| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500.0, | |
| "global_step": 2078, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02406159769008662, | |
| "grad_norm": 0.2745775878429413, | |
| "learning_rate": 0.0001997144304734381, | |
| "loss": 1.4399, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04812319538017324, | |
| "grad_norm": 0.3128788471221924, | |
| "learning_rate": 0.00019885935289284243, | |
| "loss": 1.0761, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07218479307025986, | |
| "grad_norm": 0.30212661623954773, | |
| "learning_rate": 0.00019743965094021025, | |
| "loss": 1.0595, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.09624639076034648, | |
| "grad_norm": 0.19943593442440033, | |
| "learning_rate": 0.00019546343308783103, | |
| "loss": 1.047, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.12030798845043311, | |
| "grad_norm": 0.33598530292510986, | |
| "learning_rate": 0.00019294198628763448, | |
| "loss": 1.0584, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.14436958614051973, | |
| "grad_norm": 0.21461080014705658, | |
| "learning_rate": 0.0001898897115070003, | |
| "loss": 1.0463, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.16843118383060635, | |
| "grad_norm": 0.2849867641925812, | |
| "learning_rate": 0.00018632404147920934, | |
| "loss": 1.0414, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.19249278152069296, | |
| "grad_norm": 0.16972823441028595, | |
| "learning_rate": 0.00018226534113829578, | |
| "loss": 1.0332, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2165543792107796, | |
| "grad_norm": 0.2295919805765152, | |
| "learning_rate": 0.00017773679130695595, | |
| "loss": 1.0346, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.24061597690086622, | |
| "grad_norm": 0.2062266767024994, | |
| "learning_rate": 0.0001727642563018167, | |
| "loss": 1.0341, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2646775745909528, | |
| "grad_norm": 0.2998173236846924, | |
| "learning_rate": 0.0001673761362122227, | |
| "loss": 1.0241, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.28873917228103946, | |
| "grad_norm": 0.11832105368375778, | |
| "learning_rate": 0.00016160320469623483, | |
| "loss": 1.0226, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.3128007699711261, | |
| "grad_norm": 0.1334855556488037, | |
| "learning_rate": 0.00015547843322025095, | |
| "loss": 1.0185, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.3368623676612127, | |
| "grad_norm": 0.13620489835739136, | |
| "learning_rate": 0.00014903680274608503, | |
| "loss": 1.0213, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.36092396535129934, | |
| "grad_norm": 0.13768567144870758, | |
| "learning_rate": 0.0001423151039410329, | |
| "loss": 1.0149, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.3849855630413859, | |
| "grad_norm": 0.11512122303247452, | |
| "learning_rate": 0.00013535172705200364, | |
| "loss": 1.0131, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.40904716073147257, | |
| "grad_norm": 0.1289459615945816, | |
| "learning_rate": 0.00012818644264382662, | |
| "loss": 1.0093, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.4331087584215592, | |
| "grad_norm": 0.10245691239833832, | |
| "learning_rate": 0.0001208601744540244, | |
| "loss": 1.0044, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.4571703561116458, | |
| "grad_norm": 0.09356267005205154, | |
| "learning_rate": 0.00011341476566136547, | |
| "loss": 1.0008, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.48123195380173245, | |
| "grad_norm": 0.0957803875207901, | |
| "learning_rate": 0.00010589273990312944, | |
| "loss": 1.0035, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5052935514918191, | |
| "grad_norm": 0.09853529930114746, | |
| "learning_rate": 9.833705840600763e-05, | |
| "loss": 0.9965, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.5293551491819056, | |
| "grad_norm": 0.1084134429693222, | |
| "learning_rate": 9.07908746177598e-05, | |
| "loss": 0.9947, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.5534167468719923, | |
| "grad_norm": 0.09273923188447952, | |
| "learning_rate": 8.3297287741021e-05, | |
| "loss": 0.9988, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.5774783445620789, | |
| "grad_norm": 0.09696114808320999, | |
| "learning_rate": 7.589909657692416e-05, | |
| "loss": 1.0023, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.6015399422521656, | |
| "grad_norm": 0.07934155315160751, | |
| "learning_rate": 6.863855508443216e-05, | |
| "loss": 0.9919, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.6256015399422522, | |
| "grad_norm": 0.09847329556941986, | |
| "learning_rate": 6.155713105147687e-05, | |
| "loss": 0.9873, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.6496631376323387, | |
| "grad_norm": 0.07471206784248352, | |
| "learning_rate": 5.469526925622783e-05, | |
| "loss": 0.9842, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.6737247353224254, | |
| "grad_norm": 0.07969838380813599, | |
| "learning_rate": 4.809216047116902e-05, | |
| "loss": 0.9868, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.697786333012512, | |
| "grad_norm": 0.07660534232854843, | |
| "learning_rate": 4.178551762929218e-05, | |
| "loss": 0.9846, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.7218479307025987, | |
| "grad_norm": 0.08437798917293549, | |
| "learning_rate": 3.581136043080835e-05, | |
| "loss": 0.9861, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7459095283926853, | |
| "grad_norm": 0.06967335939407349, | |
| "learning_rate": 3.0203809620573042e-05, | |
| "loss": 0.9772, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.7699711260827719, | |
| "grad_norm": 0.06973665207624435, | |
| "learning_rate": 2.499489211118732e-05, | |
| "loss": 0.9813, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.7940327237728585, | |
| "grad_norm": 0.06934628635644913, | |
| "learning_rate": 2.0214358064792172e-05, | |
| "loss": 0.9719, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.8180943214629451, | |
| "grad_norm": 0.07001589238643646, | |
| "learning_rate": 1.5889510978274558e-05, | |
| "loss": 0.977, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.8421559191530318, | |
| "grad_norm": 0.06061296537518501, | |
| "learning_rate": 1.2045051742333412e-05, | |
| "loss": 0.9764, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.8662175168431184, | |
| "grad_norm": 0.06056005507707596, | |
| "learning_rate": 8.702937565046632e-06, | |
| "loss": 0.9827, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.890279114533205, | |
| "grad_norm": 0.05652038753032684, | |
| "learning_rate": 5.882256565680689e-06, | |
| "loss": 0.9769, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.9143407122232916, | |
| "grad_norm": 0.055849190801382065, | |
| "learning_rate": 3.5991187549870077e-06, | |
| "loss": 0.9741, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.9384023099133783, | |
| "grad_norm": 0.053746215999126434, | |
| "learning_rate": 1.8665640246390836e-06, | |
| "loss": 0.9771, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.9624639076034649, | |
| "grad_norm": 0.05398011952638626, | |
| "learning_rate": 6.944876713186777e-07, | |
| "loss": 0.9755, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9865255052935515, | |
| "grad_norm": 0.05222630873322487, | |
| "learning_rate": 8.958388081204971e-08, | |
| "loss": 0.9742, | |
| "step": 2050 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 2078, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.924669146551204e+20, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |