| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9956108266276518, | |
| "eval_steps": 500, | |
| "global_step": 1023, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029261155815654718, | |
| "grad_norm": 8.98854305134706, | |
| "learning_rate": 9.615384615384617e-07, | |
| "loss": 0.886, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.058522311631309436, | |
| "grad_norm": 2.172535983028044, | |
| "learning_rate": 1.9230769230769234e-06, | |
| "loss": 0.8326, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08778346744696415, | |
| "grad_norm": 173647.7881486052, | |
| "learning_rate": 2.8846153846153845e-06, | |
| "loss": 1.1121, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11704462326261887, | |
| "grad_norm": 1.2197795451638063, | |
| "learning_rate": 3.846153846153847e-06, | |
| "loss": 0.7357, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14630577907827358, | |
| "grad_norm": 1.2235462186510278, | |
| "learning_rate": 4.807692307692308e-06, | |
| "loss": 0.717, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1755669348939283, | |
| "grad_norm": 1.1500264823307949, | |
| "learning_rate": 4.999246350291281e-06, | |
| "loss": 0.7008, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.20482809070958302, | |
| "grad_norm": 1.0809398356246653, | |
| "learning_rate": 4.996185513623117e-06, | |
| "loss": 0.6883, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23408924652523774, | |
| "grad_norm": 0.8102596570656748, | |
| "learning_rate": 4.9907735882096915e-06, | |
| "loss": 0.6773, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26335040234089246, | |
| "grad_norm": 0.6041123421413714, | |
| "learning_rate": 4.983016238728676e-06, | |
| "loss": 0.6693, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.29261155815654716, | |
| "grad_norm": 0.4679255906368303, | |
| "learning_rate": 4.9729215848197685e-06, | |
| "loss": 0.6593, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3218727139722019, | |
| "grad_norm": 0.379578037990065, | |
| "learning_rate": 4.960500192585831e-06, | |
| "loss": 0.6672, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3511338697878566, | |
| "grad_norm": 0.3628760977145694, | |
| "learning_rate": 4.945765063533333e-06, | |
| "loss": 0.6715, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.38039502560351135, | |
| "grad_norm": 0.3970159780765436, | |
| "learning_rate": 4.928731620963628e-06, | |
| "loss": 0.655, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.40965618141916604, | |
| "grad_norm": 0.3716740167179648, | |
| "learning_rate": 4.909417693829346e-06, | |
| "loss": 0.6553, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4389173372348208, | |
| "grad_norm": 0.34641025541861964, | |
| "learning_rate": 4.887843498072774e-06, | |
| "loss": 0.6505, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4681784930504755, | |
| "grad_norm": 0.3923741109320672, | |
| "learning_rate": 4.864031615465776e-06, | |
| "loss": 0.6522, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.49743964886613024, | |
| "grad_norm": 0.36292753209283274, | |
| "learning_rate": 4.838006969973388e-06, | |
| "loss": 0.6571, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5267008046817849, | |
| "grad_norm": 0.3376680362849002, | |
| "learning_rate": 4.809796801665825e-06, | |
| "loss": 0.6566, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5559619604974396, | |
| "grad_norm": 0.36203567203579706, | |
| "learning_rate": 4.779430638206237e-06, | |
| "loss": 0.645, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5852231163130943, | |
| "grad_norm": 0.3408562846700468, | |
| "learning_rate": 4.746940263944006e-06, | |
| "loss": 0.6461, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6144842721287491, | |
| "grad_norm": 0.33889751456302075, | |
| "learning_rate": 4.712359686645986e-06, | |
| "loss": 0.6526, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6437454279444038, | |
| "grad_norm": 0.35041172201449083, | |
| "learning_rate": 4.675725101900474e-06, | |
| "loss": 0.6404, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6730065837600585, | |
| "grad_norm": 0.3526449799646731, | |
| "learning_rate": 4.637074855231186e-06, | |
| "loss": 0.6403, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.7022677395757132, | |
| "grad_norm": 0.32110885822251356, | |
| "learning_rate": 4.596449401960888e-06, | |
| "loss": 0.6471, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.731528895391368, | |
| "grad_norm": 0.3431192477294489, | |
| "learning_rate": 4.553891264866696e-06, | |
| "loss": 0.6454, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7607900512070227, | |
| "grad_norm": 0.34368046757987986, | |
| "learning_rate": 4.509444989671361e-06, | |
| "loss": 0.6481, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.7900512070226774, | |
| "grad_norm": 0.37897239974426505, | |
