You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I trained the 61 examples using BERT classifier as baseline, but it gets 72.49% accuracy, and EDA gets 74.57% accuracy, but BERT-finetune and GPT2-finetune only get the 64% and 66% accuracy
How do you select the best model when finetuning complete? Is just set the flag --load_best_model_at_end?
How do you mask the tokens when augment by fine-tuned BERT? Is using the DataCollector.py? Masking the whole word or the single tokens?
Can you tell more details about the GPT2 finetune details? Because I get the mini-perplexity for 47 by epochs=10, I am confused about how to get the best fine-tune GPT2 model for augmentation.
Thank you!!!
The text was updated successfully, but these errors were encountered:
My way to choose the best model is use wandb.ai to watch the training log then get the checkpoint that have the mini eval_loss, mini eval_accuracy and max training loss, is that ok?
Hi, I'm trying to reproduce your experiment.
I trained the 61 examples using BERT classifier as baseline, but it gets 72.49% accuracy, and EDA gets 74.57% accuracy, but BERT-finetune and GPT2-finetune only get the 64% and 66% accuracy
I have some question while doing finetune BERT by MLM and GPT2 by CLM by using this two code: https://github.com/huggingface/transformers/blob/master/examples/language-modeling/run_mlm.py
https://github.com/huggingface/transformers/blob/master/examples/language-modeling/run_clm.py
How do you select the best model when finetuning complete? Is just set the flag --load_best_model_at_end?
How do you mask the tokens when augment by fine-tuned BERT? Is using the DataCollector.py? Masking the whole word or the single tokens?
Can you tell more details about the GPT2 finetune details? Because I get the mini-perplexity for 47 by epochs=10, I am confused about how to get the best fine-tune GPT2 model for augmentation.
Thank you!!!
The text was updated successfully, but these errors were encountered: