{ "best_metric": 1.5818963050842285, "best_model_checkpoint": "detr-r101-cd45rb-8ah-6l-256d-4096ffn-correcetd\\checkpoint-115150", "epoch": 25.0, "global_step": 115150, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "learning_rate": 9.501085540599219e-06, "loss": 2.3194, "step": 4606 }, { "epoch": 1.0, "eval_loss": 1.7874349355697632, "eval_runtime": 255.9695, "eval_samples_per_second": 6.958, "eval_steps_per_second": 0.871, "step": 4606 }, { "epoch": 2.0, "learning_rate": 9.001085540599219e-06, "loss": 2.3461, "step": 9212 }, { "epoch": 2.0, "eval_loss": 1.8375755548477173, "eval_runtime": 255.8256, "eval_samples_per_second": 6.962, "eval_steps_per_second": 0.872, "step": 9212 }, { "epoch": 3.0, "learning_rate": 8.501302648719063e-06, "loss": 2.3028, "step": 13818 }, { "epoch": 3.0, "eval_loss": 1.9087122678756714, "eval_runtime": 255.4494, "eval_samples_per_second": 6.972, "eval_steps_per_second": 0.873, "step": 13818 }, { "epoch": 4.0, "learning_rate": 8.001628310898828e-06, "loss": 2.2979, "step": 18424 }, { "epoch": 4.0, "eval_loss": 1.906615972518921, "eval_runtime": 255.8122, "eval_samples_per_second": 6.962, "eval_steps_per_second": 0.872, "step": 18424 }, { "epoch": 5.0, "learning_rate": 7.501736864958749e-06, "loss": 2.273, "step": 23030 }, { "epoch": 5.0, "eval_loss": 1.7688573598861694, "eval_runtime": 223.3286, "eval_samples_per_second": 7.975, "eval_steps_per_second": 0.999, "step": 23030 }, { "epoch": 6.0, "learning_rate": 7.001845419018671e-06, "loss": 2.2372, "step": 27636 }, { "epoch": 6.0, "eval_loss": 1.850079894065857, "eval_runtime": 222.161, "eval_samples_per_second": 8.017, "eval_steps_per_second": 1.004, "step": 27636 }, { "epoch": 7.0, "learning_rate": 6.501953973078594e-06, "loss": 2.2429, "step": 32242 }, { "epoch": 7.0, "eval_loss": 1.7625480890274048, "eval_runtime": 221.7461, "eval_samples_per_second": 8.032, "eval_steps_per_second": 1.006, "step": 32242 }, { "epoch": 8.0, "learning_rate": 6.0021710811984364e-06, "loss": 2.2066, "step": 36848 }, { "epoch": 8.0, "eval_loss": 1.7588337659835815, "eval_runtime": 221.9488, "eval_samples_per_second": 8.024, "eval_steps_per_second": 1.005, "step": 36848 }, { "epoch": 9.0, "learning_rate": 5.5023881893182805e-06, "loss": 2.1914, "step": 41454 }, { "epoch": 9.0, "eval_loss": 1.7061983346939087, "eval_runtime": 260.572, "eval_samples_per_second": 6.835, "eval_steps_per_second": 0.856, "step": 41454 }, { "epoch": 10.0, "learning_rate": 5.002605297438125e-06, "loss": 2.1553, "step": 46060 }, { "epoch": 10.0, "eval_loss": 1.706916093826294, "eval_runtime": 254.0051, "eval_samples_per_second": 7.012, "eval_steps_per_second": 0.878, "step": 46060 }, { "epoch": 11.0, "learning_rate": 4.502822405557969e-06, "loss": 2.1302, "step": 50666 }, { "epoch": 11.0, "eval_loss": 1.6863188743591309, "eval_runtime": 253.207, "eval_samples_per_second": 7.034, "eval_steps_per_second": 0.881, "step": 50666 }, { "epoch": 12.0, "learning_rate": 4.003039513677812e-06, "loss": 2.1321, "step": 55272 }, { "epoch": 12.0, "eval_loss": 1.7721848487854004, "eval_runtime": 253.9074, "eval_samples_per_second": 7.014, "eval_steps_per_second": 0.878, "step": 55272 }, { "epoch": 13.0, "learning_rate": 3.503148067737734e-06, "loss": 2.1227, "step": 59878 }, { "epoch": 13.0, "eval_loss": 1.6639100313186646, "eval_runtime": 254.2906, "eval_samples_per_second": 