| "learning_rate": 4.463157098417141e-06, | |
| "loss": 0.6503, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.8193123628383321, | |
| "grad_norm": 0.35185141428324446, | |
| "learning_rate": 4.415076040771041e-06, | |
| "loss": 0.6491, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.8485735186539868, | |
| "grad_norm": 0.333333492720985, | |
| "learning_rate": 4.365252143312415e-06, | |
| "loss": 0.6412, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.8778346744696416, | |
| "grad_norm": 0.34730525842530574, | |
| "learning_rate": 4.313737556855987e-06, | |
| "loss": 0.6331, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9070958302852963, | |
| "grad_norm": 0.35101537112120373, | |
| "learning_rate": 4.260586201865451e-06, | |
| "loss": 0.6461, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.936356986100951, | |
| "grad_norm": 0.3265112519469777, | |
| "learning_rate": 4.205853712014766e-06, | |
| "loss": 0.638, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.9656181419166057, | |
| "grad_norm": 0.37750068013169596, | |
| "learning_rate": 4.149597375956228e-06, | |
| "loss": 0.6413, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.9948792977322605, | |
| "grad_norm": 0.3525928158653123, | |
| "learning_rate": 4.0918760773562825e-06, | |
| "loss": 0.6373, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.9978054133138259, | |
| "eval_loss": 0.6418758034706116, | |
| "eval_runtime": 344.0656, | |
| "eval_samples_per_second": 26.765, | |
| "eval_steps_per_second": 0.419, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 1.025237746891002, | |
| "grad_norm": 0.36230468002056376, | |
| "learning_rate": 4.03275023326182e-06, | |
| "loss": 0.655, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.054498902706657, | |
| "grad_norm": 0.3782311966663319, | |
| "learning_rate": 3.972281730861482e-06, | |
| "loss": 0.6096, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.0837600585223117, | |
| "grad_norm": 0.3642553214435278, | |
| "learning_rate": 3.910533862708164e-06, | |
| "loss": 0.613, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.1130212143379663, | |
| "grad_norm": 0.31097337637296735, | |
| "learning_rate": 3.847571260470523e-06, | |
| "loss": 0.6101, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.142282370153621, | |
| "grad_norm": 0.38535301593017185, | |
| "learning_rate": 3.783459827282829e-06, | |
| "loss": 0.6155, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.1715435259692757, | |
| "grad_norm": 0.34644899266963136, | |
| "learning_rate": 3.718266668763958e-06, | |
| "loss": 0.617, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.2008046817849305, | |
| "grad_norm": 0.3594372904896393, | |
| "learning_rate": 3.652060022777762e-06, | |
| "loss": 0.6166, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.2300658376005853, | |
| "grad_norm": 0.34202267838177935, | |
| "learning_rate": 3.5849091880082976e-06, | |
| "loss": 0.6046, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.2593269934162399, | |
| "grad_norm": 0.3209790424989277, | |
| "learning_rate": 3.516884451424696e-06, | |
| "loss": 0.6148, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.2885881492318947, | |
| "grad_norm": 0.39145882313544417, | |
| "learning_rate": 3.448057014711598e-06, | |
| "loss": 0.6072, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.3178493050475493, | |
| "grad_norm": 0.33748028752444753, | |
| "learning_rate": 3.3784989197421414e-06, | |
| "loss": 0.6111, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.347110460863204, | |
| "grad_norm": 0.32484250673480136, | |
| "learning_rate": 3.3082829731715353e-06, | |
| "loss": 0.6086, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.3763716166788589, | |
| "grad_norm": 0.31957432344924297, | |
| "learning_rate": 3.237482670230125e-06, | |
| "loss": 0.6059, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.4056327724945135, | |
| "grad_norm": 0.33076862820101466, | |
| "learning_rate": 3.1661721177957238e-06, | |
| "loss": 0.6065, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.4348939283101683, | |
| "grad_norm": 0.3542135461787459, | |
| "learning_rate": 3.0944259568257374e-06, | |
| "loss": 0.6128, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.464155084125823, | |
| "grad_norm": 0.3358725180392758, | |
| "learning_rate": 3.022319284230261e-06, | |
| "loss": 0.6013, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.4934162399414777, | |
| "grad_norm": 0.33010342462196535, | |
| "learning_rate": 2.9499275742679303e-06, | |
| "loss": 0.6093, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.5226773957571325, | |
| "grad_norm": 0.3349440152012161, | |
| "learning_rate": 2.8773265995467975e-06, | |
| "loss": 0.6116, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.5519385515727873, | |
| "grad_norm": 0.3347770675456349, | |
