| { |
| "best_global_step": 120, |
| "best_metric": 1.0, |
| "best_model_checkpoint": "/projects/bffw/darora1/llm_ipc/final_models/mpi_async_n2/checkpoint-120", |
| "epoch": 1.2281952825013713, |
| "eval_steps": 40, |
| "global_step": 280, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00877674163466813, |
| "grad_norm": 45.454673767089844, |
| "learning_rate": 2.0000000000000002e-07, |
| "loss": 2.9332, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01755348326933626, |
| "grad_norm": 48.028682708740234, |
| "learning_rate": 6.000000000000001e-07, |
| "loss": 2.9542, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.026330224904004388, |
| "grad_norm": 46.46372985839844, |
| "learning_rate": 1.0000000000000002e-06, |
| "loss": 2.9605, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.03510696653867252, |
| "grad_norm": 41.78909683227539, |
| "learning_rate": 1.4000000000000001e-06, |
| "loss": 2.8479, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.04388370817334065, |
| "grad_norm": 38.01380157470703, |
| "learning_rate": 1.8000000000000001e-06, |
| "loss": 2.7259, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.052660449808008776, |
| "grad_norm": 38.49835205078125, |
| "learning_rate": 2.2e-06, |
| "loss": 2.4479, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.061437191442676904, |
| "grad_norm": 25.068660736083984, |
| "learning_rate": 2.6e-06, |
| "loss": 2.0032, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.07021393307734504, |
| "grad_norm": 21.01138687133789, |
| "learning_rate": 3e-06, |
| "loss": 1.4907, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.07899067471201317, |
| "grad_norm": 21.503671646118164, |
| "learning_rate": 3.4000000000000005e-06, |
| "loss": 1.4202, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.0877674163466813, |
| "grad_norm": 17.642776489257812, |
| "learning_rate": 3.8000000000000005e-06, |
| "loss": 0.8484, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.09654415798134942, |
| "grad_norm": 12.313624382019043, |
| "learning_rate": 4.2000000000000004e-06, |
| "loss": 0.6718, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.10532089961601755, |
| "grad_norm": 9.669478416442871, |
| "learning_rate": 4.600000000000001e-06, |
| "loss": 0.5142, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.11409764125068568, |
| "grad_norm": 8.069445610046387, |
| "learning_rate": 5e-06, |
| "loss": 0.3321, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.12287438288535381, |
| "grad_norm": 10.269947052001953, |
| "learning_rate": 5.400000000000001e-06, |
| "loss": 0.195, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.13165112452002195, |
| "grad_norm": 7.683987140655518, |
| "learning_rate": 5.8e-06, |
| "loss": 0.1483, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.14042786615469008, |
| "grad_norm": 4.9717864990234375, |
| "learning_rate": 6.200000000000001e-06, |
| "loss": 0.1094, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.1492046077893582, |
| "grad_norm": 6.056117534637451, |
| "learning_rate": 6.600000000000001e-06, |
| "loss": 0.084, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.15798134942402633, |
| "grad_norm": 7.00730037689209, |
| "learning_rate": 7e-06, |
| "loss": 0.0627, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.16675809105869446, |
| "grad_norm": 5.497600555419922, |
| "learning_rate": 7.4e-06, |
| "loss": 0.0487, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.1755348326933626, |
| "grad_norm": 4.045105457305908, |
| "learning_rate": 7.800000000000002e-06, |
| "loss": 0.0344, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.1755348326933626, |
