Qwen-2.5-7B-Simple-RL / all_results.json
alterego238's picture
Model save
f11a928 verified
{
"total_flos": 0.0,
"train_loss": 0.040922524543992915,
"train_runtime": 12307.4855,
"train_samples": 7500,
"train_samples_per_second": 0.609,
"train_steps_per_second": 0.005
}