Qwen2.5-1.5B-Open-R1-Distill / all_results.json
howey's picture
Model save
e50cd4d verified
raw
history blame contribute delete
218 Bytes
{
"total_flos": 4.418757235321078e+18,
"train_loss": 0.5497396646150902,
"train_runtime": 11730.1118,
"train_samples": 93733,
"train_samples_per_second": 2.924,
"train_steps_per_second": 0.091
}