Llama-3B-Open-R1-GRPO / all_results.json
krinetic1234's picture
End of training
f0699fe verified
raw
history blame contribute delete
364 Bytes
{
"eval_loss": 0.09372581541538239,
"eval_runtime": 337.1395,
"eval_samples": 174,
"eval_samples_per_second": 0.516,
"eval_steps_per_second": 0.012,
"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
}