| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 25, |
| "global_step": 125, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.26390790939331055, |
| "learning_rate": 0.0, |
| "loss": 1.6865234375, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.2454238384962082, |
| "learning_rate": 1.4285714285714285e-05, |
| "loss": 1.599609375, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.22271081805229187, |
| "learning_rate": 2.857142857142857e-05, |
| "loss": 1.4794921875, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.19336532056331635, |
| "learning_rate": 4.2857142857142856e-05, |
| "loss": 1.352294921875, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.16627004742622375, |
| "learning_rate": 5.714285714285714e-05, |
| "loss": 1.4140625, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.13205529749393463, |
| "learning_rate": 7.142857142857143e-05, |
| "loss": 1.505859375, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.11557494848966599, |
| "learning_rate": 8.571428571428571e-05, |
| "loss": 1.4794921875, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.1853453367948532, |
| "learning_rate": 0.0001, |
| "loss": 1.357421875, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.22436703741550446, |
| "learning_rate": 9.998405250055537e-05, |
| "loss": 1.35546875, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.1823885589838028, |
| "learning_rate": 9.99362213054543e-05, |
| "loss": 1.345703125, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.1173536404967308, |
| "learning_rate": 9.985654031638374e-05, |
| "loss": 1.337890625, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.2616179287433624, |
| "learning_rate": 9.974506600945618e-05, |
| "loss": 1.19580078125, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.07653592526912689, |
| "learning_rate": 9.960187739518034e-05, |
| "loss": 1.326171875, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.08414878696203232, |
| "learning_rate": 9.942707596246052e-05, |
| "loss": 1.30078125, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.07239817082881927, |
| "learning_rate": 9.922078560666345e-05, |
| "loss": 1.29638671875, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.06605315208435059, |
| "learning_rate": 9.8983152541804e-05, |
| "loss": 1.3271484375, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.0644218698143959, |
| "learning_rate": 9.871434519691195e-05, |
| "loss": 1.3544921875, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.052547309547662735, |
| "learning_rate": 9.841455409665323e-05, |
| "loss": 1.279296875, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.04991060495376587, |
| "learning_rate": 9.808399172629024e-05, |
| "loss": 1.28076171875, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.04158128425478935, |
| "learning_rate": 9.772289238107715e-05, |
| "loss": 1.13555908203125, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.04418198764324188, |
| "learning_rate": 9.73315120001965e-05, |
| "loss": 1.2900390625, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.04845346882939339, |
| "learning_rate": 9.691012798535524e-05, |
| "loss": 1.2900390625, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.03777270019054413, |
| "learning_rate": 9.645903900416858e-05, |
| "loss": 1.094970703125, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.06004459783434868, |
| "learning_rate": 9.59785647784711e-05, |
| "loss": 1.20166015625, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.03927459940314293, |
| "learning_rate": 9.546904585770487e-05, |
| "loss": 1.2392578125, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.25, |
| "eval_runtime": 5.5433, |
| "eval_samples_per_second": 0.541, |
| "eval_steps_per_second": 0.18, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.04, |
| "grad_norm": 0.035955242812633514, |
| "learning_rate": 9.493084337754573e-05, |
| "loss": 1.2509765625, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.08, |
| "grad_norm": 0.03168688714504242, |
| "learning_rate": 9.436433880393825e-05, |
| "loss": 1.21630859375, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.12, |
| "grad_norm": 0.03548814356327057, |
| "learning_rate": 9.376993366272128e-05, |
| "loss": 1.150390625, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.16, |
| "grad_norm": 0.0294770710170269, |
| "learning_rate": 9.314804925503519e-05, |
| "loss": 1.048828125, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 0.03293508663773537, |
| "learning_rate": 9.249912635871318e-05, |
| "loss": 1.14013671875, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.24, |
| "grad_norm": 0.03127572685480118, |
| "learning_rate": 9.18236249158676e-05, |
| "loss": 1.2470703125, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.28, |
| "grad_norm": 0.03355073928833008, |
| "learning_rate": 9.112202370689337e-05, |
| "loss": 1.2431640625, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.32, |
| "grad_norm": 0.026585428044199944, |
| "learning_rate": 9.039482001111892e-05, |
| "loss": 1.1845703125, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.3599999999999999, |
| "grad_norm": 0.02719985879957676, |
| "learning_rate": 8.964252925434579e-05, |
| "loss": 1.1826171875, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 0.031090417876839638, |
| "learning_rate": 8.886568464352622e-05, |
| "loss": 1.18408203125, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.44, |
| "grad_norm": 0.03240831941366196, |
| "learning_rate": 8.806483678883803e-05, |
| "loss": 1.203125, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.48, |
| "grad_norm": 0.1718246340751648, |
| "learning_rate": 8.724055331342418e-05, |
| "loss": 1.0579833984375, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.52, |
| "grad_norm": 0.026359252631664276, |
| "learning_rate": 8.639341845107433e-05, |
| "loss": 1.1962890625, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.56, |
| "grad_norm": 0.027787871658802032, |
| "learning_rate": 8.552403263213273e-05, |
| "loss": 1.17431640625, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 0.025798646733164787, |
| "learning_rate": 8.463301205792675e-05, |
| "loss": 1.18310546875, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6400000000000001, |
| "grad_norm": 0.028164571151137352, |
| "learning_rate": 8.37209882640169e-05, |
| "loss": 1.2138671875, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6800000000000002, |
| "grad_norm": 0.026374800130724907, |
| "learning_rate": 8.278860767257865e-05, |
| "loss": 1.2392578125, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.72, |
| "grad_norm": 0.025469204410910606, |
| "learning_rate": 8.183653113423256e-05, |
| "loss": 1.1796875, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.76, |
| "grad_norm": 0.027462013065814972, |
| "learning_rate": 8.086543345964832e-05, |
| "loss": 1.1826171875, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 0.0265539288520813, |
| "learning_rate": 7.98760029412537e-05, |
| "loss": 1.04962158203125, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.8399999999999999, |
| "grad_norm": 0.031078847125172615, |
| "learning_rate": 7.886894086538841e-05, |
| "loss": 1.2001953125, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.88, |
| "grad_norm": 0.05968401953577995, |
| "learning_rate": 7.78449610152478e-05, |
| "loss": 1.2060546875, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.92, |
| "grad_norm": 0.024476436898112297, |
| "learning_rate": 7.680478916496926e-05, |
| "loss": 1.0191650390625, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.96, |
| "grad_norm": 0.028241803869605064, |
| "learning_rate": 7.574916256521966e-05, |
| "loss": 1.12451171875, |
| "step": 49 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.027942068874835968, |
| "learning_rate": 7.46788294206485e-05, |
| "loss": 1.16015625, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.1845703125, |
| "eval_runtime": 5.5398, |
| "eval_samples_per_second": 0.542, |
| "eval_steps_per_second": 0.181, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.04, |
| "grad_norm": 0.02665187604725361, |
| "learning_rate": 7.359454835957703e-05, |
| "loss": 1.17333984375, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.08, |
| "grad_norm": 0.02502899430692196, |
| "learning_rate": 7.249708789629944e-05, |
| "loss": 1.1455078125, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.12, |
| "grad_norm": 0.027301136404275894, |
| "learning_rate": 7.138722588637701e-05, |
| "loss": 1.087890625, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.16, |
| "grad_norm": 0.023596517741680145, |
| "learning_rate": 7.026574897531137e-05, |
| "loss": 0.9910888671875, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.2, |
| "grad_norm": 0.02656257338821888, |
| "learning_rate": 6.913345204098771e-05, |
| "loss": 1.0791015625, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.24, |
| "grad_norm": 0.028178155422210693, |
| "learning_rate": 6.799113763028295e-05, |
| "loss": 1.18212890625, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.2800000000000002, |
| "grad_norm": 0.029637563973665237, |
| "learning_rate": 6.683961539023846e-05, |
| "loss": 1.181640625, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.32, |
| "grad_norm": 0.025217480957508087, |
| "learning_rate": 6.567970149420018e-05, |
| "loss": 1.13232421875, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.36, |
| "grad_norm": 0.028920279815793037, |
| "learning_rate": 6.451221806333309e-05, |
| "loss": 1.125, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 0.029677610844373703, |
| "learning_rate": 6.333799258392015e-05, |
| "loss": 1.12939453125, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.44, |
| "grad_norm": 0.02719406969845295, |
| "learning_rate": 6.215785732085823e-05, |
| "loss": 1.1474609375, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.48, |
| "grad_norm": 0.027548035606741905, |
| "learning_rate": 6.097264872776749e-05, |
| "loss": 1.005615234375, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.52, |
| "grad_norm": 0.029119368642568588, |
| "learning_rate": 5.9783206854131446e-05, |
| "loss": 1.1455078125, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.56, |
| "grad_norm": 0.02879447117447853, |
| "learning_rate": 5.859037474988874e-05, |
| "loss": 1.1201171875, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.6, |
| "grad_norm": 0.026569705456495285, |
| "learning_rate": 5.739499786789804e-05, |
| "loss": 1.1337890625, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.64, |
| "grad_norm": 0.029205532744526863, |
| "learning_rate": 5.6197923464699875e-05, |
| "loss": 1.16259765625, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.68, |
| "grad_norm": 0.030185790732502937, |
| "learning_rate": 5.500000000000001e-05, |
| "loss": 1.1865234375, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.7199999999999998, |
| "grad_norm": 0.028211696073412895, |
| "learning_rate": 5.3802076535300135e-05, |
| "loss": 1.13525390625, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.76, |
| "grad_norm": 0.029403535649180412, |
| "learning_rate": 5.260500213210198e-05, |
| "loss": 1.134765625, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 0.028107278048992157, |
| "learning_rate": 5.140962525011126e-05, |
| "loss": 1.00628662109375, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.84, |
| "grad_norm": 0.028998220339417458, |
| "learning_rate": 5.021679314586857e-05, |
| "loss": 1.1533203125, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.88, |
| "grad_norm": 0.031040361151099205, |
| "learning_rate": 4.902735127223252e-05, |
| "loss": 1.1630859375, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.92, |
| "grad_norm": 0.03426837921142578, |
| "learning_rate": 4.784214267914176e-05, |
| "loss": 0.98297119140625, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.96, |
| "grad_norm": 0.029938703402876854, |
| "learning_rate": 4.6662007416079864e-05, |
| "loss": 1.083984375, |
| "step": 74 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.030603986233472824, |
| "learning_rate": 4.5487781936666905e-05, |
| "loss": 1.1181640625, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 1.1552734375, |
| "eval_runtime": 5.5347, |
| "eval_samples_per_second": 0.542, |
| "eval_steps_per_second": 0.181, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.04, |
| "grad_norm": 0.029790814965963364, |
| "learning_rate": 4.432029850579983e-05, |
| "loss": 1.12841796875, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.08, |
| "grad_norm": 0.028323808684945107, |
| "learning_rate": 4.3160384609761553e-05, |
| "loss": 1.10888671875, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.12, |
| "grad_norm": 0.029373057186603546, |
| "learning_rate": 4.2008862369717074e-05, |
| "loss": 1.05078125, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.16, |
| "grad_norm": 0.026257459074258804, |
| "learning_rate": 4.0866547959012323e-05, |
| "loss": 0.959228515625, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.029043566435575485, |
| "learning_rate": 3.973425102468864e-05, |
| "loss": 1.044921875, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.24, |
| "grad_norm": 0.030435359105467796, |
| "learning_rate": 3.8612774113623005e-05, |
| "loss": 1.14697265625, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2800000000000002, |
| "grad_norm": 0.03247416019439697, |
| "learning_rate": 3.750291210370057e-05, |
| "loss": 1.1474609375, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.32, |
| "grad_norm": 0.026650382205843925, |
| "learning_rate": 3.640545164042299e-05, |
| "loss": 1.1005859375, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.36, |
| "grad_norm": 0.030787037685513496, |
| "learning_rate": 3.5321170579351516e-05, |
| "loss": 1.09228515625, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.4, |
| "grad_norm": 0.031921789050102234, |
| "learning_rate": 3.425083743478033e-05, |
| "loss": 1.09814453125, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.44, |
| "grad_norm": 0.02883104793727398, |
| "learning_rate": 3.319521083503075e-05, |
| "loss": 1.1181640625, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.48, |
| "grad_norm": 0.0299820676445961, |
| "learning_rate": 3.2155038984752214e-05, |
| "loss": 0.978271484375, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.52, |
| "grad_norm": 0.030900180339813232, |
| "learning_rate": 3.113105913461159e-05, |
| "loss": 1.1142578125, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.56, |
| "grad_norm": 0.03309555724263191, |
| "learning_rate": 3.0123997058746312e-05, |
| "loss": 1.08984375, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.6, |
| "grad_norm": 0.030469032004475594, |
| "learning_rate": 2.9134566540351693e-05, |
| "loss": 1.1064453125, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.64, |
| "grad_norm": 0.031541455537080765, |
| "learning_rate": 2.8163468865767434e-05, |
| "loss": 1.13427734375, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.68, |
| "grad_norm": 0.0324467197060585, |
| "learning_rate": 2.721139232742137e-05, |
| "loss": 1.16015625, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.7199999999999998, |
| "grad_norm": 0.0315207876265049, |
| "learning_rate": 2.627901173598311e-05, |
| "loss": 1.10888671875, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.76, |
| "grad_norm": 0.03146296367049217, |
| "learning_rate": 2.5366987942073267e-05, |
| "loss": 1.10791015625, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.8, |
| "grad_norm": 0.03044731356203556, |
| "learning_rate": 2.4475967367867277e-05, |
| "loss": 0.98455810546875, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.84, |
| "grad_norm": 0.032733574509620667, |
| "learning_rate": 2.3606581548925695e-05, |
| "loss": 1.126953125, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.88, |
| "grad_norm": 0.03317149356007576, |
| "learning_rate": 2.275944668657582e-05, |
| "loss": 1.140625, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.92, |
| "grad_norm": 0.02901167795062065, |
| "learning_rate": 2.1935163211161985e-05, |
| "loss": 0.96136474609375, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.96, |
| "grad_norm": 0.030736200511455536, |
| "learning_rate": 2.113431535647377e-05, |
| "loss": 1.0595703125, |
| "step": 99 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.03102080151438713, |
| "learning_rate": 2.0357470745654214e-05, |
| "loss": 1.095703125, |
| "step": 100 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 1.1435546875, |
| "eval_runtime": 5.5345, |
| "eval_samples_per_second": 0.542, |
| "eval_steps_per_second": 0.181, |
| "step": 100 |
| }, |
| { |
| "epoch": 4.04, |
| "grad_norm": 0.03211043402552605, |
| "learning_rate": 1.960517998888109e-05, |
| "loss": 1.1064453125, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.08, |
| "grad_norm": 0.030725976452231407, |
| "learning_rate": 1.8877976293106646e-05, |
| "loss": 1.08837890625, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.12, |
| "grad_norm": 0.03212733939290047, |
| "learning_rate": 1.8176375084132397e-05, |
| "loss": 1.03369140625, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.16, |
| "grad_norm": 0.0279594324529171, |
| "learning_rate": 1.7500873641286825e-05, |
| "loss": 0.94091796875, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.2, |
| "grad_norm": 0.031055450439453125, |
| "learning_rate": 1.685195074496481e-05, |
| "loss": 1.02685546875, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.24, |
| "grad_norm": 0.03178901970386505, |
| "learning_rate": 1.6230066337278724e-05, |
| "loss": 1.12939453125, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.28, |
| "grad_norm": 0.03314363583922386, |
| "learning_rate": 1.5635661196061744e-05, |
| "loss": 1.12890625, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.32, |
| "grad_norm": 0.029912060126662254, |
| "learning_rate": 1.5069156622454287e-05, |
| "loss": 1.0849609375, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.36, |
| "grad_norm": 0.03170070797204971, |
| "learning_rate": 1.453095414229514e-05, |
| "loss": 1.07421875, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.4, |
| "grad_norm": 0.03254175931215286, |
| "learning_rate": 1.4021435221528906e-05, |
| "loss": 1.08056640625, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.44, |
| "grad_norm": 0.030924495309591293, |
| "learning_rate": 1.3540960995831417e-05, |
| "loss": 1.1025390625, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.48, |
| "grad_norm": 0.030569253489375114, |
| "learning_rate": 1.3089872014644771e-05, |
| "loss": 0.96337890625, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.52, |
| "grad_norm": 0.030999232083559036, |
| "learning_rate": 1.2668487999803505e-05, |
| "loss": 1.09912109375, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.5600000000000005, |
| "grad_norm": 0.0317683182656765, |
| "learning_rate": 1.2277107618922843e-05, |
| "loss": 1.07373046875, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.6, |
| "grad_norm": 0.03217482566833496, |
| "learning_rate": 1.1916008273709755e-05, |
| "loss": 1.08984375, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.64, |
| "grad_norm": 0.03401336818933487, |
| "learning_rate": 1.1585445903346783e-05, |
| "loss": 1.12109375, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.68, |
| "grad_norm": 0.03359537199139595, |
| "learning_rate": 1.1285654803088058e-05, |
| "loss": 1.1435546875, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.72, |
| "grad_norm": 0.03091401979327202, |
| "learning_rate": 1.1016847458196001e-05, |
| "loss": 1.09521484375, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.76, |
| "grad_norm": 0.0331752672791481, |
| "learning_rate": 1.0779214393336558e-05, |
| "loss": 1.095703125, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.8, |
| "grad_norm": 0.03139505907893181, |
| "learning_rate": 1.0572924037539496e-05, |
| "loss": 0.9727783203125, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.84, |
| "grad_norm": 0.03317149356007576, |
| "learning_rate": 1.0398122604819683e-05, |
| "loss": 1.1162109375, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.88, |
| "grad_norm": 0.03348582610487938, |
| "learning_rate": 1.0254933990543831e-05, |
| "loss": 1.1298828125, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.92, |
| "grad_norm": 0.029681004583835602, |
| "learning_rate": 1.0143459683616244e-05, |
| "loss": 0.95050048828125, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.96, |
| "grad_norm": 0.031139632686972618, |
| "learning_rate": 1.0063778694545714e-05, |
| "loss": 1.05078125, |
| "step": 124 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.033313363790512085, |
| "learning_rate": 1.0015947499444633e-05, |
| "loss": 1.0849609375, |
| "step": 125 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 1.142578125, |
| "eval_runtime": 5.5301, |
| "eval_samples_per_second": 0.542, |
| "eval_steps_per_second": 0.181, |
| "step": 125 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 125, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.08762009598899e+19, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
