{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 1.0, "global_step": 492, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004073319755600814, "grad_norm": 34.300819396972656, "learning_rate": 8.130081300813008e-09, "loss": 1.59619802236557, "step": 1 }, { "epoch": 0.008146639511201629, "grad_norm": 30.720197677612305, "learning_rate": 1.6260162601626016e-08, "loss": 1.468272864818573, "step": 2 }, { "epoch": 0.012219959266802444, "grad_norm": 30.16754722595215, "learning_rate": 2.4390243902439023e-08, "loss": 1.3843095302581787, "step": 3 }, { "epoch": 0.016293279022403257, "grad_norm": 38.58047103881836, "learning_rate": 3.252032520325203e-08, "loss": 1.7031245231628418, "step": 4 }, { "epoch": 0.020366598778004074, "grad_norm": 30.89760971069336, "learning_rate": 4.065040650406504e-08, "loss": 1.4844104647636414, "step": 5 }, { "epoch": 0.024439918533604887, "grad_norm": 34.434993743896484, "learning_rate": 4.878048780487805e-08, "loss": 1.574910283088684, "step": 6 }, { "epoch": 0.028513238289205704, "grad_norm": 32.540470123291016, "learning_rate": 5.6910569105691055e-08, "loss": 1.4606674909591675, "step": 7 }, { "epoch": 0.032586558044806514, "grad_norm": 36.41299819946289, "learning_rate": 6.504065040650406e-08, "loss": 1.553576111793518, "step": 8 }, { "epoch": 0.03665987780040733, "grad_norm": 34.50511932373047, "learning_rate": 7.317073170731706e-08, "loss": 1.3344553709030151, "step": 9 }, { "epoch": 0.04073319755600815, "grad_norm": 27.898704528808594, "learning_rate": 8.130081300813008e-08, "loss": 1.3406395316123962, "step": 10 }, { "epoch": 0.04480651731160896, "grad_norm": 29.29271125793457, "learning_rate": 8.943089430894309e-08, "loss": 1.4415303468704224, "step": 11 }, { "epoch": 0.048879837067209775, "grad_norm": 28.2354736328125, "learning_rate": 9.75609756097561e-08, "loss": 1.2696096301078796, "step": 12 }, { "epoch": 0.05295315682281059, "grad_norm": 35.44163131713867, "learning_rate": 1.0569105691056911e-07, "loss": 1.598312497138977, "step": 13 }, { "epoch": 0.05702647657841141, "grad_norm": 26.94402313232422, "learning_rate": 1.1382113821138211e-07, "loss": 1.3497812747955322, "step": 14 }, { "epoch": 0.06109979633401222, "grad_norm": 37.78248977661133, "learning_rate": 1.219512195121951e-07, "loss": 1.5689660906791687, "step": 15 }, { "epoch": 0.06517311608961303, "grad_norm": 31.73078155517578, "learning_rate": 1.3008130081300813e-07, "loss": 1.525648295879364, "step": 16 }, { "epoch": 0.06924643584521385, "grad_norm": 27.77250862121582, "learning_rate": 1.3821138211382114e-07, "loss": 1.304672360420227, "step": 17 }, { "epoch": 0.07331975560081466, "grad_norm": 28.092498779296875, "learning_rate": 1.4634146341463413e-07, "loss": 1.346445381641388, "step": 18 }, { "epoch": 0.07739307535641547, "grad_norm": 30.995866775512695, "learning_rate": 1.5447154471544717e-07, "loss": 1.447025179862976, "step": 19 }, { "epoch": 0.0814663951120163, "grad_norm": 28.858421325683594, "learning_rate": 1.6260162601626016e-07, "loss": 1.3801668882369995, "step": 20 }, { "epoch": 0.0855397148676171, "grad_norm": 31.91228485107422, "learning_rate": 1.7073170731707317e-07, "loss": 1.4577875137329102, "step": 21 }, { "epoch": 0.08961303462321792, "grad_norm": 31.215259552001953, "learning_rate": 1.7886178861788619e-07, "loss": 1.4091373682022095, "step": 22 }, { "epoch": 0.09368635437881874, "grad_norm": 30.24734115600586, "learning_rate": 1.8699186991869917e-07, "loss": 1.4649581909179688, "step": 23 }, { "epoch": 0.09775967413441955, "grad_norm": 31.560291290283203, "learning_rate": 1.951219512195122e-07, "loss": 1.5308585166931152, "step": 24 }, { "epoch": 0.10183299389002037, "grad_norm": 27.27391242980957, "learning_rate": 2.032520325203252e-07, "loss": 1.5144553780555725, "step": 25 }, { "epoch": 0.10590631364562118, "grad_norm": 29.813785552978516, "learning_rate": 2.1138211382113822e-07, "loss": 1.519466757774353, "step": 26 }, { "epoch": 0.109979633401222, "grad_norm": 24.201751708984375, "learning_rate": 2.195121951219512e-07, "loss": 1.3116011023521423, "step": 27 }, { "epoch": 0.11405295315682282, "grad_norm": 27.95865249633789, "learning_rate": 2.2764227642276422e-07, "loss": 1.4637184143066406, "step": 28 }, { "epoch": 0.11812627291242363, "grad_norm": 26.65915870666504, "learning_rate": 2.3577235772357723e-07, "loss": 1.4885194301605225, "step": 29 }, { "epoch": 0.12219959266802444, "grad_norm": 27.386289596557617, "learning_rate": 2.439024390243902e-07, "loss": 1.3836334347724915, "step": 30 }, { "epoch": 0.12627291242362526, "grad_norm": 25.87419319152832, "learning_rate": 2.520325203252032e-07, "loss": 1.3642336130142212, "step": 31 }, { "epoch": 0.13034623217922606, "grad_norm": 26.620105743408203, "learning_rate": 2.6016260162601625e-07, "loss": 1.3461121916770935, "step": 32 }, { "epoch": 0.13441955193482688, "grad_norm": 22.665058135986328, "learning_rate": 2.682926829268293e-07, "loss": 1.2577590942382812, "step": 33 }, { "epoch": 0.1384928716904277, "grad_norm": 23.679920196533203, "learning_rate": 2.764227642276423e-07, "loss": 1.2572017908096313, "step": 34 }, { "epoch": 0.1425661914460285, "grad_norm": 25.136371612548828, "learning_rate": 2.8455284552845527e-07, "loss": 1.2670851349830627, "step": 35 }, { "epoch": 0.14663951120162932, "grad_norm": 21.567337036132812, "learning_rate": 2.9268292682926825e-07, "loss": 1.242683231830597, "step": 36 }, { "epoch": 0.15071283095723015, "grad_norm": 20.61647605895996, "learning_rate": 3.008130081300813e-07, "loss": 1.279579222202301, "step": 37 }, { "epoch": 0.15478615071283094, "grad_norm": 20.656513214111328, "learning_rate": 3.0894308943089434e-07, "loss": 1.2040475606918335, "step": 38 }, { "epoch": 0.15885947046843177, "grad_norm": 22.86530876159668, "learning_rate": 3.170731707317073e-07, "loss": 1.2522715330123901, "step": 39 }, { "epoch": 0.1629327902240326, "grad_norm": 20.22757911682129, "learning_rate": 3.252032520325203e-07, "loss": 1.2012774348258972, "step": 40 }, { "epoch": 0.1670061099796334, "grad_norm": 23.09739875793457, "learning_rate": 3.333333333333333e-07, "loss": 1.2088268399238586, "step": 41 }, { "epoch": 0.1710794297352342, "grad_norm": 22.845685958862305, "learning_rate": 3.4146341463414634e-07, "loss": 1.0982880592346191, "step": 42 }, { "epoch": 0.17515274949083504, "grad_norm": 19.80814552307129, "learning_rate": 3.4959349593495933e-07, "loss": 1.1271469593048096, "step": 43 }, { "epoch": 0.17922606924643583, "grad_norm": 20.553686141967773, "learning_rate": 3.5772357723577237e-07, "loss": 1.0008204579353333, "step": 44 }, { "epoch": 0.18329938900203666, "grad_norm": 16.66282844543457, "learning_rate": 3.6585365853658536e-07, "loss": 0.9251897931098938, "step": 45 }, { "epoch": 0.18737270875763748, "grad_norm": 15.797308921813965, "learning_rate": 3.7398373983739835e-07, "loss": 1.0191328525543213, "step": 46 }, { "epoch": 0.19144602851323828, "grad_norm": 13.579208374023438, "learning_rate": 3.821138211382114e-07, "loss": 0.774791806936264, "step": 47 }, { "epoch": 0.1955193482688391, "grad_norm": 14.556002616882324, "learning_rate": 3.902439024390244e-07, "loss": 1.0026790797710419, "step": 48 }, { "epoch": 0.19959266802443992, "grad_norm": 14.489509582519531, "learning_rate": 3.9837398373983736e-07, "loss": 0.9430837631225586, "step": 49 }, { "epoch": 0.20366598778004075, "grad_norm": 12.495223999023438, "learning_rate": 4.065040650406504e-07, "loss": 0.8999880254268646, "step": 50 }, { "epoch": 0.20773930753564154, "grad_norm": 11.441575050354004, "learning_rate": 4.146341463414634e-07, "loss": 0.8320233225822449, "step": 51 }, { "epoch": 0.21181262729124237, "grad_norm": 10.894216537475586, "learning_rate": 4.2276422764227643e-07, "loss": 0.8139239549636841, "step": 52 }, { "epoch": 0.2158859470468432, "grad_norm": 10.404220581054688, "learning_rate": 4.308943089430894e-07, "loss": 0.8323288261890411, "step": 53 }, { "epoch": 0.219959266802444, "grad_norm": 10.463072776794434, "learning_rate": 4.390243902439024e-07, "loss": 0.882573276758194, "step": 54 }, { "epoch": 0.2240325865580448, "grad_norm": 10.669075012207031, "learning_rate": 4.471544715447154e-07, "loss": 0.749780923128128, "step": 55 }, { "epoch": 0.22810590631364563, "grad_norm": 10.453638076782227, "learning_rate": 4.5528455284552844e-07, "loss": 0.7727148830890656, "step": 56 }, { "epoch": 0.23217922606924643, "grad_norm": 11.427080154418945, "learning_rate": 4.634146341463415e-07, "loss": 0.8585084676742554, "step": 57 }, { "epoch": 0.23625254582484725, "grad_norm": 8.558117866516113, "learning_rate": 4.7154471544715447e-07, "loss": 0.7314337491989136, "step": 58 }, { "epoch": 0.24032586558044808, "grad_norm": 9.031648635864258, "learning_rate": 4.796747967479675e-07, "loss": 0.701579749584198, "step": 59 }, { "epoch": 0.24439918533604887, "grad_norm": 8.817708969116211, "learning_rate": 4.878048780487804e-07, "loss": 0.7815204560756683, "step": 60 }, { "epoch": 0.2484725050916497, "grad_norm": 8.00804615020752, "learning_rate": 4.959349593495934e-07, "loss": 0.655106246471405, "step": 