zycalice's picture
Training in progress, step 1060, checkpoint
41faeb0 verified
Raw History Blame Contribute Delete
183 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.192843691148776,
"eval_steps": 500,
"global_step": 1060,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0030131826741996233,
"grad_norm": 34.6861457824707,
"learning_rate": 0.0,
"loss": 4.7036,
"step": 1
},
{
"epoch": 0.006026365348399247,
"grad_norm": 33.215126037597656,
"learning_rate": 2e-07,
"loss": 4.4381,
"step": 2
},
{
"epoch": 0.00903954802259887,
"grad_norm": 31.91962242126465,
"learning_rate": 4e-07,
"loss": 4.2738,
"step": 3
},
{
"epoch": 0.012052730696798493,
"grad_norm": 33.510711669921875,
"learning_rate": 6e-07,
"loss": 4.5457,
"step": 4
},
{
"epoch": 0.015065913370998116,
"grad_norm": 33.2039909362793,
"learning_rate": 8e-07,
"loss": 4.4126,
"step": 5
},
{
"epoch": 0.01807909604519774,
"grad_norm": 34.26924514770508,
"learning_rate": 1e-06,
"loss": 4.4619,
"step": 6
},
{
"epoch": 0.021092278719397364,
"grad_norm": 34.04632568359375,
"learning_rate": 9.993957703927493e-07,
"loss": 4.1716,
"step": 7
},
{
"epoch": 0.024105461393596987,
"grad_norm": 32.70482635498047,
"learning_rate": 9.987915407854984e-07,
"loss": 4.1148,
"step": 8
},
{
"epoch": 0.02711864406779661,
"grad_norm": 37.01934814453125,
"learning_rate": 9.981873111782478e-07,
"loss": 4.3351,
"step": 9
},
{
"epoch": 0.030131826741996232,
"grad_norm": 36.172142028808594,
"learning_rate": 9.97583081570997e-07,
"loss": 4.1667,
"step": 10
},
{
"epoch": 0.03314500941619586,
"grad_norm": 40.31679153442383,
"learning_rate": 9.969788519637462e-07,
"loss": 4.2093,
"step": 11
},
{
"epoch": 0.03615819209039548,
"grad_norm": 40.15742492675781,
"learning_rate": 9.963746223564954e-07,
"loss": 4.2268,
"step": 12
},
{
"epoch": 0.039171374764595104,
"grad_norm": 39.929691314697266,
"learning_rate": 9.957703927492447e-07,
"loss": 3.9355,
"step": 13
},
{
"epoch": 0.04218455743879473,
"grad_norm": 39.41320037841797,
"learning_rate": 9.951661631419938e-07,
"loss": 4.0088,
"step": 14
},
{
"epoch": 0.04519774011299435,
"grad_norm": 37.93269729614258,
"learning_rate": 9.945619335347432e-07,
"loss": 3.6819,
"step": 15
},
{
"epoch": 0.04821092278719397,
"grad_norm": 38.64561462402344,
"learning_rate": 9.939577039274925e-07,
"loss": 3.7213,
"step": 16
},
{
"epoch": 0.051224105461393596,
"grad_norm": 33.3484001159668,
"learning_rate": 9.933534743202417e-07,
"loss": 3.7547,
"step": 17
},
{
"epoch": 0.05423728813559322,
"grad_norm": 28.220916748046875,
"learning_rate": 9.92749244712991e-07,
"loss": 3.5524,
"step": 18
},
{
"epoch": 0.05725047080979284,
"grad_norm": 22.749616622924805,
"learning_rate": 9.921450151057401e-07,
"loss": 3.5342,
"step": 19
},
{
"epoch": 0.060263653483992465,
"grad_norm": 15.116613388061523,
"learning_rate": 9.915407854984895e-07,
"loss": 3.4557,
"step": 20
},
{
"epoch": 0.06327683615819209,
"grad_norm": 14.70132064819336,
"learning_rate": 9.909365558912386e-07,
"loss": 3.4788,
"step": 21
},
{
"epoch": 0.06629001883239172,
"grad_norm": 14.527510643005371,
