Files
DRA-DR_GRPO/all_results.json

8 lines
201 B
JSON
Raw Normal View History

{
"total_flos": 0.0,
"train_loss": 0.007517670260873274,
"train_runtime": 53153.3665,
"train_samples": 7000,
"train_samples_per_second": 0.452,
"train_steps_per_second": 0.009
}