61 }, { "epoch": 0.2525458248472505, "grad_norm": 6.538842678070068, "learning_rate": 5.040650406504064e-07, "loss": 0.6697916388511658, "step": 62 }, { "epoch": 0.25661914460285135, "grad_norm": 7.5446553230285645, "learning_rate": 5.121951219512195e-07, "loss": 0.7426944077014923, "step": 63 }, { "epoch": 0.2606924643584521, "grad_norm": 6.402474403381348, "learning_rate": 5.203252032520325e-07, "loss": 0.6401277780532837, "step": 64 }, { "epoch": 0.26476578411405294, "grad_norm": 7.257569313049316, "learning_rate": 5.284552845528455e-07, "loss": 0.6731106042861938, "step": 65 }, { "epoch": 0.26883910386965376, "grad_norm": 6.263636589050293, "learning_rate": 5.365853658536586e-07, "loss": 0.5806022882461548, "step": 66 }, { "epoch": 0.2729124236252546, "grad_norm": 5.273800849914551, "learning_rate": 5.447154471544715e-07, "loss": 0.5338439792394638, "step": 67 }, { "epoch": 0.2769857433808554, "grad_norm": 5.2786149978637695, "learning_rate": 5.528455284552846e-07, "loss": 0.5390533208847046, "step": 68 }, { "epoch": 0.28105906313645623, "grad_norm": 4.901702404022217, "learning_rate": 5.609756097560975e-07, "loss": 0.5899032056331635, "step": 69 }, { "epoch": 0.285132382892057, "grad_norm": 4.853933811187744, "learning_rate": 5.691056910569105e-07, "loss": 0.5600310862064362, "step": 70 }, { "epoch": 0.2892057026476578, "grad_norm": 4.680273532867432, "learning_rate": 5.772357723577236e-07, "loss": 0.5319355428218842, "step": 71 }, { "epoch": 0.29327902240325865, "grad_norm": 3.7406885623931885, "learning_rate": 5.853658536585365e-07, "loss": 0.508156955242157, "step": 72 }, { "epoch": 0.2973523421588595, "grad_norm": 4.389779567718506, "learning_rate": 5.934959349593496e-07, "loss": 0.49855048954486847, "step": 73 }, { "epoch": 0.3014256619144603, "grad_norm": 4.23866081237793, "learning_rate": 6.016260162601626e-07, "loss": 0.5242476612329483, "step": 74 }, { "epoch": 0.3054989816700611, "grad_norm": 4.1824951171875, "learning_rate": 6.097560975609756e-07, "loss": 0.532037615776062, "step": 75 }, { "epoch": 0.3095723014256619, "grad_norm": 3.7223150730133057, "learning_rate": 6.178861788617887e-07, "loss": 0.46959882974624634, "step": 76 }, { "epoch": 0.3136456211812627, "grad_norm": 3.545388698577881, "learning_rate": 6.260162601626016e-07, "loss": 0.4825982600450516, "step": 77 }, { "epoch": 0.31771894093686354, "grad_norm": 3.6351099014282227, "learning_rate": 6.341463414634146e-07, "loss": 0.5095209777355194, "step": 78 }, { "epoch": 0.32179226069246436, "grad_norm": 3.243072271347046, "learning_rate": 6.422764227642276e-07, "loss": 0.4842926263809204, "step": 79 }, { "epoch": 0.3258655804480652, "grad_norm": 3.5646300315856934, "learning_rate": 6.504065040650406e-07, "loss": 0.4908552020788193, "step": 80 }, { "epoch": 0.329938900203666, "grad_norm": 3.5380759239196777, "learning_rate": 6.585365853658536e-07, "loss": 0.4536065459251404, "step": 81 }, { "epoch": 0.3340122199592668, "grad_norm": 3.128525495529175, "learning_rate": 6.666666666666666e-07, "loss": 0.47657161951065063, "step": 82 }, { "epoch": 0.3380855397148676, "grad_norm": 3.3621485233306885, "learning_rate": 6.747967479674797e-07, "loss": 0.43791596591472626, "step": 83 }, { "epoch": 0.3421588594704684, "grad_norm": 3.39066219329834, "learning_rate": 6.829268292682927e-07, "loss": 0.42947711050510406, "step": 84 }, { "epoch": 0.34623217922606925, "grad_norm": 3.7795698642730713, "learning_rate": 6.910569105691057e-07, "loss": 0.4219910502433777, "step": 85 }, { "epoch": 0.35030549898167007, "grad_norm": 3.633206367492676, "learning_rate": 6.991869918699187e-07, "loss": 0.4253977984189987, "step": 86 }, { "epoch": 0.3543788187372709, "grad_norm": 3.6160175800323486, "learning_rate": 7.073170731707316e-07, "loss": 0.449339896440506, "step": 87 }, { "epoch": 0.35845213849287166, "grad_norm": 3.30557918548584, "learning_rate": 7.154471544715447e-07, "loss": 0.45001736283302307, "step": 88 }, { "epoch": 0.3625254582484725, "grad_norm": 3.1727640628814697, "learning_rate": 7.235772357723577e-07, "loss": 0.4165496975183487, "step": 89 }, { "epoch": 0.3665987780040733, "grad_norm": 3.073976516723633, "learning_rate": 7.317073170731707e-07, "loss": 0.4443822205066681, "step": 90 }, { "epoch": 0.37067209775967414, "grad_norm": 3.129105567932129, "learning_rate": 7.398373983739837e-07, "loss": 0.4265598952770233, "step": 91 }, { "epoch": 0.37474541751527496, "grad_norm": 3.1485190391540527, "learning_rate": 7.479674796747967e-07, "loss": 0.3882734924554825, "step": 92 }, { "epoch": 0.3788187372708758, "grad_norm": 3.1610565185546875, "learning_rate": 7.560975609756097e-07, "loss": 0.37010858952999115, "step": 93 }, { "epoch": 0.38289205702647655, "grad_norm": 3.039264440536499, "learning_rate": 7.642276422764228e-07, "loss": 0.400989294052124, "step": 94 }, { "epoch": 0.3869653767820774, "grad_norm": 2.9321980476379395, "learning_rate": 7.723577235772358e-07, "loss": 0.3771343380212784, "step": 95 }, { "epoch": 0.3910386965376782, "grad_norm": 2.807072162628174, "learning_rate": 7.804878048780488e-07, "loss": 0.4001482129096985, "step": 96 }, { "epoch": 0.395112016293279, "grad_norm": 2.8286941051483154, "learning_rate": 7.886178861788617e-07, "loss": 0.4234430640935898, "step": 97 }, { "epoch": 0.39918533604887985, "grad_norm": 2.9245986938476562, "learning_rate": 7.967479674796747e-07, "loss": 0.3854667395353317, "step": 98 }, { "epoch": 0.40325865580448067, "grad_norm": 3.015875816345215, "learning_rate": 8.048780487804878e-07, "loss": 0.38027653098106384, "step": 99 }, { "epoch": 0.4073319755600815, "grad_norm": 2.907216787338257, "learning_rate": 8.130081300813008e-07, "loss": 0.34937676787376404, "step": 100 }, { "epoch": 0.41140529531568226, "grad_norm": 3.131850004196167, "learning_rate": 8.211382113821138e-07, "loss": 0.4414845108985901, "step": 101 }, { "epoch": 0.4154786150712831, "grad_norm": 2.9019775390625, "learning_rate": 8.292682926829268e-07, "loss": 0.3990558981895447, "step": 102 }, { "epoch": 0.4195519348268839, "grad_norm": 2.9362523555755615, "learning_rate": 8.373983739837398e-07, "loss": 0.41413092613220215, "step": 103 }, { "epoch": 0.42362525458248473, "grad_norm": 3.0895473957061768, "learning_rate": 8.455284552845529e-07, "loss": 0.3904542028903961, "step": 104 }, { "epoch": 0.42769857433808556, "grad_norm": 2.9235992431640625, "learning_rate": 8.536585365853657e-07, "loss": 0.3995140939950943, "step": 105 }, { "epoch": 0.4317718940936864, "grad_norm": 2.919102668762207, "learning_rate": 8.617886178861788e-07, "loss": 0.32857778668403625, "step": 106 }, { "epoch": 0.43584521384928715, "grad_norm": 2.831698417663574, "learning_rate": 8.699186991869918e-07, "loss": 0.3507983237504959, "step": 107 }, { "epoch": 0.439918533604888, "grad_norm": 2.952693223953247, "learning_rate": 8.780487804878048e-07, "loss": 0.37046514451503754, "step": 108 }, { "epoch": 0.4439918533604888, "grad_norm": 3.315002679824829, "learning_rate": 8.861788617886179e-07, "loss": 0.391086682677269, "step": 109 }, { "epoch": 0.4480651731160896, "grad_norm": 2.7241294384002686, "learning_rate": 8.943089430894308e-07, "loss": 0.3864188492298126, "step": 110 }, { "epoch": 0.45213849287169044, "grad_norm": 2.782064199447632, "learning_rate": 9.024390243902439e-07, "loss": 0.38219109177589417, "step": 111 }, { "epoch": 0.45621181262729127, "grad_norm": 4.001572132110596, "learning_rate": 9.105691056910569e-07, "loss": 0.3784598410129547, "step": 112 }, { "epoch": 0.46028513238289204, "grad_norm": 2.607434034347534, "learning_rate": 9.186991869918699e-07, "loss": 0.3763512521982193, "step": 113 }, { "epoch": 0.46435845213849286, "grad_norm": 2.97188138961792, "learning_rate": 9.26829268292683e-07, "loss": 0.36788034439086914, "step": 114 }, { "epoch": 0.4684317718940937, "grad_norm": 2.9631524085998535, "learning_rate": 9.349593495934958e-07, "loss": 0.3696867823600769, "step": 115 }, { "epoch": 0.4725050916496945, "grad_norm": 2.5895049571990967, "learning_rate": 9.430894308943089e-07, "loss": 0.3349902927875519, "step": 116 }, { "epoch": 0.47657841140529533, "grad_norm": 2.600832462310791, "learning_rate": 9.512195121951218e-07, "loss": 0.34966227412223816, "step": 117 }, { "epoch": 0.48065173116089616, "grad_norm": 3.0639443397521973, "learning_rate": 9.59349593495935e-07, "loss": 0.38310858607292175, "step": 118 }, { "epoch": 0.4847250509164969, "grad_norm": 2.6944706439971924, "learning_rate": 9.67479674796748e-07, "loss": 0.3360476493835449, "step": 119 }, { "epoch": 0.48879837067209775, "grad_norm": 2.8398237228393555, "learning_rate": 9.756097560975609e-07, "loss": 0.39176714420318604, "step": 120 }, { "epoch": 0.49287169042769857, "grad_norm": 2.8028745651245117, "learning_rate": 9.83739837398374e-07, "loss": 0.37909021973609924, "step": 121 }, { "epoch": 0.4969450101832994, "grad_norm": 2.6169185638427734, "learning_rate": 9.918699186991869e-07, "loss": 0.37069061398506165, "step": 122 }, { "epoch": 0.5010183299389002, "grad_norm": 2.572046995162964, "learning_rate": 1e-06, "loss": 