Llama-3B-Open-R1-GRPO / train_results.json
krinetic1234's picture
Model save
b1b124f verified
raw
history blame contribute delete
197 Bytes
{
"total_flos": 0.0,
"train_loss": 0.13259683549404144,
"train_runtime": 313.1662,
"train_samples": 174,
"train_samples_per_second": 0.556,
"train_steps_per_second": 0.003
}