| { | |
| "best_metric": 1.6708096265792847, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-250", | |
| "epoch": 1.9065776930409915, | |
| "eval_steps": 25, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0076263107721639654, | |
| "grad_norm": 0.9196067452430725, | |
| "learning_rate": 4.285714285714285e-05, | |
| "loss": 3.2672, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0076263107721639654, | |
| "eval_loss": 3.787529230117798, | |
| "eval_runtime": 0.2862, | |
| "eval_samples_per_second": 174.68, | |
| "eval_steps_per_second": 45.417, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015252621544327931, | |
| "grad_norm": 0.8998702168464661, | |
| "learning_rate": 8.57142857142857e-05, | |
| "loss": 3.4083, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.022878932316491896, | |
| "grad_norm": 0.9599621295928955, | |
| "learning_rate": 0.00012857142857142855, | |
| "loss": 3.5199, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.030505243088655862, | |
| "grad_norm": 0.9405797123908997, | |
| "learning_rate": 0.0001714285714285714, | |
| "loss": 3.5021, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03813155386081983, | |
| "grad_norm": 0.9620326161384583, | |
| "learning_rate": 0.00021428571428571427, | |
| "loss": 3.5165, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04575786463298379, | |
| "grad_norm": 0.9596439003944397, | |
| "learning_rate": 0.0002571428571428571, | |
| "loss": 3.4724, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05338417540514776, | |
| "grad_norm": 0.917304277420044, | |
| "learning_rate": 0.0003, | |
| "loss": 3.4023, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.061010486177311724, | |
| "grad_norm": 0.8579983711242676, | |
| "learning_rate": 0.0002999898347482845, | |
| "loss": 3.3249, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06863679694947569, | |
| "grad_norm": 0.8907164335250854, | |
| "learning_rate": 0.00029995934052398757, | |
| "loss": 3.2235, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07626310772163966, | |
| "grad_norm": 0.9348911046981812, | |
| "learning_rate": 0.00029990852191942715, | |
| "loss": 3.1403, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08388941849380362, | |
| "grad_norm": 0.9178524613380432, | |
| "learning_rate": 0.0002998373865876983, | |
| "loss": 3.1472, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09151572926596759, | |
| "grad_norm": 1.1779893636703491, | |
| "learning_rate": 0.0002997459452415201, | |
| "loss": 3.1228, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09914204003813155, | |
| "grad_norm": 1.2700427770614624, | |
| "learning_rate": 0.00029963421165162316, | |
| "loss": 2.8118, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10676835081029552, | |
| "grad_norm": 1.2745684385299683, | |
| "learning_rate": 0.00029950220264467496, | |
| "loss": 2.5948, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11439466158245949, | |
| "grad_norm": 1.0857181549072266, | |
| "learning_rate": 0.0002993499381007466, | |
| "loss": 2.5336, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12202097235462345, | |
| "grad_norm": 0.926810622215271, | |
| "learning_rate": 0.00029917744095031806, | |
| "loss": 2.5163, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12964728312678742, | |
| "grad_norm": 0.7827774882316589, | |
| "learning_rate": 0.0002989847371708258, | |
| "loss": 2.4039, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.13727359389895138, | |
| "grad_norm": 0.6036872863769531, | |
| "learning_rate": 0.00029877185578275025, | |
| "loss": 2.3962, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.14489990467111535, | |
| "grad_norm": 0.8695657253265381, | |
| "learning_rate": 0.0002985388288452454, | |
| "loss": 2.3643, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.15252621544327932, | |
| "grad_norm": 0.9263712763786316, | |
| "learning_rate": 0.0002982856914513109, | |
| "loss": 2.3404, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1601525262154433, | |
| "grad_norm": 0.41602811217308044, | |
| "learning_rate": 0.00029801248172250705, | |
| "loss": 2.3645, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.16777883698760723, | |
| "grad_norm": 0.8675795197486877, | |
| "learning_rate": 0.0002977192408032142, | |
| "loss": 2.3502, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1754051477597712, | |
| "grad_norm": 0.9460420608520508, | |
| "learning_rate": 0.0002974060128544361, | |
| "loss": 2.374, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.18303145853193517, | |
| "grad_norm": 0.6238827705383301, | |
| "learning_rate": 0.0002970728450471497, | |
| "loss": 2.4411, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.19065776930409914, | |
| "grad_norm": 0.6706355214118958, | |
| "learning_rate": 0.0002967197875552013, | |
| "loss": 2.5664, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.19065776930409914, | |
| "eval_loss": 2.3339245319366455, | |
| "eval_runtime": 0.2802, | |
| "eval_samples_per_second": 178.467, | |
| "eval_steps_per_second": 46.402, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1982840800762631, | |
| "grad_norm": 1.384001612663269, | |
| "learning_rate": 0.0002963468935477506, | |
| "loss": 2.1595, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.20591039084842708, | |
| "grad_norm": 0.8498388528823853, | |
| "learning_rate": 0.00029595421918126344, | |
| "loss": 2.109, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.21353670162059105, | |
| "grad_norm": 0.3540984094142914, | |
| "learning_rate": 0.00029554182359105497, | |
| "loss": 2.1542, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.22116301239275502, | |
| "grad_norm": 0.6427699327468872, | |
| "learning_rate": 0.00029510976888238435, | |
| "loss": 2.1396, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.22878932316491898, | |
| "grad_norm": 0.9017099738121033, | |
| "learning_rate": 0.0002946581201211013, | |
