{ "achieved_tflops_per_gpu": 0.010354545414379324, "achieved_tflops_per_gpu_theoretical": 1519.821207581491, "epoch": 5.0, "loss_nan_ranks": 0, "loss_rank_avg": 0.21731798350811005, "mfu_percent": 0.0007317699939490688, "mfu_percent_theoretical": 107.40785919303823, "total_flos": 9850857283649536.0, "train_loss": 0.03974963869139502, "train_runtime": 9909.9567, "train_samples_per_second": 14.475, "train_steps_per_second": 0.151, "valid_targets_mean": 1465.8, "valid_targets_min": 325 }