Files
Qwen3-8B-base-Open-R1-GRPO_…/all_results.json

8 lines
205 B
JSON
Raw Normal View History

{
"total_flos": 0.0,
"train_loss": -0.00041466000025666894,
"train_runtime": 232889.004,
"train_samples": 14116,
"train_samples_per_second": 1.924,
"train_steps_per_second": 0.004
}