Files
v43_v29_paper_mix_low_lr25e…/train_results.json

8 lines
220 B
JSON
Raw Normal View History

{
"epoch": 1.5002627430373097,
"total_flos": 3.414600284463329e+17,
"train_loss": 1.907181319736299,
"train_runtime": 5553.447,
"train_samples_per_second": 0.514,
"train_steps_per_second": 0.129
}