7.004, "eval_steps_per_second": 0.877, "step": 59878 }, { "epoch": 14.0, "learning_rate": 3.003365175857577e-06, "loss": 2.087, "step": 64484 }, { "epoch": 14.0, "eval_loss": 1.6486269235610962, "eval_runtime": 254.2198, "eval_samples_per_second": 7.006, "eval_steps_per_second": 0.877, "step": 64484 }, { "epoch": 15.0, "learning_rate": 2.5036908380373426e-06, "loss": 2.0676, "step": 69090 }, { "epoch": 15.0, "eval_loss": 1.6632195711135864, "eval_runtime": 253.8344, "eval_samples_per_second": 7.016, "eval_steps_per_second": 0.879, "step": 69090 }, { "epoch": 16.0, "learning_rate": 2.0036908380373427e-06, "loss": 2.0604, "step": 73696 }, { "epoch": 16.0, "eval_loss": 1.6428617238998413, "eval_runtime": 252.8055, "eval_samples_per_second": 7.045, "eval_steps_per_second": 0.882, "step": 73696 }, { "epoch": 17.0, "learning_rate": 1.5039079461571866e-06, "loss": 2.0435, "step": 78302 }, { "epoch": 17.0, "eval_loss": 1.6223891973495483, "eval_runtime": 252.2863, "eval_samples_per_second": 7.059, "eval_steps_per_second": 0.884, "step": 78302 }, { "epoch": 18.0, "learning_rate": 1.004233608336952e-06, "loss": 2.0241, "step": 82908 }, { "epoch": 18.0, "eval_loss": 1.632068157196045, "eval_runtime": 255.263, "eval_samples_per_second": 6.977, "eval_steps_per_second": 0.874, "step": 82908 }, { "epoch": 19.0, "learning_rate": 5.044507164567955e-07, "loss": 2.0041, "step": 87514 }, { "epoch": 19.0, "eval_loss": 1.5970158576965332, "eval_runtime": 252.5106, "eval_samples_per_second": 7.053, "eval_steps_per_second": 0.883, "step": 87514 }, { "epoch": 20.0, "learning_rate": 4.559270516717325e-09, "loss": 1.9966, "step": 92120 }, { "epoch": 20.0, "eval_loss": 1.5942937135696411, "eval_runtime": 253.5474, "eval_samples_per_second": 7.024, "eval_steps_per_second": 0.88, "step": 92120 }, { "epoch": 21.0, "learning_rate": 1.603821102909249e-06, "loss": 2.0165, "step": 96726 }, { "epoch": 21.0, "eval_loss": 1.6092338562011719, "eval_runtime": 906.9743, "eval_samples_per_second": 1.964, "eval_steps_per_second": 0.246, "step": 96726 }, { "epoch": 22.0, "learning_rate": 1.2039079461571863e-06, "loss": 2.007, "step": 101332 }, { "epoch": 22.0, "eval_loss": 1.5986328125, "eval_runtime": 1255.6495, "eval_samples_per_second": 1.418, "eval_steps_per_second": 0.178, "step": 101332 }, { "epoch": 23.0, "learning_rate": 8.039947894051238e-07, "loss": 2.0009, "step": 105938 }, { "epoch": 23.0, "eval_loss": 1.5931391716003418, "eval_runtime": 1400.4232, "eval_samples_per_second": 1.272, "eval_steps_per_second": 0.159, "step": 105938 }, { "epoch": 24.0, "learning_rate": 4.041684759009987e-07, "loss": 1.992, "step": 110544 }, { "epoch": 24.0, "eval_loss": 1.5898462533950806, "eval_runtime": 1322.312, "eval_samples_per_second": 1.347, "eval_steps_per_second": 0.169, "step": 110544 }, { "epoch": 25.0, "learning_rate": 4.342162396873643e-09, "loss": 1.9769, "step": 115150 }, { "epoch": 25.0, "eval_loss": 1.5818963050842285, "eval_runtime": 1441.7733, "eval_samples_per_second": 1.235, "eval_steps_per_second": 0.155, "step": 115150 }, { "epoch": 25.0, "step": 115150, "total_flos": 3.874481502652799e+20, "train_loss": 0.3997329824549501, "train_runtime": 88532.2397, "train_samples_per_second": 5.202, "train_steps_per_second": 1.301 } ], "max_steps": 115150, "num_train_epochs": 25, "total_flos": 3.874481502652799e+20, "trial_name": null, "trial_params": null }