FF_L0.2_H0.2_dr_grpo / all_results.json
LLucass's picture
Model save
36853fa verified
{
"total_flos": 0.0,
"train_loss": 0.03711814505979419,
"train_runtime": 10340.5912,
"train_samples": 7000,
"train_samples_per_second": 1.238,
"train_steps_per_second": 0.019
}