Qwen2.5-0.5B-Open-R1-Distill / all_results.json
CHENGEX's picture
Model save
6e3228a verified
raw
history blame contribute delete
214 Bytes
{
"total_flos": 120412440625152.0,
"train_loss": 0.8387799017897276,
"train_runtime": 16365.4967,
"train_samples": 46866,
"train_samples_per_second": 16.74,
"train_steps_per_second": 0.065
}