Files
qwen3-8b-full-sft-prm-opus-…/all_results.json

8 lines
208 B
JSON
Raw Normal View History

{
"epoch": 3.0,
"total_flos": 6.988388070252872e+17,
"train_loss": 0.41709409590923424,
"train_runtime": 37712.5646,
"train_samples_per_second": 0.14,
"train_steps_per_second": 0.018
}