Files
Qwen3-1.7B-Base-SFT-Tulu3-d…/all_results.json

8 lines
217 B
JSON
Raw Normal View History

{
"total_flos": 2054647610245120.0,
"train_loss": 0.8722328752120434,
"train_runtime": 78239.8608,
"train_samples": 936509,
"train_samples_per_second": 23.939,
"train_steps_per_second": 0.187
}