| "eval_accuracy": 0.9908390662995566, |
| "eval_loss": 0.02551591955125332, |
| "eval_runtime": 26.7939, |
| "eval_samples_per_second": 37.322, |
| "eval_steps_per_second": 18.661, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.18431157432803072, |
| "grad_norm": 3.0727834701538086, |
| "learning_rate": 8.2e-06, |
| "loss": 0.0215, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.19308831596269885, |
| "grad_norm": 1.7004352807998657, |
| "learning_rate": 8.6e-06, |
| "loss": 0.0172, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.20186505759736698, |
| "grad_norm": 31.896760940551758, |
| "learning_rate": 9e-06, |
| "loss": 0.0345, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.2106417992320351, |
| "grad_norm": 4.731893062591553, |
| "learning_rate": 9.4e-06, |
| "loss": 0.0291, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.21941854086670323, |
| "grad_norm": 0.8632926344871521, |
| "learning_rate": 9.800000000000001e-06, |
| "loss": 0.0117, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.22819528250137136, |
| "grad_norm": 1.1372809410095215, |
| "learning_rate": 9.999998993000299e-06, |
| "loss": 0.0096, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.2369720241360395, |
| "grad_norm": 1.35813307762146, |
| "learning_rate": 9.999990937005126e-06, |
| "loss": 0.0074, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.24574876577070762, |
| "grad_norm": 1.8251152038574219, |
| "learning_rate": 9.999974825027756e-06, |
| "loss": 0.0056, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.2545255074053758, |
| "grad_norm": 3.9003660678863525, |
| "learning_rate": 9.999950657094151e-06, |
| "loss": 0.0035, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.2633022490400439, |
| "grad_norm": 0.40562182664871216, |
| "learning_rate": 9.999918433243253e-06, |
| "loss": 0.0023, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.27207899067471203, |
| "grad_norm": 0.4589959383010864, |
| "learning_rate": 9.999878153526974e-06, |
| "loss": 0.0039, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.28085573230938016, |
| "grad_norm": 1.4256044626235962, |
| "learning_rate": 9.99982981801022e-06, |
| "loss": 0.0039, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.2896324739440483, |
| "grad_norm": 1.2097476720809937, |
| "learning_rate": 9.999773426770864e-06, |
| "loss": 0.0008, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.2984092155787164, |
| "grad_norm": 1.3794668912887573, |
| "learning_rate": 9.999708979899769e-06, |
| "loss": 0.0022, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.30718595721338454, |
| "grad_norm": 0.9129151105880737, |
| "learning_rate": 9.999636477500765e-06, |
| "loss": 0.0008, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.31596269884805267, |
| "grad_norm": 2.035865068435669, |
| "learning_rate": 9.999555919690673e-06, |
| "loss": 0.0024, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.3247394404827208, |
| "grad_norm": 0.33494269847869873, |
| "learning_rate": 9.999467306599285e-06, |
| "loss": 0.0009, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.3335161821173889, |
| "grad_norm": 1.9235092401504517, |
| "learning_rate": 9.999370638369377e-06, |
| "loss": 0.0015, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.34229292375205705, |
| "grad_norm": 0.06841372698545456, |
| "learning_rate": 9.999265915156697e-06, |
| "loss": 0.0005, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.3510696653867252, |
| "grad_norm": 3.6089587211608887, |
| "learning_rate": 9.999153137129978e-06, |
| "loss": 0.0013, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.3510696653867252, |
