| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 156, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.2914280891418457, |
| "epoch": 0.012965964343598054, |
| "grad_norm": 1.112913966178894, |
| "learning_rate": 0.0, |
| "loss": 2.1718008518218994, |
| "mean_token_accuracy": 0.5190608203411102, |
| "num_tokens": 130726.0, |
| "step": 1 |
| }, |
| { |
| "entropy": 1.2813172340393066, |
| "epoch": 0.02593192868719611, |
| "grad_norm": 1.0995973348617554, |
| "learning_rate": 4.166666666666667e-06, |
| "loss": 2.1320834159851074, |
| "mean_token_accuracy": 0.5265823230147362, |
| "num_tokens": 257394.0, |
| "step": 2 |
| }, |
| { |
| "entropy": 1.327770620584488, |
| "epoch": 0.03889789303079417, |
| "grad_norm": 0.9902980327606201, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 2.1106252670288086, |
| "mean_token_accuracy": 0.5237875208258629, |
| "num_tokens": 387496.0, |
| "step": 3 |
| }, |
| { |
| "entropy": 1.3719477504491806, |
| "epoch": 0.05186385737439222, |
| "grad_norm": 0.8683141469955444, |
| "learning_rate": 1.25e-05, |
| "loss": 2.0806920528411865, |
| "mean_token_accuracy": 0.526897743344307, |
| "num_tokens": 517915.0, |
| "step": 4 |
| }, |
| { |
| "entropy": 1.4400453567504883, |
| "epoch": 0.06482982171799027, |
| "grad_norm": 0.6660990715026855, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 1.9889618158340454, |
| "mean_token_accuracy": 0.5334466248750687, |
| "num_tokens": 648540.0, |
| "step": 5 |
| }, |
| { |
| "entropy": 1.5626330226659775, |
| "epoch": 0.07779578606158834, |
| "grad_norm": 0.5204595923423767, |
| "learning_rate": 2.0833333333333336e-05, |
| "loss": 1.9843950271606445, |
| "mean_token_accuracy": 0.5293373018503189, |
| "num_tokens": 779170.0, |
| "step": 6 |
| }, |
| { |
| "entropy": 1.6014426946640015, |
| "epoch": 0.09076175040518639, |
| "grad_norm": 0.3845070004463196, |
| "learning_rate": 2.5e-05, |
| "loss": 1.887692928314209, |
| "mean_token_accuracy": 0.5425543487071991, |
| "num_tokens": 909516.0, |
| "step": 7 |
| }, |
| { |
| "entropy": 1.6851050555706024, |
| "epoch": 0.10372771474878444, |
| "grad_norm": 0.30755460262298584, |
| "learning_rate": 2.916666666666667e-05, |
| "loss": 1.8439122438430786, |
| "mean_token_accuracy": 0.5476168766617775, |
| "num_tokens": 1039198.0, |
| "step": 8 |
| }, |
| { |
| "entropy": 1.7548235952854156, |
| "epoch": 0.1166936790923825, |
| "grad_norm": 0.26733461022377014, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 1.8185280561447144, |
| "mean_token_accuracy": 0.5502617135643959, |
| "num_tokens": 1169425.0, |
| "step": 9 |
| }, |
| { |
| "entropy": 1.7970841228961945, |
| "epoch": 0.12965964343598055, |
| "grad_norm": 0.26483356952667236, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 1.7471606731414795, |
| "mean_token_accuracy": 0.5560443699359894, |
| "num_tokens": 1299168.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 1.8392730802297592, |
| "epoch": 0.1426256077795786, |
| "grad_norm": 0.2690557837486267, |
| "learning_rate": 4.166666666666667e-05, |
| "loss": 1.736329197883606, |
| "mean_token_accuracy": 0.5596349760890007, |
| "num_tokens": 1430062.0, |
| "step": 11 |
| }, |
| { |
| "entropy": 1.885682463645935, |
| "epoch": 0.15559157212317667, |
| "grad_norm": 0.2904511094093323, |
| "learning_rate": 4.5833333333333334e-05, |
| "loss": 1.7258615493774414, |
| "mean_token_accuracy": 0.5618793666362762, |
| "num_tokens": 1560442.0, |
| "step": 12 |
| }, |
| { |
| "entropy": 1.9065079540014267, |
| "epoch": 0.1685575364667747, |
| "grad_norm": 0.3055932819843292, |
| "learning_rate": 5e-05, |
| "loss": 1.709148645401001, |
| "mean_token_accuracy": 0.5631825849413872, |
| "num_tokens": 1687626.0, |
| "step": 13 |
| }, |
| { |
| "entropy": 1.8885795921087265, |
| "epoch": 0.18152350081037277, |
| "grad_norm": 0.31618642807006836, |
| "learning_rate": 4.9997496794168726e-05, |
| "loss": 1.6640710830688477, |
| "mean_token_accuracy": 0.5704818964004517, |
| "num_tokens": 1817839.0, |
| "step": 14 |
| }, |
| { |
| "entropy": 1.799900770187378, |
| "epoch": 0.19448946515397084, |
| "grad_norm": 0.28537100553512573, |
| "learning_rate": 4.998998767795805e-05, |
| "loss": 1.5893642902374268, |
| "mean_token_accuracy": 0.5844717845320702, |
| "num_tokens": 1947846.0, |
| "step": 15 |
| }, |
| { |
| "entropy": 1.7524273693561554, |
| "epoch": 0.20745542949756887, |
| "grad_norm": 0.25802257657051086, |
| "learning_rate": 4.9977474155117045e-05, |
| "loss": 1.57011079788208, |
| "mean_token_accuracy": 0.5896653309464455, |
| "num_tokens": 2078221.0, |
| "step": 16 |
| }, |
| { |
| "entropy": 1.709429755806923, |
| "epoch": 0.22042139384116693, |
| "grad_norm": 0.22759748995304108, |
| "learning_rate": 4.995995873155958e-05, |
| "loss": 1.5693228244781494, |
| "mean_token_accuracy": 0.5865247845649719, |
| "num_tokens": 2208236.0, |
| "step": 17 |
| }, |
| { |
| "entropy": 1.6319102048873901, |
| "epoch": 0.233387358184765, |
| "grad_norm": 0.19342641532421112, |
| "learning_rate": 4.99374449148625e-05, |
| "loss": 1.528588056564331, |
| "mean_token_accuracy": 0.5946438014507294, |
| "num_tokens": 2338245.0, |
| "step": 18 |
| }, |
| { |
| "entropy": 1.5404616594314575, |
| "epoch": 0.24635332252836303, |
| "grad_norm": 0.1698416769504547, |
| "learning_rate": 4.9909937213563165e-05, |
| "loss": 1.4880129098892212, |
| "mean_token_accuracy": 0.6007702648639679, |
| "num_tokens": 2467411.0, |
| "step": 19 |
| }, |
| { |
| "entropy": 1.5045948326587677, |
| "epoch": 0.2593192868719611, |
| "grad_norm": 0.1683117300271988, |
| "learning_rate": 4.987744113625665e-05, |
| "loss": 1.5048375129699707, |
| "mean_token_accuracy": 0.5982850342988968, |
| "num_tokens": 2598113.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 1.4073765128850937, |
| "epoch": 0.27228525121555913, |
| "grad_norm": 0.19874629378318787, |
| "learning_rate": 4.9839963190492576e-05, |
| "loss": 1.456631064414978, |
| "mean_token_accuracy": 0.6086618900299072, |
| "num_tokens": 2728430.0, |
| "step": 21 |
| }, |
| { |
| "entropy": 1.3884904980659485, |
| "epoch": 0.2852512155591572, |
| "grad_norm": 0.21319466829299927, |
| "learning_rate": 4.979751088147192e-05, |
| "loss": 1.4507615566253662, |
| "mean_token_accuracy": 0.6082002520561218, |
| "num_tokens": 2858506.0, |
| "step": 22 |
| }, |
| { |
| "entropy": 1.3483813256025314, |
| "epoch": 0.29821717990275526, |
| "grad_norm": 0.23800760507583618, |
| "learning_rate": 4.975009271054409e-05, |
| "loss": 1.4227944612503052, |
| "mean_token_accuracy": 0.611847274005413, |
| "num_tokens": 2985950.0, |
| "step": 23 |
| }, |
| { |
| "entropy": 1.3535500168800354, |
| "epoch": 0.31118314424635335, |
| "grad_norm": 0.21581389009952545, |
| "learning_rate": 4.969771817350445e-05, |
| "loss": 1.4188156127929688, |
| "mean_token_accuracy": 0.6119491159915924, |
| "num_tokens": 3112407.0, |
| "step": 24 |
| }, |
| { |
| "entropy": 1.338183343410492, |
| "epoch": 0.3241491085899514, |
| "grad_norm": 0.19480355083942413, |
| "learning_rate": 4.9640397758692715e-05, |
| "loss": 1.3919925689697266, |
| "mean_token_accuracy": 0.6192305833101273, |
| "num_tokens": 3242148.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 1.3593887984752655, |
| "epoch": 0.3371150729335494, |
| "grad_norm": 0.15354962646961212, |
| "learning_rate": 4.957814294489261e-05, |
| "loss": 1.3766716718673706, |
| "mean_token_accuracy": 0.6211562678217888, |
| "num_tokens": 3373129.0, |
| "step": 26 |
| }, |
| { |
| "entropy": 1.362599864602089, |
| "epoch": 0.3500810372771475, |
| "grad_norm": 0.13560850918293, |
| "learning_rate": 4.9510966199033174e-05, |
| "loss": 1.349892258644104, |
| "mean_token_accuracy": 0.6282063350081444, |
| "num_tokens": 3503490.0, |
| "step": 27 |
| }, |
| { |
| "entropy": 1.3730409890413284, |
| "epoch": 0.36304700162074555, |
| "grad_norm": 0.13365128636360168, |
| "learning_rate": 4.943888097369216e-05, |
| "loss": 1.3391973972320557, |
| "mean_token_accuracy": 0.6288642287254333, |
| "num_tokens": 3631734.0, |
| "step": 28 |
| }, |
| { |
| "entropy": 1.371128425002098, |
| "epoch": 0.3760129659643436, |
| "grad_norm": 0.14155763387680054, |
| "learning_rate": 4.936190170440208e-05, |
| "loss": 1.32077956199646, |
| "mean_token_accuracy": 0.6326342150568962, |
| "num_tokens": 3762573.0, |
| "step": 29 |
| }, |
| { |
| "entropy": 1.407492458820343, |
| "epoch": 0.3889789303079417, |
| "grad_norm": 0.14185482263565063, |
| "learning_rate": 4.928004380675941e-05, |
| "loss": 1.3511477708816528, |
| "mean_token_accuracy": 0.625172384083271, |
| "num_tokens": 3893064.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 1.3961241841316223, |
| "epoch": 0.4019448946515397, |
| "grad_norm": 0.13855496048927307, |
| "learning_rate": 4.9193323673337476e-05, |
| "loss": 1.336405873298645, |
| "mean_token_accuracy": 0.6296647489070892, |
| "num_tokens": 4023676.0, |
| "step": 31 |
| }, |
| { |
| "entropy": 1.3903988599777222, |
| "epoch": 0.41491085899513774, |
| "grad_norm": 0.13400253653526306, |
| "learning_rate": 4.910175867040377e-05, |
| "loss": 1.3442656993865967, |
| "mean_token_accuracy": 0.627065122127533, |
| "num_tokens": 4153956.0, |
| "step": 32 |
| }, |
| { |
| "entropy": 1.351208671927452, |
| "epoch": 0.42787682333873583, |
| "grad_norm": 0.12610815465450287, |
| "learning_rate": 4.9005367134442235e-05, |
| "loss": 1.3147870302200317, |
| "mean_token_accuracy": 0.6329845190048218, |
| "num_tokens": 4283315.0, |
| "step": 33 |
| }, |
| { |
| "entropy": 1.3148349225521088, |
| "epoch": 0.44084278768233387, |
| "grad_norm": 0.11920498311519623, |
| "learning_rate": 4.890416836848127e-05, |
| "loss": 1.2881569862365723, |
| "mean_token_accuracy": 0.6375886723399162, |
| "num_tokens": 4414063.0, |
| "step": 34 |
| }, |
| { |
| "entropy": 1.3178757429122925, |
| "epoch": 0.4538087520259319, |
| "grad_norm": 0.11554136872291565, |
| "learning_rate": 4.8798182638228166e-05, |
| "loss": 1.3023653030395508, |
| "mean_token_accuracy": 0.635626994073391, |
| "num_tokens": 4542894.0, |
| "step": 35 |
| }, |
| { |
| "entropy": 1.2868364304304123, |
| "epoch": 0.46677471636953, |
| "grad_norm": 0.11724869906902313, |
| "learning_rate": 4.868743116801074e-05, |
| "loss": 1.276515245437622, |
| "mean_token_accuracy": 0.6388825476169586, |
| "num_tokens": 4673393.0, |
| "step": 36 |
| }, |
| { |
| "entropy": 1.3117478638887405, |
| "epoch": 0.47974068071312803, |
| "grad_norm": 0.11675813794136047, |
| "learning_rate": 4.857193613652711e-05, |
| "loss": 1.319561243057251, |
| "mean_token_accuracy": 0.6311607211828232, |
| "num_tokens": 4803020.0, |
| "step": 37 |
| }, |
| { |
| "entropy": 1.269007459282875, |
| "epoch": 0.49270664505672607, |
| "grad_norm": 0.11431621760129929, |
| "learning_rate": 4.845172067240415e-05, |
| "loss": 1.2735211849212646, |
| "mean_token_accuracy": 0.6423661559820175, |
| "num_tokens": 4932686.0, |
| "step": 38 |
| }, |
| { |
| "entropy": 1.2656036466360092, |
| "epoch": 0.5056726094003241, |
| "grad_norm": 0.11062812805175781, |
| "learning_rate": 4.8326808849565936e-05, |
| "loss": 1.265828251838684, |
| "mean_token_accuracy": 0.6441638022661209, |
| "num_tokens": 5062963.0, |
| "step": 39 |
| }, |
| { |
| "entropy": 1.27534119784832, |
| "epoch": 0.5186385737439222, |
| "grad_norm": 0.11323992908000946, |
| "learning_rate": 4.819722568241274e-05, |
| "loss": 1.281820297241211, |
| "mean_token_accuracy": 0.6388759091496468, |
| "num_tokens": 5192982.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 1.2759585976600647, |
| "epoch": 0.5316045380875203, |
| "grad_norm": 0.11570397019386292, |
| "learning_rate": 4.806299712081172e-05, |
| "loss": 1.276839256286621, |
| "mean_token_accuracy": 0.6385012120008469, |
| "num_tokens": 5323413.0, |
| "step": 41 |
| }, |
| { |
| "entropy": 1.265689566731453, |
| "epoch": 0.5445705024311183, |
| "grad_norm": 0.10930497944355011, |
| "learning_rate": 4.792415004490034e-05, |
| "loss": 1.2645472288131714, |
| "mean_token_accuracy": 0.6423149555921555, |
| "num_tokens": 5454255.0, |
| "step": 42 |
| }, |
| { |
| "entropy": 1.254970133304596, |
| "epoch": 0.5575364667747164, |
| "grad_norm": 0.10787371546030045, |
| "learning_rate": 4.77807122597034e-05, |
| "loss": 1.2552263736724854, |
| "mean_token_accuracy": 0.6437231004238129, |
| "num_tokens": 5583881.0, |
| "step": 43 |
| }, |
| { |
| "entropy": 1.2431457936763763, |
| "epoch": 0.5705024311183144, |
| "grad_norm": 0.10893784463405609, |
| "learning_rate": 4.7632712489564926e-05, |
| "loss": 1.2408338785171509, |
| "mean_token_accuracy": 0.6460021436214447, |
| "num_tokens": 5714257.0, |
| "step": 44 |
| }, |
| { |
| "entropy": 1.228305697441101, |
| "epoch": 0.5834683954619124, |
| "grad_norm": 0.11218206584453583, |
| "learning_rate": 4.748018037239592e-05, |
| "loss": 1.2231602668762207, |
| "mean_token_accuracy": 0.6500201225280762, |
| "num_tokens": 5844960.0, |
| "step": 45 |
| }, |
| { |
| "entropy": 1.2626090496778488, |
| "epoch": 0.5964343598055105, |
| "grad_norm": 0.11627671867609024, |
| "learning_rate": 4.732314645373921e-05, |
| "loss": 1.2628517150878906, |
| "mean_token_accuracy": 0.6433948427438736, |
| "num_tokens": 5974432.0, |
| "step": 46 |
| }, |
| { |
| "entropy": 1.2499435395002365, |
| "epoch": 0.6094003241491086, |
| "grad_norm": 0.1064961850643158, |
| "learning_rate": 4.7161642180652464e-05, |
| "loss": 1.2429689168930054, |
| "mean_token_accuracy": 0.6463894993066788, |
| "num_tokens": 6105159.0, |
| "step": 47 |
| }, |
| { |
| "entropy": 1.2387475371360779, |
| "epoch": 0.6223662884927067, |
| "grad_norm": 0.1059798151254654, |
| "learning_rate": 4.699569989541074e-05, |
| "loss": 1.2348564863204956, |
| "mean_token_accuracy": 0.6485447883605957, |
| "num_tokens": 6234686.0, |
| "step": 48 |
| }, |
| { |
| "entropy": 1.230888694524765, |
| "epoch": 0.6353322528363047, |
| "grad_norm": 0.10563136637210846, |
| "learning_rate": 4.6825352829029705e-05, |
| "loss": 1.2326059341430664, |
| "mean_token_accuracy": 0.650854229927063, |
| "num_tokens": 6364713.0, |
| "step": 49 |
| }, |
| { |
| "entropy": 1.2304238229990005, |
| "epoch": 0.6482982171799028, |
| "grad_norm": 0.10895860940217972, |
| "learning_rate": 4.665063509461097e-05, |
| "loss": 1.2246171236038208, |
| "mean_token_accuracy": 0.6520287021994591, |
| "num_tokens": 6494067.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.2349478155374527, |
| "epoch": 0.6612641815235009, |
| "grad_norm": 0.11149362474679947, |
| "learning_rate": 4.647158168051066e-05, |
| "loss": 1.2276027202606201, |
| "mean_token_accuracy": 0.6503733918070793, |
| "num_tokens": 6624643.0, |
| "step": 51 |
| }, |
| { |
| "entropy": 1.2219702452421188, |
| "epoch": 0.6742301458670988, |
| "grad_norm": 0.10449287295341492, |
| "learning_rate": 4.628822844333278e-05, |
| "loss": 1.2258139848709106, |
| "mean_token_accuracy": 0.6509344652295113, |
| "num_tokens": 6754416.0, |
| "step": 52 |
| }, |
| { |
| "entropy": 1.2058308869600296, |
| "epoch": 0.6871961102106969, |
| "grad_norm": 0.10380305349826813, |
| "learning_rate": 4.6100612100748765e-05, |
| "loss": 1.214524745941162, |
| "mean_token_accuracy": 0.6529537662863731, |
| "num_tokens": 6885227.0, |
| "step": 53 |
| }, |
| { |
| "entropy": 1.2204056680202484, |
| "epoch": 0.700162074554295, |
| "grad_norm": 0.10786499083042145, |
| "learning_rate": 4.59087702241444e-05, |
| "loss": 1.2236121892929077, |
| "mean_token_accuracy": 0.648014634847641, |
| "num_tokens": 7011809.0, |
| "step": 54 |
| }, |
| { |
| "entropy": 1.2288042306900024, |
| "epoch": 0.713128038897893, |
| "grad_norm": 0.1033908799290657, |
| "learning_rate": 4.571274123109606e-05, |
| "loss": 1.2249078750610352, |
| "mean_token_accuracy": 0.6486673802137375, |
| "num_tokens": 7141874.0, |
| "step": 55 |
| }, |
| { |
| "entropy": 1.1886361241340637, |
| "epoch": 0.7260940032414911, |
| "grad_norm": 0.10556555539369583, |
| "learning_rate": 4.551256437767719e-05, |
| "loss": 1.1965718269348145, |
| "mean_token_accuracy": 0.6559380367398262, |
| "num_tokens": 7272536.0, |
| "step": 56 |
| }, |
| { |
| "entropy": 1.1931221783161163, |
| "epoch": 0.7390599675850892, |
| "grad_norm": 0.10483699291944504, |
| "learning_rate": 4.530827975059715e-05, |
| "loss": 1.1899445056915283, |
| "mean_token_accuracy": 0.6578836813569069, |
| "num_tokens": 7402306.0, |
| "step": 57 |
| }, |
| { |
| "entropy": 1.2073332518339157, |
| "epoch": 0.7520259319286872, |
| "grad_norm": 0.10389534384012222, |
| "learning_rate": 4.5099928259173516e-05, |
| "loss": 1.2089029550552368, |
| "mean_token_accuracy": 0.6548937857151031, |
| "num_tokens": 7532812.0, |
| "step": 58 |
| }, |
| { |
| "entropy": 1.2048113197088242, |
| "epoch": 0.7649918962722853, |
| "grad_norm": 0.10125990211963654, |
| "learning_rate": 4.488755162713975e-05, |
| "loss": 1.2044589519500732, |
| "mean_token_accuracy": 0.6544741094112396, |
| "num_tokens": 7663455.0, |
| "step": 59 |
| }, |
| { |
| "entropy": 1.1779465079307556, |
| "epoch": 0.7779578606158833, |
| "grad_norm": 0.10293558984994888, |
| "learning_rate": 4.467119238428975e-05, |
| "loss": 1.1754040718078613, |
| "mean_token_accuracy": 0.6628620699048042, |
| "num_tokens": 7791205.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 1.2144263088703156, |
| "epoch": 0.7909238249594813, |
| "grad_norm": 0.10379968583583832, |
| "learning_rate": 4.445089385796099e-05, |
| "loss": 1.2083706855773926, |
| "mean_token_accuracy": 0.6543944776058197, |
| "num_tokens": 7918409.0, |
| "step": 61 |
| }, |
| { |
| "entropy": 1.1998531073331833, |
| "epoch": 0.8038897893030794, |
| "grad_norm": 0.10215966403484344, |
| "learning_rate": 4.422670016435792e-05, |
| "loss": 1.1933221817016602, |
| "mean_token_accuracy": 0.6570570692420006, |
| "num_tokens": 8048417.0, |
| "step": 62 |
| }, |
| { |
| "entropy": 1.200714260339737, |
| "epoch": 0.8168557536466775, |
| "grad_norm": 0.100275419652462, |
| "learning_rate": 4.3998656199717435e-05, |
| "loss": 1.189272165298462, |
| "mean_token_accuracy": 0.6573792845010757, |
| "num_tokens": 8179053.0, |
| "step": 63 |
| }, |
| { |
| "entropy": 1.1872155517339706, |
| "epoch": 0.8298217179902755, |
| "grad_norm": 0.10071317106485367, |
| "learning_rate": 4.3766807631318106e-05, |
| "loss": 1.1810928583145142, |
| "mean_token_accuracy": 0.6583103537559509, |
| "num_tokens": 8309355.0, |
| "step": 64 |
| }, |
| { |
| "entropy": 1.1796019226312637, |
| "epoch": 0.8427876823338736, |
| "grad_norm": 0.10065017640590668, |
| "learning_rate": 4.353120088833501e-05, |
| "loss": 1.17380952835083, |
| "mean_token_accuracy": 0.6608408540487289, |
| "num_tokens": 8439678.0, |
| "step": 65 |
| }, |
| { |
| "entropy": 1.1712117940187454, |
| "epoch": 0.8557536466774717, |
| "grad_norm": 0.09942107647657394, |
| "learning_rate": 4.329188315254196e-05, |
| "loss": 1.1702531576156616, |
| "mean_token_accuracy": 0.6607685834169388, |
| "num_tokens": 8569426.0, |
| "step": 66 |
| }, |
| { |
| "entropy": 1.1880214363336563, |
| "epoch": 0.8687196110210696, |
| "grad_norm": 0.10245856642723083, |
| "learning_rate": 4.3048902348863116e-05, |
| "loss": 1.1839733123779297, |
| "mean_token_accuracy": 0.658528208732605, |
| "num_tokens": 8698056.0, |
| "step": 67 |
| }, |
| { |
| "entropy": 1.1805013716220856, |
| "epoch": 0.8816855753646677, |
| "grad_norm": 0.1010119840502739, |
| "learning_rate": 4.280230713577564e-05, |
| "loss": 1.179073452949524, |
| "mean_token_accuracy": 0.6590162664651871, |
| "num_tokens": 8828822.0, |
| "step": 68 |
| }, |
| { |
| "entropy": 1.1775793582201004, |
| "epoch": 0.8946515397082658, |
| "grad_norm": 0.10408595204353333, |
| "learning_rate": 4.255214689556557e-05, |
| "loss": 1.1802899837493896, |
| "mean_token_accuracy": 0.6601392850279808, |
| "num_tokens": 8958617.0, |
| "step": 69 |
| }, |
| { |
| "entropy": 1.1794121712446213, |
| "epoch": 0.9076175040518638, |
| "grad_norm": 0.10349196195602417, |
| "learning_rate": 4.229847172443866e-05, |
| "loss": 1.1859654188156128, |
| "mean_token_accuracy": 0.6571361273527145, |
| "num_tokens": 9089619.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 1.1704782098531723, |
| "epoch": 0.9205834683954619, |
| "grad_norm": 0.10455135256052017, |
| "learning_rate": 4.204133242248832e-05, |
| "loss": 1.1761753559112549, |
| "mean_token_accuracy": 0.661134235560894, |
| "num_tokens": 9220349.0, |
| "step": 71 |
| }, |
| { |
| "entropy": 1.2045030444860458, |
| "epoch": 0.93354943273906, |
| "grad_norm": 0.10628621280193329, |
| "learning_rate": 4.1780780483522575e-05, |
| "loss": 1.1999099254608154, |
| "mean_token_accuracy": 0.6541163548827171, |
| "num_tokens": 9350922.0, |
| "step": 72 |
| }, |
| { |
| "entropy": 1.194443255662918, |
| "epoch": 0.946515397082658, |
| "grad_norm": 0.10347249358892441, |
| "learning_rate": 4.151686808475204e-05, |
| "loss": 1.191763162612915, |
| "mean_token_accuracy": 0.6565472781658173, |
| "num_tokens": 9479617.0, |
| "step": 73 |
| }, |
| { |
| "entropy": 1.1695558428764343, |
| "epoch": 0.9594813614262561, |
| "grad_norm": 0.1053929403424263, |
| "learning_rate": 4.1249648076341165e-05, |
| "loss": 1.17070472240448, |
| "mean_token_accuracy": 0.662074476480484, |
| "num_tokens": 9609933.0, |
| "step": 74 |
| }, |
| { |
| "entropy": 1.1687128692865372, |
| "epoch": 0.9724473257698542, |
| "grad_norm": 0.10350026190280914, |
| "learning_rate": 4.0979173970824626e-05, |
| "loss": 1.1742582321166992, |
| "mean_token_accuracy": 0.6614358499646187, |
| "num_tokens": 9740065.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 1.1681682914495468, |
| "epoch": 0.9854132901134521, |
| "grad_norm": 0.10243335366249084, |
| "learning_rate": 4.070549993239106e-05, |
| "loss": 1.1658577919006348, |
| "mean_token_accuracy": 0.6637781262397766, |
| "num_tokens": 9870742.0, |
| "step": 76 |
| }, |
| { |
| "entropy": 1.1639882773160934, |
| "epoch": 0.9983792544570502, |
| "grad_norm": 0.10228604823350906, |
| "learning_rate": 4.0428680766036384e-05, |
| "loss": 1.1644949913024902, |
| "mean_token_accuracy": 0.6624981611967087, |
| "num_tokens": 10001320.0, |
| "step": 77 |
| }, |
| { |
| "entropy": 1.1632845401763916, |
| "epoch": 1.0, |
| "grad_norm": 0.2728025019168854, |
| "learning_rate": 4.0148771906588706e-05, |
| "loss": 1.1762704849243164, |
| "mean_token_accuracy": 0.6677740812301636, |
| "num_tokens": 10009153.0, |
| "step": 78 |
| }, |
| { |
| "entropy": 1.1636807769536972, |
| "epoch": 1.012965964343598, |
| "grad_norm": 0.10475616157054901, |
| "learning_rate": 3.986582940760717e-05, |
| "loss": 1.148669958114624, |
| "mean_token_accuracy": 0.6649533659219742, |
| "num_tokens": 10140011.0, |
| "step": 79 |
| }, |
| { |
| "entropy": 1.1557996571063995, |
| "epoch": 1.0259319286871962, |
| "grad_norm": 0.10492753237485886, |
| "learning_rate": 3.957990993015683e-05, |
| "loss": 1.1505277156829834, |
| "mean_token_accuracy": 0.6668093428015709, |
| "num_tokens": 10270495.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 1.15270234644413, |
| "epoch": 1.0388978930307942, |
| "grad_norm": 0.11243247240781784, |
| "learning_rate": 3.929107073146197e-05, |
| "loss": 1.1362740993499756, |
| "mean_token_accuracy": 0.6668569073081017, |
| "num_tokens": 10399470.0, |
| "step": 81 |
| }, |
| { |
| "entropy": 1.1315193176269531, |
| "epoch": 1.0518638573743921, |
| "grad_norm": 0.10758878290653229, |
| "learning_rate": 3.899936965343989e-05, |
| "loss": 1.124503254890442, |
| "mean_token_accuracy": 0.6695496663451195, |
| "num_tokens": 10529305.0, |
| "step": 82 |
| }, |
| { |
| "entropy": 1.1181457191705704, |
| "epoch": 1.0648298217179903, |
| "grad_norm": 0.10492865741252899, |
| "learning_rate": 3.8704865111117746e-05, |
| "loss": 1.115187406539917, |
| "mean_token_accuracy": 0.6714175269007683, |
| "num_tokens": 10658946.0, |
| "step": 83 |
| }, |
| { |
| "entropy": 1.0976143777370453, |
| "epoch": 1.0777957860615883, |
| "grad_norm": 0.1108441948890686, |
| "learning_rate": 3.840761608093456e-05, |
| "loss": 1.1016005277633667, |
| "mean_token_accuracy": 0.6776464283466339, |
| "num_tokens": 10785329.0, |
| "step": 84 |
| }, |
| { |
| "entropy": 1.0979181677103043, |
| "epoch": 1.0907617504051863, |
| "grad_norm": 0.10647857189178467, |
| "learning_rate": 3.8107682088930794e-05, |
| "loss": 1.1082489490509033, |
| "mean_token_accuracy": 0.6754170134663582, |
| "num_tokens": 10915123.0, |
| "step": 85 |
| }, |
| { |
| "entropy": 1.116148591041565, |
| "epoch": 1.1037277147487845, |
| "grad_norm": 0.10859860479831696, |
| "learning_rate": 3.7805123198827857e-05, |
| "loss": 1.1278622150421143, |
| "mean_token_accuracy": 0.6695821657776833, |
| "num_tokens": 11045591.0, |
| "step": 86 |
| }, |
| { |
| "entropy": 1.1232954412698746, |
| "epoch": 1.1166936790923825, |
| "grad_norm": 0.11128611862659454, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 1.1274020671844482, |
| "mean_token_accuracy": 0.671474426984787, |
| "num_tokens": 11175412.0, |
| "step": 87 |
| }, |
| { |
| "entropy": 1.1286661922931671, |
| "epoch": 1.1296596434359805, |
| "grad_norm": 0.10658227652311325, |
| "learning_rate": 3.719237359534087e-05, |
| "loss": 1.1328142881393433, |
| "mean_token_accuracy": 0.6698684319853783, |
| "num_tokens": 11305669.0, |
| "step": 88 |
| }, |
| { |
| "entropy": 1.127964898943901, |
| "epoch": 1.1426256077795787, |
| "grad_norm": 0.1069759875535965, |
| "learning_rate": 3.688230558902725e-05, |
| "loss": 1.1221802234649658, |
| "mean_token_accuracy": 0.6720241084694862, |
| "num_tokens": 11433238.0, |
| "step": 89 |
| }, |
| { |
| "entropy": 1.1164967715740204, |
| "epoch": 1.1555915721231766, |
| "grad_norm": 0.1038687601685524, |
| "learning_rate": 3.656985807418248e-05, |
| "loss": 1.1091525554656982, |
| "mean_token_accuracy": 0.6741333156824112, |
| "num_tokens": 11563958.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 1.119084969162941, |
| "epoch": 1.1685575364667746, |
| "grad_norm": 0.10730428993701935, |
| "learning_rate": 3.6255093620441834e-05, |
| "loss": 1.1172475814819336, |
| "mean_token_accuracy": 0.6720305904746056, |
| "num_tokens": 11694626.0, |
| "step": 91 |
| }, |
| { |
| "entropy": 1.1386660188436508, |
| "epoch": 1.1815235008103728, |
| "grad_norm": 0.11028113216161728, |
| "learning_rate": 3.593807526142261e-05, |
| "loss": 1.1373463869094849, |
| "mean_token_accuracy": 0.6680505573749542, |
| "num_tokens": 11824157.0, |
| "step": 92 |
| }, |
| { |
| "entropy": 1.128893181681633, |
| "epoch": 1.1944894651539708, |
| "grad_norm": 0.11066646128892899, |
| "learning_rate": 3.56188664821012e-05, |
| "loss": 1.1258357763290405, |
| "mean_token_accuracy": 0.6708294078707695, |
| "num_tokens": 11954860.0, |
| "step": 93 |
| }, |
| { |
| "entropy": 1.1333434879779816, |
| "epoch": 1.2074554294975688, |
| "grad_norm": 0.10427077114582062, |
| "learning_rate": 3.529753120609982e-05, |
| "loss": 1.1275739669799805, |
| "mean_token_accuracy": 0.6714382618665695, |
| "num_tokens": 12084728.0, |
| "step": 94 |
| }, |
| { |
| "entropy": 1.1430685371160507, |
| "epoch": 1.220421393841167, |
| "grad_norm": 0.10981430858373642, |
| "learning_rate": 3.497413378288541e-05, |
| "loss": 1.1324477195739746, |
| "mean_token_accuracy": 0.6704236418008804, |
| "num_tokens": 12215214.0, |
| "step": 95 |
| }, |
| { |
| "entropy": 1.1366370916366577, |
| "epoch": 1.233387358184765, |
| "grad_norm": 0.10740207880735397, |
| "learning_rate": 3.464873897488322e-05, |
| "loss": 1.1347224712371826, |
| "mean_token_accuracy": 0.6679130420088768, |
| "num_tokens": 12345791.0, |
| "step": 96 |
| }, |
| { |
| "entropy": 1.1018346101045609, |
| "epoch": 1.246353322528363, |
| "grad_norm": 0.10746090114116669, |
| "learning_rate": 3.432141194450772e-05, |
| "loss": 1.0866354703903198, |
| "mean_token_accuracy": 0.6808393970131874, |
| "num_tokens": 12475633.0, |
| "step": 97 |
| }, |
| { |
| "entropy": 1.1090585142374039, |
| "epoch": 1.2593192868719612, |
| "grad_norm": 0.10877131670713425, |
| "learning_rate": 3.39922182411134e-05, |
| "loss": 1.1041377782821655, |
| "mean_token_accuracy": 0.6753545328974724, |
| "num_tokens": 12605177.0, |
| "step": 98 |
| }, |
| { |
| "entropy": 1.1077013164758682, |
| "epoch": 1.2722852512155591, |
| "grad_norm": 0.10926997661590576, |
| "learning_rate": 3.3661223787868094e-05, |
| "loss": 1.1172577142715454, |
| "mean_token_accuracy": 0.6722195670008659, |
| "num_tokens": 12735595.0, |
| "step": 99 |
| }, |
| { |
| "entropy": 1.1127658933401108, |
| "epoch": 1.2852512155591573, |
| "grad_norm": 0.10727502405643463, |
| "learning_rate": 3.332849486855144e-05, |
| "loss": 1.1174246072769165, |
| "mean_token_accuracy": 0.6732314750552177, |
| "num_tokens": 12865899.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 1.0990982204675674, |
| "epoch": 1.2982171799027553, |
| "grad_norm": 0.10772087424993515, |
| "learning_rate": 3.2994098114281134e-05, |
| "loss": 1.1063733100891113, |
| "mean_token_accuracy": 0.6763543859124184, |
| "num_tokens": 12996509.0, |
| "step": 101 |
| }, |
| { |
| "entropy": 1.1201854348182678, |
| "epoch": 1.3111831442463533, |
| "grad_norm": 0.11184152215719223, |
| "learning_rate": 3.265810049016959e-05, |
| "loss": 1.1337658166885376, |
| "mean_token_accuracy": 0.6663447916507721, |
| "num_tokens": 13126367.0, |
| "step": 102 |
| }, |
| { |
| "entropy": 1.1044498831033707, |
| "epoch": 1.3241491085899515, |
| "grad_norm": 0.10385634750127792, |
| "learning_rate": 3.232056928191376e-05, |
| "loss": 1.1014032363891602, |
| "mean_token_accuracy": 0.6749187037348747, |
| "num_tokens": 13256160.0, |
| "step": 103 |
| }, |
| { |
| "entropy": 1.1139792203903198, |
| "epoch": 1.3371150729335495, |
| "grad_norm": 0.10617262125015259, |
| "learning_rate": 3.1981572082320756e-05, |
| "loss": 1.114381194114685, |
| "mean_token_accuracy": 0.6730919182300568, |
| "num_tokens": 13386686.0, |
| "step": 104 |
| }, |
| { |
| "entropy": 1.109263002872467, |
| "epoch": 1.3500810372771475, |
| "grad_norm": 0.10793962329626083, |
| "learning_rate": 3.164117677777191e-05, |
| "loss": 1.1114559173583984, |
| "mean_token_accuracy": 0.6728995367884636, |
| "num_tokens": 13517375.0, |
| "step": 105 |
| }, |
| { |
| "entropy": 1.1261898875236511, |
| "epoch": 1.3630470016207457, |
| "grad_norm": 0.11161792278289795, |
| "learning_rate": 3.1299451534628135e-05, |
| "loss": 1.1193037033081055, |
| "mean_token_accuracy": 0.6697596535086632, |
| "num_tokens": 13646394.0, |
| "step": 106 |
| }, |
| { |
| "entropy": 1.1466472148895264, |
| "epoch": 1.3760129659643436, |
| "grad_norm": 0.10738440603017807, |
| "learning_rate": 3.0956464785579124e-05, |
| "loss": 1.1412131786346436, |
| "mean_token_accuracy": 0.6665833070874214, |
| "num_tokens": 13773038.0, |
| "step": 107 |
| }, |
| { |
| "entropy": 1.1069310754537582, |
| "epoch": 1.3889789303079416, |
| "grad_norm": 0.10599587112665176, |
| "learning_rate": 3.061228521593931e-05, |
| "loss": 1.0983221530914307, |
| "mean_token_accuracy": 0.674115814268589, |
| "num_tokens": 13903468.0, |
| "step": 108 |
| }, |
| { |
| "entropy": 1.1233480125665665, |
| "epoch": 1.4019448946515398, |
| "grad_norm": 0.10892873257398605, |
| "learning_rate": 3.0266981749893157e-05, |
| "loss": 1.126780390739441, |
| "mean_token_accuracy": 0.6726226657629013, |
| "num_tokens": 14033787.0, |
| "step": 109 |
| }, |
| { |
| "entropy": 1.096241980791092, |
| "epoch": 1.4149108589951378, |
| "grad_norm": 0.10745301842689514, |
| "learning_rate": 2.9920623536692638e-05, |
| "loss": 1.1037087440490723, |
| "mean_token_accuracy": 0.6748801171779633, |
| "num_tokens": 14163916.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 1.1101316660642624, |
| "epoch": 1.4278768233387358, |
| "grad_norm": 0.10952413827180862, |
| "learning_rate": 2.9573279936809667e-05, |
| "loss": 1.1070921421051025, |
| "mean_token_accuracy": 0.6747486442327499, |
| "num_tokens": 14294199.0, |
| "step": 111 |
| }, |
| { |
| "entropy": 1.0932272672653198, |
| "epoch": 1.440842787682334, |
| "grad_norm": 0.11039680987596512, |
| "learning_rate": 2.9225020508046232e-05, |
| "loss": 1.091570496559143, |
| "mean_token_accuracy": 0.677759513258934, |
| "num_tokens": 14424508.0, |
| "step": 112 |
| }, |
| { |
| "entropy": 1.1011270582675934, |
| "epoch": 1.453808752025932, |
| "grad_norm": 0.10966617614030838, |
| "learning_rate": 2.8875914991604948e-05, |
| "loss": 1.0965993404388428, |
| "mean_token_accuracy": 0.6767654791474342, |
| "num_tokens": 14555279.0, |
| "step": 113 |
| }, |
| { |
| "entropy": 1.121464490890503, |
| "epoch": 1.46677471636953, |
| "grad_norm": 0.1066274344921112, |
| "learning_rate": 2.8526033298122985e-05, |
| "loss": 1.1188894510269165, |
| "mean_token_accuracy": 0.672943226993084, |
| "num_tokens": 14685565.0, |
| "step": 114 |
| }, |
| { |
| "entropy": 1.1038088649511337, |
| "epoch": 1.4797406807131281, |
| "grad_norm": 0.10668732225894928, |
| "learning_rate": 2.8175445493671972e-05, |
| "loss": 1.1041887998580933, |
| "mean_token_accuracy": 0.6750313937664032, |
| "num_tokens": 14812759.0, |
| "step": 115 |
| }, |
| { |
| "entropy": 1.0958739817142487, |
| "epoch": 1.4927066450567261, |
| "grad_norm": 0.10686630755662918, |
| "learning_rate": 2.782422178572682e-05, |
| "loss": 1.0925776958465576, |
| "mean_token_accuracy": 0.6785185039043427, |
| "num_tokens": 14941000.0, |
| "step": 116 |
| }, |
| { |
| "entropy": 1.0849932879209518, |
| "epoch": 1.505672609400324, |
| "grad_norm": 0.11030446738004684, |
| "learning_rate": 2.7472432509106248e-05, |
| "loss": 1.089538812637329, |
| "mean_token_accuracy": 0.6786462068557739, |
| "num_tokens": 15070714.0, |
| "step": 117 |
| }, |
| { |
| "entropy": 1.0971782058477402, |
| "epoch": 1.5186385737439223, |
| "grad_norm": 0.10946783423423767, |
| "learning_rate": 2.7120148111887732e-05, |
| "loss": 1.1029260158538818, |
| "mean_token_accuracy": 0.6733038946986198, |
| "num_tokens": 15200961.0, |
| "step": 118 |
| }, |
| { |
| "entropy": 1.097448006272316, |
| "epoch": 1.5316045380875203, |
| "grad_norm": 0.11014755070209503, |
| "learning_rate": 2.6767439141299865e-05, |
| "loss": 1.108152151107788, |
| "mean_token_accuracy": 0.6721945106983185, |
| "num_tokens": 15331874.0, |
| "step": 119 |
| }, |
| { |
| "entropy": 1.0913252234458923, |
| "epoch": 1.5445705024311183, |
| "grad_norm": 0.11296916753053665, |
| "learning_rate": 2.6414376229594813e-05, |
| "loss": 1.0995609760284424, |
| "mean_token_accuracy": 0.6765489876270294, |
| "num_tokens": 15461994.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 1.085170827805996, |
| "epoch": 1.5575364667747165, |
| "grad_norm": 0.10830508917570114, |
| "learning_rate": 2.606103007990371e-05, |
| "loss": 1.0883557796478271, |
| "mean_token_accuracy": 0.6772569045424461, |
| "num_tokens": 15590673.0, |
| "step": 121 |
| }, |
| { |
| "entropy": 1.1014840751886368, |
| "epoch": 1.5705024311183144, |
| "grad_norm": 0.10925617814064026, |
| "learning_rate": 2.570747145207796e-05, |
| "loss": 1.1025630235671997, |
| "mean_token_accuracy": 0.6747682243585587, |
| "num_tokens": 15719889.0, |
| "step": 122 |
| }, |
| { |
| "entropy": 1.1068747788667679, |
| "epoch": 1.5834683954619124, |
| "grad_norm": 0.11549171060323715, |
| "learning_rate": 2.5353771148519057e-05, |
| "loss": 1.0953247547149658, |
| "mean_token_accuracy": 0.6782373338937759, |
| "num_tokens": 15849490.0, |
| "step": 123 |
| }, |
| { |
| "entropy": 1.108807235956192, |
| "epoch": 1.5964343598055106, |
| "grad_norm": 0.11398264020681381, |
| "learning_rate": 2.5e-05, |
| "loss": 1.1013944149017334, |
| "mean_token_accuracy": 0.6768676191568375, |
| "num_tokens": 15976291.0, |
| "step": 124 |
| }, |
| { |
| "entropy": 1.1027465015649796, |
| "epoch": 1.6094003241491086, |
| "grad_norm": 0.10796625912189484, |
| "learning_rate": 2.4646228851480956e-05, |
| "loss": 1.104917049407959, |
| "mean_token_accuracy": 0.6731575652956963, |
| "num_tokens": 16106724.0, |
| "step": 125 |
| }, |
| { |
| "entropy": 1.1067415177822113, |
| "epoch": 1.6223662884927066, |
| "grad_norm": 0.1104840338230133, |
| "learning_rate": 2.429252854792205e-05, |
| "loss": 1.1054627895355225, |
| "mean_token_accuracy": 0.6742062270641327, |
| "num_tokens": 16234720.0, |
| "step": 126 |
| }, |
| { |
| "entropy": 1.0894858539104462, |
| "epoch": 1.6353322528363048, |
| "grad_norm": 0.10652334243059158, |
| "learning_rate": 2.39389699200963e-05, |
| "loss": 1.086952805519104, |
| "mean_token_accuracy": 0.6782950535416603, |
| "num_tokens": 16365259.0, |
| "step": 127 |
| }, |
| { |
| "entropy": 1.0954291075468063, |
| "epoch": 1.6482982171799028, |
| "grad_norm": 0.10658770799636841, |
| "learning_rate": 2.358562377040519e-05, |
| "loss": 1.0909897089004517, |
| "mean_token_accuracy": 0.6780865713953972, |
| "num_tokens": 16495495.0, |
| "step": 128 |
| }, |
| { |
| "entropy": 1.1093836724758148, |
| "epoch": 1.6612641815235007, |
| "grad_norm": 0.10828336328268051, |
| "learning_rate": 2.3232560858700137e-05, |
| "loss": 1.1097731590270996, |
| "mean_token_accuracy": 0.6727545708417892, |
| "num_tokens": 16626073.0, |
| "step": 129 |
| }, |
| { |
| "entropy": 1.0927350223064423, |
| "epoch": 1.674230145867099, |
| "grad_norm": 0.10621214658021927, |
| "learning_rate": 2.287985188811228e-05, |
| "loss": 1.0940251350402832, |
| "mean_token_accuracy": 0.6761066913604736, |
| "num_tokens": 16756555.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 1.086726352572441, |
| "epoch": 1.687196110210697, |
| "grad_norm": 0.11290633678436279, |
| "learning_rate": 2.2527567490893758e-05, |
| "loss": 1.077509880065918, |
| "mean_token_accuracy": 0.6806528195738792, |
| "num_tokens": 16885995.0, |
| "step": 131 |
| }, |
| { |
| "entropy": 1.1018610298633575, |
| "epoch": 1.700162074554295, |
| "grad_norm": 0.10830546915531158, |
| "learning_rate": 2.2175778214273185e-05, |
| "loss": 1.0975083112716675, |
| "mean_token_accuracy": 0.673214353621006, |
| "num_tokens": 17016748.0, |
| "step": 132 |
| }, |
| { |
| "entropy": 1.0952757894992828, |
| "epoch": 1.7131280388978931, |
| "grad_norm": 0.10807640105485916, |
| "learning_rate": 2.182455450632803e-05, |
| "loss": 1.0957316160202026, |
| "mean_token_accuracy": 0.6757252290844917, |
| "num_tokens": 17146683.0, |
| "step": 133 |
| }, |
| { |
| "entropy": 1.0976209491491318, |
| "epoch": 1.726094003241491, |
| "grad_norm": 0.10800565779209137, |
| "learning_rate": 2.1473966701877025e-05, |
| "loss": 1.096419334411621, |
| "mean_token_accuracy": 0.6746199205517769, |
| "num_tokens": 17274973.0, |
| "step": 134 |
| }, |
| { |
| "entropy": 1.0751748234033585, |
| "epoch": 1.739059967585089, |
| "grad_norm": 0.10800585150718689, |
| "learning_rate": 2.1124085008395054e-05, |
| "loss": 1.0767910480499268, |
| "mean_token_accuracy": 0.6789162456989288, |
| "num_tokens": 17405875.0, |
| "step": 135 |
| }, |
| { |
| "entropy": 1.0925790071487427, |
| "epoch": 1.7520259319286873, |
| "grad_norm": 0.11018182337284088, |
| "learning_rate": 2.0774979491953777e-05, |
| "loss": 1.0945611000061035, |
| "mean_token_accuracy": 0.6763977259397507, |
| "num_tokens": 17536552.0, |
| "step": 136 |
| }, |
| { |
| "entropy": 1.0801940858364105, |
| "epoch": 1.7649918962722853, |
| "grad_norm": 0.11004664748907089, |
| "learning_rate": 2.0426720063190335e-05, |
| "loss": 1.0840024948120117, |
| "mean_token_accuracy": 0.6795907840132713, |
| "num_tokens": 17667084.0, |
| "step": 137 |
| }, |
| { |
| "entropy": 1.101774275302887, |
| "epoch": 1.7779578606158832, |
| "grad_norm": 0.11290085315704346, |
| "learning_rate": 2.0079376463307368e-05, |
| "loss": 1.1003146171569824, |
| "mean_token_accuracy": 0.6725303083658218, |
| "num_tokens": 17797154.0, |
| "step": 138 |
| }, |
| { |
| "entropy": 1.0876109898090363, |
| "epoch": 1.7909238249594814, |
| "grad_norm": 0.10923700779676437, |
| "learning_rate": 1.973301825010685e-05, |
| "loss": 1.0939981937408447, |
| "mean_token_accuracy": 0.6761084944009781, |
| "num_tokens": 17927623.0, |
| "step": 139 |
| }, |
| { |
| "entropy": 1.0950998067855835, |
| "epoch": 1.8038897893030794, |
| "grad_norm": 0.10761875659227371, |
| "learning_rate": 1.9387714784060685e-05, |
| "loss": 1.0969429016113281, |
| "mean_token_accuracy": 0.6767537295818329, |
| "num_tokens": 18057219.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 1.0717721432447433, |
| "epoch": 1.8168557536466774, |
| "grad_norm": 0.10666397213935852, |
| "learning_rate": 1.904353521442088e-05, |
| "loss": 1.0674877166748047, |
| "mean_token_accuracy": 0.6818057596683502, |
| "num_tokens": 18187740.0, |
| "step": 141 |
| }, |
| { |
| "entropy": 1.0777895599603653, |
| "epoch": 1.8298217179902756, |
| "grad_norm": 0.10904243588447571, |
| "learning_rate": 1.8700548465371874e-05, |
| "loss": 1.0738530158996582, |
| "mean_token_accuracy": 0.6809927076101303, |
| "num_tokens": 18317756.0, |
| "step": 142 |
| }, |
| { |
| "entropy": 1.101785123348236, |
| "epoch": 1.8427876823338736, |
| "grad_norm": 0.10715875774621964, |
| "learning_rate": 1.8358823222228097e-05, |
| "loss": 1.0919270515441895, |
| "mean_token_accuracy": 0.678776703774929, |
| "num_tokens": 18447271.0, |
| "step": 143 |
| }, |
| { |
| "entropy": 1.0927452445030212, |
| "epoch": 1.8557536466774716, |
| "grad_norm": 0.10798949003219604, |
| "learning_rate": 1.801842791767925e-05, |
| "loss": 1.0860735177993774, |
| "mean_token_accuracy": 0.6769154742360115, |
| "num_tokens": 18575231.0, |
| "step": 144 |
| }, |
| { |
| "entropy": 1.0916397273540497, |
| "epoch": 1.8687196110210698, |
| "grad_norm": 0.10715705901384354, |
| "learning_rate": 1.7679430718086243e-05, |
| "loss": 1.0911304950714111, |
| "mean_token_accuracy": 0.6768953427672386, |
| "num_tokens": 18706048.0, |
| "step": 145 |
| }, |
| { |
| "entropy": 1.0951158255338669, |
| "epoch": 1.8816855753646677, |
| "grad_norm": 0.1076439917087555, |
| "learning_rate": 1.7341899509830416e-05, |
| "loss": 1.0997498035430908, |
| "mean_token_accuracy": 0.6743926852941513, |
| "num_tokens": 18835570.0, |
| "step": 146 |
| }, |
| { |
| "entropy": 1.0841081887483597, |
| "epoch": 1.8946515397082657, |
| "grad_norm": 0.10601551085710526, |
| "learning_rate": 1.700590188571887e-05, |
| "loss": 1.0836725234985352, |
| "mean_token_accuracy": 0.6787150353193283, |
| "num_tokens": 18965989.0, |
| "step": 147 |
| }, |
| { |
| "entropy": 1.0767425745725632, |
| "epoch": 1.907617504051864, |
| "grad_norm": 0.10804559290409088, |
| "learning_rate": 1.667150513144856e-05, |
| "loss": 1.0883257389068604, |
| "mean_token_accuracy": 0.6779815703630447, |
| "num_tokens": 19096708.0, |
| "step": 148 |
| }, |
| { |
| "entropy": 1.060413271188736, |
| "epoch": 1.920583468395462, |
| "grad_norm": 0.10727375745773315, |
| "learning_rate": 1.633877621213192e-05, |
| "loss": 1.0628106594085693, |
| "mean_token_accuracy": 0.6838557049632072, |
| "num_tokens": 19227293.0, |
| "step": 149 |
| }, |
| { |
| "entropy": 1.0897396057844162, |
| "epoch": 1.9335494327390599, |
| "grad_norm": 0.10783149302005768, |
| "learning_rate": 1.6007781758886607e-05, |
| "loss": 1.094234824180603, |
| "mean_token_accuracy": 0.6787025779485703, |
| "num_tokens": 19357895.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 1.0884075164794922, |
| "epoch": 1.946515397082658, |
| "grad_norm": 0.10528931021690369, |
| "learning_rate": 1.567858805549229e-05, |
| "loss": 1.0923658609390259, |
| "mean_token_accuracy": 0.6776427254080772, |
| "num_tokens": 19488633.0, |
| "step": 151 |
| }, |
| { |
| "entropy": 1.0847600251436234, |
| "epoch": 1.959481361426256, |
| "grad_norm": 0.10627288371324539, |
| "learning_rate": 1.535126102511678e-05, |
| "loss": 1.0859086513519287, |
| "mean_token_accuracy": 0.6780032217502594, |
| "num_tokens": 19619364.0, |
| "step": 152 |
| }, |
| { |
| "entropy": 1.0796795934438705, |
| "epoch": 1.972447325769854, |
| "grad_norm": 0.10828571766614914, |
| "learning_rate": 1.5025866217114592e-05, |
| "loss": 1.0796010494232178, |
| "mean_token_accuracy": 0.6792254149913788, |
| "num_tokens": 19749912.0, |
| "step": 153 |
| }, |
| { |
| "entropy": 1.0738196671009064, |
| "epoch": 1.9854132901134522, |
| "grad_norm": 0.1061541959643364, |
| "learning_rate": 1.4702468793900188e-05, |
| "loss": 1.0770832300186157, |
| "mean_token_accuracy": 0.68254254758358, |
| "num_tokens": 19879298.0, |
| "step": 154 |
| }, |
| { |
| "entropy": 1.0984497964382172, |
| "epoch": 1.9983792544570502, |
| "grad_norm": 0.11212106049060822, |
| "learning_rate": 1.4381133517898804e-05, |
| "loss": 1.0974631309509277, |
| "mean_token_accuracy": 0.6762187778949738, |
| "num_tokens": 20010115.0, |
| "step": 155 |
| }, |
| { |
| "entropy": 1.0801098346710205, |
| "epoch": 2.0, |
| "grad_norm": 0.2994791865348816, |
| "learning_rate": 1.4061924738577403e-05, |
| "loss": 1.0866824388504028, |
| "mean_token_accuracy": 0.6810408234596252, |
| "num_tokens": 20018306.0, |
| "step": 156 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 234, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9.773824948630979e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
