| { | |
| "best_metric": 4.393705368041992, | |
| "best_model_checkpoint": "output/mf-doom/checkpoint-193", | |
| "epoch": 1.0, | |
| "global_step": 193, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00013697291967368176, | |
| "loss": 4.7696, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001362931820613334, | |
| "loss": 4.9375, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00013516528730985944, | |
| "loss": 4.6377, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00013359670255361022, | |
| "loss": 4.7907, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00013159781247883373, | |
| "loss": 4.8492, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00012918185057271526, | |
| "loss": 4.698, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00012636481151216485, | |
| "loss": 4.6354, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001231653452723755, | |
| "loss": 4.7479, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00011960463365619783, | |
| "loss": 4.6099, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.000115706250061758, | |
| "loss": 4.4771, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.000111496003416716, | |
| "loss": 4.6176, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00010700176731238488, | |
| "loss": 4.5517, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00010225329546891398, | |
| "loss": 4.6173, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.728202475323418e-05, | |
| "loss": 4.5918, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.21208670538683e-05, | |
| "loss": 4.4796, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 8.680399139048255e-05, | |
| "loss": 4.5046, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 8.136659770070481e-05, | |
| "loss": 4.5786, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7.584468380183525e-05, | |
| "loss": 4.5974, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 7.027480707026031e-05, | |
| "loss": 4.4949, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 6.469384241635202e-05, | |
| "loss": 4.5468, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.9138738157159314e-05, | |
| "loss": 4.2671, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5.364627140311692e-05, | |
| "loss": 4.5739, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.825280457821314e-05, | |
| "loss": 4.4114, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.299404468555545e-05, | |
| "loss": 4.403, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.7904806912095865e-05, | |
| "loss": 4.5395, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.30187841375518e-05, | |
| "loss": 4.478, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.8368323873469696e-05, | |
| "loss": 4.5482, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.39842141091877e-05, | |
| "loss": 4.5102, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.9895479482486794e-05, | |
| "loss": 4.3508, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.61291891243658e-05, | |
| "loss": 4.3784, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.2710277450088041e-05, | |
| "loss": 4.5042, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.661379082937688e-06, | |
| "loss": 4.3445, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.002679003559785e-06, | |
| "loss": 4.5091, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.7517789169574735e-06, | |
| "loss": 4.4888, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.9235807218530457e-06, | |
| "loss": 4.354, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.5301878538942795e-06, | |
| "loss": 4.3435, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.808251558551173e-07, | |
| "loss": 4.3824, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 8.177780532344056e-08, | |
| "loss": 4.4941, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 4.393705368041992, | |
| "eval_runtime": 13.4209, | |
| "eval_samples_per_second": 22.428, | |
| "eval_steps_per_second": 2.831, | |
| "step": 193 | |
| } | |
| ], | |
| "max_steps": 193, | |
| "num_train_epochs": 1, | |
| "total_flos": 201586802688000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |