license: apache-2.0
datasets:
- ambrosfitz/ps_data_v2.2
Run history:
train/epoch βββββββββββ β β ββββββββ train/global_step βββββββββββ β β ββββββββ train/grad_norm ββββ ββ ββββββββββββββ train/learning_rate βββββ β ββββββββ β βββββ train/loss βββββ β ββββββββββββββ train/total_flos β train/train_loss β train/train_runtime β train/train_samples_per_second β train/train_steps_per_second β
Run summary:
train/epoch 2.0 train/global_step 20 train/grad_norm 0.13779 train/learning_rate 0.0 train/loss 1.1365 train/total_flos 4.579249185376512e+16 train/train_loss 1.29891 train/train_runtime 1552.5749 train/train_samples_per_second 1.649 train/train_steps_per_second 0.013