| "eval_accuracy": 0.9955795537921697, |
| "eval_loss": 0.033373381942510605, |
| "eval_runtime": 27.5485, |
| "eval_samples_per_second": 36.3, |
| "eval_steps_per_second": 18.15, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.3598464070213933, |
| "grad_norm": 1.6794105768203735, |
| "learning_rate": 9.999032304470926e-06, |
| "loss": 0.0157, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.36862314865606144, |
| "grad_norm": 4.490398406982422, |
| "learning_rate": 9.998903417374228e-06, |
| "loss": 0.0021, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.37739989029072957, |
| "grad_norm": 0.12031521648168564, |
| "learning_rate": 9.998766476047546e-06, |
| "loss": 0.0003, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.3861766319253977, |
| "grad_norm": 0.055538520216941833, |
| "learning_rate": 9.998621480711522e-06, |
| "loss": 0.0014, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.3949533735600658, |
| "grad_norm": 0.12411190569400787, |
| "learning_rate": 9.998468431599768e-06, |
| "loss": 0.0009, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.40373011519473395, |
| "grad_norm": 0.2620101869106293, |
| "learning_rate": 9.99830732895888e-06, |
| "loss": 0.0002, |
| "step": 92 |
| }, |
| { |
| "epoch": 0.4125068568294021, |
| "grad_norm": 0.02486434578895569, |
| "learning_rate": 9.998138173048424e-06, |
| "loss": 0.0003, |
| "step": 94 |
| }, |
| { |
| "epoch": 0.4212835984640702, |
| "grad_norm": 0.048864614218473434, |
| "learning_rate": 9.997960964140946e-06, |
| "loss": 0.0001, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.43006034009873834, |
| "grad_norm": 0.12352154403924942, |
| "learning_rate": 9.997775702521965e-06, |
| "loss": 0.0002, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.43883708173340646, |
| "grad_norm": 0.02925235591828823, |
| "learning_rate": 9.997582388489975e-06, |
| "loss": 0.0001, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.4476138233680746, |
| "grad_norm": 0.007072501815855503, |
| "learning_rate": 9.99738102235644e-06, |
| "loss": 0.0, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.4563905650027427, |
| "grad_norm": 0.018334778025746346, |
| "learning_rate": 9.997171604445803e-06, |
| "loss": 0.0, |
| "step": 104 |
| }, |
| { |
| "epoch": 0.46516730663741085, |
| "grad_norm": 0.017481721937656403, |
| "learning_rate": 9.99695413509548e-06, |
| "loss": 0.0, |
| "step": 106 |
| }, |
| { |
| "epoch": 0.473944048272079, |
| "grad_norm": 0.02275106869637966, |
| "learning_rate": 9.996728614655854e-06, |
| "loss": 0.0, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.4827207899067471, |
| "grad_norm": 0.006805419921875, |
| "learning_rate": 9.996495043490285e-06, |
| "loss": 0.0, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.49149753154141523, |
| "grad_norm": 0.012757470831274986, |
| "learning_rate": 9.996253421975103e-06, |
| "loss": 0.0, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.5002742731760834, |
| "grad_norm": 0.014855819754302502, |
| "learning_rate": 9.996003750499608e-06, |
| "loss": 0.0, |
| "step": 114 |
| }, |
| { |
| "epoch": 0.5090510148107515, |
| "grad_norm": 0.001869674539193511, |
| "learning_rate": 9.995746029466071e-06, |
| "loss": 0.0, |
| "step": 116 |
| }, |
| { |
| "epoch": 0.5178277564454197, |
| "grad_norm": 0.001857027062214911, |
| "learning_rate": 9.995480259289731e-06, |
| "loss": 0.0, |
| "step": 118 |
| }, |
| { |
| "epoch": 0.5266044980800878, |
| "grad_norm": 0.0015473720850422978, |
| "learning_rate": 9.995206440398798e-06, |
| "loss": 0.0, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.5266044980800878, |