| "loss": 2.1525, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.23641563393708293, | |
| "grad_norm": 0.5602626204490662, | |
| "learning_rate": 0.00029418694532384816, | |
| "loss": 2.1099, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2440419447092469, | |
| "grad_norm": 0.35870033502578735, | |
| "learning_rate": 0.0002936963154478161, | |
| "loss": 2.073, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.25166825548141086, | |
| "grad_norm": 0.4111023545265198, | |
| "learning_rate": 0.0002931863043800599, | |
| "loss": 2.1075, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.25929456625357483, | |
| "grad_norm": 0.5750699043273926, | |
| "learning_rate": 0.00029265698892637034, | |
| "loss": 2.0506, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2669208770257388, | |
| "grad_norm": 0.687319278717041, | |
| "learning_rate": 0.00029210844879970775, | |
| "loss": 2.154, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.27454718779790277, | |
| "grad_norm": 0.49932411313056946, | |
| "learning_rate": 0.0002915407666081976, | |
| "loss": 2.165, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.28217349857006674, | |
| "grad_norm": 0.48046040534973145, | |
| "learning_rate": 0.0002909540278426897, | |
| "loss": 2.1741, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2897998093422307, | |
| "grad_norm": 0.797716498374939, | |
| "learning_rate": 0.0002903483208638841, | |
| "loss": 2.1329, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2974261201143947, | |
| "grad_norm": 0.425375372171402, | |
| "learning_rate": 0.0002897237368890237, | |
| "loss": 1.916, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.30505243088655865, | |
| "grad_norm": 0.40925440192222595, | |
| "learning_rate": 0.0002890803699781578, | |
| "loss": 1.904, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3126787416587226, | |
| "grad_norm": 0.575661838054657, | |
| "learning_rate": 0.0002884183170199766, | |
| "loss": 1.9828, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3203050524308866, | |
| "grad_norm": 0.7085393667221069, | |
| "learning_rate": 0.0002877376777172205, | |
| "loss": 1.9275, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3279313632030505, | |
| "grad_norm": 0.4340769648551941, | |
| "learning_rate": 0.00028703855457166483, | |
| "loss": 1.9285, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.33555767397521447, | |
| "grad_norm": 0.32672634720802307, | |
| "learning_rate": 0.00028632105286868374, | |
| "loss": 1.9382, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.34318398474737843, | |
| "grad_norm": 0.3794914782047272, | |
| "learning_rate": 0.0002855852806613945, | |
| "loss": 1.8947, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3508102955195424, | |
| "grad_norm": 0.37154510617256165, | |
| "learning_rate": 0.00028483134875438527, | |
| "loss": 1.9039, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.35843660629170637, | |
| "grad_norm": 0.3726259768009186, | |
| "learning_rate": 0.0002840593706870279, | |
| "loss": 1.9194, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.36606291706387034, | |
| "grad_norm": 0.370515912771225, | |
| "learning_rate": 0.00028326946271637986, | |
| "loss": 1.8939, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3736892278360343, | |
| "grad_norm": 0.42510128021240234, | |
| "learning_rate": 0.00028246174379967606, | |
| "loss": 1.9624, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3813155386081983, | |
| "grad_norm": 0.531184732913971, | |
| "learning_rate": 0.0002816363355764142, | |
| "loss": 2.0973, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3813155386081983, | |
| "eval_loss": 1.9253315925598145, | |
| "eval_runtime": 0.2792, | |
| "eval_samples_per_second": 179.063, | |
| "eval_steps_per_second": 46.557, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.38894184938036225, | |
| "grad_norm": 1.3231308460235596, | |
| "learning_rate": 0.00028079336235003674, | |
| "loss": 1.8672, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.3965681601525262, | |
| "grad_norm": 0.3953985869884491, | |
| "learning_rate": 0.0002799329510692108, | |
| "loss": 1.7821, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.4041944709246902, | |
| "grad_norm": 0.34664496779441833, | |
| "learning_rate": 0.0002790552313087104, | |
| "loss": 1.8357, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.41182078169685415, | |
| "grad_norm": 0.32160669565200806, | |
| "learning_rate": 0.0002781603352499031, | |
| "loss": 1.8114, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.4194470924690181, | |
| "grad_norm": 0.35647809505462646, | |
| "learning_rate": 0.0002772483976608436, | |
| "loss": 1.9044, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.4270734032411821, | |
| "grad_norm": 0.5951141715049744, | |
| "learning_rate": 0.0002763195558759784, | |
| "loss": 1.8211, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.43469971401334606, | |
| "grad_norm": 0.5895670652389526, | |
| "learning_rate": 0.00027537394977546377, | |
| "loss": 1.8736, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.44232602478551003, | |
| "grad_norm": 0.3808022439479828, | |
| "learning_rate": 0.00027441172176410027, | |
| "loss": 1.8487, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.449952335557674, | |
| "grad_norm": 0.3616071343421936, | |
| "learning_rate": 0.000273433016749887, | |
| "loss": 1.86, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.45757864632983797, | |
| "grad_norm": 0.34098148345947266, | |
| "learning_rate": 0.00027243798212219926, | |
| "loss": 1.8849, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4652049571020019, | |
| "grad_norm": 0.3677496910095215, | |
| "learning_rate": 0.0002714267677295918, | |
| "loss": 1.9066, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.47283126787416585, | |
| "grad_norm": 0.42355066537857056, | |
| "learning_rate": 0.0002703995258572327, | |
| "loss": 1.8943, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4804575786463298, | |
| "grad_norm": 0.8111021518707275, | |
| "learning_rate": 0.0002693564112039695, | |
| "loss": 1.8816, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4880838894184938, | |
| "grad_norm": 0.5244035720825195, | |
| "learning_rate": 0.00026829758085903196, | |
| "loss": 1.7596, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.49571020019065776, | |
| "grad_norm": 0.49128928780555725, | |
| "learning_rate": 0.0002672231942783754, | |
| "loss": 1.7882, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5033365109628217, | |
| "grad_norm": 0.35969385504722595, | |
| "learning_rate": 0.000266133413260667, | |
| "loss": 1.7607, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5109628217349858, | |
| "grad_norm": 0.30560654401779175, | |
| "learning_rate": 0.0002650284019229195, | |
| "loss": 1.7378, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.5185891325071497, | |
| "grad_norm": 0.2821063697338104, | |
| "learning_rate": 0.0002639083266757757, | |
| "loss": 1.7452, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.5262154432793136, | |
| "grad_norm": 0.30434897541999817, | |
| "learning_rate": 0.000262773356198448, | |
| "loss": 1.757, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.5338417540514776, | |
| "grad_norm": 0.35866251587867737, | |
| "learning_rate": 0.0002616236614133155, | |
| "loss": 1.8456, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5414680648236415, | |
| "grad_norm": 0.36527636647224426, | |
| "learning_rate": 0.0002604594154601839, | |
| "loss": 1.7636, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.5490943755958055, | |
| "grad_norm": 0.4293094575405121, | |
| "learning_rate": 0.00025928079367021134, | |
| "loss": 1.7983, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.5567206863679695, | |
| "grad_norm": 0.4558382034301758, | |
| "learning_rate": 0.000258087973539504, | |
| "loss": 1.8167, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.5643469971401335, | |
| "grad_norm": 0.46237555146217346, | |
| "learning_rate": 0.00025688113470238616, | |
| "loss": 1.8516, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.5719733079122974, | |
| "grad_norm": 0.5830234885215759, | |
| "learning_rate": 0.00025566045890434747, | |
| "loss": 1.8979, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5719733079122974, | |
| "eval_loss": 1.8215560913085938, | |
| "eval_runtime": 0.2804, | |
| "eval_samples_per_second": 178.348, | |
| "eval_steps_per_second": 46.371, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5795996186844614, | |
| "grad_norm": 0.4658236503601074, | |
| "learning_rate": 0.00025442612997467315, | |
| "loss": 1.7275, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.5872259294566253, | |
| "grad_norm": 0.45749977231025696, | |
| "learning_rate": 0.0002531783337987598, | |
| "loss": 1.7482, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.5948522402287894, | |
| "grad_norm": 0.4462372660636902, | |
| "learning_rate": 0.0002519172582901218, | |
| "loss": 1.7561, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.6024785510009533, | |
| "grad_norm": 0.38078993558883667, | |
| "learning_rate": 0.00025064309336209214, | |
| "loss": 1.7398, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.6101048617731173, | |
| "grad_norm": 0.3360918164253235, | |
| "learning_rate": 0.00024935603089922215, | |
| "loss": 1.7546, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6177311725452812, | |
| "grad_norm": 0.30906444787979126, | |
| "learning_rate": 0.0002480562647283846, | |
| "loss": 1.7487, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.6253574833174452, | |
| "grad_norm": 0.36905303597450256, | |
| "learning_rate": 0.00024674399058958394, | |
| "loss": 1.7589, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.6329837940896091, | |
| "grad_norm": 0.3760243058204651, | |
| "learning_rate": 0.0002454194061064785, | |
| "loss": 1.7732, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.6406101048617732, | |
| "grad_norm": 0.41075772047042847, | |
| "learning_rate": 0.0002440827107566192, | |
| "loss": 1.7812, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.6482364156339371, | |
| "grad_norm": 0.41905277967453003, | |
| "learning_rate": 0.00024273410584140913, | |
| "loss": 1.7692, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.655862726406101, | |
| "grad_norm": 0.41411152482032776, | |
| "learning_rate": 0.00024137379445578774, | |
| "loss": 1.8508, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.663489037178265, | |
| "grad_norm": 0.47408804297447205, | |
| "learning_rate": 0.0002400019814576463, | |
| "loss": 1.847, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.6711153479504289, | |
| "grad_norm": 0.4235435724258423, | |
| "learning_rate": 0.00023861887343697624, | |
| "loss": 1.8122, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.678741658722593, | |
| "grad_norm": 0.3859807252883911, | |
| "learning_rate": 0.00023722467868475812, | |
| "loss": 1.6975, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.6863679694947569, | |
| "grad_norm": 0.3468429148197174, | |
| "learning_rate": 0.0002358196071615933, | |
| "loss": 1.694, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6939942802669209, | |
| "grad_norm": 0.3533165156841278, | |
| "learning_rate": 0.00023440387046608487, | |
| "loss": 1.6882, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.7016205910390848, | |
| "grad_norm": 0.3266445994377136, | |
| "learning_rate": 0.00023297768180297187, | |
| "loss": 1.6909, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.7092469018112488, | |
| "grad_norm": 0.3379365801811218, | |
| "learning_rate": 0.00023154125595102083, | |
| "loss": 1.7055, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.7168732125834127, | |
| "grad_norm": 0.32845547795295715, | |
| "learning_rate": 0.00023009480923068157, | |
