HuggingFaceH4/Qwen2.5-Math-7B-Instruct-PRM-0.2
024
1{2 "epoch": 1.0,3 "eval_accuracy": 0.9302021162207228,4 "eval_loss": 0.2495153844356537,5 "eval_runtime": 59.5203,6 "eval_samples_per_second": 172.143,7 "eval_steps_per_second": 5.3938}