0.3428824096918106, "step": 123 }, { "epoch": 0.505091649694501, "grad_norm": 2.7804417610168457, "learning_rate": 9.999979682219186e-07, "loss": 0.3680119812488556, "step": 124 }, { "epoch": 0.5091649694501018, "grad_norm": 2.5910799503326416, "learning_rate": 9.999918729041868e-07, "loss": 0.33467385172843933, "step": 125 }, { "epoch": 0.5132382892057027, "grad_norm": 2.8417587280273438, "learning_rate": 9.999817140963419e-07, "loss": 0.35100705921649933, "step": 126 }, { "epoch": 0.5173116089613035, "grad_norm": 2.905728340148926, "learning_rate": 9.999674918809457e-07, "loss": 0.32811686396598816, "step": 127 }, { "epoch": 0.5213849287169042, "grad_norm": 2.5878095626831055, "learning_rate": 9.99949206373584e-07, "loss": 0.32490645349025726, "step": 128 }, { "epoch": 0.5254582484725051, "grad_norm": 2.9762229919433594, "learning_rate": 9.999268577228648e-07, "loss": 0.3934018760919571, "step": 129 }, { "epoch": 0.5295315682281059, "grad_norm": 2.792989492416382, "learning_rate": 9.99900446110418e-07, "loss": 0.3315049111843109, "step": 130 }, { "epoch": 0.5336048879837068, "grad_norm": 2.6891062259674072, "learning_rate": 9.998699717508945e-07, "loss": 0.3097301423549652, "step": 131 }, { "epoch": 0.5376782077393075, "grad_norm": 2.92191481590271, "learning_rate": 9.99835434891962e-07, "loss": 0.34749817848205566, "step": 132 }, { "epoch": 0.5417515274949084, "grad_norm": 2.980543851852417, "learning_rate": 9.99796835814306e-07, "loss": 0.3367327153682709, "step": 133 }, { "epoch": 0.5458248472505092, "grad_norm": 2.50433611869812, "learning_rate": 9.99754174831625e-07, "loss": 0.3090934008359909, "step": 134 }, { "epoch": 0.5498981670061099, "grad_norm": 2.869647979736328, "learning_rate": 9.9970745229063e-07, "loss": 0.35603591799736023, "step": 135 }, { "epoch": 0.5539714867617108, "grad_norm": 2.6435837745666504, "learning_rate": 9.9965666857104e-07, "loss": 0.3288918733596802, "step": 136 }, { "epoch": 0.5580448065173116, "grad_norm": 2.7970142364501953, "learning_rate": 9.996018240855806e-07, "loss": 0.3878723680973053, "step": 137 }, { "epoch": 0.5621181262729125, "grad_norm": 2.593043327331543, "learning_rate": 9.995429192799788e-07, "loss": 0.3534126281738281, "step": 138 }, { "epoch": 0.5661914460285132, "grad_norm": 2.8867013454437256, "learning_rate": 9.994799546329602e-07, "loss": 0.38061630725860596, "step": 139 }, { "epoch": 0.570264765784114, "grad_norm": 2.589017152786255, "learning_rate": 9.994129306562458e-07, "loss": 0.37725748121738434, "step": 140 }, { "epoch": 0.5743380855397149, "grad_norm": 2.369696617126465, "learning_rate": 9.993418478945472e-07, "loss": 0.32034583389759064, "step": 141 }, { "epoch": 0.5784114052953157, "grad_norm": 2.6410069465637207, "learning_rate": 9.992667069255618e-07, "loss": 0.36017628014087677, "step": 142 }, { "epoch": 0.5824847250509165, "grad_norm": 2.597259283065796, "learning_rate": 9.991875083599688e-07, "loss": 0.32577911019325256, "step": 143 }, { "epoch": 0.5865580448065173, "grad_norm": 2.761859655380249, "learning_rate": 9.991042528414237e-07, "loss": 0.33353830873966217, "step": 144 }, { "epoch": 0.5906313645621182, "grad_norm": 2.7634713649749756, "learning_rate": 9.990169410465536e-07, "loss": 0.33604632318019867, "step": 145 }, { "epoch": 0.594704684317719, "grad_norm": 2.820897340774536, "learning_rate": 9.98925573684951e-07, "loss": 0.3069554716348648, "step": 146 }, { "epoch": 0.5987780040733197, "grad_norm": 2.856700897216797, "learning_rate": 9.98830151499169e-07, "loss": 0.33896636962890625, "step": 147 }, { "epoch": 0.6028513238289206, "grad_norm": 2.9203782081604004, "learning_rate": 9.987306752647142e-07, "loss": 0.35070909559726715, "step": 148 }, { "epoch": 0.6069246435845214, "grad_norm": 2.679352283477783, "learning_rate": 9.986271457900414e-07, "loss": 0.3325359970331192, "step": 149 }, { "epoch": 0.6109979633401222, "grad_norm": 2.4953606128692627, "learning_rate": 9.98519563916546e-07, "loss": 0.32330869138240814, "step": 150 }, { "epoch": 0.615071283095723, "grad_norm": 2.618744134902954, "learning_rate": 9.98407930518558e-07, "loss": 0.33912393450737, "step": 151 }, { "epoch": 0.6191446028513238, "grad_norm": 2.6512296199798584, "learning_rate": 9.982922465033348e-07, "loss": 0.3045920431613922, "step": 152 }, { "epoch": 0.6232179226069247, "grad_norm": 2.7606050968170166, "learning_rate": 9.981725128110532e-07, "loss": 0.32916732132434845, "step": 153 }, { "epoch": 0.6272912423625254, "grad_norm": 2.95037841796875, "learning_rate": 9.980487304148024e-07, "loss": 0.36757831275463104, "step": 154 }, { "epoch": 0.6313645621181263, "grad_norm": 2.890489339828491, "learning_rate": 9.97920900320576e-07, "loss": 0.36117151379585266, "step": 155 }, { "epoch": 0.6354378818737271, "grad_norm": 2.7488858699798584, "learning_rate": 9.97789023567263e-07, "loss": 0.35026322305202484, "step": 156 }, { "epoch": 0.639511201629328, "grad_norm": 2.5479671955108643, "learning_rate": 9.976531012266413e-07, "loss": 0.308156818151474, "step": 157 }, { "epoch": 0.6435845213849287, "grad_norm": 2.717344045639038, "learning_rate": 9.975131344033664e-07, "loss": 0.29827529191970825, "step": 158 }, { "epoch": 0.6476578411405295, "grad_norm": 2.569551467895508, "learning_rate": 9.973691242349648e-07, "loss": 0.3232528269290924, "step": 159 }, { "epoch": 0.6517311608961304, "grad_norm": 3.0013420581817627, "learning_rate": 9.972210718918233e-07, "loss": 0.3270832598209381, "step": 160 }, { "epoch": 0.6558044806517311, "grad_norm": 2.7339162826538086, "learning_rate": 9.970689785771798e-07, "loss": 0.3668155074119568, "step": 161 }, { "epoch": 0.659877800407332, "grad_norm": 2.6689724922180176, "learning_rate": 9.969128455271137e-07, "loss": 0.32853490114212036, "step": 162 }, { "epoch": 0.6639511201629328, "grad_norm": 3.042081117630005, "learning_rate": 9.967526740105358e-07, "loss": 0.3487651199102402, "step": 163 }, { "epoch": 0.6680244399185336, "grad_norm": 2.4641284942626953, "learning_rate": 9.965884653291783e-07, "loss": 0.35704147815704346, "step": 164 }, { "epoch": 0.6720977596741344, "grad_norm": 2.6836225986480713, "learning_rate": 9.964202208175833e-07, "loss": 0.33587950468063354, "step": 165 }, { "epoch": 0.6761710794297352, "grad_norm": 2.2905988693237305, "learning_rate": 9.962479418430932e-07, "loss": 0.3061918318271637, "step": 166 }, { "epoch": 0.6802443991853361, "grad_norm": 2.4772934913635254, "learning_rate": 9.960716298058381e-07, "loss": 0.2896444499492645, "step": 167 }, { "epoch": 0.6843177189409368, "grad_norm": 2.6987321376800537, "learning_rate": 9.958912861387258e-07, "loss": 0.3374595195055008, "step": 168 }, { "epoch": 0.6883910386965377, "grad_norm": 2.6165449619293213, "learning_rate": 9.9570691230743e-07, "loss": 0.33027225732803345, "step": 169 }, { "epoch": 0.6924643584521385, "grad_norm": 3.1326680183410645, "learning_rate": 9.955185098103771e-07, "loss": 0.3138381540775299, "step": 170 }, { "epoch": 0.6965376782077393, "grad_norm": 2.5313732624053955, "learning_rate": 9.953260801787356e-07, "loss": 0.31824737787246704, "step": 171 }, { "epoch": 0.7006109979633401, "grad_norm": 2.529325008392334, "learning_rate": 9.951296249764025e-07, "loss": 0.298155277967453, "step": 172 }, { "epoch": 0.7046843177189409, "grad_norm": 2.6821744441986084, "learning_rate": 9.949291457999916e-07, "loss": 0.33296874165534973, "step": 173 }, { "epoch": 0.7087576374745418, "grad_norm": 2.588157892227173, "learning_rate": 9.947246442788193e-07, "loss": 0.31226691603660583, "step": 174 }, { "epoch": 0.7128309572301426, "grad_norm": 2.7822420597076416, "learning_rate": 9.945161220748927e-07, "loss": 0.322743222117424, "step": 175 }, { "epoch": 0.7169042769857433, "grad_norm": 2.379702091217041, "learning_rate": 9.943035808828953e-07, "loss": 0.3056500107049942, "step": 176 }, { "epoch": 0.7209775967413442, "grad_norm": 2.4450721740722656, "learning_rate": 9.94087022430173e-07, "loss": 0.3037564754486084, "step": 177 }, { "epoch": 0.725050916496945, "grad_norm": 2.5885887145996094, "learning_rate": 9.938664484767205e-07, "loss": 0.327587828040123, "step": 178 }, { "epoch": 0.7291242362525459, "grad_norm": 2.613290309906006, "learning_rate": 9.936418608151675e-07, "loss": 0.33323927223682404, "step": 179 }, { "epoch": 0.7331975560081466, "grad_norm": 2.6541707515716553, "learning_rate": 9.93413261270763e-07, "loss": 0.3316569924354553, "step": 180 }, { "epoch": 0.7372708757637475, "grad_norm": 2.646383047103882, "learning_rate": 9.931806517013612e-07, "loss": 0.35486292839050293, "step": 181 }, { "epoch": 0.7413441955193483, "grad_norm": 2.5270328521728516, "learning_rate": 9.92944033997406e-07, "loss": 0.3157142102718353, "step": 182 }, { "epoch": 0.745417515274949, "grad_norm": 2.5851869583129883, "learning_rate": 9.927034100819163e-07, "loss": 0.3013855814933777, "step": 183 }, { "epoch": 0.7494908350305499, "grad_norm": 2.75219988822937, "learning_rate": 9.924587819104695e-07, "loss": 0.3420049250125885, "step": 184 }, { "epoch": 0.7535641547861507, "grad_norm": 2.436596632003784, "learning_rate": 