| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9993746091307066, | |
| "eval_steps": 500, | |
| "global_step": 799, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012507817385866166, | |
| "grad_norm": 15.50371147983014, | |
| "learning_rate": 6.25e-08, | |
| "loss": 2.39, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025015634771732333, | |
| "grad_norm": 16.377043356637174, | |
| "learning_rate": 1.25e-07, | |
| "loss": 2.4206, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0375234521575985, | |
| "grad_norm": 16.596531841198026, | |
| "learning_rate": 1.875e-07, | |
| "loss": 2.3735, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.050031269543464665, | |
| "grad_norm": 11.7365845286366, | |
| "learning_rate": 2.5e-07, | |
| "loss": 2.3416, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06253908692933083, | |
| "grad_norm": 11.18800914938059, | |
| "learning_rate": 3.1249999999999997e-07, | |
| "loss": 2.3512, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.075046904315197, | |
| "grad_norm": 7.018014667910915, | |
| "learning_rate": 3.75e-07, | |
| "loss": 2.2364, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.08755472170106317, | |
| "grad_norm": 6.333030569859783, | |
| "learning_rate": 4.375e-07, | |
| "loss": 2.2577, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.10006253908692933, | |
| "grad_norm": 4.7577630065749155, | |
| "learning_rate": 5e-07, | |
| "loss": 2.2443, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1125703564727955, | |
| "grad_norm": 4.270646018694652, | |
| "learning_rate": 4.997613931640598e-07, | |
| "loss": 2.0968, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.12507817385866166, | |
| "grad_norm": 3.7719895745693144, | |
| "learning_rate": 4.990460281220164e-07, | |
| "loss": 2.0786, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13758599124452783, | |
| "grad_norm": 3.822159552325772, | |
| "learning_rate": 4.978552704017834e-07, | |
| "loss": 1.9348, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.150093808630394, | |
| "grad_norm": 3.6639855496417577, | |
| "learning_rate": 4.961913929868171e-07, | |
| "loss": 1.9247, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.16260162601626016, | |
| "grad_norm": 3.901015564156351, | |
| "learning_rate": 4.940575719773205e-07, | |
| "loss": 1.9058, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.17510944340212634, | |
| "grad_norm": 3.6368127187289336, | |
| "learning_rate": 4.914578805275297e-07, | |
| "loss": 1.8596, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.18761726078799248, | |
| "grad_norm": 2.992979752090568, | |
| "learning_rate": 4.883972810706548e-07, | |
| "loss": 1.8314, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.20012507817385866, | |
| "grad_norm": 3.3873843484182466, | |
| "learning_rate": 4.848816158463157e-07, | |
| "loss": 1.8075, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.21263289555972484, | |
| "grad_norm": 3.3435874749901937, | |
| "learning_rate": 4.809175957485557e-07, | |
| "loss": 1.772, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.225140712945591, | |
| "grad_norm": 3.4374510709255492, | |
| "learning_rate": 4.765127875157198e-07, | |
| "loss": 1.7533, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.23764853033145716, | |
| "grad_norm": 3.6689585209658873, | |
| "learning_rate": 4.7167559928665085e-07, | |
| "loss": 1.7891, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.2501563477173233, | |
| "grad_norm": 3.8434986912697187, | |
| "learning_rate": 4.664152645507743e-07, | |
| "loss": 1.8084, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2626641651031895, | |
| "grad_norm": 2.8530782226054003, | |
| "learning_rate": 4.6074182452270883e-07, | |
| "loss": 1.7419, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.27517198248905567, | |
| "grad_norm": 3.4661505185006183, | |
| "learning_rate": 4.546661089750462e-07, | |
| "loss": 1.7693, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.2876797998749218, | |
| "grad_norm": 3.8663130075517875, | |
| "learning_rate": 4.4819971556588977e-07, | |
| "loss": 1.7335, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.300187617260788, | |
| "grad_norm": 3.105644191017463, | |
| "learning_rate": 4.4135498770060986e-07, | |
| "loss": 1.8318, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.31269543464665417, | |
| "grad_norm": 2.9687504404830465, | |
| "learning_rate": 4.3414499097007697e-07, | |
| "loss": 1.7344, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.3252032520325203, | |
| "grad_norm": 3.475648300031111, | |
| "learning_rate": 4.265834882103472e-07, | |
| "loss": 1.7508, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.33771106941838647, | |
| "grad_norm": 2.9742467574673226, | |
| "learning_rate": 4.186849132314081e-07, | |
| "loss": 1.7215, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.35021888680425267, | |
| "grad_norm": 3.1787099419252667, | |
| "learning_rate": 4.1046434326513303e-07, | |
| "loss": 1.752, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.3627267041901188, | |
| "grad_norm": 3.3558933667673667, | |
| "learning_rate": 4.0193747018503614e-07, | |
| "loss": 1.7647, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.37523452157598497, | |
| "grad_norm": 3.5099375875164407, | |
| "learning_rate": 3.9312057055276636e-07, | |
| "loss": 1.7102, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3877423389618512, | |
| "grad_norm": 3.591142245670379, | |
| "learning_rate": 3.8403047454851615e-07, | |
| "loss": 1.7913, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.4002501563477173, | |
| "grad_norm": 3.527758971554222, | |
| "learning_rate": 3.7468453384465326e-07, | |
| "loss": 1.757, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.41275797373358347, | |
| "grad_norm": 2.9495017861006976, | |
| "learning_rate": 3.6510058848389946e-07, | |
| "loss": 1.7136, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.4252657911194497, | |
| "grad_norm": 3.586714858280363, | |
| "learning_rate": 3.5529693282528167e-07, | |
| "loss": 1.7576, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.4377736085053158, | |
| "grad_norm": 3.549806024215502, | |
| "learning_rate": 3.4529228062285864e-07, | |
| "loss": 1.7853, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.450281425891182, | |
| "grad_norm": 3.3751243069059726, | |
| "learning_rate": 3.351057293038841e-07, | |
| "loss": 1.7072, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4627892432770482, | |
| "grad_norm": 3.0260065815967834, | |
| "learning_rate": 3.247567235145928e-07, | |
| "loss": 1.6807, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.47529706066291433, | |
| "grad_norm": 2.640773300956867, | |
| "learning_rate": 3.1426501800319697e-07, | |
| "loss": 1.6653, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 3.2410844977370252, | |
| "learning_rate": 3.03650639910942e-07, | |
| "loss": 1.669, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.5003126954346466, | |
| "grad_norm": 3.390139626995187, | |
| "learning_rate": 2.9293385054320446e-07, | |
| "loss": 1.6675, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 3.032547484860861, | |
| "learning_rate": 2.8213510669360425e-07, | |
| "loss": 1.6581, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.525328330206379, | |
| "grad_norm": 3.0579494870999597, | |
| "learning_rate": 2.712750215949578e-07, | |
| "loss": 1.6945, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.5378361475922452, | |
| "grad_norm": 3.3503627954919537, | |
| "learning_rate": 2.6037432557161284e-07, | |
| "loss": 1.7825, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.5503439649781113, | |
| "grad_norm": 3.257201806161219, | |
| "learning_rate": 2.494538264682706e-07, | |
| "loss": 1.7377, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.5628517823639775, | |
| "grad_norm": 3.6489839167255274, | |
| "learning_rate": 2.385343699308345e-07, | |
| "loss": 1.7268, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5753595997498436, | |
| "grad_norm": 3.105178719456824, | |
| "learning_rate": 2.2763679961510135e-07, | |
| "loss": 1.7919, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5878674171357098, | |
| "grad_norm": 3.050954751841531, | |
| "learning_rate": 2.1678191739925102e-07, | |
| "loss": 1.7826, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.600375234521576, | |
| "grad_norm": 3.445788669098754, | |
| "learning_rate": 2.0599044367608349e-07, | |
| "loss": 1.6794, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.6128830519074422, | |
| "grad_norm": 3.268302307641069, | |
| "learning_rate": 1.9528297780080066e-07, | |
| "loss": 1.7104, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.6253908692933083, | |
| "grad_norm": 3.170030908287175, | |
| "learning_rate": 1.8467995876983001e-07, | |
| "loss": 1.6521, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6253908692933083, | |
| "eval_loss": 1.9212596416473389, | |
| "eval_runtime": 52.2748, | |
| "eval_samples_per_second": 108.752, | |
| "eval_steps_per_second": 13.601, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6378986866791745, | |
| "grad_norm": 3.0945261612885893, | |
| "learning_rate": 1.742016262057507e-07, | |
| "loss": 1.748, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.6504065040650406, | |
| "grad_norm": 3.5211162697926484, | |
| "learning_rate": 1.6386798172279508e-07, | |
| "loss": 1.702, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.6629143214509068, | |
| "grad_norm": 2.82400028169299, | |
| "learning_rate": 1.5369875074667365e-07, | |
| "loss": 1.6578, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.6754221388367729, | |
| "grad_norm": 3.4126613341000342, | |
| "learning_rate": 1.4371334486160352e-07, | |
| "loss": 1.6457, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.6879299562226392, | |
| "grad_norm": 3.080219874111456, | |
| "learning_rate": 1.3393082475641544e-07, | |
| "loss": 1.6502, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.7004377736085053, | |
| "grad_norm": 3.2091545865497135, | |
| "learning_rate": 1.2436986384046786e-07, | |
| "loss": 1.8363, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.7129455909943715, | |
| "grad_norm": 2.9795468307340998, | |
| "learning_rate": 1.150487125988224e-07, | |
| "loss": 1.646, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.7254534083802376, | |
| "grad_norm": 3.3814030136771636, | |
| "learning_rate": 1.0598516375471978e-07, | |
| "loss": 1.7004, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.7379612257661038, | |
| "grad_norm": 2.9635741473039086, | |
| "learning_rate": 9.719651830585668e-08, | |
| "loss": 1.6428, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.7504690431519699, | |
| "grad_norm": 3.341303101666117, | |
| "learning_rate": 8.86995524992951e-08, | |
| "loss": 1.6991, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7629768605378362, | |
| "grad_norm": 3.2990151037358117, | |
| "learning_rate": 8.051048580804456e-08, | |
| "loss": 1.7138, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.7754846779237023, | |
| "grad_norm": 3.7604514079322544, | |
| "learning_rate": 7.264494997044521e-08, | |
| "loss": 1.6684, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.7879924953095685, | |
| "grad_norm": 3.1090607489783264, | |
| "learning_rate": 6.51179591514505e-08, | |
| "loss": 1.6755, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.8005003126954346, | |
| "grad_norm": 3.218850148666728, | |
| "learning_rate": 5.794388128276798e-08, | |
| "loss": 1.6433, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.8130081300813008, | |
| "grad_norm": 3.381481766181872, | |
| "learning_rate": 5.113641063656618e-08, | |
| "loss": 1.7482, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.8255159474671669, | |
| "grad_norm": 3.271540252470752, | |
| "learning_rate": 4.470854168509819e-08, | |
| "loss": 1.7041, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.8380237648530331, | |
| "grad_norm": 2.8589321850258265, | |
| "learning_rate": 3.867254429614281e-08, | |
| "loss": 1.7051, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.8505315822388994, | |
| "grad_norm": 2.8732647074299535, | |
| "learning_rate": 3.3039940311609866e-08, | |
| "loss": 1.6833, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.8630393996247655, | |
| "grad_norm": 3.354421287892463, | |
| "learning_rate": 2.782148155401806e-08, | |
| "loss": 1.7021, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.8755472170106317, | |
| "grad_norm": 3.255677211190932, | |
| "learning_rate": 2.302712930282849e-08, | |
| "loss": 1.724, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8880550343964978, | |
| "grad_norm": 3.6035792434299814, | |
| "learning_rate": 1.8666035279809533e-08, | |
| "loss": 1.6296, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.900562851782364, | |
| "grad_norm": 2.932020685282119, | |
| "learning_rate": 1.474652417972974e-08, | |
| "loss": 1.7291, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.9130706691682301, | |
| "grad_norm": 3.1442941331116767, | |
| "learning_rate": 1.1276077779725335e-08, | |
| "loss": 1.7443, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.9255784865540964, | |
| "grad_norm": 2.856048609833897, | |
| "learning_rate": 8.261320657674626e-09, | |
| "loss": 1.6627, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.9380863039399625, | |
| "grad_norm": 3.1836824042626897, | |
| "learning_rate": 5.708007546841892e-09, | |
| "loss": 1.631, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9505941213258287, | |
| "grad_norm": 3.246017077240641, | |
| "learning_rate": 3.621012350927377e-09, | |
| "loss": 1.7077, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.9631019387116948, | |
| "grad_norm": 3.3755110020876815, | |
| "learning_rate": 2.004318840493707e-09, | |
| "loss": 1.7075, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 3.215190396177525, | |
| "learning_rate": 8.610130485265655e-10, | |
| "loss": 1.6703, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.9881175734834271, | |
| "grad_norm": 3.0778055684285497, | |
| "learning_rate": 1.932773796461673e-10, | |
| "loss": 1.6873, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.9993746091307066, | |
| "step": 799, | |
| "total_flos": 10053203263488.0, | |
| "train_loss": 1.7967723003764624, | |
| "train_runtime": 569.5544, | |
| "train_samples_per_second": 89.832, | |
| "train_steps_per_second": 1.403 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 799, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 10053203263488.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |