Files
qwen2.5-3b-sft-10/all_results.json

14 lines
400 B
JSON
Raw Normal View History

{
"epoch": 10.0,
"eval_loss": 1.1112251281738281,
"eval_runtime": 18.0527,
"eval_samples": 9148,
"eval_samples_per_second": 76.609,
"eval_steps_per_second": 1.219,
"total_flos": 737402935050240.0,
"train_loss": 0.556043832511017,
"train_runtime": 12515.2297,
"train_samples": 164653,
"train_samples_per_second": 19.797,
"train_steps_per_second": 0.31
}