Qwen2.5-0.5B-Open-R1-Distill / all_results.json
rhinocamp's picture
Model save
971e654 verified
{
"total_flos": 241268013662208.0,
"train_loss": 0.6583015036894314,
"train_runtime": 13168.5767,
"train_samples": 93733,
"train_samples_per_second": 2.605,
"train_steps_per_second": 0.163
}