Qwen-2.5-7B-Simple-RL / train_results.json
kkish's picture
Model save
2d303ff verified
{
"total_flos": 0.0,
"train_loss": 0.01571170037346621,
"train_runtime": 7483.8014,
"train_samples": 7500,
"train_samples_per_second": 1.002,
"train_steps_per_second": 0.008
}