Issues
- 0
How to fine-tune ALBERT for NER
#48 opened by Branislava - 8
Pretraining of albert from scratch is stuck
#36 opened by 008karan - 0
ALBERT model not learning
#41 opened by raviolli - 0
metrics about CoLA
#40 opened by cyjj - 0
- 0
- 0
Getting huge number training steps
#37 opened by 008karan - 9
tf.saved_model.save and predict a single value
#25 opened by Bidek56 - 3
Pre-training on GPUs seems to be stuck
#16 opened by tomohideshibata - 0
"lamp" should be "lamb"
#35 opened by donghyeonk - 3
Fine Tune Error
#30 opened by zzj0402 - 2
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[16,128,3072]
#33 opened by suresh96458 - 3
Unable to open file (unable to open file: name = 'large//tf2_model.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)
#32 opened by suresh96458 - 1
Create Fine-Tuning Data
#28 opened by zzj0402 - 2
run_classifier.py Error COLA
#31 opened by zzj0402 - 0
Natural Question Data Prep Script
#29 opened by zzj0402 - 4
Pre-training using GPUs is strange
#21 opened by tomohideshibata - 0
Docker Containerization
#27 opened by zzj0402 - 0
Freezing layers during training
#26 opened by birdmw - 1
Gradients do not exist for variables
#18 opened by guozhiyu - 1
Unused weights from saved model
#23 opened by xixiaoyao - 1
- 0
SQuAD predictions fail
#22 opened by WingCode - 4
Multi GPU finetuning
#19 opened by steindor - 1
Suggestion on Readme.MD
#20 opened by birdmw - 8
AssertionError
#17 opened by chiragsanghvi10 - 4
Resuming training from tf checkpoints
#15 opened by steindor - 2
KeyError: 5.0
#14 opened by chiragsanghvi10 - 1
Training from scratch in another language
#11 opened by peregilk - 1
run pretraining in TPU
#10 opened by nhocqn - 5
Pretraining from scatch
#7 opened by hairzooc - 3
- 2
How to continue the finetuning?
#12 opened by loginaway - 22
do_predict?
#3 opened by acmilannesta - 5
- 1
- 1
training parameter
#8 opened by shawei3000 - 3
same tf2_model.h5 (v1 & v2, for xxlarge)?
#6 opened by shawei3000