Training log of RepLLaMA
kyriemao opened this issue · comments
this looks a bit weird. what is your batch size/ training group size setting?
this looks a bit weird. what is your batch size/ training group size setting?
The param settings are:
- per_gpu_train_batch_size=8,
- hard_negatives_per_sample=15,
- learning_rate=1e-4,
- gradient_accumulation_steps=4.
I use 6 A100 40G GPUs for training.
Solved. It is because of my own bug about processing the EOS token. Thanks!
Hello, I met the same problem. Can you please tell me how do you solve it? Thank you a lot!