9.922101514711865e-07, "loss": 0.3062688261270523, "step": 185 }, { "epoch": 0.7576374745417516, "grad_norm": 2.9479236602783203, "learning_rate": 9.919575207847145e-07, "loss": 0.31793762743473053, "step": 186 }, { "epoch": 0.7617107942973523, "grad_norm": 2.5482208728790283, "learning_rate": 9.917008919042116e-07, "loss": 0.3306496888399124, "step": 187 }, { "epoch": 0.7657841140529531, "grad_norm": 2.609839677810669, "learning_rate": 9.914402669153295e-07, "loss": 0.29324449598789215, "step": 188 }, { "epoch": 0.769857433808554, "grad_norm": 2.5740039348602295, "learning_rate": 9.91175647936197e-07, "loss": 0.3193310797214508, "step": 189 }, { "epoch": 0.7739307535641547, "grad_norm": 2.3878629207611084, "learning_rate": 9.909070371174019e-07, "loss": 0.3040658235549927, "step": 190 }, { "epoch": 0.7780040733197556, "grad_norm": 2.755152463912964, "learning_rate": 9.906344366419746e-07, "loss": 0.33930477499961853, "step": 191 }, { "epoch": 0.7820773930753564, "grad_norm": 2.58367657661438, "learning_rate": 9.9035784872537e-07, "loss": 0.3244568109512329, "step": 192 }, { "epoch": 0.7861507128309573, "grad_norm": 2.350712537765503, "learning_rate": 9.90077275615449e-07, "loss": 0.2779058516025543, "step": 193 }, { "epoch": 0.790224032586558, "grad_norm": 2.7418465614318848, "learning_rate": 9.897927195924608e-07, "loss": 0.32641272246837616, "step": 194 }, { "epoch": 0.7942973523421588, "grad_norm": 2.516510009765625, "learning_rate": 9.895041829690238e-07, "loss": 0.3083319664001465, "step": 195 }, { "epoch": 0.7983706720977597, "grad_norm": 2.7772316932678223, "learning_rate": 9.892116680901084e-07, "loss": 0.30357757210731506, "step": 196 }, { "epoch": 0.8024439918533605, "grad_norm": 2.5389041900634766, "learning_rate": 9.88915177333015e-07, "loss": 0.30694054067134857, "step": 197 }, { "epoch": 0.8065173116089613, "grad_norm": 2.7129383087158203, "learning_rate": 9.886147131073579e-07, "loss": 0.3402569591999054, "step": 198 }, { "epoch": 0.8105906313645621, "grad_norm": 2.654186248779297, "learning_rate": 9.883102778550434e-07, "loss": 0.3343619704246521, "step": 199 }, { "epoch": 0.814663951120163, "grad_norm": 2.380168914794922, "learning_rate": 9.880018740502508e-07, "loss": 0.3020651191473007, "step": 200 }, { "epoch": 0.8187372708757638, "grad_norm": 2.771951198577881, "learning_rate": 9.876895041994127e-07, "loss": 0.30565840005874634, "step": 201 }, { "epoch": 0.8228105906313645, "grad_norm": 2.4966540336608887, "learning_rate": 9.873731708411939e-07, "loss": 0.3085058331489563, "step": 202 }, { "epoch": 0.8268839103869654, "grad_norm": 2.5919551849365234, "learning_rate": 9.870528765464711e-07, "loss": 0.34540820121765137, "step": 203 }, { "epoch": 0.8309572301425662, "grad_norm": 3.0668885707855225, "learning_rate": 9.867286239183122e-07, "loss": 0.3307037353515625, "step": 204 }, { "epoch": 0.835030549898167, "grad_norm": 2.4281554222106934, "learning_rate": 9.864004155919544e-07, "loss": 0.28929875791072845, "step": 205 }, { "epoch": 0.8391038696537678, "grad_norm": 2.5561623573303223, "learning_rate": 9.860682542347838e-07, "loss": 0.3272414803504944, "step": 206 }, { "epoch": 0.8431771894093686, "grad_norm": 2.824591636657715, "learning_rate": 9.85732142546313e-07, "loss": 0.3192295432090759, "step": 207 }, { "epoch": 0.8472505091649695, "grad_norm": 2.643718719482422, "learning_rate": 9.853920832581597e-07, "loss": 0.31284041702747345, "step": 208 }, { "epoch": 0.8513238289205702, "grad_norm": 2.6777195930480957, "learning_rate": 9.850480791340236e-07, "loss": 0.3136574327945709, "step": 209 }, { "epoch": 0.8553971486761711, "grad_norm": 2.5229766368865967, "learning_rate": 9.847001329696652e-07, "loss": 0.3047819435596466, "step": 210 }, { "epoch": 0.8594704684317719, "grad_norm": 2.659447431564331, "learning_rate": 9.843482475928818e-07, "loss": 0.3642407953739166, "step": 211 }, { "epoch": 0.8635437881873728, "grad_norm": 2.697049379348755, "learning_rate": 9.839924258634853e-07, "loss": 0.3134022653102875, "step": 212 }, { "epoch": 0.8676171079429735, "grad_norm": 2.629868745803833, "learning_rate": 9.83632670673279e-07, "loss": 0.306331992149353, "step": 213 }, { "epoch": 0.8716904276985743, "grad_norm": 2.4997003078460693, "learning_rate": 9.832689849460339e-07, "loss": 0.3142865002155304, "step": 214 }, { "epoch": 0.8757637474541752, "grad_norm": 2.826869010925293, "learning_rate": 9.829013716374647e-07, "loss": 0.2904099076986313, "step": 215 }, { "epoch": 0.879837067209776, "grad_norm": 2.6697499752044678, "learning_rate": 9.825298337352058e-07, "loss": 0.29838354885578156, "step": 216 }, { "epoch": 0.8839103869653768, "grad_norm": 2.5330023765563965, "learning_rate": 9.821543742587876e-07, "loss": 0.3052047789096832, "step": 217 }, { "epoch": 0.8879837067209776, "grad_norm": 2.806683301925659, "learning_rate": 9.817749962596114e-07, "loss": 0.3121778964996338, "step": 218 }, { "epoch": 0.8920570264765784, "grad_norm": 2.718122720718384, "learning_rate": 9.81391702820925e-07, "loss": 0.32955022156238556, "step": 219 }, { "epoch": 0.8961303462321792, "grad_norm": 2.346466541290283, "learning_rate": 9.81004497057797e-07, "loss": 0.291049063205719, "step": 220 }, { "epoch": 0.90020366598778, "grad_norm": 2.4048361778259277, "learning_rate": 9.806133821170924e-07, "loss": 0.30249159038066864, "step": 221 }, { "epoch": 0.9042769857433809, "grad_norm": 2.681546688079834, "learning_rate": 9.80218361177446e-07, "loss": 0.362154021859169, "step": 222 }, { "epoch": 0.9083503054989817, "grad_norm": 2.792266368865967, "learning_rate": 9.798194374492375e-07, "loss": 0.28344525396823883, "step": 223 }, { "epoch": 0.9124236252545825, "grad_norm": 2.507050037384033, "learning_rate": 9.794166141745646e-07, "loss": 0.2935172915458679, "step": 224 }, { "epoch": 0.9164969450101833, "grad_norm": 2.7160379886627197, "learning_rate": 9.790098946272177e-07, "loss": 0.3005199581384659, "step": 225 }, { "epoch": 0.9205702647657841, "grad_norm": 2.666494131088257, "learning_rate": 9.785992821126518e-07, "loss": 0.30710943043231964, "step": 226 }, { "epoch": 0.924643584521385, "grad_norm": 2.699313163757324, "learning_rate": 9.781847799679615e-07, "loss": 0.3164513558149338, "step": 227 }, { "epoch": 0.9287169042769857, "grad_norm": 2.49406099319458, "learning_rate": 9.777663915618517e-07, "loss": 0.3061770647764206, "step": 228 }, { "epoch": 0.9327902240325866, "grad_norm": 2.552093029022217, "learning_rate": 9.773441202946121e-07, "loss": 0.2973909080028534, "step": 229 }, { "epoch": 0.9368635437881874, "grad_norm": 2.5773231983184814, "learning_rate": 9.76917969598089e-07, "loss": 0.31120532751083374, "step": 230 }, { "epoch": 0.9409368635437881, "grad_norm": 2.653515100479126, "learning_rate": 9.76487942935657e-07, "loss": 0.3365926146507263, "step": 231 }, { "epoch": 0.945010183299389, "grad_norm": 2.670433282852173, "learning_rate": 9.760540438021907e-07, "loss": 0.3196941614151001, "step": 232 }, { "epoch": 0.9490835030549898, "grad_norm": 2.892035961151123, "learning_rate": 9.756162757240373e-07, "loss": 0.33982205390930176, "step": 233 }, { "epoch": 0.9531568228105907, "grad_norm": 2.5157856941223145, "learning_rate": 9.751746422589872e-07, "loss": 0.2537951096892357, "step": 234 }, { "epoch": 0.9572301425661914, "grad_norm": 2.6808388233184814, "learning_rate": 9.747291469962452e-07, "loss": 0.2846526652574539, "step": 235 }, { "epoch": 0.9613034623217923, "grad_norm": 2.451559066772461, "learning_rate": 9.742797935564011e-07, "loss": 0.29611095786094666, "step": 236 }, { "epoch": 0.9653767820773931, "grad_norm": 2.7313358783721924, "learning_rate": 9.738265855914012e-07, "loss": 0.3275996297597885, "step": 237 }, { "epoch": 0.9694501018329938, "grad_norm": 2.5593299865722656, "learning_rate": 9.733695267845171e-07, "loss": 0.2993656247854233, "step": 238 }, { "epoch": 0.9735234215885947, "grad_norm": 2.6013288497924805, "learning_rate": 9.729086208503173e-07, "loss": 0.31615155935287476, "step": 239 }, { "epoch": 0.9775967413441955, "grad_norm": 2.5403575897216797, "learning_rate": 9.72443871534636e-07, "loss": 0.2843424677848816, "step": 240 }, { "epoch": 0.9816700610997964, "grad_norm": 2.4495410919189453, "learning_rate": 9.719752826145432e-07, "loss": 0.2987358868122101, "step": 241 }, { "epoch": 0.9857433808553971, "grad_norm": 2.719775676727295, "learning_rate": 9.715028578983136e-07, "loss": 0.34320636093616486, "step": 242 }, { "epoch": 0.9898167006109979, "grad_norm": 2.7152929306030273, "learning_rate": 9.71026601225396e-07, "loss": 0.2937510758638382, "step": 243 }, { "epoch": 0.9938900203665988, "grad_norm": 2.4305663108825684, "learning_rate": 9.705465164663817e-07, "loss": 0.29807206988334656, "step": 244 }, { "epoch": 0.9979633401221996, "grad_norm": 2.322704792022705, "learning_rate": 9.700626075229738e-07, "loss": 0.3189048618078232, "step": 245 }, { "epoch": 1.0, "grad_norm": 2.322704792022705, "learning_rate": 9.695748783279544e-07, "loss": 0.3195984363555908, "step": 246 }, { "epoch": 1.0040733197556009, "grad_norm": 2.505608081817627, "learning_rate": 9.690833328451532e-07, "loss": 0.24639207869768143, "step": 247 }, { "epoch": 1.0081466395112015, "grad_norm": 2.5328471660614014, "learning_rate": 9.68587975069416e-07, "loss": 0.3204229325056076, "step": 248 }, { "epoch": 1.0122199592668024, "grad_norm": 2.462449073791504, "learning_rate": 9.680888090265713e-07, "loss": 0.29177573323249817, "step": 249 }, { "epoch": 1.0162932790224033, "grad_norm": 2.4300286769866943, "learning_rate": 9.67585838773397e-07, "loss": 0.2859930992126465, "step": 250 }, { "epoch": 1.0203665987780042, "grad_norm": 2.4073538780212402, "learning_rate": 9.67079068397589e-07, "loss": 0.253083311021328, "step": 251 }, { "epoch": 1.0244399185336048, "grad_norm": 2.4259159564971924, "learning_rate": 9.66568502017727e-07, "loss": 0.27018117904663086, "step": 252 }, { "epoch": 1.0285132382892057, "grad_norm": 2.490452766418457, "learning_rate": 9.660541437832416e-07, "loss": 0.270308181643486, "step": 253 }, { "epoch": 1.0325865580448066, "grad_norm": 2.2988967895507812, "learning_rate": 9.655359978743798e-07, "loss": 0.2865062654018402, "step": 254 }, { "epoch": 1.0366598778004072, "grad_norm": 2.3249478340148926, "learning_rate": 9.650140685021716e-07, "loss": 0.30297039449214935, "step": 255 }, { "epoch": 1.0407331975560081, "grad_norm": 2.530956506729126, "learning_rate": 9.644883599083957e-07, "loss": 0.2875078618526459, "step": 256 }, { "epoch": 1.044806517311609, "grad_norm": 2.462820053100586, "learning_rate": 9.639588763655448e-07, "loss": 0.3308262676000595, "step": 257 }, { "epoch": 1.0488798370672097, "grad_norm": 2.733877658843994, "learning_rate": 9.634256221767912e-07, "loss": 0.3172256797552109, "step": 258 }, { "epoch": 1.0529531568228105, "grad_norm": 2.5849740505218506, "learning_rate": 9.628886016759515e-07, "loss": 0.24582470953464508, "step": 259 }, { "epoch": 1.0570264765784114, "grad_norm": 2.495885133743286, "learning_rate": 9.623478192274517e-07, "loss": 0.29177717864513397, "step": 260 }, { "epoch": 1.0610997963340123, "grad_norm": 2.7560508251190186, "learning_rate": 9.618032792262914e-07, "loss": 0.2618248611688614, "step": 261 }, { "epoch": 1.065173116089613, "grad_norm": 2.5949246883392334, "learning_rate": 9.612549860980087e-07, "loss": 0.29752814769744873, "step": 262 }, { "epoch": 1.0692464358452138, "grad_norm": 2.5723235607147217, "learning_rate": 9.60702944298643e-07, "loss": 0.283334344625473, "step": 263 }, { "epoch": 1.0733197556008147, "grad_norm": 2.5463922023773193, "learning_rate": 9.601471583147002e-07, "loss": 0.29830360412597656, "step": 264 }, { "epoch": 1.0773930753564154, "grad_norm": 2.4415295124053955, "learning_rate": 9.595876326631153e-07, "loss": 0.278356209397316, "step": 265 }, { "epoch": 1.0814663951120163, "grad_norm": 2.4167826175689697, "learning_rate": 9.590243718912164e-07, "loss": 0.2482159435749054, "step": 266 }, { "epoch": 1.0855397148676171, "grad_norm": 2.4946138858795166, "learning_rate": 9.584573805766867e-07, "loss": 0.2892283797264099, "step": 267 }, { "epoch": 1.089613034623218, "grad_norm": 2.585139036178589, "learning_rate": 9.578866633275286e-07, "loss": 0.28597134351730347, "step": 268 }, { "epoch": 1.0936863543788187, "grad_norm": 2.5749940872192383, "learning_rate": 9.573122247820253e-07, "loss": 0.24586065858602524, "step": 269 }, { "epoch": 1.0977596741344195, "grad_norm": 2.6099436283111572, "learning_rate": 9.567340696087032e-07, "loss": 0.2968917638063431, "step": 270 }, { "epoch": 1.1018329938900204, "grad_norm": 2.5843560695648193, "learning_rate": 9.561522025062946e-07, "loss": 0.3214084059000015, "step": 271 }, { "epoch": 1.105906313645621, "grad_norm": 2.7599520683288574, "learning_rate": 9.555666282036984e-07, "loss": 0.2851483225822449, "step": 272 }, { "epoch": 1.109979633401222, "grad_norm": 2.340637683868408, "learning_rate": 9.549773514599428e-07, "loss": 0.2864815294742584, "step": 273 }, { "epoch": 1.1140529531568228, "grad_norm": 2.682030200958252, "learning_rate": 9.543843770641463e-07, "loss": 0.2536205053329468, "step": 274 }, { "epoch": 1.1181262729124237, "grad_norm": 2.3765580654144287, "learning_rate": 9.537877098354784e-07, "loss": 0.24970313906669617, "step": 275 }, { "epoch": 1.1221995926680244, "grad_norm": 2.5046305656433105, "learning_rate": 9.531873546231208e-07, "loss": 0.2925817370414734, "step": 276 }, { "epoch": 1.1262729124236253, "grad_norm": 2.487609386444092, "learning_rate": 9.525833163062273e-07, "loss": 0.28858567774295807, "step": 277 }, { "epoch": 1.1303462321792261, "grad_norm": 2.5617923736572266, "learning_rate": 9.519755997938856e-07, "loss": 0.29943670332431793, "step": 278 }, { "epoch": 1.1344195519348268, "grad_norm": 2.5144989490509033, "learning_rate": 9.51364210025076e-07, "loss": 0.26054797321558, "step": 279 }, { "epoch": 1.1384928716904277, "grad_norm": 2.393367290496826, "learning_rate": 9.507491519686315e-07, "loss": 0.2766056954860687, "step": 280 }, { "epoch": 1.1425661914460286, "grad_norm": 2.5914998054504395, "learning_rate": 9.501304306231983e-07, "loss": 0.2934035658836365, "step": 281 }, { "epoch": 1.1466395112016294, "grad_norm": 2.6555488109588623, "learning_rate": 9.495080510171942e-07, "loss": 0.27582375705242157, "step": 282 }, { "epoch": 1.15071283095723, "grad_norm": 2.4485878944396973, "learning_rate": 9.488820182087682e-07, "loss": 0.27037250250577927, "step": 283 }, { "epoch": 1.154786150712831, "grad_norm": 2.5796926021575928, "learning_rate": 9.482523372857592e-07, "loss": 0.25297392159700394, "step": 284 }, { "epoch": 1.1588594704684319, "grad_norm": 2.4900271892547607, "learning_rate": 9.476190133656548e-07, "loss": 0.2928699851036072, "step": 285 }, { "epoch": 1.1629327902240325, "grad_norm": 2.378876209259033, "learning_rate": 9.469820515955497e-07, "loss": 0.3021889925003052, "step": 286 }, { "epoch": 1.1670061099796334, "grad_norm": 2.377063751220703, "learning_rate": 9.463414571521036e-07, "loss": 0.26095758378505707, "step": 287 }, { "epoch": 1.1710794297352343, "grad_norm": 2.347393274307251, "learning_rate": 9.456972352414997e-07, "loss": 0.24494879692792892, "step": 288 }, { "epoch": 1.175152749490835, "grad_norm": 2.3959014415740967, "learning_rate": 9.450493910994017e-07, "loss": 0.28228186070919037, "step": 289 }, { "epoch": 1.1792260692464358, "grad_norm": 2.5725162029266357, "learning_rate": 9.443979299909117e-07, "loss": 0.3038964122533798, "step": 290 }, { "epoch": 1.1832993890020367, "grad_norm": 3.050133228302002, "learning_rate": 9.437428572105274e-07, "loss": 0.28559453785419464, "step": 291 }, { "epoch": 1.1873727087576376, "grad_norm": 2.4305083751678467, "learning_rate": 9.430841780820988e-07, "loss": 0.26872922480106354, "step": 292 }, { "epoch": 1.1914460285132382, "grad_norm": 2.3637914657592773, "learning_rate": 9.424218979587852e-07, "loss": 0.2783532440662384, "step": 293 }, { "epoch": 1.195519348268839, "grad_norm": 2.4774560928344727, "learning_rate": 9.417560222230114e-07, "loss": 0.2842411994934082, "step": 294 }, { "epoch": 1.19959266802444, "grad_norm": 2.5469460487365723, "learning_rate": 9.410865562864245e-07, "loss": 0.2584770694375038, "step": 295 }, { "epoch": 1.2036659877800409, "grad_norm": 2.3821113109588623, "learning_rate": 9.404135055898495e-07, "loss": 0.29300089180469513, "step": 296 }, { "epoch": 1.2077393075356415, "grad_norm": 2.7043542861938477, "learning_rate": 9.397368756032444e-07, "loss": 0.2970714569091797, "step": 297 }, { "epoch": 1.2118126272912424, "grad_norm": 2.353179693222046, "learning_rate": 9.390566718256578e-07, "loss": 0.28464287519454956, "step": 298 }, { "epoch": 1.2158859470468433, "grad_norm": 2.615365743637085, "learning_rate": 9.383728997851819e-07, "loss": 0.2843187004327774, "step": 299 }, { "epoch": 1.219959266802444, "grad_norm": 2.526761054992676, "learning_rate": 9.376855650389089e-07, "loss": 0.29214321076869965, "step": 300 }, { "epoch": 1.2240325865580448, "grad_norm": 2.416611909866333, "learning_rate": 9.369946731728854e-07, "loss": 0.2746543139219284, "step": 301 }, { "epoch": 1.2281059063136457, "grad_norm": 2.6475841999053955, "learning_rate": 9.363002298020673e-07, "loss": 0.32700057327747345, "step": 302 }, { "epoch": 1.2321792260692463, "grad_norm": 2.7061877250671387, "learning_rate": 9.356022405702739e-07, "loss": 0.26850761473178864, "step": 303 }, { "epoch": 1.2362525458248472, "grad_norm": 2.578963279724121, "learning_rate": 9.349007111501419e-07, "loss": 0.2758927643299103, "step": 304 }, { "epoch": 1.240325865580448, "grad_norm": 2.476339340209961, "learning_rate": 9.341956472430801e-07, "loss": 0.3046765774488449, "step": 305 }, { "epoch": 1.2443991853360488, "grad_norm": 2.594074249267578, "learning_rate": 9.334870545792217e-07, "loss": 0.30949874222278595, "step": 306 }, { "epoch": 1.2484725050916496, "grad_norm": 2.311086416244507, "learning_rate": 9.32774938917379e-07, "loss": 0.27652885019779205, "step": 307 }, { "epoch": 1.2525458248472505, "grad_norm": 2.5869719982147217, "learning_rate": 9.320593060449958e-07, "loss": 0.2891390472650528, "step": 308 }, { "epoch": 1.2566191446028514, "grad_norm": 2.7591726779937744, "learning_rate": 9.313401617781012e-07, "loss": 0.2366793006658554, "step": 309 }, { "epoch": 1.260692464358452, "grad_norm": 2.394120693206787, "learning_rate": 9.306175119612612e-07, "loss": 0.2750696837902069, "step": 310 }, { "epoch": 1.264765784114053, "grad_norm": 2.542830228805542, "learning_rate": 9.29891362467532e-07, "loss": 0.29537804424762726, "step": 311 }, { "epoch": 1.2688391038696538, "grad_norm": 2.63010573387146, "learning_rate": 9.291617191984123e-07, "loss": 0.28230538964271545, "step": 312 }, { "epoch": 1.2729124236252547, "grad_norm": 2.4835424423217773, "learning_rate": 9.284285880837946e-07, "loss": 0.2597920596599579, "step": 313 }, { "epoch": 1.2769857433808554, "grad_norm": 2.4826974868774414, "learning_rate": 9.276919750819181e-07, "loss": 0.28388310968875885, "step": 314 }, { "epoch": 1.2810590631364562, "grad_norm": 2.495941400527954, "learning_rate": 9.269518861793193e-07, "loss": 0.2510681226849556, "step": 315 }, { "epoch": 1.2851323828920571, "grad_norm": 2.3886849880218506, "learning_rate": 9.262083273907837e-07, "loss": 0.28582368791103363, "step": 316 }, { "epoch": 1.2892057026476578, "grad_norm": 2.443054437637329, "learning_rate": 9.254613047592974e-07, "loss": 0.2807822525501251, "step": 317 }, { "epoch": 1.2932790224032586, "grad_norm": 2.2685866355895996, "learning_rate": 9.247108243559971e-07, "loss": 0.2636859193444252, "step": 318 }, { "epoch": 1.2973523421588595, "grad_norm": 2.4459731578826904, "learning_rate": 9.239568922801212e-07, "loss": 0.28120698034763336, "step": 319 }, { "epoch": 1.3014256619144602, "grad_norm": 2.4667344093322754, "learning_rate": 9.231995146589605e-07, "loss": 0.27484674006700516, "step": 320 }, { "epoch": 1.305498981670061, "grad_norm": 2.432385206222534, "learning_rate": 9.22438697647808e-07, "loss": 0.3200181722640991, "step": 321 }, { "epoch": 1.309572301425662, "grad_norm": 2.594827175140381, "learning_rate": 9.21674447429909e-07, "loss": 0.26146167516708374, "step": 322 }, { "epoch": 1.3136456211812626, "grad_norm": 2.6781699657440186, "learning_rate": 9.209067702164108e-07, "loss": 0.30198925733566284, "step": 323 }, { "epoch": 1.3177189409368635, "grad_norm": 2.382455348968506, "learning_rate": 9.201356722463124e-07, "loss": 0.2656544893980026, "step": 324 }, { "epoch": 1.3217922606924644, "grad_norm": 2.3920562267303467, "learning_rate": 9.193611597864137e-07, "loss": 0.30542662739753723, "step": 325 }, { "epoch": 1.3258655804480652, "grad_norm": 2.5210139751434326, "learning_rate": 9.185832391312642e-07, "loss": 0.33505627512931824, "step": 326 }, { "epoch": 1.3299389002036661, "grad_norm": 2.530137777328491, "learning_rate": 9.178019166031128e-07, "loss": 0.28073740005493164, "step": 327 }, { "epoch": 1.3340122199592668, "grad_norm": 2.6757373809814453, "learning_rate": 9.170171985518551e-07, "loss": 0.2617020010948181, "step": 328 }, { "epoch": 1.3380855397148677, "grad_norm": 2.737130880355835, "learning_rate": 9.162290913549831e-07, "loss": 0.31688614189624786, "step": 329 }, { "epoch": 1.3421588594704685, "grad_norm": 2.4106035232543945, "learning_rate": 9.154376014175325e-07, "loss": 0.25045838952064514, "step": 330 }, { "epoch": 1.3462321792260692, "grad_norm": 2.5006155967712402, "learning_rate": 9.146427351720307e-07, "loss": 0.2350526750087738, "step": 331 }, { "epoch": 1.35030549898167, "grad_norm": 2.443948268890381, "learning_rate": 9.138444990784453e-07, "loss": 0.3193846642971039, "step": 332 }, { "epoch": 1.354378818737271, "grad_norm": 2.5271644592285156, "learning_rate": 9.130428996241304e-07, "loss": 0.2833334505558014, "step": 333 }, { "epoch": 1.3584521384928716, "grad_norm": 2.3211746215820312, "learning_rate": 9.122379433237748e-07, "loss": 0.27067267149686813, "step": 334 }, { "epoch": 1.3625254582484725, "grad_norm": 2.5455574989318848, "learning_rate": 9.11429636719349e-07, "loss": 0.3177233636379242, "step": 335 }, { "epoch": 1.3665987780040734, "grad_norm": 2.9286653995513916, "learning_rate": 9.106179863800513e-07, "loss": 0.30554522573947906, "step": 336 }, { "epoch": 1.370672097759674, "grad_norm": 2.452594757080078, "learning_rate": 9.098029989022557e-07, "loss": 0.29210953414440155, "step": 337 }, { "epoch": 1.374745417515275, "grad_norm": 2.5022428035736084, "learning_rate": 9.089846809094563e-07, "loss": 0.25522106885910034, "step": 338 }, { "epoch": 1.3788187372708758, "grad_norm": 2.6464457511901855, "learning_rate": 9.081630390522157e-07, "loss": 0.287350669503212, "step": 339 }, { "epoch": 1.3828920570264764, "grad_norm": 2.3021206855773926, "learning_rate": 9.073380800081096e-07, "loss": 0.2737245708703995, "step": 340 }, { "epoch": 1.3869653767820773, "grad_norm": 2.5468103885650635, "learning_rate": 9.065098104816726e-07, "loss": 0.26481032371520996, "step": 341 }, { "epoch": 1.3910386965376782, "grad_norm": 2.3847126960754395, "learning_rate": 9.056782372043445e-07, "loss": 0.270496666431427, "step": 342 }, { "epoch": 1.395112016293279, "grad_norm": 2.586550235748291, "learning_rate": 9.048433669344144e-07, "loss": 0.32853636145591736, "step": 343 }, { "epoch": 1.39918533604888, "grad_norm": 2.5621798038482666, "learning_rate": 9.04005206456967e-07, "loss": 0.2707676887512207, "step": 344 }, { "epoch": 1.4032586558044806, "grad_norm": 2.405062198638916, "learning_rate": 9.031637625838264e-07, "loss": 0.285464346408844, "step": 345 }, { "epoch": 1.4073319755600815, "grad_norm": 2.382589817047119, "learning_rate": 9.023190421535016e-07, "loss": 0.2704601585865021, "step": 346 }, { "epoch": 1.4114052953156824, "grad_norm": 2.2916622161865234, "learning_rate": 9.014710520311306e-07, "loss": 0.2510330229997635, "step": 347 }, { "epoch": 1.415478615071283, "grad_norm": 2.3999521732330322, "learning_rate": 9.006197991084241e-07, "loss": 0.2853076159954071, "step": 348 }, { "epoch": 1.419551934826884, "grad_norm": 2.6907191276550293, "learning_rate": 8.997652903036104e-07, "loss": 0.27804453670978546, "step": 349 }, { "epoch": 1.4236252545824848, "grad_norm": 2.3953359127044678, "learning_rate": 8.989075325613784e-07, "loss": 0.24225353449583054, "step": 350 }, { "epoch": 1.4276985743380854, "grad_norm": 2.5458950996398926, "learning_rate": 8.980465328528218e-07, "loss": 0.29082323610782623, "step": 351 }, { "epoch": 1.4317718940936863, "grad_norm": 2.570434093475342, "learning_rate": 8.971822981753818e-07, "loss": 0.2637802064418793, "step": 352 }, { "epoch": 1.4358452138492872, "grad_norm": 2.608654260635376, "learning_rate": 8.963148355527908e-07, "loss": 0.267157182097435, "step": 353 }, { "epoch": 1.4399185336048879, "grad_norm": 2.505756139755249, "learning_rate": 8.954441520350149e-07, "loss": 0.31443025171756744, "step": 354 }, { "epoch": 1.4439918533604887, "grad_norm": 2.8767051696777344, "learning_rate": 8.945702546981968e-07, "loss": 0.28173527121543884, "step": 355 }, { "epoch": 1.4480651731160896, "grad_norm": 2.5839850902557373, "learning_rate": 8.936931506445984e-07, "loss": 0.2735389843583107, "step": 356 }, { "epoch": 1.4521384928716905, "grad_norm": 2.380516529083252, "learning_rate": 8.928128470025429e-07, "loss": 0.2868722528219223, "step": 357 }, { "epoch": 1.4562118126272914, "grad_norm": 2.373098134994507, "learning_rate": 8.919293509263567e-07, "loss": 0.266360841691494, "step": 358 }, { "epoch": 1.460285132382892, "grad_norm": 2.440216541290283, "learning_rate": 8.910426695963118e-07, "loss": 0.26618482172489166, "step": 359 }, { "epoch": 1.464358452138493, "grad_norm": 2.374094247817993, "learning_rate": 8.901528102185669e-07, "loss": 0.27816291898489, "step": 360 }, { "epoch": 1.4684317718940938, "grad_norm": 2.3657944202423096, "learning_rate": 8.892597800251093e-07, "loss": 0.25230376422405243, "step": 361 }, { "epoch": 1.4725050916496945, "grad_norm": 2.3009097576141357, "learning_rate": 8.883635862736956e-07, "loss": 0.26984117925167084, "step": 362 }, { "epoch": 1.4765784114052953, "grad_norm": 2.9458165168762207, "learning_rate": 8.874642362477929e-07, "loss": 0.29643698036670685, "step": 363 }, { "epoch": 1.4806517311608962, "grad_norm": 2.8554880619049072, "learning_rate": 8.865617372565199e-07, "loss": 0.256381556391716, "step": 364 }, { "epoch": 1.4847250509164969, "grad_norm": 2.5279104709625244, "learning_rate": 8.856560966345876e-07, "loss": 0.24138055741786957, "step": 365 }, { "epoch": 1.4887983706720977, "grad_norm": 2.4175782203674316, "learning_rate": 8.847473217422388e-07, "loss": 0.27801232039928436, "step": 366 }, { "epoch": 1.4928716904276986, "grad_norm": 2.7168712615966797, "learning_rate": 8.838354199651891e-07, "loss": 0.28772565722465515, "step": 367 }, { "epoch": 1.4969450101832993, "grad_norm": 2.5258262157440186, "learning_rate": 8.829203987145669e-07, "loss": 0.2848212271928787, "step": 368 }, { "epoch": 1.5010183299389002, "grad_norm": 2.424790859222412, "learning_rate": 8.820022654268525e-07, "loss": 0.2653035372495651, "step": 369 }, { "epoch": 1.505091649694501, "grad_norm": 2.416537284851074, "learning_rate": 8.810810275638182e-07, "loss": 0.27215129137039185, "step": 370 }, { "epoch": 1.5091649694501017, "grad_norm": 2.5008385181427, "learning_rate": 8.801566926124677e-07, "loss": 0.2523413300514221, "step": 371 }, { "epoch": 1.5132382892057028, "grad_norm": 2.5779659748077393, "learning_rate": 8.79229268084975e-07, "loss": 0.2584775537252426, "step": 372 }, { "epoch": 1.5173116089613035, "grad_norm": 2.631009340286255, "learning_rate": 8.782987615186234e-07, "loss": 0.27790168672800064, "step": 373 }, { "epoch": 1.5213849287169041, "grad_norm": 2.4295825958251953, "learning_rate": 8.773651804757443e-07, "loss": 0.26932528614997864, "step": 374 }, { "epoch": 1.5254582484725052, "grad_norm": 2.6135988235473633, "learning_rate": 8.764285325436555e-07, "loss": 0.28256936371326447, "step": 375 }, { "epoch": 1.5295315682281059, "grad_norm": 2.5016775131225586, "learning_rate": 8.754888253346002e-07, "loss": 0.28559644520282745, "step": 376 }, { "epoch": 1.5336048879837068, "grad_norm": 2.5780680179595947, "learning_rate": 8.745460664856844e-07, "loss": 0.2705298289656639, "step": 377 }, { "epoch": 1.5376782077393076, "grad_norm": 2.7102303504943848, "learning_rate": 8.736002636588151e-07, "loss": 0.27591292560100555, "step": 378 }, { "epoch": 1.5417515274949083, "grad_norm": 2.520955801010132, "learning_rate": 8.72651424540638e-07, "loss": 0.2621312141418457, "step": 379 }, { "epoch": 1.5458248472505092, "grad_norm": 3.2938437461853027, "learning_rate": 8.716995568424754e-07, "loss": 0.2692745327949524, "step": 380 }, { "epoch": 1.54989816700611, "grad_norm": 2.4736831188201904, "learning_rate": 8.70744668300263e-07, "loss": 0.24611817300319672, "step": 381 }, { "epoch": 1.5539714867617107, "grad_norm": 2.3731565475463867, "learning_rate": 8.697867666744871e-07, "loss": 0.2787970006465912, "step": 382 }, { "epoch": 1.5580448065173116, "grad_norm": 2.5973782539367676, "learning_rate": 8.688258597501219e-07, "loss": 0.3056941330432892, "step": 383 }, { "epoch": 1.5621181262729125, "grad_norm": 2.490133285522461, "learning_rate": 8.678619553365658e-07, "loss": 0.28115689754486084, "step": 384 }, { "epoch": 1.5661914460285131, "grad_norm": 2.7315447330474854, "learning_rate": 8.668950612675783e-07, "loss": 0.2873499393463135, "step": 385 }, { "epoch": 1.570264765784114, "grad_norm": 2.518087387084961, "learning_rate": 8.659251854012161e-07, "loss": 0.28173641860485077, "step": 386 }, { "epoch": 1.5743380855397149, "grad_norm": 2.214815378189087, "learning_rate": 8.649523356197695e-07, "loss": 0.2376307100057602, "step": 387 }, { "epoch": 1.5784114052953155, "grad_norm": 2.2534103393554688, "learning_rate": 8.639765198296977e-07, "loss": 0.2530301362276077, "step": 388 }, { "epoch": 1.5824847250509166, "grad_norm": 2.5998353958129883, "learning_rate": 8.629977459615654e-07, "loss": 0.26012372225522995, "step": 389 }, { "epoch": 1.5865580448065173, "grad_norm": 2.4811596870422363, "learning_rate": 8.620160219699777e-07, "loss": 0.26469268649816513, "step": 390 }, { "epoch": 1.5906313645621182, "grad_norm": 2.4212377071380615, "learning_rate": 8.610313558335156e-07, "loss": 0.2749471068382263, "step": 391 }, { "epoch": 1.594704684317719, "grad_norm": 2.3209803104400635, "learning_rate": 8.600437555546716e-07, "loss": 0.2666809409856796, "step": 392 }, { "epoch": 1.5987780040733197, "grad_norm": 2.6138010025024414, "learning_rate": 8.59053229159784e-07, "loss": 0.2631463557481766, "step": 393 }, { "epoch": 1.6028513238289206, "grad_norm": 2.4465487003326416, "learning_rate": 8.580597846989721e-07, "loss": 0.2840096950531006, "step": 394 }, { "epoch": 1.6069246435845215, "grad_norm": 2.781353235244751, "learning_rate": 8.570634302460706e-07, "loss": 0.26131805777549744, "step": 395 }, { "epoch": 1.6109979633401221, "grad_norm": 2.4190244674682617, "learning_rate": 8.560641738985641e-07, "loss": 0.28362704813480377, "step": 396 }, { "epoch": 1.615071283095723, "grad_norm": 2.461918354034424, "learning_rate": 8.550620237775213e-07, "loss": 0.2682417184114456, "step": 397 }, { "epoch": 1.6191446028513239, "grad_norm": 2.4705612659454346, "learning_rate": 8.540569880275286e-07, "loss": 0.2832501232624054, "step": 398 }, { "epoch": 1.6232179226069245, "grad_norm": 2.401193380355835, "learning_rate": 8.530490748166244e-07, "loss": 0.2732377126812935, "step": 399 }, { "epoch": 1.6272912423625254, "grad_norm": 2.7205650806427, "learning_rate": 8.520382923362328e-07, "loss": 0.2597970813512802, "step": 400 }, { "epoch": 1.6313645621181263, "grad_norm": 2.6480019092559814, "learning_rate": 8.510246488010964e-07, "loss": 0.2697395384311676, "step": 401 }, { "epoch": 1.635437881873727, "grad_norm": 2.5444276332855225, "learning_rate": 8.5000815244921e-07, "loss": 0.26779498159885406, "step": 402 }, { "epoch": 1.639511201629328, "grad_norm": 2.3247053623199463, "learning_rate": 8.489888115417537e-07, "loss": 0.2565397247672081, "step": 403 }, { "epoch": 1.6435845213849287, "grad_norm": 2.8525049686431885, "learning_rate": 8.479666343630256e-07, "loss": 0.29496023058891296, "step": 404 }, { "epoch": 1.6476578411405294, "grad_norm": 2.5987389087677, "learning_rate": 8.469416292203746e-07, "loss": 0.24137818068265915, "step": 405 }, { "epoch": 1.6517311608961305, "grad_norm": 2.4682445526123047, "learning_rate": 8.459138044441323e-07, "loss": 0.3068127781152725, "step": 406 }, { "epoch": 1.6558044806517311, "grad_norm": 2.43457293510437, "learning_rate": 8.448831683875464e-07, "loss": 0.2586989253759384, "step": 407 }, { "epoch": 1.659877800407332, "grad_norm": 2.446392297744751, "learning_rate": 8.438497294267116e-07, "loss": 0.2845039367675781, "step": 408 }, { "epoch": 1.663951120162933, "grad_norm": 2.4405159950256348, "learning_rate": 8.428134959605027e-07, "loss": 0.2668181359767914, "step": 409 }, { "epoch": 1.6680244399185336, "grad_norm": 2.398472309112549, "learning_rate": 8.417744764105053e-07, "loss": 0.294752761721611, "step": 410 }, { "epoch": 1.6720977596741344, "grad_norm": 2.485675096511841, "learning_rate": 8.407326792209481e-07, "loss": 0.27970798313617706, "step": 411 }, { "epoch": 1.6761710794297353, "grad_norm": 2.326519250869751, "learning_rate": 8.396881128586338e-07, "loss": 0.27439168095588684, "step": 412 }, { "epoch": 1.680244399185336, "grad_norm": 2.5076746940612793, "learning_rate": 8.386407858128706e-07, "loss": 0.24190914630889893, "step": 413 }, { "epoch": 1.6843177189409368, "grad_norm": 2.418656349182129, "learning_rate": 8.375907065954028e-07, "loss": 0.302260160446167, "step": 414 }, { "epoch": 1.6883910386965377, "grad_norm": 2.431206226348877, "learning_rate": 8.365378837403427e-07, "loss": 0.24484054744243622, "step": 415 }, { "epoch": 1.6924643584521384, "grad_norm": 2.1974987983703613, "learning_rate": 8.354823258040995e-07, "loss": 0.23830442130565643, "step": 416 }, { "epoch": 1.6965376782077393, "grad_norm": 2.531301498413086, "learning_rate": 8.344240413653111e-07, "loss": 0.23077362775802612, "step": 417 }, { "epoch": 1.7006109979633401, "grad_norm": 2.3643598556518555, "learning_rate": 8.333630390247741e-07, "loss": 0.2691231817007065, "step": 418 }, { "epoch": 1.7046843177189408, "grad_norm": 2.429917335510254, "learning_rate": 8.322993274053738e-07, "loss": 0.26382092386484146, "step": 419 }, { "epoch": 1.708757637474542, "grad_norm": 2.3184382915496826, "learning_rate": 8.312329151520139e-07, "loss": 0.24146142601966858, "step": 420 }, { "epoch": 1.7128309572301426, "grad_norm": 2.3974194526672363, "learning_rate": 8.301638109315465e-07, "loss": 0.28932487964630127, "step": 421 }, { "epoch": 1.7169042769857432, "grad_norm": 2.445939064025879, "learning_rate": 8.290920234327019e-07, "loss": 0.2816842496395111, "step": 422 }, { "epoch": 1.7209775967413443, "grad_norm": 2.517059087753296, "learning_rate": 8.280175613660175e-07, "loss": 0.28957797586917877, "step": 423 }, { "epoch": 1.725050916496945, "grad_norm": 2.7085039615631104, "learning_rate": 8.269404334637666e-07, "loss": 0.2929697036743164, "step": 424 }, { "epoch": 1.7291242362525459, "grad_norm": 2.3027985095977783, "learning_rate": 8.258606484798896e-07, "loss": 0.2602064907550812, "step": 425 }, { "epoch": 1.7331975560081467, "grad_norm": 2.4261462688446045, "learning_rate": 8.247782151899195e-07, "loss": 0.2826506048440933, "step": 426 }, { "epoch": 1.7372708757637474, "grad_norm": 2.6706831455230713, "learning_rate": 8.236931423909138e-07, "loss": 0.25307597219944, "step": 427 }, { "epoch": 1.7413441955193483, "grad_norm": 2.6151740550994873, "learning_rate": 8.226054389013808e-07, "loss": 0.31587836146354675, "step": 428 }, { "epoch": 1.7454175152749491, "grad_norm": 2.3904056549072266, "learning_rate": 8.215151135612088e-07, "loss": 0.2650100588798523, "step": 429 }, { "epoch": 1.7494908350305498, "grad_norm": 2.48195219039917, "learning_rate": 8.204221752315948e-07, "loss": 0.24214383959770203, "step": 430 }, { "epoch": 1.7535641547861507, "grad_norm": 2.28658390045166, "learning_rate": 8.193266327949708e-07, "loss": 0.26451194286346436, "step": 431 }, { "epoch": 1.7576374745417516, "grad_norm": 2.365696430206299, "learning_rate": 8.182284951549335e-07, "loss": 0.26112615317106247, "step": 432 }, { "epoch": 1.7617107942973522, "grad_norm": 2.467344284057617, "learning_rate": 8.171277712361708e-07, "loss": 0.2644128352403641, "step": 433 }, { "epoch": 1.765784114052953, "grad_norm": 2.6279022693634033, "learning_rate": 8.160244699843899e-07, "loss": 0.26811327785253525, "step": 434 }, { "epoch": 1.769857433808554, "grad_norm": 2.196678638458252, "learning_rate": 8.149186003662437e-07, "loss": 0.2764963060617447, "step": 435 }, { "epoch": 1.7739307535641546, "grad_norm": 2.582368850708008, "learning_rate": 8.138101713692587e-07, "loss": 0.24663043022155762, "step": 436 }, { "epoch": 1.7780040733197557, "grad_norm": 2.4632701873779297, "learning_rate": 8.12699192001762e-07, "loss": 0.24030117690563202, "step": 437 }, { "epoch": 1.7820773930753564, "grad_norm": 2.549862861633301, "learning_rate": 8.115856712928077e-07, "loss": 0.2775857746601105, "step": 438 }, { "epoch": 1.7861507128309573, "grad_norm": 2.460521936416626, "learning_rate": 8.104696182921039e-07, "loss": 0.24370034784078598, "step": 439 }, { "epoch": 1.7902240325865582, "grad_norm": 2.489588975906372, "learning_rate": 8.093510420699386e-07, "loss": 0.2672967165708542, "step": 440 }, { "epoch": 1.7942973523421588, "grad_norm": 2.442493438720703, "learning_rate": 8.082299517171061e-07, "loss": 0.2774495333433151, "step": 441 }, { "epoch": 1.7983706720977597, "grad_norm": 2.6533353328704834, "learning_rate": 8.071063563448339e-07, "loss": 0.27777694165706635, "step": 442 }, { "epoch": 1.8024439918533606, "grad_norm": 2.546030282974243, "learning_rate": 8.059802650847077e-07, "loss": 0.2475699484348297, "step": 443 }, { "epoch": 1.8065173116089612, "grad_norm": 2.603074789047241, "learning_rate": 8.048516870885977e-07, "loss": 0.2610132396221161, "step": 444 }, { "epoch": 1.810590631364562, "grad_norm": 2.5384109020233154, "learning_rate": 8.037206315285841e-07, "loss": 0.26541996002197266, "step": 445 }, { "epoch": 1.814663951120163, "grad_norm": 2.5843305587768555, "learning_rate": 8.025871075968826e-07, "loss": 0.26443643867969513, "step": 446 }, { "epoch": 1.8187372708757636, "grad_norm": 2.428213119506836, "learning_rate": 8.014511245057691e-07, "loss": 0.27873335778713226, "step": 447 }, { "epoch": 1.8228105906313645, "grad_norm": 2.622931480407715, "learning_rate": 8.003126914875063e-07, "loss": 0.2784544825553894, "step": 448 }, { "epoch": 1.8268839103869654, "grad_norm": 2.4025309085845947, "learning_rate": 7.991718177942666e-07, "loss": 0.22745566070079803, "step": 449 }, { "epoch": 1.830957230142566, "grad_norm": 2.426877498626709, "learning_rate": 7.980285126980591e-07, "loss": 0.2900083065032959, "step": 450 }, { "epoch": 1.8350305498981672, "grad_norm": 2.506085157394409, "learning_rate": 7.968827854906528e-07, "loss": 0.3019551932811737, "step": 451 }, { "epoch": 1.8391038696537678, "grad_norm": 2.428899049758911, "learning_rate": 7.95734645483501e-07, "loss": 0.2602303624153137, "step": 452 }, { "epoch": 1.8431771894093685, "grad_norm": 2.7357733249664307, "learning_rate": 7.945841020076669e-07, "loss": 0.2674318701028824, "step": 453 }, { "epoch": 1.8472505091649696, "grad_norm": 2.492051124572754, "learning_rate": 7.934311644137463e-07, "loss": 0.29544439911842346, "step": 454 }, { "epoch": 1.8513238289205702, "grad_norm": 2.751485586166382, "learning_rate": 7.922758420717928e-07, "loss": 0.2730901688337326, "step": 455 }, { "epoch": 1.8553971486761711, "grad_norm": 2.469752550125122, "learning_rate": 7.911181443712407e-07, "loss": 0.28135350346565247, "step": 456 }, { "epoch": 1.859470468431772, "grad_norm": 2.5486271381378174, "learning_rate": 7.89958080720829e-07, "loss": 0.2647327482700348, "step": 457 }, { "epoch": 1.8635437881873727, "grad_norm": 2.328063726425171, "learning_rate": 7.887956605485258e-07, "loss": 0.29177480936050415, "step": 458 }, { "epoch": 1.8676171079429735, "grad_norm": 2.3431217670440674, "learning_rate": 7.876308933014502e-07, "loss": 0.2461807057261467, "step": 459 }, { "epoch": 1.8716904276985744, "grad_norm": 2.346773862838745, "learning_rate": 7.864637884457961e-07, "loss": 0.2737877368927002, "step": 460 }, { "epoch": 1.875763747454175, "grad_norm": 2.6286261081695557, "learning_rate": 7.852943554667561e-07, "loss": 0.29079559445381165, "step": 461 }, { "epoch": 1.879837067209776, "grad_norm": 2.3207788467407227, "learning_rate": 7.841226038684434e-07, "loss": 0.261492520570755, "step": 462 }, { "epoch": 1.8839103869653768, "grad_norm": 2.4097938537597656, "learning_rate": 7.829485431738148e-07, "loss": 0.2779378667473793, "step": 463 }, { "epoch": 1.8879837067209775, "grad_norm": 2.580665349960327, "learning_rate": 7.817721829245935e-07, "loss": 0.26885151863098145, "step": 464 }, { "epoch": 1.8920570264765784, "grad_norm": 2.5190136432647705, "learning_rate": 7.805935326811912e-07, "loss": 0.2348337173461914, "step": 465 }, { "epoch": 1.8961303462321792, "grad_norm": 2.6823647022247314, "learning_rate": 7.794126020226309e-07, "loss": 0.31435824930667877, "step": 466 }, { "epoch": 1.90020366598778, "grad_norm": 2.678208827972412, "learning_rate": 7.782294005464686e-07, "loss": 0.2894388735294342, "step": 467 }, { "epoch": 1.904276985743381, "grad_norm": 2.519721269607544, "learning_rate": 7.770439378687161e-07, "loss": 0.3156396448612213, "step": 468 }, { "epoch": 1.9083503054989817, "grad_norm": 2.6619021892547607, "learning_rate": 7.758562236237614e-07, "loss": 0.2675836831331253, "step": 469 }, { "epoch": 1.9124236252545825, "grad_norm": 2.2732584476470947, "learning_rate": 7.746662674642912e-07, "loss": 0.21649424731731415, "step": 470 }, { "epoch": 1.9164969450101834, "grad_norm": 2.302424669265747, "learning_rate": 7.734740790612136e-07, "loss": 0.2436254546046257, "step": 471 }, { "epoch": 1.920570264765784, "grad_norm": 2.3057138919830322, "learning_rate": 7.722796681035769e-07, "loss": 0.25994570553302765, "step": 472 }, { "epoch": 1.924643584521385, "grad_norm": 2.327444076538086, "learning_rate": 7.710830442984937e-07, "loss": 0.2572202906012535, "step": 473 }, { "epoch": 1.9287169042769858, "grad_norm": 2.3709921836853027, "learning_rate": 7.698842173710599e-07, "loss": 0.2600872740149498, "step": 474 }, { "epoch": 1.9327902240325865, "grad_norm": 2.463008165359497, "learning_rate": 7.686831970642766e-07, "loss": 0.2489926964044571, "step": 475 }, { "epoch": 1.9368635437881874, "grad_norm": 2.4627251625061035, "learning_rate": 7.674799931389708e-07, "loss": 0.2903194725513458, "step": 476 }, { "epoch": 1.9409368635437882, "grad_norm": 2.9676828384399414, "learning_rate": 7.662746153737156e-07, "loss": 0.2674560844898224, "step": 477 }, { "epoch": 1.945010183299389, "grad_norm": 2.448298692703247, "learning_rate": 7.65067073564752e-07, "loss": 0.3171275407075882, "step": 478 }, { "epoch": 1.9490835030549898, "grad_norm": 2.524946451187134, "learning_rate": 7.638573775259077e-07, "loss": 0.2637060284614563, "step": 479 }, { "epoch": 1.9531568228105907, "grad_norm": 2.4001801013946533, "learning_rate": 7.62645537088518e-07, "loss": 0.23155802488327026, "step": 480 }, { "epoch": 1.9572301425661913, "grad_norm": 2.287005662918091, "learning_rate": 7.614315621013469e-07, "loss": 0.27207742631435394, "step": 481 }, { "epoch": 1.9613034623217924, "grad_norm": 2.453338623046875, "learning_rate": 7.60215462430505e-07, "loss": 0.2895518094301224, "step": 482 }, { "epoch": 1.965376782077393, "grad_norm": 2.5567643642425537, "learning_rate": 7.58997247959371e-07, "loss": 0.2574731409549713, "step": 483 }, { "epoch": 1.9694501018329937, "grad_norm": 2.365522623062134, "learning_rate": 7.577769285885108e-07, "loss": 0.22622792422771454, "step": 484 }, { "epoch": 1.9735234215885948, "grad_norm": 2.2915074825286865, "learning_rate": 7.56554514235597e-07, "loss": 0.26031681150197983, "step": 485 }, { "epoch": 1.9775967413441955, "grad_norm": 2.651094436645508, "learning_rate": 7.553300148353284e-07, "loss": 0.2904250845313072, "step": 486 }, { "epoch": 1.9816700610997964, "grad_norm": 2.416658639907837, "learning_rate": 7.541034403393489e-07, "loss": 0.2949088215827942, "step": 487 }, { "epoch": 1.9857433808553973, "grad_norm": 2.4140050411224365, "learning_rate": 7.528748007161676e-07, "loss": 0.2634105682373047, "step": 488 }, { "epoch": 1.989816700610998, "grad_norm": 2.684359550476074, "learning_rate": 7.516441059510764e-07, "loss": 0.27155014872550964, "step": 489 }, { "epoch": 1.9938900203665988, "grad_norm": 2.4172725677490234, "learning_rate": 7.5041136604607e-07, "loss": 0.25667136907577515, "step": 490 }, { "epoch": 1.9979633401221997, "grad_norm": 2.3175907135009766, "learning_rate": 7.491765910197643e-07, "loss": 0.2724708914756775, "step": 491 }, { "epoch": 2.0, "grad_norm": 2.5458946228027344, "learning_rate": 7.479397909073143e-07, "loss": 0.2475520372390747, "step": 492 } ], "logging_steps": 1.0, "max_steps": 1225, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 100.0, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }