GRPO / train_results.json
LLucass's picture
Model save
439dfa7 verified
raw
history blame contribute delete
203 Bytes
{
"total_flos": 0.0,
"train_loss": 0.00011944215420650531,
"train_runtime": 12092.6435,
"train_samples": 7000,
"train_samples_per_second": 1.191,
"train_steps_per_second": 0.012
}