| { | |
| "best_metric": 2.2496395111083984, | |
| "best_model_checkpoint": "./yue_finetuned/checkpoint-900", | |
| "epoch": 2.99290780141844, | |
| "eval_steps": 100, | |
| "global_step": 951, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03152088258471237, | |
| "grad_norm": 1.0658416748046875, | |
| "learning_rate": 6.896551724137931e-05, | |
| "loss": 6.814, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06304176516942474, | |
| "grad_norm": 2.7176384925842285, | |
| "learning_rate": 0.00013793103448275863, | |
| "loss": 6.4042, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09456264775413711, | |
| "grad_norm": 1.2143285274505615, | |
| "learning_rate": 0.0001997830802603037, | |
| "loss": 4.8034, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12608353033884948, | |
| "grad_norm": 1.1138572692871094, | |
| "learning_rate": 0.00019761388286334056, | |
| "loss": 3.8628, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15760441292356187, | |
| "grad_norm": 0.7702319025993347, | |
| "learning_rate": 0.00019544468546637745, | |
| "loss": 3.3674, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18912529550827423, | |
| "grad_norm": 0.4743233919143677, | |
| "learning_rate": 0.00019327548806941433, | |
| "loss": 3.1137, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.22064617809298662, | |
| "grad_norm": 0.4091566205024719, | |
| "learning_rate": 0.0001911062906724512, | |
| "loss": 2.8457, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.25216706067769895, | |
| "grad_norm": 0.39599528908729553, | |
| "learning_rate": 0.00018893709327548808, | |
| "loss": 2.6799, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.28368794326241137, | |
| "grad_norm": 0.36687061190605164, | |
| "learning_rate": 0.00018676789587852494, | |
| "loss": 2.7454, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.31520882584712373, | |
| "grad_norm": 0.5227386951446533, | |
| "learning_rate": 0.00018459869848156183, | |
| "loss": 2.7114, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31520882584712373, | |
| "eval_loss": 2.610507011413574, | |
| "eval_runtime": 1093.6124, | |
| "eval_samples_per_second": 0.517, | |
| "eval_steps_per_second": 0.259, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3467297084318361, | |
| "grad_norm": 0.41864681243896484, | |
| "learning_rate": 0.0001824295010845987, | |
| "loss": 2.6228, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.37825059101654845, | |
| "grad_norm": 0.4326777756214142, | |
| "learning_rate": 0.00018026030368763557, | |
| "loss": 2.4956, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4097714736012608, | |
| "grad_norm": 0.41428521275520325, | |
| "learning_rate": 0.00017809110629067246, | |
| "loss": 2.5776, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.44129235618597323, | |
| "grad_norm": 0.41970375180244446, | |
| "learning_rate": 0.00017592190889370934, | |
| "loss": 2.5208, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4728132387706856, | |
| "grad_norm": 0.45651790499687195, | |
| "learning_rate": 0.0001737527114967462, | |
| "loss": 2.4897, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5043341213553979, | |
| "grad_norm": 0.44131532311439514, | |
| "learning_rate": 0.0001715835140997831, | |
| "loss": 2.5342, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5358550039401103, | |
| "grad_norm": 0.5060796737670898, | |
| "learning_rate": 0.00016941431670281998, | |
| "loss": 2.5113, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5673758865248227, | |
| "grad_norm": 0.4486294686794281, | |
| "learning_rate": 0.00016724511930585684, | |
| "loss": 2.5553, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.598896769109535, | |
| "grad_norm": 0.45511698722839355, | |
| "learning_rate": 0.00016507592190889372, | |
| "loss": 2.4714, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.6304176516942475, | |
| "grad_norm": 0.49814826250076294, | |
| "learning_rate": 0.00016290672451193058, | |
| "loss": 2.4529, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6304176516942475, | |
| "eval_loss": 2.440239906311035, | |
| "eval_runtime": 28.5385, | |
| "eval_samples_per_second": 19.798, | |
| "eval_steps_per_second": 9.916, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6619385342789598, | |
| "grad_norm": 0.5318950414657593, | |
| "learning_rate": 0.00016073752711496747, | |
| "loss": 2.5319, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6934594168636722, | |
| "grad_norm": 0.6193626523017883, | |
| "learning_rate": 0.00015856832971800435, | |
| "loss": 2.4968, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.7249802994483846, | |
| "grad_norm": 0.5659565329551697, | |
| "learning_rate": 0.00015639913232104121, | |
| "loss": 2.4063, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.7565011820330969, | |
| "grad_norm": 0.4969359338283539, | |
| "learning_rate": 0.0001542299349240781, | |
| "loss": 2.4599, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.7880220646178093, | |
| "grad_norm": 0.5683227777481079, | |
| "learning_rate": 0.000152060737527115, | |
| "loss": 2.4214, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.8195429472025216, | |
| "grad_norm": 0.5504446029663086, | |
| "learning_rate": 0.00014989154013015185, | |
| "loss": 2.3597, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 0.6029040217399597, | |
| "learning_rate": 0.00014772234273318873, | |
| "loss": 2.4472, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.8825847123719465, | |
| "grad_norm": 0.5572171807289124, | |
| "learning_rate": 0.0001455531453362256, | |
| "loss": 2.3552, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.9141055949566588, | |
| "grad_norm": 0.6272566914558411, | |
| "learning_rate": 0.00014338394793926248, | |
| "loss": 2.4717, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.9456264775413712, | |
| "grad_norm": 0.6014458537101746, | |
| "learning_rate": 0.00014121475054229936, | |
| "loss": 2.4543, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9456264775413712, | |
| "eval_loss": 2.3703479766845703, | |
| "eval_runtime": 28.5951, | |
| "eval_samples_per_second": 19.759, | |
| "eval_steps_per_second": 9.897, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9771473601260835, | |
| "grad_norm": 0.6145516037940979, | |
| "learning_rate": 0.00013904555314533622, | |
| "loss": 2.4109, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.0063041765169425, | |
| "grad_norm": 0.6649049520492554, | |
| "learning_rate": 0.0001368763557483731, | |
| "loss": 2.4834, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.037825059101655, | |
| "grad_norm": 0.6200373768806458, | |
| "learning_rate": 0.00013470715835141, | |
| "loss": 2.3862, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.0693459416863673, | |
| "grad_norm": 0.5306605100631714, | |
| "learning_rate": 0.00013253796095444686, | |
| "loss": 2.3856, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.1008668242710795, | |
| "grad_norm": 0.5235586762428284, | |
| "learning_rate": 0.00013036876355748374, | |
| "loss": 2.4574, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.132387706855792, | |
| "grad_norm": 0.5824336409568787, | |
| "learning_rate": 0.00012819956616052063, | |
| "loss": 2.4134, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.1639085894405043, | |
| "grad_norm": 0.5699276328086853, | |
| "learning_rate": 0.0001260303687635575, | |
| "loss": 2.323, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.1954294720252168, | |
| "grad_norm": 0.6251928806304932, | |
| "learning_rate": 0.00012386117136659438, | |
| "loss": 2.4463, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.226950354609929, | |
| "grad_norm": 0.6418842673301697, | |
| "learning_rate": 0.00012169197396963123, | |
| "loss": 2.406, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.2584712371946414, | |
| "grad_norm": 0.5105799436569214, | |
| "learning_rate": 0.00011952277657266812, | |
| "loss": 2.351, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.2584712371946414, | |
| "eval_loss": 2.3272600173950195, | |
| "eval_runtime": 28.699, | |
| "eval_samples_per_second": 19.687, | |
| "eval_steps_per_second": 9.861, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.2899921197793538, | |
| "grad_norm": 0.6160938143730164, | |
| "learning_rate": 0.000117353579175705, | |
| "loss": 2.3101, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.3215130023640662, | |
| "grad_norm": 0.6558836698532104, | |
| "learning_rate": 0.00011518438177874187, | |
| "loss": 2.3196, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.3530338849487786, | |
| "grad_norm": 0.6231864094734192, | |
| "learning_rate": 0.00011301518438177874, | |
| "loss": 2.3871, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.384554767533491, | |
| "grad_norm": 0.5435105562210083, | |
| "learning_rate": 0.00011084598698481563, | |
| "loss": 2.3389, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.4160756501182032, | |
| "grad_norm": 0.5544334650039673, | |
| "learning_rate": 0.0001086767895878525, | |
| "loss": 2.2573, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.4475965327029157, | |
| "grad_norm": 0.6390591859817505, | |
| "learning_rate": 0.00010650759219088937, | |
| "loss": 2.4043, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.479117415287628, | |
| "grad_norm": 0.6744779348373413, | |
| "learning_rate": 0.00010433839479392625, | |
| "loss": 2.2799, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.5106382978723403, | |
| "grad_norm": 0.6263852715492249, | |
| "learning_rate": 0.00010216919739696313, | |
| "loss": 2.2408, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.5421591804570527, | |
| "grad_norm": 0.5550678968429565, | |
| "learning_rate": 0.0001, | |
| "loss": 2.405, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.573680063041765, | |
| "grad_norm": 0.6078540086746216, | |
| "learning_rate": 9.783080260303689e-05, | |
| "loss": 2.3524, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.573680063041765, | |
| "eval_loss": 2.3018314838409424, | |
| "eval_runtime": 28.7339, | |
| "eval_samples_per_second": 19.663, | |
| "eval_steps_per_second": 9.849, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.6052009456264775, | |
| "grad_norm": 0.6397316455841064, | |
| "learning_rate": 9.566160520607375e-05, | |
| "loss": 2.3176, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.63672182821119, | |
| "grad_norm": 0.5407721996307373, | |
| "learning_rate": 9.349240780911064e-05, | |
| "loss": 2.2957, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.6682427107959024, | |
| "grad_norm": 0.5824908018112183, | |
| "learning_rate": 9.132321041214751e-05, | |
| "loss": 2.2554, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.6997635933806148, | |
| "grad_norm": 0.6469699740409851, | |
| "learning_rate": 8.91540130151844e-05, | |
| "loss": 2.3222, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.731284475965327, | |
| "grad_norm": 0.5473052263259888, | |
| "learning_rate": 8.698481561822126e-05, | |
| "loss": 2.339, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.7628053585500394, | |
| "grad_norm": 0.6402776837348938, | |
| "learning_rate": 8.481561822125814e-05, | |
| "loss": 2.2986, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.7943262411347518, | |
| "grad_norm": 0.6581558585166931, | |
| "learning_rate": 8.264642082429502e-05, | |
| "loss": 2.3298, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.825847123719464, | |
| "grad_norm": 0.623936653137207, | |
| "learning_rate": 8.047722342733189e-05, | |
| "loss": 2.3413, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.8573680063041764, | |
| "grad_norm": 0.674414873123169, | |
| "learning_rate": 7.830802603036876e-05, | |
| "loss": 2.3229, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.8888888888888888, | |
| "grad_norm": 0.7090038657188416, | |
| "learning_rate": 7.613882863340565e-05, | |
| "loss": 2.2195, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.8888888888888888, | |
| "eval_loss": 2.280967950820923, | |
| "eval_runtime": 29.0942, | |
| "eval_samples_per_second": 19.42, | |
| "eval_steps_per_second": 9.727, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.9204097714736013, | |
| "grad_norm": 0.6059763431549072, | |
| "learning_rate": 7.396963123644252e-05, | |
| "loss": 2.3873, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.9519306540583137, | |
| "grad_norm": 0.6435537934303284, | |
| "learning_rate": 7.18004338394794e-05, | |
| "loss": 2.3815, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.983451536643026, | |
| "grad_norm": 0.6055386066436768, | |
| "learning_rate": 6.963123644251627e-05, | |
| "loss": 2.2811, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.012608353033885, | |
| "grad_norm": 0.6461377739906311, | |
| "learning_rate": 6.746203904555315e-05, | |
| "loss": 2.268, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.0441292356185974, | |
| "grad_norm": 0.6220865249633789, | |
| "learning_rate": 6.529284164859003e-05, | |
| "loss": 2.2531, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.07565011820331, | |
| "grad_norm": 0.7532601356506348, | |
| "learning_rate": 6.31236442516269e-05, | |
| "loss": 2.3595, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.107171000788022, | |
| "grad_norm": 0.6474109888076782, | |
| "learning_rate": 6.0954446854663785e-05, | |
| "loss": 2.2329, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.1386918833727346, | |
| "grad_norm": 0.6826472878456116, | |
| "learning_rate": 5.878524945770065e-05, | |
| "loss": 2.2751, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.1702127659574466, | |
| "grad_norm": 0.6584506630897522, | |
| "learning_rate": 5.661605206073753e-05, | |
| "loss": 2.3674, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.201733648542159, | |
| "grad_norm": 0.7180963158607483, | |
| "learning_rate": 5.4446854663774404e-05, | |
| "loss": 2.2365, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.201733648542159, | |
| "eval_loss": 2.2675509452819824, | |
| "eval_runtime": 29.0656, | |
| "eval_samples_per_second": 19.439, | |
| "eval_steps_per_second": 9.737, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.2332545311268714, | |
| "grad_norm": 0.5672284960746765, | |
| "learning_rate": 5.2277657266811284e-05, | |
| "loss": 2.2923, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.264775413711584, | |
| "grad_norm": 0.6805603504180908, | |
