Qwen2.5-1.5B-Open-R1-Distill / train_results.json
Loong-Ma's picture
Model save
bd1eb2f verified
raw
history blame contribute delete
220 Bytes
{
"total_flos": 2.7844372399870968e+19,
"train_loss": 0.4556342206203221,
"train_runtime": 169635.2867,
"train_samples": 93733,
"train_samples_per_second": 0.553,
"train_steps_per_second": 0.004
}