| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9977298524404086, | |
| "eval_steps": 500, | |
| "global_step": 1174, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04256526674233825, | |
| "grad_norm": 0.23498961329460144, | |
| "learning_rate": 0.00019657827202737384, | |
| "loss": 0.1046, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0851305334846765, | |
| "grad_norm": 0.14751878380775452, | |
| "learning_rate": 0.00019230111206159113, | |
| "loss": 0.0926, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12769580022701477, | |
| "grad_norm": 0.2522989511489868, | |
| "learning_rate": 0.0001880239520958084, | |
| "loss": 0.0971, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.170261066969353, | |
| "grad_norm": 0.15176503360271454, | |
| "learning_rate": 0.00018374679213002568, | |
| "loss": 0.0928, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.21282633371169127, | |
| "grad_norm": 0.16757148504257202, | |
| "learning_rate": 0.00017946963216424296, | |
| "loss": 0.0916, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.25539160045402953, | |
| "grad_norm": 0.2590785026550293, | |
| "learning_rate": 0.00017519247219846022, | |
| "loss": 0.0923, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.29795686719636777, | |
| "grad_norm": 0.19378352165222168, | |
| "learning_rate": 0.0001709153122326775, | |
| "loss": 0.0921, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.340522133938706, | |
| "grad_norm": 0.2084362953901291, | |
| "learning_rate": 0.0001666381522668948, | |
| "loss": 0.0888, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.38308740068104424, | |
| "grad_norm": 0.17699547111988068, | |
| "learning_rate": 0.00016236099230111209, | |
| "loss": 0.0898, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.42565266742338254, | |
| "grad_norm": 0.1759597808122635, | |
| "learning_rate": 0.00015808383233532935, | |
| "loss": 0.0868, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4682179341657208, | |
| "grad_norm": 0.1610288918018341, | |
| "learning_rate": 0.00015380667236954663, | |
| "loss": 0.0907, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.5107832009080591, | |
| "grad_norm": 0.13977083563804626, | |
| "learning_rate": 0.00014952951240376392, | |
| "loss": 0.086, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5533484676503972, | |
| "grad_norm": 0.18051184713840485, | |
| "learning_rate": 0.00014525235243798118, | |
| "loss": 0.0831, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.5959137343927355, | |
| "grad_norm": 0.2083287537097931, | |
| "learning_rate": 0.00014097519247219847, | |
| "loss": 0.086, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6384790011350738, | |
| "grad_norm": 0.1912999302148819, | |
| "learning_rate": 0.00013669803250641576, | |
| "loss": 0.0839, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.681044267877412, | |
| "grad_norm": 0.17170144617557526, | |
| "learning_rate": 0.00013242087254063302, | |
| "loss": 0.0848, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7236095346197503, | |
| "grad_norm": 0.2047215849161148, | |
| "learning_rate": 0.0001281437125748503, | |
| "loss": 0.079, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.7661748013620885, | |
| "grad_norm": 0.14967381954193115, | |
| "learning_rate": 0.0001238665526090676, | |
| "loss": 0.0844, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.8087400681044268, | |
| "grad_norm": 0.15834014117717743, | |
| "learning_rate": 0.00011958939264328485, | |
| "loss": 0.0821, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.8513053348467651, | |
| "grad_norm": 0.16844715178012848, | |
| "learning_rate": 0.00011531223267750215, | |
| "loss": 0.0836, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8938706015891033, | |
| "grad_norm": 0.18447309732437134, | |
| "learning_rate": 0.00011103507271171943, | |
| "loss": 0.0829, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.9364358683314415, | |
| "grad_norm": 0.1440054476261139, | |
| "learning_rate": 0.00010675791274593669, | |
| "loss": 0.0792, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.9790011350737798, | |
| "grad_norm": 0.17830029129981995, | |
| "learning_rate": 0.00010248075278015399, | |
| "loss": 0.0821, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.0204313280363224, | |
