Qwen2.5-1.5B-Open-R1-Distill / train_results.json
Chrisp33's picture
Model save
373ed83 verified
{
"total_flos": 490444463013888.0,
"train_loss": 0.5787177183371051,
"train_runtime": 11570.0559,
"train_samples": 93733,
"train_samples_per_second": 2.965,
"train_steps_per_second": 0.023
}