{ "achieved_tflops_per_gpu": 0.003753359957425086, "achieved_tflops_per_gpu_theoretical": 548.8405391773532, "epoch": 7.0, "loss_nan_ranks": 0, "loss_rank_avg": 0.1645904779434204, "mfu_percent": 0.00026525512066608384, "mfu_percent_theoretical": 38.78731725635005, "total_flos": 1702570888593408.0, "train_loss": 0.19200077259858897, "train_runtime": 28350.7795, "train_samples_per_second": 2.597, "train_steps_per_second": 0.162, "valid_targets_mean": 3879.8, "valid_targets_min": 728 }