Files
qwen25_plan_sft_10k/train_results.json

8 lines
208 B
JSON
Raw Permalink Normal View History

{
"epoch": 3.0,
"total_flos": 1.2370288879507341e+19,
"train_loss": 0.13962188102543227,
"train_runtime": 7247.2658,
"train_samples_per_second": 4.139,
"train_steps_per_second": 0.13
}