Files
aup-fullft-kto_w1-w1lam9.68…/train_results.json

8 lines
208 B
JSON
Raw Normal View History

{
"epoch": 3.0,
"total_flos": 9.969850461966828e+17,
"train_loss": 0.5859840150941839,
"train_runtime": 11024.7736,
"train_samples_per_second": 13.444,
"train_steps_per_second": 0.21
}