| "loss": 1.7529, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.7244995233555768, | |
| "grad_norm": 0.3393206000328064, | |
| "learning_rate": 0.00022863855947150968, | |
| "loss": 1.7702, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7321258341277407, | |
| "grad_norm": 0.3422520160675049, | |
| "learning_rate": 0.0002271727259793624, | |
| "loss": 1.7063, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.7397521448999047, | |
| "grad_norm": 0.378302663564682, | |
| "learning_rate": 0.0002256975295033719, | |
| "loss": 1.7602, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.7473784556720686, | |
| "grad_norm": 0.41780129075050354, | |
| "learning_rate": 0.0002242131922027012, | |
| "loss": 1.8039, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.7550047664442326, | |
| "grad_norm": 0.44365987181663513, | |
| "learning_rate": 0.00022271993761308807, | |
| "loss": 1.7738, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.7626310772163966, | |
| "grad_norm": 0.5752303600311279, | |
| "learning_rate": 0.00022121799061318104, | |
| "loss": 1.9044, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7626310772163966, | |
| "eval_loss": 1.7645323276519775, | |
| "eval_runtime": 0.28, | |
| "eval_samples_per_second": 178.583, | |
| "eval_steps_per_second": 46.431, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7702573879885606, | |
| "grad_norm": 0.5027046203613281, | |
| "learning_rate": 0.00021970757739067358, | |
| "loss": 1.6627, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.7778836987607245, | |
| "grad_norm": 0.4292294681072235, | |
| "learning_rate": 0.00021818892540824148, | |
| "loss": 1.6495, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.7855100095328885, | |
| "grad_norm": 0.37569937109947205, | |
| "learning_rate": 0.00021666226336928708, | |
| "loss": 1.6692, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.7931363203050524, | |
| "grad_norm": 0.3786998391151428, | |
| "learning_rate": 0.00021512782118349806, | |
| "loss": 1.6581, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.8007626310772163, | |
| "grad_norm": 0.36832037568092346, | |
| "learning_rate": 0.0002135858299322234, | |
| "loss": 1.6714, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.8083889418493804, | |
| "grad_norm": 0.336896687746048, | |
| "learning_rate": 0.00021203652183367363, | |
| "loss": 1.7207, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.8160152526215443, | |
| "grad_norm": 0.35588911175727844, | |
| "learning_rate": 0.00021048013020794968, | |
| "loss": 1.7085, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.8236415633937083, | |
| "grad_norm": 0.4056905508041382, | |
| "learning_rate": 0.00020891688944190548, | |
| "loss": 1.7094, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.8312678741658722, | |
| "grad_norm": 0.40606462955474854, | |
| "learning_rate": 0.00020734703495385037, | |
| "loss": 1.7239, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.8388941849380362, | |
| "grad_norm": 0.40182796120643616, | |
| "learning_rate": 0.0002057708031580958, | |
| "loss": 1.7333, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8465204957102002, | |
| "grad_norm": 0.44995224475860596, | |
| "learning_rate": 0.00020418843142935237, | |
| "loss": 1.7049, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.8541468064823642, | |
| "grad_norm": 0.4388667047023773, | |
| "learning_rate": 0.00020260015806698213, | |
| "loss": 1.783, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.8617731172545281, | |
| "grad_norm": 0.44865381717681885, | |
| "learning_rate": 0.00020100622225911128, | |
| "loss": 1.7508, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.8693994280266921, | |
| "grad_norm": 0.4294881522655487, | |
| "learning_rate": 0.00019940686404660947, | |
| "loss": 1.6571, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.877025738798856, | |
| "grad_norm": 0.3841921091079712, | |
| "learning_rate": 0.00019780232428694063, | |
| "loss": 1.695, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.8846520495710201, | |
| "grad_norm": 0.3785157799720764, | |
| "learning_rate": 0.0001961928446178906, | |
| "loss": 1.6545, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.892278360343184, | |
| "grad_norm": 0.33887144923210144, | |
| "learning_rate": 0.00019457866742117737, | |
| "loss": 1.6715, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.899904671115348, | |
| "grad_norm": 0.32863056659698486, | |
| "learning_rate": 0.00019296003578594948, | |
| "loss": 1.6952, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.9075309818875119, | |
| "grad_norm": 0.3387095034122467, | |
| "learning_rate": 0.00019133719347217733, | |
| "loss": 1.6291, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.9151572926596759, | |
| "grad_norm": 0.3665367066860199, | |
| "learning_rate": 0.00018971038487394402, | |
| "loss": 1.7321, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9227836034318398, | |
| "grad_norm": 0.3495505452156067, | |
| "learning_rate": 0.00018807985498264066, | |
| "loss": 1.6587, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.9304099142040038, | |
| "grad_norm": 0.40355828404426575, | |
| "learning_rate": 0.00018644584935007127, | |
| "loss": 1.7027, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.9380362249761678, | |
| "grad_norm": 0.4357530474662781, | |
| "learning_rate": 0.0001848086140514738, | |
| "loss": 1.7724, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.9456625357483317, | |
| "grad_norm": 0.44958412647247314, | |
| "learning_rate": 0.000183168395648462, | |
| "loss": 1.7454, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.9532888465204957, | |
| "grad_norm": 0.5644071102142334, | |
| "learning_rate": 0.00018152544115189416, | |
| "loss": 1.8156, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.9532888465204957, | |
| "eval_loss": 1.7262933254241943, | |
| "eval_runtime": 0.2797, | |
| "eval_samples_per_second": 178.792, | |
| "eval_steps_per_second": 46.486, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.9609151572926596, | |
| "grad_norm": 0.45155230164527893, | |
| "learning_rate": 0.0001798799979846742, | |
| "loss": 1.6338, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.9685414680648237, | |
| "grad_norm": 0.41884180903434753, | |
| "learning_rate": 0.00017823231394449072, | |
| "loss": 1.6829, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.9761677788369876, | |
| "grad_norm": 0.3723445534706116, | |
| "learning_rate": 0.0001765826371664994, | |
| "loss": 1.6707, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.9837940896091516, | |
| "grad_norm": 0.3832674026489258, | |
| "learning_rate": 0.00017493121608595511, | |
| "loss": 1.7397, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.9914204003813155, | |
| "grad_norm": 0.37408822774887085, | |
| "learning_rate": 0.00017327829940079817, | |
| "loss": 1.6765, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.9990467111534795, | |
| "grad_norm": 0.42527204751968384, | |
| "learning_rate": 0.00017162413603420142, | |
| "loss": 1.791, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.0066730219256435, | |
| "grad_norm": 1.3834341764450073, | |
| "learning_rate": 0.00016996897509708345, | |
| "loss": 3.4039, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.0142993326978074, | |
| "grad_norm": 0.43991145491600037, | |
| "learning_rate": 0.00016831306585059317, | |
| "loss": 1.6506, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.0219256434699715, | |
| "grad_norm": 0.37817224860191345, | |
| "learning_rate": 0.0001666566576685722, | |
| "loss": 1.5943, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.0295519542421354, | |
| "grad_norm": 0.34133297204971313, | |
| "learning_rate": 0.000165, | |
| "loss": 1.5756, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.0371782650142993, | |
| "grad_norm": 0.32997646927833557, | |
| "learning_rate": 0.0001633433423314278, | |
| "loss": 1.6236, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.0448045757864632, | |
| "grad_norm": 0.3591316342353821, | |
| "learning_rate": 0.00016168693414940683, | |
| "loss": 1.6221, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.0524308865586272, | |
| "grad_norm": 0.3701683580875397, | |
| "learning_rate": 0.00016003102490291655, | |
| "loss": 1.6099, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.0600571973307913, | |
| "grad_norm": 0.3921620845794678, | |
| "learning_rate": 0.00015837586396579858, | |
| "loss": 1.6507, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.0676835081029552, | |
| "grad_norm": 0.411425918340683, | |
| "learning_rate": 0.00015672170059920183, | |
| "loss": 1.6658, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0753098188751191, | |
| "grad_norm": 0.4283716082572937, | |
| "learning_rate": 0.00015506878391404488, | |
| "loss": 1.6525, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.082936129647283, | |
| "grad_norm": 0.43306857347488403, | |
| "learning_rate": 0.00015341736283350064, | |
| "loss": 1.6808, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.0905624404194472, | |
| "grad_norm": 0.46868017315864563, | |
| "learning_rate": 0.0001517676860555093, | |
| "loss": 1.7022, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.098188751191611, | |
| "grad_norm": 0.3939070403575897, | |
| "learning_rate": 0.0001501200020153258, | |
| "loss": 1.608, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.105815061963775, | |
| "grad_norm": 0.5079172253608704, | |
| "learning_rate": 0.00014847455884810581, | |
| "loss": 1.664, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.113441372735939, | |
| "grad_norm": 0.4701906740665436, | |
| "learning_rate": 0.00014683160435153796, | |
| "loss": 1.5924, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.121067683508103, | |
| "grad_norm": 0.4438985288143158, | |
| "learning_rate": 0.00014519138594852615, | |
| "loss": 1.6186, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.128693994280267, | |
| "grad_norm": 0.40085965394973755, | |
| "learning_rate": 0.00014355415064992873, | |
| "loss": 1.6421, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.1363203050524309, | |
| "grad_norm": 0.3875059485435486, | |
| "learning_rate": 0.00014192014501735934, | |
| "loss": 1.5903, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.1439466158245948, | |
| "grad_norm": 0.3794068992137909, | |
| "learning_rate": 0.00014028961512605598, | |
| "loss": 1.6741, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1439466158245948, | |
| "eval_loss": 1.7033360004425049, | |
| "eval_runtime": 0.2798, | |
| "eval_samples_per_second": 178.678, | |
| "eval_steps_per_second": 46.456, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1515729265967587, | |
| "grad_norm": 0.38320392370224, | |
| "learning_rate": 0.00013866280652782267, | |
| "loss": 1.6258, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.1591992373689228, | |
| "grad_norm": 0.3931479752063751, | |
| "learning_rate": 0.00013703996421405052, | |
| "loss": 1.6313, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.1668255481410867, | |
| "grad_norm": 0.4570615589618683, | |
| "learning_rate": 0.00013542133257882257, | |
| "loss": 1.6801, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.1744518589132507, | |
| "grad_norm": 0.47714921832084656, | |
| "learning_rate": 0.0001338071553821094, | |
| "loss": 1.6307, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.1820781696854148, | |
| "grad_norm": 0.4591121971607208, | |
| "learning_rate": 0.00013219767571305937, | |
| "loss": 1.7064, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.1897044804575787, | |
| "grad_norm": 0.5732882022857666, | |
| "learning_rate": 0.00013059313595339053, | |
| "loss": 1.7405, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.1973307912297426, | |
| "grad_norm": 0.4108792543411255, | |
| "learning_rate": 0.00012899377774088872, | |
| "loss": 1.6063, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.2049571020019065, | |
| "grad_norm": 0.42478087544441223, | |
| "learning_rate": 0.00012739984193301784, | |
| "loss": 1.5782, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.2125834127740704, | |
| "grad_norm": 0.44489574432373047, | |
| "learning_rate": 0.0001258115685706476, | |
| "loss": 1.5959, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.2202097235462346, | |
| "grad_norm": 0.41875404119491577, | |
| "learning_rate": 0.0001242291968419042, | |
| "loss": 1.6163, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.2278360343183985, | |
| "grad_norm": 0.3827251195907593, | |
| "learning_rate": 0.00012265296504614963, | |
| "loss": 1.6228, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.2354623450905624, | |
| "grad_norm": 0.3817841112613678, | |
| "learning_rate": 0.0001210831105580945, | |
| "loss": 1.5694, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.2430886558627263, | |
| "grad_norm": 0.3716193735599518, | |
| "learning_rate": 0.00011951986979205029, | |
| "loss": 1.6367, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.2507149666348902, | |
| "grad_norm": 0.37516316771507263, | |
| "learning_rate": 0.00011796347816632634, | |
| "loss": 1.6157, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.2583412774070544, | |
| "grad_norm": 0.4124738276004791, | |
| "learning_rate": 0.00011641417006777658, | |
| "loss": 1.5697, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.2659675881792183, | |
| "grad_norm": 0.4279733896255493, | |
| "learning_rate": 0.00011487217881650195, | |
| "loss": 1.6447, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.2735938989513822, | |
| "grad_norm": 0.4881094992160797, | |
| "learning_rate": 0.00011333773663071288, | |
| "loss": 1.6122, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.2812202097235463, | |
| "grad_norm": 0.521618127822876, | |
| "learning_rate": 0.00011181107459175851, | |
| "loss": 1.7202, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.2888465204957102, | |
| "grad_norm": 0.3777306079864502, | |
| "learning_rate": 0.00011029242260932638, | |
| "loss": 1.5756, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.2964728312678742, | |
| "grad_norm": 0.4733025133609772, | |
| "learning_rate": 0.000108782009386819, | |
| "loss": 1.6479, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.304099142040038, | |
| "grad_norm": 0.41860291361808777, | |
| "learning_rate": 0.00010728006238691194, | |
| "loss": 1.5983, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.311725452812202, | |
| "grad_norm": 0.46844813227653503, | |
| "learning_rate": 0.00010578680779729879, | |
| "loss": 1.578, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.3193517635843661, | |
| "grad_norm": 0.40656524896621704, | |
| "learning_rate": 0.0001043024704966281, | |
| "loss": 1.6255, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.32697807435653, | |
| "grad_norm": 0.38256990909576416, | |
| "learning_rate": 0.00010282727402063758, | |
| "loss": 1.5675, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.334604385128694, | |
| "grad_norm": 0.3779941201210022, | |
| "learning_rate": 0.00010136144052849031, | |
| "loss": 1.5789, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.334604385128694, | |
| "eval_loss": 1.695977807044983, | |
| "eval_runtime": 0.2808, | |
| "eval_samples_per_second": 178.081, | |
| "eval_steps_per_second": 46.301, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.342230695900858, | |
| "grad_norm": 0.3875720798969269, | |
| "learning_rate": 9.990519076931843e-05, | |
| "loss": 1.656, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.349857006673022, | |
| "grad_norm": 0.38068655133247375, | |
| "learning_rate": 9.845874404897915e-05, | |
| "loss": 1.623, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.357483317445186, | |
| "grad_norm": 0.4605511724948883, | |
| "learning_rate": 9.702231819702814e-05, | |
| "loss": 1.627, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.3651096282173498, | |
| "grad_norm": 0.4176296889781952, | |
| "learning_rate": 9.559612953391507e-05, | |
| "loss": 1.6706, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.3727359389895137, | |
| "grad_norm": 0.4767864942550659, | |
| "learning_rate": 9.418039283840671e-05, | |
| "loss": 1.6709, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.3803622497616779, | |
| "grad_norm": 0.567336916923523, | |
| "learning_rate": 9.27753213152419e-05, | |
| "loss": 1.8214, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.3879885605338418, | |
| "grad_norm": 0.4051623046398163, | |
| "learning_rate": 9.138112656302376e-05, | |
| "loss": 1.6248, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.3956148713060057, | |
| "grad_norm": 0.380164235830307, | |
| "learning_rate": 8.999801854235373e-05, | |
| "loss": 1.5668, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.4032411820781696, | |
| "grad_norm": 0.37853559851646423, | |
| "learning_rate": 8.862620554421221e-05, | |
| "loss": 1.6079, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.4108674928503335, | |
| "grad_norm": 0.38022464513778687, | |
| "learning_rate": 8.726589415859088e-05, | |
| "loss": 1.6109, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.4184938036224977, | |
| "grad_norm": 0.3726414442062378, | |
| "learning_rate": 8.591728924338075e-05, | |
| "loss": 1.5726, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.4261201143946616, | |
| "grad_norm": 0.39313751459121704, | |
| "learning_rate": 8.45805938935215e-05, | |
| "loss": 1.5881, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.4337464251668255, | |
| "grad_norm": 0.40941789746284485, | |
| "learning_rate": 8.325600941041607e-05, | |
| "loss": 1.6375, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.4413727359389896, | |
| "grad_norm": 0.38843002915382385, | |
| "learning_rate": 8.194373527161539e-05, | |
| "loss": 1.5911, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.4489990467111535, | |
| "grad_norm": 0.38351744413375854, | |
| "learning_rate": 8.064396910077785e-05, | |
| "loss": 1.6153, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.4566253574833175, | |
| "grad_norm": 0.42547914385795593, | |
| "learning_rate": 7.935690663790787e-05, | |
| "loss": 1.5872, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.4642516682554814, | |
| "grad_norm": 0.45052269101142883, | |
| "learning_rate": 7.808274170987818e-05, | |
| "loss": 1.6048, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.4718779790276453, | |
| "grad_norm": 0.5102285742759705, | |
| "learning_rate": 7.682166620124017e-05, | |
| "loss": 1.6611, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.4795042897998094, | |
| "grad_norm": 0.3973918855190277, | |
| "learning_rate": 7.55738700253268e-05, | |
| "loss": 1.6591, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.4871306005719733, | |
| "grad_norm": 0.4221573770046234, | |
| "learning_rate": 7.43395410956525e-05, | |
| "loss": 1.5788, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.4947569113441372, | |
| "grad_norm": 0.38037997484207153, | |
| "learning_rate": 7.311886529761383e-05, | |
| "loss": 1.543, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.5023832221163014, | |
| "grad_norm": 0.3961423635482788, | |
| "learning_rate": 7.191202646049596e-05, | |
| "loss": 1.5559, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.510009532888465, | |
| "grad_norm": 0.40945950150489807, | |
| "learning_rate": 7.071920632978867e-05, | |
| "loss": 1.6016, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.5176358436606292, | |
| "grad_norm": 0.3885650038719177, | |
| "learning_rate": 6.954058453981609e-05, | |
| "loss": 1.587, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 1.5252621544327931, | |
| "grad_norm": 0.4135299623012543, | |
| "learning_rate": 6.837633858668448e-05, | |
| "loss": 1.6103, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.5252621544327931, | |
| "eval_loss": 1.6848325729370117, | |
| "eval_runtime": 0.2814, | |
| "eval_samples_per_second": 177.685, | |
| "eval_steps_per_second": 46.198, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.532888465204957, | |
| "grad_norm": 0.382758229970932, | |
| "learning_rate": 6.722664380155198e-05, | |
| "loss": 1.6259, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 1.5405147759771212, | |
| "grad_norm": 0.3803237974643707, | |
| "learning_rate": 6.609167332422427e-05, | |
| "loss": 1.5547, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 1.548141086749285, | |
| "grad_norm": 0.4076535701751709, | |
| "learning_rate": 6.497159807708055e-05, | |
| "loss": 1.5846, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 1.555767397521449, | |
| "grad_norm": 0.41619113087654114, | |
| "learning_rate": 6.386658673933301e-05, | |
| "loss": 1.6648, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 1.5633937082936131, | |
| "grad_norm": 0.4555559754371643, | |
| "learning_rate": 6.277680572162459e-05, | |
| "loss": 1.6636, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.5710200190657768, | |
| "grad_norm": 0.5715373158454895, | |
| "learning_rate": 6.170241914096804e-05, | |
| "loss": 1.7265, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 1.578646329837941, | |
| "grad_norm": 0.39986926317214966, | |
| "learning_rate": 6.06435887960305e-05, | |
| "loss": 1.614, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 1.5862726406101049, | |
| "grad_norm": 0.4014238119125366, | |
| "learning_rate": 5.960047414276724e-05, | |
| "loss": 1.5169, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 1.5938989513822688, | |
| "grad_norm": 0.40676450729370117, | |
| "learning_rate": 5.857323227040816e-05, | |
| "loss": 1.5836, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 1.601525262154433, | |
| "grad_norm": 0.38130614161491394, | |
| "learning_rate": 5.756201787780074e-05, | |
| "loss": 1.5636, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.6091515729265966, | |
| "grad_norm": 0.4001769721508026, | |
| "learning_rate": 5.656698325011295e-05, | |
| "loss": 1.5641, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 1.6167778836987607, | |
| "grad_norm": 0.3762960433959961, | |
| "learning_rate": 5.5588278235899724e-05, | |
| "loss": 1.615, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 1.6244041944709247, | |
| "grad_norm": 0.372916042804718, | |
| "learning_rate": 5.462605022453621e-05, | |
| "loss": 1.6307, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 1.6320305052430886, | |
| "grad_norm": 0.4022381603717804, | |
| "learning_rate": 5.368044412402161e-05, | |
| "loss": 1.5634, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 1.6396568160152527, | |
| "grad_norm": 0.39602571725845337, | |
| "learning_rate": 5.275160233915637e-05, | |
| "loss": 1.6328, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.6472831267874166, | |
| "grad_norm": 0.4366743266582489, | |
| "learning_rate": 5.183966475009686e-05, | |
| "loss": 1.6038, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.6549094375595805, | |
| "grad_norm": 0.458132803440094, | |
| "learning_rate": 5.0944768691289534e-05, | |
| "loss": 1.6384, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 1.6625357483317447, | |
| "grad_norm": 0.4853437840938568, | |
| "learning_rate": 5.0067048930789196e-05, | |
| "loss": 1.6787, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 1.6701620591039084, | |
| "grad_norm": 0.4034062325954437, | |
| "learning_rate": 4.920663764996328e-05, | |
| "loss": 1.5721, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 1.6777883698760725, | |
| "grad_norm": 0.4523112177848816, | |
| "learning_rate": 4.8363664423585795e-05, | |
| "loss": 1.6327, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.6854146806482364, | |
| "grad_norm": 0.4193178415298462, | |
