Files
Qwen3-4B-grpo-medmcqa/all_results.json

8 lines
204 B
JSON
Raw Normal View History

{
"total_flos": 0.0,
"train_loss": 0.0036022694108365965,
"train_runtime": 15331.4788,
"train_samples": 182822,
"train_samples_per_second": 5.962,
"train_steps_per_second": 0.124
}