"learning_rate": 9.90332326283988e-07,
"loss": 3.3028,
"step": 22
},
{
"epoch": 0.06930320150659133,
"grad_norm": 12.996399879455566,
"learning_rate": 9.89728096676737e-07,
"loss": 3.2357,
"step": 23
},
{
"epoch": 0.07231638418079096,
"grad_norm": 13.773697853088379,
"learning_rate": 9.891238670694864e-07,
"loss": 3.2755,
"step": 24
},
{
"epoch": 0.07532956685499058,
"grad_norm": 13.862228393554688,
"learning_rate": 9.885196374622357e-07,
"loss": 3.3604,
"step": 25
},
{
"epoch": 0.07834274952919021,
"grad_norm": 12.897477149963379,
"learning_rate": 9.879154078549849e-07,
"loss": 3.3267,
"step": 26
},
{
"epoch": 0.08135593220338982,
"grad_norm": 14.752609252929688,
"learning_rate": 9.873111782477342e-07,
"loss": 3.2435,
"step": 27
},
{
"epoch": 0.08436911487758945,
"grad_norm": 12.743549346923828,
"learning_rate": 9.867069486404833e-07,
"loss": 3.1507,
"step": 28
},
{
"epoch": 0.08738229755178907,
"grad_norm": 11.101383209228516,
"learning_rate": 9.861027190332327e-07,
"loss": 3.1273,
"step": 29
},
{
"epoch": 0.0903954802259887,
"grad_norm": 11.95251178741455,
"learning_rate": 9.854984894259818e-07,
"loss": 3.0316,
"step": 30
},
{
"epoch": 0.09340866290018833,
"grad_norm": 10.766655921936035,
"learning_rate": 9.848942598187312e-07,
"loss": 3.1074,
"step": 31
},
{
"epoch": 0.09642184557438795,
"grad_norm": 11.15977954864502,
"learning_rate": 9.842900302114803e-07,
"loss": 2.9768,
"step": 32
},
{
"epoch": 0.09943502824858758,
"grad_norm": 10.29792594909668,
"learning_rate": 9.836858006042296e-07,
"loss": 3.083,
"step": 33
},
{
"epoch": 0.10244821092278719,
"grad_norm": 9.040534019470215,
"learning_rate": 9.830815709969788e-07,
"loss": 2.8304,
"step": 34
},
{
"epoch": 0.10546139359698682,
"grad_norm": 9.023050308227539,
"learning_rate": 9.82477341389728e-07,
"loss": 2.6917,
"step": 35
},
{
"epoch": 0.10847457627118644,
"grad_norm": 10.378137588500977,
"learning_rate": 9.818731117824774e-07,
"loss": 2.8607,
"step": 36
},
{
"epoch": 0.11148775894538607,
"grad_norm": 9.073391914367676,
"learning_rate": 9.812688821752266e-07,
"loss": 2.8967,
"step": 37
},
{
"epoch": 0.11450094161958568,
"grad_norm": 8.33003044128418,
"learning_rate": 9.80664652567976e-07,
"loss": 2.6255,
"step": 38
},
{
"epoch": 0.11751412429378531,
"grad_norm": 8.349893569946289,
"learning_rate": 9.80060422960725e-07,
"loss": 2.7113,
"step": 39
},
{
"epoch": 0.12052730696798493,
"grad_norm": 8.032829284667969,
"learning_rate": 9.794561933534744e-07,
"loss": 2.7488,
"step": 40
},
{
"epoch": 0.12354048964218456,
"grad_norm": 8.089343070983887,
"learning_rate": 9.788519637462235e-07,
"loss": 2.5701,
"step": 41
},
{
"epoch": 0.12655367231638417,
"grad_norm": 8.112906455993652,
"learning_rate": 9.782477341389729e-07,
"loss": 2.5999,
"step": 42
},
{
"epoch": 0.1295668549905838,
"grad_norm": 7.398575782775879,
"learning_rate": 9.77643504531722e-07,
"loss": 2.6078,
"step": 43
},
{
"epoch": 0.13258003766478343,
"grad_norm": 7.844170093536377,
"learning_rate": 9.770392749244713e-07,
"loss": 2.5361,
"step": 44
},
{
"epoch": 0.13559322033898305,
"grad_norm": 7.322074890136719,
"learning_rate": 9.764350453172205e-07,
"loss": 2.5254,
"step": 45
},
{
"epoch": 0.13860640301318267,
"grad_norm": 6.919925689697266,
"learning_rate": 9.758308157099698e-07,
"loss": 2.4676,
"step": 46
},
{
"epoch": 0.1416195856873823,
"grad_norm": 6.065021514892578,
"learning_rate": 9.75226586102719e-07,
"loss": 2.338,
"step": 47
},
{
"epoch": 0.14463276836158193,
"grad_norm": 7.550880432128906,
"learning_rate": 9.746223564954683e-07,
"loss": 2.4482,
"step": 48
},
{
"epoch": 0.14764595103578154,
"grad_norm": 6.961904525756836,
"learning_rate": 9.740181268882174e-07,
"loss": 2.635,
"step": 49
},
{
"epoch": 0.15065913370998116,
"grad_norm": 6.212646484375,
"learning_rate": 9.734138972809667e-07,
"loss": 2.3776,
"step": 50
},
{
"epoch": 0.1536723163841808,
"grad_norm": 6.006916046142578,
"learning_rate": 9.728096676737159e-07,
"loss": 2.3018,
"step": 51
},
{
"epoch": 0.15668549905838042,
"grad_norm": 6.0531325340271,
"learning_rate": 9.722054380664652e-07,
"loss": 2.3164,
"step": 52
},
{
"epoch": 0.15969868173258003,
"grad_norm": 5.674480438232422,
"learning_rate": 9.716012084592146e-07,
"loss": 2.3049,
"step": 53
},
{
"epoch": 0.16271186440677965,
"grad_norm": 6.283177375793457,
"learning_rate": 9.709969788519637e-07,
"loss": 2.2727,
"step": 54
},
{
"epoch": 0.1657250470809793,
"grad_norm": 5.819633960723877,
"learning_rate": 9.70392749244713e-07,
"loss": 2.2122,
"step": 55
},
{
"epoch": 0.1687382297551789,
"grad_norm": 5.006446838378906,
"learning_rate": 9.697885196374622e-07,
"loss": 2.2215,
"step": 56
},
{
"epoch": 0.17175141242937852,
"grad_norm": 5.97379732131958,
"learning_rate": 9.691842900302115e-07,
"loss": 2.2061,
"step": 57
},
{
"epoch": 0.17476459510357814,
"grad_norm": 5.025632381439209,
"learning_rate": 9.685800604229606e-07,
"loss": 2.3006,
"step": 58
},
{
"epoch": 0.17777777777777778,
"grad_norm": 6.5014472007751465,
"learning_rate": 9.6797583081571e-07,
"loss": 2.2979,
"step": 59
},
{
"epoch": 0.1807909604519774,
"grad_norm": 4.874022960662842,
"learning_rate": 9.67371601208459e-07,
"loss": 2.095,
"step": 60
},
{
"epoch": 0.18380414312617702,
"grad_norm": 5.257139682769775,
"learning_rate": 9.667673716012084e-07,
"loss": 2.2371,
"step": 61
},
{
"epoch": 0.18681732580037666,
"grad_norm": 4.8642377853393555,
"learning_rate": 9.661631419939576e-07,
"loss": 2.2551,
"step": 62
},
{
"epoch": 0.18983050847457628,
"grad_norm": 5.601889610290527,
"learning_rate": 9.65558912386707e-07,
"loss": 2.1867,
"step": 63
},
{
"epoch": 0.1928436911487759,
"grad_norm": 5.198556900024414,
"learning_rate": 9.64954682779456e-07,
"loss": 2.0829,
"step": 64
},
{
"epoch": 0.1958568738229755,
"grad_norm": 5.988768100738525,
"learning_rate": 9.643504531722054e-07,
"loss": 2.1105,
"step": 65
},
{
"epoch": 0.19887005649717515,
"grad_norm": 5.178367614746094,
"learning_rate": 9.637462235649545e-07,
"loss": 2.0064,
"step": 66
},
{
"epoch": 0.20188323917137477,
"grad_norm": 5.225499153137207,
"learning_rate": 9.631419939577038e-07,
"loss": 1.9879,
"step": 67
},
{
"epoch": 0.20489642184557438,
"grad_norm": 5.521583080291748,