| "eval_accuracy": 1.0, |
| "eval_loss": 9.006173968373332e-06, |
| "eval_runtime": 27.2815, |
| "eval_samples_per_second": 36.655, |
| "eval_steps_per_second": 18.327, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.5353812397147559, |
| "grad_norm": 0.0015787497395649552, |
| "learning_rate": 9.994924573234448e-06, |
| "loss": 0.0, |
| "step": 122 |
| }, |
| { |
| "epoch": 0.5441579813494241, |
| "grad_norm": 0.0009497110149823129, |
| "learning_rate": 9.994634658250825e-06, |
| "loss": 0.0, |
| "step": 124 |
| }, |
| { |
| "epoch": 0.5529347229840922, |
| "grad_norm": 0.010696510784327984, |
| "learning_rate": 9.994336695915041e-06, |
| "loss": 0.0, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.5617114646187603, |
| "grad_norm": 0.0011760975467041135, |
| "learning_rate": 9.994030686707171e-06, |
| "loss": 0.0, |
| "step": 128 |
| }, |
| { |
| "epoch": 0.5704882062534284, |
| "grad_norm": 0.0009388104663230479, |
| "learning_rate": 9.993716631120259e-06, |
| "loss": 0.0, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.5792649478880966, |
| "grad_norm": 0.0007937882328405976, |
| "learning_rate": 9.993394529660307e-06, |
| "loss": 0.0, |
| "step": 132 |
| }, |
| { |
| "epoch": 0.5880416895227647, |
| "grad_norm": 0.0007054200395941734, |
| "learning_rate": 9.99306438284629e-06, |
| "loss": 0.0, |
| "step": 134 |
| }, |
| { |
| "epoch": 0.5968184311574328, |
| "grad_norm": 0.0007900617201812565, |
| "learning_rate": 9.992726191210139e-06, |
| "loss": 0.0, |
| "step": 136 |
| }, |
| { |
| "epoch": 0.605595172792101, |
| "grad_norm": 0.0006902568857185543, |
| "learning_rate": 9.992379955296745e-06, |
| "loss": 0.0, |
| "step": 138 |
| }, |
| { |
| "epoch": 0.6143719144267691, |
| "grad_norm": 0.0007422619964927435, |
| "learning_rate": 9.992025675663966e-06, |
| "loss": 0.0, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.6231486560614372, |
| "grad_norm": 0.03101375699043274, |
| "learning_rate": 9.991663352882615e-06, |
| "loss": 0.0, |
| "step": 142 |
| }, |
| { |
| "epoch": 0.6319253976961053, |
| "grad_norm": 0.000703384168446064, |
| "learning_rate": 9.991292987536469e-06, |
| "loss": 0.0, |
| "step": 144 |
| }, |
| { |
| "epoch": 0.6407021393307735, |
| "grad_norm": 0.000645720399916172, |
| "learning_rate": 9.990914580222258e-06, |
| "loss": 0.0, |
| "step": 146 |
| }, |
| { |
| "epoch": 0.6494788809654416, |
| "grad_norm": 0.0005880170501768589, |
| "learning_rate": 9.990528131549674e-06, |
| "loss": 0.0, |
| "step": 148 |
| }, |
| { |
| "epoch": 0.6582556226001097, |
| "grad_norm": 0.0005776435136795044, |
| "learning_rate": 9.990133642141359e-06, |
| "loss": 0.0, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.6670323642347779, |
| "grad_norm": 0.0005855935742147267, |
| "learning_rate": 9.989731112632917e-06, |
| "loss": 0.0, |
| "step": 152 |
| }, |
| { |
| "epoch": 0.675809105869446, |
| "grad_norm": 0.0005201378371566534, |
| "learning_rate": 9.989320543672904e-06, |
| "loss": 0.0, |
| "step": 154 |
| }, |
| { |
| "epoch": 0.6845858475041141, |
| "grad_norm": 0.0004889736883342266, |
| "learning_rate": 9.988901935922826e-06, |
| "loss": 0.0, |
| "step": 156 |
| }, |
| { |
| "epoch": 0.6933625891387822, |
| "grad_norm": 0.0014288433594629169, |
| "learning_rate": 9.988475290057145e-06, |
| "loss": 0.0, |
| "step": 158 |
| }, |
| { |
| "epoch": 0.7021393307734504, |
| "grad_norm": 0.000509511970449239, |
| "learning_rate": 9.988040606763272e-06, |
| "loss": 0.0, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.7021393307734504, |
| "eval_accuracy": 1.0, |
| "eval_loss": 4.382986389828147e-06, |
| "eval_runtime": 27.0687, |
| "eval_samples_per_second": 36.943, |
| "eval_steps_per_second": 18.471, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.7109160724081185, |
| "grad_norm": 0.0005291936104185879, |
| "learning_rate": 9.98759788674157e-06, |
| "loss": 0.0, |
| "step": 162 |
| }, |
| { |
| "epoch": 0.7196928140427866, |
| "grad_norm": 0.0011958482209593058, |
| "learning_rate": 9.987147130705347e-06, |
| "loss": 0.0, |
| "step": 164 |
| }, |
| { |
| "epoch": 0.7284695556774547, |
| "grad_norm": 0.000418210169300437, |
| "learning_rate": 9.986688339380863e-06, |
| "loss": 0.0, |
| "step": 166 |
| }, |
| { |
| "epoch": 0.7372462973121229, |
| "grad_norm": 0.00041748053627088666, |
| "learning_rate": 9.98622151350732e-06, |
| "loss": 0.0, |
| "step": 168 |
| }, |
| { |
| "epoch": 0.746023038946791, |
| "grad_norm": 0.0004505082033574581, |
| "learning_rate": 9.985746653836867e-06, |
| "loss": 0.0, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.7547997805814591, |
| "grad_norm": 0.00039788082358427346, |
| "learning_rate": 9.985263761134602e-06, |
| "loss": 0.0, |
| "step": 172 |
| }, |
| { |
| "epoch": 0.7635765222161273, |
| "grad_norm": 0.0004020440683234483, |
| "learning_rate": 9.984772836178559e-06, |
| "loss": 0.0, |
| "step": 174 |
| }, |
| { |
| "epoch": 0.7723532638507954, |
| "grad_norm": 0.0007427522796206176, |
| "learning_rate": 9.984273879759713e-06, |
| "loss": 0.0, |
| "step": 176 |
| }, |
| { |
| "epoch": 0.7811300054854635, |
| "grad_norm": 0.0009939726442098618, |
| "learning_rate": 9.983766892681985e-06, |
| "loss": 0.0, |
| "step": 178 |
| }, |
| { |
| "epoch": 0.7899067471201316, |
| "grad_norm": 0.0003770038892980665, |
| "learning_rate": 9.983251875762234e-06, |
| "loss": 0.0, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.7986834887547998, |
| "grad_norm": 0.0003830124333035201, |
| "learning_rate": 9.982728829830252e-06, |
| "loss": 0.0, |
| "step": 182 |
| }, |
| { |
| "epoch": 0.8074602303894679, |
| "grad_norm": 0.0003769229515455663, |
| "learning_rate": 9.982197755728771e-06, |
| "loss": 0.0, |
| "step": 184 |
| }, |
| { |
| "epoch": 0.816236972024136, |
| "grad_norm": 0.00034873795812018216, |
| "learning_rate": 9.981658654313458e-06, |
| "loss": 0.0, |
| "step": 186 |
| }, |
| { |
| "epoch": 0.8250137136588042, |
| "grad_norm": 0.0006776470108889043, |
| "learning_rate": 9.981111526452912e-06, |
| "loss": 0.0, |
| "step": 188 |
| }, |
| { |
| "epoch": 0.8337904552934723, |
| "grad_norm": 0.0003451018419582397, |
| "learning_rate": 9.980556373028665e-06, |
| "loss": 0.0, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.8425671969281404, |
| "grad_norm": 0.0005146560142748058, |
| "learning_rate": 9.979993194935182e-06, |
| "loss": 0.0, |
| "step": 192 |
| }, |
| { |
| "epoch": 0.8513439385628085, |
| "grad_norm": 0.0003344170399941504, |
| "learning_rate": 9.979421993079853e-06, |
| "loss": 0.0, |
| "step": 194 |
| }, |
| { |
| "epoch": 0.8601206801974767, |
| "grad_norm": 0.00037026862264610827, |
| "learning_rate": 9.978842768382999e-06, |
| "loss": 0.0, |
| "step": 196 |
| }, |
| { |
| "epoch": 0.8688974218321448, |
| "grad_norm": 0.00033089827047660947, |
| "learning_rate": 9.978255521777865e-06, |
| "loss": 0.0, |
| "step": 198 |
| }, |
| { |
| "epoch": 0.8776741634668129, |
| "grad_norm": 0.0003343552234582603, |
| "learning_rate": 9.977660254210623e-06, |
| "loss": 0.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.8776741634668129, |
| "eval_accuracy": 1.0, |
| "eval_loss": 3.085134494540398e-06, |
| "eval_runtime": 26.6311, |
| "eval_samples_per_second": 37.55, |
| "eval_steps_per_second": 18.775, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.8864509051014811, |
| "grad_norm": 0.0003209022688679397, |
| "learning_rate": 9.977056966640368e-06, |
| "loss": 0.0, |
| "step": 202 |
| }, |
| { |
| "epoch": 0.8952276467361492, |
| "grad_norm": 0.0003875560942105949, |
| "learning_rate": 9.976445660039118e-06, |
| "loss": 0.0, |
| "step": 204 |
| }, |
| { |
| "epoch": 0.9040043883708173, |
| "grad_norm": 0.000311438663629815, |
| "learning_rate": 9.975826335391808e-06, |
| "loss": 0.0, |
| "step": 206 |
| }, |
| { |
| "epoch": 0.9127811300054854, |
| "grad_norm": 0.00031096808379516006, |
| "learning_rate": 9.975198993696294e-06, |
| "loss": 0.0, |
| "step": 208 |
| }, |
| { |
| "epoch": 0.9215578716401536, |
| "grad_norm": 0.0005075507797300816, |
| "learning_rate": 9.974563635963348e-06, |
| "loss": 0.0, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.9303346132748217, |
| "grad_norm": 0.00029596491367556155, |
| "learning_rate": 9.973920263216658e-06, |
| "loss": 0.0, |
| "step": 212 |
| }, |
| { |
| "epoch": 0.9391113549094898, |
| "grad_norm": 0.000583572022151202, |
| "learning_rate": 9.973268876492827e-06, |
| "loss": 0.0, |
| "step": 214 |
| }, |
| { |
| "epoch": 0.947888096544158, |
| "grad_norm": 0.00031335651874542236, |
| "learning_rate": 9.972609476841368e-06, |
| "loss": 0.0, |
| "step": 216 |
| }, |
| { |
| "epoch": 0.9566648381788261, |
| "grad_norm": 0.0003140955523122102, |
| "learning_rate": 9.971942065324704e-06, |
| "loss": 0.0, |
| "step": 218 |
| }, |
| { |
| "epoch": 0.9654415798134942, |
| "grad_norm": 0.00029426993569359183, |
| "learning_rate": 9.971266643018171e-06, |
| "loss": 0.0, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.9742183214481623, |
| "grad_norm": 0.0005635425914078951, |
| "learning_rate": 9.970583211010008e-06, |
| "loss": 0.0, |
| "step": 222 |
| }, |
| { |
| "epoch": 0.9829950630828305, |
| "grad_norm": 0.0002683993661776185, |
| "learning_rate": 9.969891770401358e-06, |
| "loss": 0.0, |
| "step": 224 |
| }, |
| { |
| "epoch": 0.9917718047174986, |
| "grad_norm": 0.00028738679247908294, |
| "learning_rate": 9.969192322306271e-06, |
| "loss": 0.0, |
| "step": 226 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.00046732599730603397, |
| "learning_rate": 9.968484867851698e-06, |
| "loss": 0.0, |
| "step": 228 |
| }, |
| { |
| "epoch": 1.0087767416346682, |
| "grad_norm": 0.0002722733770497143, |
| "learning_rate": 9.96776940817749e-06, |
| "loss": 0.0, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.0175534832693363, |
| "grad_norm": 0.00028377954731695354, |
| "learning_rate": 9.967045944436392e-06, |
| "loss": 0.0, |
| "step": 232 |
| }, |
| { |
| "epoch": 1.0263302249040045, |
| "grad_norm": 0.0002573099918663502, |
| "learning_rate": 9.966314477794052e-06, |
| "loss": 0.0, |
| "step": 234 |
| }, |
| { |
| "epoch": 1.0351069665386725, |
| "grad_norm": 0.0004235700471326709, |
| "learning_rate": 9.965575009429006e-06, |
| "loss": 0.0, |
| "step": 236 |
| }, |
| { |
| "epoch": 1.0438837081733408, |
| "grad_norm": 0.0007151885074563324, |
| "learning_rate": 9.964827540532685e-06, |
| "loss": 0.0, |
| "step": 238 |
| }, |
| { |
| "epoch": 1.0526604498080088, |
| "grad_norm": 0.0002589399227872491, |
| "learning_rate": 9.964072072309412e-06, |
| "loss": 0.0, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.0526604498080088, |
| "eval_accuracy": 1.0, |
| "eval_loss": 2.4207340629800456e-06, |
| "eval_runtime": 29.8042, |
| "eval_samples_per_second": 33.552, |
| "eval_steps_per_second": 16.776, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.061437191442677, |
| "grad_norm": 0.00024218352336902171, |
| "learning_rate": 9.963308605976397e-06, |
| "loss": 0.0, |
| "step": 242 |
| }, |
| { |
| "epoch": 1.070213933077345, |
| "grad_norm": 0.0003983522765338421, |
| "learning_rate": 9.962537142763733e-06, |
| "loss": 0.0, |
| "step": 244 |
| }, |
| { |
| "epoch": 1.0789906747120133, |
| "grad_norm": 0.00023251764650922269, |
| "learning_rate": 9.961757683914406e-06, |
| "loss": 0.0, |
| "step": 246 |
| }, |
| { |
| "epoch": 1.0877674163466813, |
| "grad_norm": 0.0002750585845205933, |
| "learning_rate": 9.960970230684276e-06, |
| "loss": 0.0, |
| "step": 248 |
| }, |
| { |
| "epoch": 1.0965441579813495, |
| "grad_norm": 0.0002548044722061604, |
| "learning_rate": 9.96017478434209e-06, |
| "loss": 0.0, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.1053208996160175, |
| "grad_norm": 0.00024573353584855795, |
| "learning_rate": 9.959371346169466e-06, |
| "loss": 0.0, |
| "step": 252 |
| }, |
| { |
| "epoch": 1.1140976412506858, |
| "grad_norm": 0.0003012689994648099, |
| "learning_rate": 9.958559917460909e-06, |
| "loss": 0.0, |
| "step": 254 |
| }, |
| { |
| "epoch": 1.1228743828853538, |
| "grad_norm": 0.00022236473159864545, |
| "learning_rate": 9.957740499523787e-06, |
| "loss": 0.0, |
| "step": 256 |
| }, |
| { |
| "epoch": 1.131651124520022, |
| "grad_norm": 0.00022309472842607647, |
| "learning_rate": 9.95691309367835e-06, |
| "loss": 0.0, |
| "step": 258 |
| }, |
| { |
| "epoch": 1.14042786615469, |
| "grad_norm": 0.00036199891474097967, |
| "learning_rate": 9.95607770125771e-06, |
| "loss": 0.0, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.1492046077893583, |
| "grad_norm": 0.0002264819631818682, |
| "learning_rate": 9.955234323607854e-06, |
| "loss": 0.0, |
| "step": 262 |
| }, |
| { |
| "epoch": 1.1579813494240263, |
| "grad_norm": 0.0002222947805421427, |
| "learning_rate": 9.954382962087628e-06, |
| "loss": 0.0, |
| "step": 264 |
| }, |
| { |
| "epoch": 1.1667580910586945, |
| "grad_norm": 0.0002369284484302625, |
| "learning_rate": 9.95352361806875e-06, |
| "loss": 0.0, |
| "step": 266 |
| }, |
| { |
| "epoch": 1.1755348326933626, |
| "grad_norm": 0.0002466253063175827, |
| "learning_rate": 9.95265629293579e-06, |
| "loss": 0.0, |
| "step": 268 |
| }, |
| { |
| "epoch": 1.1843115743280308, |
| "grad_norm": 0.0002238057932117954, |
| "learning_rate": 9.951780988086183e-06, |
| "loss": 0.0, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.1930883159626988, |
| "grad_norm": 0.00020709357340820134, |
| "learning_rate": 9.950897704930223e-06, |
| "loss": 0.0, |
| "step": 272 |
| }, |
| { |
| "epoch": 1.201865057597367, |
| "grad_norm": 0.000194857973838225, |
| "learning_rate": 9.95000644489105e-06, |
| "loss": 0.0, |
| "step": 274 |
| }, |
| { |
| "epoch": 1.210641799232035, |
| "grad_norm": 0.00019957115000579506, |
| "learning_rate": 9.949107209404664e-06, |
| "loss": 0.0, |
| "step": 276 |
| }, |
| { |
| "epoch": 1.2194185408667033, |
| "grad_norm": 0.00020521250553429127, |
| "learning_rate": 9.948199999919914e-06, |
| "loss": 0.0, |
| "step": 278 |
| }, |
| { |
| "epoch": 1.2281952825013713, |
| "grad_norm": 0.0002061008126474917, |
| "learning_rate": 9.947284817898493e-06, |
| "loss": 0.0, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.2281952825013713, |
| "eval_accuracy": 1.0, |
| "eval_loss": 1.949304987647338e-06, |
| "eval_runtime": 29.4785, |
| "eval_samples_per_second": 33.923, |
| "eval_steps_per_second": 16.962, |
| "step": 280 |
| } |
| ], |
| "logging_steps": 2, |
| "max_steps": 5000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 22, |
| "save_steps": 40, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.0478480881811456e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
