Files
OpenRS-GRPO/train_results.json

8 lines
201 B
JSON
Raw Permalink Normal View History

{
"total_flos": 0.0,
"train_loss": 0.0008326698157195504,
"train_runtime": 30165.0377,
"train_samples": 7000,
"train_samples_per_second": 0.239,
"train_steps_per_second": 0.01
}