI_bert-base-uncased.json` is generated in the output folder. It...

Do_predict does not make predictions for all instances in the test.tsv

2

Hi. I am running below command to make predictions using my trained BERT binary classifier. The code executed without any error. However, when I look into the `test_results.tsv` file, the...

TypeError: convert_examples_to_features() got an unexpected keyword argument 'sep_token_extra'

6

I am getting this error when I run: `if args['do_train']: train_dataset = load_and_cache_examples(task, tokenizer) global_step, tr_loss = train(train_dataset, model, tokenizer) logger.info(" global_step = %s, average loss = %s", global_step, tr_loss`...

How to run utils.py?

3

Is there any specific parameter that we should pass to run the utils.py? Running the file itself seems does nothing. It does not create the InputFeature objects or anything. What...

Apply ganbert on other classification tasks

1

Hi. Thanks for the great repo. I am running ganbert on my data which is a binary classification task with labels 0 and 1. However, label_maps is causing issues when...

Hi @taolei87 . I am running your sentiment classification code. I used the dataset that was specified in the description. However, I am getting this error. First, I ran the...

Hi. In the code/sentiment section, it is mentioned to run below command. However, there is only one `main.py` in the directory, there is no `model.py`. Does `main.py` does the job?...

Hi. Thanks for the repo. Does the code support multi-label text classification task?

ERROR: No matching distribution found for aum

1

Hi. I am trying to install `aum` on ubuntu, using `pip install -U aum`. However, I am getting this error: `ERROR: Could not find a version that satisfies the requirement...

Train-dev-test splits

1

Hi. Is there any way to use 3 datasets of train, dev, test for training, calculating hyperparameters, and evaluating the model? It seems that the code only uses train.tsv form...