| "learning_rate": 2.804592351712937e-06, | |
| "loss": 0.6102, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.5811997073884418, | |
| "grad_norm": 0.32807277985651556, | |
| "learning_rate": 2.731800961909764e-06, | |
| "loss": 0.6168, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.6104608632040964, | |
| "grad_norm": 0.34394938763944105, | |
| "learning_rate": 2.6590286210913557e-06, | |
| "loss": 0.6076, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.6397220190197512, | |
| "grad_norm": 0.3338905788072409, | |
| "learning_rate": 2.5863515002731645e-06, | |
| "loss": 0.6094, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.668983174835406, | |
| "grad_norm": 0.3264863178278298, | |
| "learning_rate": 2.5138456708035952e-06, | |
| "loss": 0.5999, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.6982443306510606, | |
| "grad_norm": 0.33312679764478187, | |
| "learning_rate": 2.441587024739917e-06, | |
| "loss": 0.6095, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.7275054864667154, | |
| "grad_norm": 0.32189993245032417, | |
| "learning_rate": 2.3696511954118236e-06, | |
| "loss": 0.6092, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.7567666422823702, | |
| "grad_norm": 0.3406006209905999, | |
| "learning_rate": 2.2981134782558192e-06, | |
| "loss": 0.6063, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.7860277980980248, | |
| "grad_norm": 0.3523904881790879, | |
| "learning_rate": 2.2270487520032656e-06, | |
| "loss": 0.6087, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.8152889539136796, | |
| "grad_norm": 0.31402762046992583, | |
| "learning_rate": 2.1565314003046083e-06, | |
| "loss": 0.609, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.8445501097293344, | |
| "grad_norm": 0.3205352263710775, | |
| "learning_rate": 2.0866352338717924e-06, | |
| "loss": 0.6082, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.873811265544989, | |
| "grad_norm": 0.31888506747610823, | |
| "learning_rate": 2.0174334132203865e-06, | |
| "loss": 0.603, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.9030724213606436, | |
| "grad_norm": 0.3364346855436591, | |
| "learning_rate": 1.9489983720922596e-06, | |
| "loss": 0.6087, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.9323335771762986, | |
| "grad_norm": 0.3188456233134923, | |
| "learning_rate": 1.8814017416389813e-06, | |
| "loss": 0.6093, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.9615947329919532, | |
| "grad_norm": 0.32907133034135566, | |
| "learning_rate": 1.8147142754452888e-06, | |
| "loss": 0.598, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.9908558888076078, | |
| "grad_norm": 0.3137569353732775, | |
| "learning_rate": 1.7490057754711138e-06, | |
| "loss": 0.6126, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.9967081199707388, | |
| "eval_loss": 0.634891152381897, | |
| "eval_runtime": 343.5767, | |
| "eval_samples_per_second": 26.803, | |
| "eval_steps_per_second": 0.419, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 2.0212143379663496, | |
| "grad_norm": 0.3203598916756129, | |
| "learning_rate": 1.6843450189896675e-06, | |
| "loss": 0.6316, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.050475493782004, | |
| "grad_norm": 0.3121584618138378, | |
| "learning_rate": 1.620799686598081e-06, | |
| "loss": 0.5826, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.0797366495976592, | |
| "grad_norm": 0.3077301379603627, | |
| "learning_rate": 1.558436291375923e-06, | |
| "loss": 0.5847, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.108997805413314, | |
| "grad_norm": 0.32533505697453335, | |
| "learning_rate": 1.497320109265781e-06, | |
| "loss": 0.5857, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.1382589612289684, | |
| "grad_norm": 0.3195086645547528, | |
| "learning_rate": 1.4375151107487388e-06, | |
| "loss": 0.5873, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.1675201170446234, | |
| "grad_norm": 0.3330446987320431, | |
| "learning_rate": 1.3790838938862973e-06, | |
| "loss": 0.5922, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.196781272860278, | |
| "grad_norm": 0.3299155176826055, | |
| "learning_rate": 1.3220876187988046e-06, | |
| "loss": 0.5909, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.2260424286759326, | |
| "grad_norm": 0.3434531818196139, | |
| "learning_rate": 1.2665859436489852e-06, | |
| "loss": 0.5879, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.255303584491587, | |
| "grad_norm": 0.3055793504536637, | |
| "learning_rate": 1.2126369621975703e-06, | |
| "loss": 0.5863, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.284564740307242, | |
| "grad_norm": 0.32739465865049094, | |
| "learning_rate": 1.1602971429963966e-06, | |
| "loss": 0.5856, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.313825896122897, | |
| "grad_norm": 0.30600023197231446, | |
| "learning_rate": 1.1096212702826087e-06, | |
| "loss": 0.5837, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.3430870519385514, | |
| "grad_norm": 0.3167798036799912, | |
| "learning_rate": 1.0606623866358496e-06, | |
| "loss": 0.5913, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.3723482077542064, | |
| "grad_norm": 0.30861506318915694, | |
| "learning_rate": 1.0134717374584333e-06, | |
| "loss": 0.5863, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.401609363569861, | |
| "grad_norm": 0.3282720702061679, | |
| "learning_rate": 9.680987173366452e-07, | |
| "loss": 0.5925, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.4308705193855156, | |
| "grad_norm": 0.295462519102209, | |
| "learning_rate": 9.245908183392827e-07, | |
| "loss": 0.5849, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.4601316752011706, | |
| "grad_norm": 0.3027364063325311, | |
| "learning_rate": 8.829935803075765e-07, | |
| "loss": 0.5851, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.489392831016825, | |
| "grad_norm": 0.3129238717661994, | |
| "learning_rate": 8.433505431885053e-07, | |
| "loss": 0.5869, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.5186539868324798, | |
| "grad_norm": 0.31616510805578135, | |
| "learning_rate": 8.057032014614151e-07, | |
| "loss": 0.58, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.547915142648135, | |
| "grad_norm": 0.3063728049938137, | |
| "learning_rate": 7.700909607056239e-07, | |
| "loss": 0.5824, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.5771762984637894, | |
| "grad_norm": 0.29740345091723525, | |
| "learning_rate": 7.365510963544958e-07, | |
| "loss": 0.5864, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.606437454279444, | |
| "grad_norm": 0.30981329357585746, | |
| "learning_rate": 7.05118714679136e-07, | |
| "loss": 0.5858, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.6356986100950985, | |
| "grad_norm": 0.30780806957740076, | |
| "learning_rate": 6.758267160425574e-07, | |
| "loss": 0.5904, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.6649597659107536, | |
| "grad_norm": 0.31109647888764025, | |
| "learning_rate": 6.487057604627791e-07, | |
| "loss": 0.5906, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.694220921726408, | |
| "grad_norm": 0.32083524501934124, | |
| "learning_rate": 6.237842355208961e-07, | |
| "loss": 0.5846, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.723482077542063, | |
| "grad_norm": 0.31324844821827436, | |
| "learning_rate": 6.010882266477213e-07, | |
| "loss": 0.5881, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.7527432333577178, | |
| "grad_norm": 0.3175561726099663, | |
| "learning_rate": 5.806414898200865e-07, | |
| "loss": 0.5871, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.7820043891733723, | |
| "grad_norm": 0.2984100866178075, | |
| "learning_rate": 5.62465426695398e-07, | |
| "loss": 0.5857, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.811265544989027, | |
| "grad_norm": 0.304486800782011, | |
| "learning_rate": 5.465790622104596e-07, | |
| "loss": 0.5896, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.840526700804682, | |
| "grad_norm": 0.29859411604012787, | |
| "learning_rate": 5.329990246680166e-07, | |
| "loss": 0.5853, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.8697878566203365, | |
| "grad_norm": 0.3044740888118332, | |
| "learning_rate": 5.21739528331866e-07, | |
| "loss": 0.5851, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.899049012435991, | |
| "grad_norm": 0.3038848632087947, | |
| "learning_rate": 5.128123585487441e-07, | |
| "loss": 0.5779, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.928310168251646, | |
| "grad_norm": 0.30622813167771706, | |
| "learning_rate": 5.062268594125722e-07, | |
| "loss": 0.5858, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.9575713240673007, | |
| "grad_norm": 0.3068908017681571, | |
| "learning_rate": 5.01989923983967e-07, | |
| "loss": 0.5771, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.9868324798829553, | |
| "grad_norm": 0.3045684042515058, | |
| "learning_rate": 5.00105987075254e-07, | |
| "loss": 0.5891, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.9956108266276518, | |
| "eval_loss": 0.6350145936012268, | |
| "eval_runtime": 341.4521, | |
| "eval_samples_per_second": 26.97, | |
| "eval_steps_per_second": 0.422, | |
| "step": 1023 | |
| }, | |
| { | |
| "epoch": 2.9956108266276518, | |
| "step": 1023, | |
| "total_flos": 2144987064041472.0, | |
| "train_loss": 0.6271805009301223, | |
| "train_runtime": 55047.6195, | |
| "train_samples_per_second": 9.535, | |
| "train_steps_per_second": 0.019 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1023, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 2144987064041472.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |