Files
v34_v29_paper_mix_lr5e7_ep10/train_results.json

8 lines
206 B
JSON
Raw Normal View History

{
"epoch": 1.0,
"total_flos": 2.27705175303125e+17,
"train_loss": 1.8975331122133912,
"train_runtime": 3756.1832,
"train_samples_per_second": 0.507,
"train_steps_per_second": 0.127
}