Qwen2.5-1.5B-Open-R1-GRPO-lora / train_results.json
T1anyu's picture
Model save
1298acc verified
raw
history blame contribute delete
204 Bytes
{
"total_flos": 0.0,
"train_loss": 0.00019750852083552672,
"train_runtime": 15991.8306,
"train_samples": 93733,
"train_samples_per_second": 0.125,
"train_steps_per_second": 0.031
}