OLMoE-1B-7B-0125-Instruct-grpo / all_results.json
chenggong1995's picture
Model save
38cbaf4 verified
raw
history blame
202 Bytes
{
"total_flos": 0.0,
"train_loss": 0.01271514138510042,
"train_runtime": 147461.7668,
"train_samples": 72441,
"train_samples_per_second": 0.491,
"train_steps_per_second": 0.004
}