epoch = 2.0 | |
total_flos = 9.602043799869562e+16 | |
train_loss = 0.42129573760465744 | |
train_runtime = 3759.5481 | |
train_samples = 69399 | |
train_samples_per_second = 36.919 | |
train_steps_per_second = 2.308 | |
epoch = 2.0 | |
total_flos = 9.602043799869562e+16 | |
train_loss = 0.42129573760465744 | |
train_runtime = 3759.5481 | |
train_samples = 69399 | |
train_samples_per_second = 36.919 | |
train_steps_per_second = 2.308 | |