| "learning_rate": 4.753825620032397e-05, | |
| "loss": 1.5354, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 1.6930409914204003, | |
| "grad_norm": 0.3819790482521057, | |
| "learning_rate": 4.673053728362012e-05, | |
| "loss": 1.5833, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 1.7006673021925645, | |
| "grad_norm": 0.3742893636226654, | |
| "learning_rate": 4.5940629312972085e-05, | |
| "loss": 1.5805, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 1.7082936129647281, | |
| "grad_norm": 0.37698328495025635, | |
| "learning_rate": 4.516865124561473e-05, | |
| "loss": 1.5632, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.7159199237368923, | |
| "grad_norm": 0.39410701394081116, | |
| "learning_rate": 4.4414719338605445e-05, | |
| "loss": 1.6016, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.7159199237368923, | |
| "eval_loss": 1.6763724088668823, | |
| "eval_runtime": 0.281, | |
| "eval_samples_per_second": 177.963, | |
| "eval_steps_per_second": 46.27, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.7235462345090562, | |
| "grad_norm": 0.41081416606903076, | |
| "learning_rate": 4.367894713131622e-05, | |
| "loss": 1.5998, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 1.73117254528122, | |
| "grad_norm": 0.4001181721687317, | |
| "learning_rate": 4.296144542833515e-05, | |
| "loss": 1.6213, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 1.7387988560533842, | |
| "grad_norm": 0.4368586242198944, | |
| "learning_rate": 4.226232228277948e-05, | |
| "loss": 1.6338, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 1.7464251668255482, | |
| "grad_norm": 0.4104710817337036, | |
| "learning_rate": 4.1581682980023354e-05, | |
| "loss": 1.6433, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 1.754051477597712, | |
| "grad_norm": 0.4876128137111664, | |
| "learning_rate": 4.0919630021842204e-05, | |
| "loss": 1.6381, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.7616777883698762, | |
| "grad_norm": 0.5875245332717896, | |
| "learning_rate": 4.027626311097629e-05, | |
| "loss": 1.7134, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 1.76930409914204, | |
| "grad_norm": 0.40997183322906494, | |
| "learning_rate": 3.965167913611591e-05, | |
| "loss": 1.5599, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 1.776930409914204, | |
| "grad_norm": 0.42695024609565735, | |
| "learning_rate": 3.9045972157310256e-05, | |
| "loss": 1.5685, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 1.784556720686368, | |
| "grad_norm": 0.4017082452774048, | |
| "learning_rate": 3.845923339180239e-05, | |
| "loss": 1.5493, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 1.7921830314585319, | |
| "grad_norm": 0.38347816467285156, | |
| "learning_rate": 3.78915512002922e-05, | |
| "loss": 1.5464, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.799809342230696, | |
| "grad_norm": 0.40365535020828247, | |
| "learning_rate": 3.734301107362964e-05, | |
| "loss": 1.6257, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 1.80743565300286, | |
| "grad_norm": 0.3748120963573456, | |
| "learning_rate": 3.681369561994005e-05, | |
| "loss": 1.5456, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 1.8150619637750238, | |
| "grad_norm": 0.36911335587501526, | |
| "learning_rate": 3.6303684552183827e-05, | |
| "loss": 1.5886, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 1.822688274547188, | |
| "grad_norm": 0.3796713948249817, | |
| "learning_rate": 3.581305467615181e-05, | |
| "loss": 1.5858, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 1.8303145853193517, | |
| "grad_norm": 0.4003843665122986, | |
| "learning_rate": 3.5341879878898615e-05, | |
| "loss": 1.6126, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.8379408960915158, | |
| "grad_norm": 0.4427483379840851, | |
| "learning_rate": 3.489023111761562e-05, | |
| "loss": 1.6487, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 1.8455672068636797, | |
| "grad_norm": 0.4299188554286957, | |
| "learning_rate": 3.445817640894497e-05, | |
| "loss": 1.6723, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 1.8531935176358436, | |
| "grad_norm": 0.5241357684135437, | |
| "learning_rate": 3.404578081873656e-05, | |
| "loss": 1.6198, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 1.8608198284080077, | |
| "grad_norm": 0.40499526262283325, | |
| "learning_rate": 3.365310645224939e-05, | |
| "loss": 1.5758, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 1.8684461391801714, | |
| "grad_norm": 0.43495872616767883, | |
| "learning_rate": 3.328021244479866e-05, | |
| "loss": 1.5897, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.8760724499523356, | |
| "grad_norm": 0.39778581261634827, | |
| "learning_rate": 3.292715495285028e-05, | |
| "loss": 1.5267, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 1.8836987607244995, | |
| "grad_norm": 0.3671037256717682, | |
| "learning_rate": 3.259398714556389e-05, | |
| "loss": 1.5499, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 1.8913250714966634, | |
| "grad_norm": 0.38671308755874634, | |
| "learning_rate": 3.2280759196785803e-05, | |
| "loss": 1.628, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 1.8989513822688275, | |
| "grad_norm": 0.41623926162719727, | |
| "learning_rate": 3.1987518277492934e-05, | |
| "loss": 1.5699, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 1.9065776930409915, | |
| "grad_norm": 0.38484105467796326, | |
| "learning_rate": 3.171430854868911e-05, | |
| "loss": 1.5702, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.9065776930409915, | |
| "eval_loss": 1.6708096265792847, | |
| "eval_runtime": 0.2807, | |
| "eval_samples_per_second": 178.136, | |
| "eval_steps_per_second": 46.315, | |
| "step": 250 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 263, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.11070068867072e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |