| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9957356076759063, | |
| "eval_steps": 1000, | |
| "global_step": 468, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.042643923240938165, | |
| "grad_norm": 3.179123776279851, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.432, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08528784648187633, | |
| "grad_norm": 2.0834838340230113, | |
| "learning_rate": 1.999398868012663e-05, | |
| "loss": 0.266, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1279317697228145, | |
| "grad_norm": 1.839885995199569, | |
| "learning_rate": 1.9945941475610623e-05, | |
| "loss": 0.189, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.17057569296375266, | |
| "grad_norm": 0.3374452319668954, | |
| "learning_rate": 1.9850078058821615e-05, | |
| "loss": 0.1405, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.21321961620469082, | |
| "grad_norm": 0.35572662705742497, | |
| "learning_rate": 1.970685930372489e-05, | |
| "loss": 0.1352, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.255863539445629, | |
| "grad_norm": 0.34732501425850515, | |
| "learning_rate": 1.951697375030553e-05, | |
| "loss": 0.1311, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 0.29120729702844944, | |
| "learning_rate": 1.9281334294336364e-05, | |
| "loss": 0.1211, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3411513859275053, | |
| "grad_norm": 0.2548677782780123, | |
| "learning_rate": 1.90010737985307e-05, | |
| "loss": 0.1204, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3837953091684435, | |
| "grad_norm": 0.23124279128247788, | |
| "learning_rate": 1.8677539646179706e-05, | |
| "loss": 0.1216, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.42643923240938164, | |
| "grad_norm": 0.2233543638243816, | |
| "learning_rate": 1.831228726345841e-05, | |
| "loss": 0.1187, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4690831556503198, | |
| "grad_norm": 0.21228773844702403, | |
| "learning_rate": 1.7907072641542527e-05, | |
| "loss": 0.1147, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.511727078891258, | |
| "grad_norm": 0.21240166483768347, | |
| "learning_rate": 1.746384389448694e-05, | |
| "loss": 0.1123, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5543710021321961, | |
| "grad_norm": 0.22092994006720384, | |
| "learning_rate": 1.6984731893452174e-05, | |
| "loss": 0.1122, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 0.2146266283518355, | |
| "learning_rate": 1.647204002230594e-05, | |
| "loss": 0.1104, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6396588486140725, | |
| "grad_norm": 0.20918171426009047, | |
| "learning_rate": 1.592823310385073e-05, | |
| "loss": 0.1112, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6823027718550106, | |
| "grad_norm": 0.1967909221104072, | |
| "learning_rate": 1.5355925549915943e-05, | |
| "loss": 0.1124, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.7249466950959488, | |
| "grad_norm": 0.2240605099251795, | |
| "learning_rate": 1.4757868792284231e-05, | |
| "loss": 0.1137, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.767590618336887, | |
| "grad_norm": 0.20377236444556038, | |
| "learning_rate": 1.4136938054879284e-05, | |
| "loss": 0.1097, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8102345415778252, | |
| "grad_norm": 0.2106109081511342, | |
| "learning_rate": 1.3496118530809195e-05, | |
| "loss": 0.112, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8528784648187633, | |
| "grad_norm": 0.18132699922626352, | |
| "learning_rate": 1.2838491030720882e-05, | |
| "loss": 0.1079, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 0.1926837140760371, | |
| "learning_rate": 1.2167217171462566e-05, | |
| "loss": 0.1087, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9381663113006397, | |
| "grad_norm": 0.19627892114205173, | |
| "learning_rate": 1.148552417626157e-05, | |
| "loss": 0.1115, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9808102345415778, | |
| "grad_norm": 0.19029596670392074, | |
| "learning_rate": 1.0796689359492154e-05, | |
| "loss": 0.108, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.023454157782516, | |
| "grad_norm": 0.18044861833183792, | |
| "learning_rate": 1.0104024370624644e-05, | |
| "loss": 0.0849, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0660980810234542, | |
