I am new to OpenNMT, while training, command line is almost empty during training.
How can I print epoch number, time left for current epoch or loss while training network??
what and where should I add print(“XXXX”) statements??
Many thanks in advance.
How long have you waited while the command line kept empty?
If you use cpu to run the training process, It will be very slowly. So maybe it should evaluate your hardware. I have run the training in the VPS with 8cores and the script seems dead in about half an hours… So it’s bad experience if you don’t have GPU.
I think you can buy a GPU like gtx1060~1080ti or rtx2060/2070/2080 to training your model.
Anyway. Just goole: how to start deep learning.
Hi yaren, Thanks for your reply.
I am using Titan V for training. I think there is Probem with command I am using.
If I use CPU with below command
“python train.py -src_word_vec_size 200 -tgt_word_vec_size 200 -data data/model -save_model sum_eng-model -batch_size 64 -valid_steps 5000 -train_steps 100000 -report_every 50”
Traning start with CPU, slow but fine.
But when I try with GPU, with below command
“python train.py -src_word_vec_size 200 -tgt_word_vec_size 200 -data data/model -save_model sum_eng-model -save_checkpoint_steps 100 -world_size 2 -gpu_ranks 1 -batch_size 32 -valid_steps 1000 -train_steps 100000 -report_every 1”
Here I even reduced the batch size, checkpoint step and report step, but nothing happens, even description of model is not showing. (I have GTX 1070 as GPU 0, so using -gpu_ranks 1 for titan)
Am I using right command???