| "grad_norm": 0.2284756600856781, | |
| "learning_rate": 9.820359281437126e-05, | |
| "loss": 0.0793, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.0629965947786606, | |
| "grad_norm": 0.15237772464752197, | |
| "learning_rate": 9.392643284858854e-05, | |
| "loss": 0.0771, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.1055618615209988, | |
| "grad_norm": 0.18322055041790009, | |
| "learning_rate": 8.964927288280582e-05, | |
| "loss": 0.0815, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.1481271282633372, | |
| "grad_norm": 0.17401781678199768, | |
| "learning_rate": 8.537211291702311e-05, | |
| "loss": 0.0826, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.1906923950056754, | |
| "grad_norm": 0.23275992274284363, | |
| "learning_rate": 8.109495295124037e-05, | |
| "loss": 0.0769, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.2332576617480135, | |
| "grad_norm": 0.23144161701202393, | |
| "learning_rate": 7.681779298545766e-05, | |
| "loss": 0.0761, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.275822928490352, | |
| "grad_norm": 0.2251117080450058, | |
| "learning_rate": 7.254063301967495e-05, | |
| "loss": 0.0768, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.3183881952326901, | |
| "grad_norm": 0.18892104923725128, | |
| "learning_rate": 6.826347305389222e-05, | |
| "loss": 0.0787, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.3609534619750283, | |
| "grad_norm": 0.19995813071727753, | |
| "learning_rate": 6.39863130881095e-05, | |
| "loss": 0.0725, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.4035187287173665, | |
| "grad_norm": 0.19511419534683228, | |
| "learning_rate": 5.9709153122326776e-05, | |
| "loss": 0.0729, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.446083995459705, | |
| "grad_norm": 0.2229546159505844, | |
| "learning_rate": 5.543199315654406e-05, | |
| "loss": 0.0721, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.488649262202043, | |
| "grad_norm": 0.2024296671152115, | |
| "learning_rate": 5.1154833190761344e-05, | |
| "loss": 0.0727, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.5312145289443815, | |
| "grad_norm": 0.24508166313171387, | |
| "learning_rate": 4.687767322497862e-05, | |
| "loss": 0.071, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.5737797956867197, | |
| "grad_norm": 0.2000231146812439, | |
| "learning_rate": 4.260051325919589e-05, | |
| "loss": 0.0722, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.6163450624290578, | |
| "grad_norm": 0.16820313036441803, | |
| "learning_rate": 3.832335329341318e-05, | |
| "loss": 0.07, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.658910329171396, | |
| "grad_norm": 0.17715366184711456, | |
| "learning_rate": 3.4046193327630454e-05, | |
| "loss": 0.0552, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.7014755959137344, | |
| "grad_norm": 0.17357434332370758, | |
| "learning_rate": 2.9769033361847738e-05, | |
| "loss": 0.0708, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.7440408626560726, | |
| "grad_norm": 0.19597357511520386, | |
| "learning_rate": 2.5491873396065015e-05, | |
| "loss": 0.0618, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.786606129398411, | |
| "grad_norm": 0.2510164976119995, | |
| "learning_rate": 2.1214713430282293e-05, | |
| "loss": 0.068, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.8291713961407492, | |
| "grad_norm": 0.30005839467048645, | |
| "learning_rate": 1.6937553464499573e-05, | |
| "loss": 0.0672, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.8717366628830874, | |
| "grad_norm": 0.19194893538951874, | |
| "learning_rate": 1.2660393498716852e-05, | |
| "loss": 0.0681, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.9143019296254256, | |
| "grad_norm": 0.16069871187210083, | |
| "learning_rate": 8.383233532934131e-06, | |
| "loss": 0.0682, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1.9568671963677637, | |
| "grad_norm": 0.22674943506717682, | |
| "learning_rate": 4.106073567151412e-06, | |
| "loss": 0.0686, | |
| "step": 1150 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1174, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.90004424169257e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |