Qwen-2.5-7B-Simple-RL / all_results.json
susumuota's picture
Model save
8805cfa verified
{
"total_flos": 0.0,
"train_loss": 0.03837096903087764,
"train_runtime": 7408.2441,
"train_samples": 7500,
"train_samples_per_second": 1.012,
"train_steps_per_second": 0.008
}