Qwen2.5-1.5B-Open-R1-Distill / all_results.json
hdong0's picture
Model save
2f3bbec verified
{
"total_flos": 3436437652111360.0,
"train_loss": 0.4596632290483199,
"train_runtime": 36029.2862,
"train_samples": 93733,
"train_samples_per_second": 7.805,
"train_steps_per_second": 0.122
}