grpo-llama-3-1-8b-math-ep3 / all_results.json
nghind's picture
Model save
355d9d3 verified
raw
history blame contribute delete
203 Bytes
{
"total_flos": 0.0,
"train_loss": 0.00012346780326337724,
"train_runtime": 38700.7369,
"train_samples": 7943,
"train_samples_per_second": 0.616,
"train_steps_per_second": 0.019
}