| "grad_norm": 0.19142738031135273, | |
| "learning_rate": 9.410859273104823e-06, | |
| "loss": 0.0661, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.1087420042643923, | |
| "grad_norm": 0.17150102289558444, | |
| "learning_rate": 8.720526534706052e-06, | |
| "loss": 0.0642, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.1513859275053304, | |
| "grad_norm": 0.2442559352462789, | |
| "learning_rate": 8.036345006322358e-06, | |
| "loss": 0.0645, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.1940298507462686, | |
| "grad_norm": 0.17495312344390224, | |
| "learning_rate": 7.361603966226165e-06, | |
| "loss": 0.0621, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.236673773987207, | |
| "grad_norm": 0.16258359858243326, | |
| "learning_rate": 6.6995473064996455e-06, | |
| "loss": 0.0595, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.279317697228145, | |
| "grad_norm": 0.17596476037955336, | |
| "learning_rate": 6.053357937665237e-06, | |
| "loss": 0.0622, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.3219616204690832, | |
| "grad_norm": 0.158017144205196, | |
| "learning_rate": 5.4261424864917075e-06, | |
| "loss": 0.0608, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.3646055437100213, | |
| "grad_norm": 0.17821374662840944, | |
| "learning_rate": 4.82091636054281e-06, | |
| "loss": 0.061, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.4072494669509594, | |
| "grad_norm": 0.1909778433139327, | |
| "learning_rate": 4.240589251272342e-06, | |
| "loss": 0.0605, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.4498933901918978, | |
| "grad_norm": 0.18171746562096064, | |
| "learning_rate": 3.687951145361073e-06, | |
| "loss": 0.0631, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.4925373134328357, | |
| "grad_norm": 0.17460796522473127, | |
| "learning_rate": 3.165658911547592e-06, | |
| "loss": 0.06, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.535181236673774, | |
| "grad_norm": 0.1810617961103566, | |
| "learning_rate": 2.6762235274383775e-06, | |
| "loss": 0.0612, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.5778251599147122, | |
| "grad_norm": 0.15880550118378636, | |
| "learning_rate": 2.2219980077055756e-06, | |
| "loss": 0.0616, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.6204690831556503, | |
| "grad_norm": 0.17610380896685834, | |
| "learning_rate": 1.8051660917090718e-06, | |
| "loss": 0.0593, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.6631130063965884, | |
| "grad_norm": 0.1852362138493889, | |
| "learning_rate": 1.4277317449282834e-06, | |
| "loss": 0.0608, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.7057569296375266, | |
| "grad_norm": 0.18397811408680578, | |
| "learning_rate": 1.0915095246767692e-06, | |
| "loss": 0.0603, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.748400852878465, | |
| "grad_norm": 0.18777942289827937, | |
| "learning_rate": 7.981158564175074e-07, | |
| "loss": 0.0607, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.7910447761194028, | |
| "grad_norm": 0.1785060533694166, | |
| "learning_rate": 5.489612626189245e-07, | |
| "loss": 0.0569, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.8336886993603412, | |
| "grad_norm": 0.17603977808158508, | |
| "learning_rate": 3.452435815123323e-07, | |
| "loss": 0.0604, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.8763326226012793, | |
| "grad_norm": 0.18882098153064591, | |
| "learning_rate": 1.8794220835231413e-07, | |
| "loss": 0.0609, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.9189765458422174, | |
| "grad_norm": 0.1838499771403163, | |
| "learning_rate": 7.781338686584928e-08, | |
| "loss": 0.0597, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.9616204690831558, | |
| "grad_norm": 0.17454958184966676, | |
| "learning_rate": 1.5386573527067516e-08, | |
| "loss": 0.0618, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.9957356076759063, | |
| "step": 468, | |
| "total_flos": 140358569164800.0, | |
| "train_loss": 0.10031582892705233, | |
| "train_runtime": 1756.1076, | |
| "train_samples_per_second": 34.132, | |
| "train_steps_per_second": 0.266 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 468, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 5000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 140358569164800.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |