Files
Qwen3-1.7B-Base-DPO-Tulu3-d…/train_results.json

9 lines
218 B
JSON
Raw Permalink Normal View History

{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 3.058436307772784,
"train_runtime": 6320.6844,
"train_samples": 272585,
"train_samples_per_second": 43.126,
"train_steps_per_second": 0.337
}