| "learning_rate": 5.010845986984816e-05, | |
| "loss": 2.3719, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.2962962962962963, | |
| "grad_norm": 0.5467990040779114, | |
| "learning_rate": 4.793926247288503e-05, | |
| "loss": 2.2015, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.3278171788810087, | |
| "grad_norm": 0.6205419301986694, | |
| "learning_rate": 4.577006507592191e-05, | |
| "loss": 2.2902, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.359338061465721, | |
| "grad_norm": 0.7138726711273193, | |
| "learning_rate": 4.360086767895879e-05, | |
| "loss": 2.2435, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.3908589440504335, | |
| "grad_norm": 0.6206688284873962, | |
| "learning_rate": 4.143167028199567e-05, | |
| "loss": 2.2338, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.422379826635146, | |
| "grad_norm": 0.5491693615913391, | |
| "learning_rate": 3.926247288503254e-05, | |
| "loss": 2.3459, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.453900709219858, | |
| "grad_norm": 0.7104467153549194, | |
| "learning_rate": 3.7093275488069415e-05, | |
| "loss": 2.2649, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.4854215918045703, | |
| "grad_norm": 0.7069652080535889, | |
| "learning_rate": 3.4924078091106294e-05, | |
| "loss": 2.2289, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.5169424743892828, | |
| "grad_norm": 0.7097485661506653, | |
| "learning_rate": 3.275488069414317e-05, | |
| "loss": 2.2986, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.5169424743892828, | |
| "eval_loss": 2.2567555904388428, | |
| "eval_runtime": 28.9859, | |
| "eval_samples_per_second": 19.492, | |
| "eval_steps_per_second": 9.763, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.548463356973995, | |
| "grad_norm": 0.6493655443191528, | |
| "learning_rate": 3.058568329718005e-05, | |
| "loss": 2.3154, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.5799842395587076, | |
| "grad_norm": 0.5883040428161621, | |
| "learning_rate": 2.841648590021692e-05, | |
| "loss": 2.3223, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.61150512214342, | |
| "grad_norm": 0.716276228427887, | |
| "learning_rate": 2.6247288503253796e-05, | |
| "loss": 2.2199, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.6430260047281324, | |
| "grad_norm": 0.5637353658676147, | |
| "learning_rate": 2.4078091106290673e-05, | |
| "loss": 2.4102, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.674546887312845, | |
| "grad_norm": 0.673851728439331, | |
| "learning_rate": 2.190889370932755e-05, | |
| "loss": 2.2731, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.7060677698975573, | |
| "grad_norm": 0.6776373386383057, | |
| "learning_rate": 1.9739696312364425e-05, | |
| "loss": 2.1956, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.7375886524822697, | |
| "grad_norm": 0.7007333636283875, | |
| "learning_rate": 1.75704989154013e-05, | |
| "loss": 2.2303, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.769109535066982, | |
| "grad_norm": 0.6189983487129211, | |
| "learning_rate": 1.540130151843818e-05, | |
| "loss": 2.2987, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.8006304176516945, | |
| "grad_norm": 0.6148092150688171, | |
| "learning_rate": 1.3232104121475056e-05, | |
| "loss": 2.2527, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.8321513002364065, | |
| "grad_norm": 0.6943378448486328, | |
| "learning_rate": 1.1062906724511932e-05, | |
| "loss": 2.3205, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.8321513002364065, | |
| "eval_loss": 2.2496395111083984, | |
| "eval_runtime": 29.1023, | |
| "eval_samples_per_second": 19.414, | |
| "eval_steps_per_second": 9.724, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.863672182821119, | |
| "grad_norm": 0.6751441359519958, | |
| "learning_rate": 8.893709327548807e-06, | |
| "loss": 2.2436, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.8951930654058313, | |
| "grad_norm": 0.669208824634552, | |
| "learning_rate": 6.724511930585684e-06, | |
| "loss": 2.2762, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.9267139479905437, | |
| "grad_norm": 0.6294866800308228, | |
| "learning_rate": 4.55531453362256e-06, | |
| "loss": 2.2291, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.958234830575256, | |
| "grad_norm": 0.6172659397125244, | |
| "learning_rate": 2.386117136659436e-06, | |
| "loss": 2.2527, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.9897557131599686, | |
| "grad_norm": 0.6540963649749756, | |
| "learning_rate": 2.1691973969631237e-07, | |
| "loss": 2.2856, | |
| "step": 950 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 951, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.610585377989755e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |