Files
qwen3-8b-base-sft-hh-harmle…/train_results.json

9 lines
234 B
JSON
Raw Normal View History

{
"epoch": 1.0,
"total_flos": 8.03524877305774e+16,
"train_loss": 1.7498196733218652,
"train_runtime": 326.8611,
"train_samples": 42336,
"train_samples_per_second": 42.278,
"train_steps_per_second": 0.661
}