"learning_rate": 9.625377643504532e-07,
"loss": 2.1283,
"step": 68
},
{
"epoch": 0.207909604519774,
"grad_norm": 5.450455188751221,
"learning_rate": 9.619335347432023e-07,
"loss": 2.1023,
"step": 69
},
{
"epoch": 0.21092278719397364,
"grad_norm": 6.377326011657715,
"learning_rate": 9.613293051359517e-07,
"loss": 2.0945,
"step": 70
},
{
"epoch": 0.21393596986817326,
"grad_norm": 5.580687046051025,
"learning_rate": 9.607250755287008e-07,
"loss": 2.0603,
"step": 71
},
{
"epoch": 0.21694915254237288,
"grad_norm": 5.663399696350098,
"learning_rate": 9.601208459214501e-07,
"loss": 2.0243,
"step": 72
},
{
"epoch": 0.2199623352165725,
"grad_norm": 4.719912528991699,
"learning_rate": 9.595166163141993e-07,
"loss": 2.0211,
"step": 73
},
{
"epoch": 0.22297551789077213,
"grad_norm": 4.904620170593262,
"learning_rate": 9.589123867069486e-07,
"loss": 2.0721,
"step": 74
},
{
"epoch": 0.22598870056497175,
"grad_norm": 5.553138732910156,
"learning_rate": 9.583081570996977e-07,
"loss": 1.9293,
"step": 75
},
{
"epoch": 0.22900188323917137,
"grad_norm": 5.154430866241455,
"learning_rate": 9.57703927492447e-07,
"loss": 1.9106,
"step": 76
},
{
"epoch": 0.232015065913371,
"grad_norm": 5.0921630859375,
"learning_rate": 9.570996978851962e-07,
"loss": 1.8061,
"step": 77
},
{
"epoch": 0.23502824858757063,
"grad_norm": 5.445968151092529,
"learning_rate": 9.564954682779455e-07,
"loss": 1.8985,
"step": 78
},
{
"epoch": 0.23804143126177024,
"grad_norm": 4.871007442474365,
"learning_rate": 9.558912386706947e-07,
"loss": 1.9315,
"step": 79
},
{
"epoch": 0.24105461393596986,
"grad_norm": 5.1469526290893555,
"learning_rate": 9.55287009063444e-07,
"loss": 1.8471,
"step": 80
},
{
"epoch": 0.2440677966101695,
"grad_norm": 5.5420241355896,
"learning_rate": 9.546827794561934e-07,
"loss": 1.8587,
"step": 81
},
{
"epoch": 0.24708097928436912,
"grad_norm": 5.493891716003418,
"learning_rate": 9.540785498489425e-07,
"loss": 1.8932,
"step": 82
},
{
"epoch": 0.25009416195856876,
"grad_norm": 4.842357635498047,
"learning_rate": 9.534743202416918e-07,
"loss": 1.7296,
"step": 83
},
{
"epoch": 0.25310734463276835,
"grad_norm": 5.839240550994873,
"learning_rate": 9.528700906344411e-07,
"loss": 1.8418,
"step": 84
},
{
"epoch": 0.256120527306968,
"grad_norm": 6.450507640838623,
"learning_rate": 9.522658610271903e-07,
"loss": 1.7847,
"step": 85
},
{
"epoch": 0.2591337099811676,
"grad_norm": 5.740670204162598,
"learning_rate": 9.516616314199395e-07,
"loss": 1.8536,
"step": 86
},
{
"epoch": 0.2621468926553672,
"grad_norm": 5.523307800292969,
"learning_rate": 9.510574018126888e-07,
"loss": 1.8073,
"step": 87
},
{
"epoch": 0.26516007532956687,
"grad_norm": 4.190532207489014,
"learning_rate": 9.50453172205438e-07,
"loss": 1.7689,
"step": 88
},
{
"epoch": 0.26817325800376646,
"grad_norm": 4.71892786026001,
"learning_rate": 9.498489425981872e-07,
"loss": 1.7927,
"step": 89
},
{
"epoch": 0.2711864406779661,
"grad_norm": 3.9276342391967773,
"learning_rate": 9.492447129909366e-07,
"loss": 1.8459,
"step": 90
},
{
"epoch": 0.27419962335216574,
"grad_norm": 4.415136337280273,
"learning_rate": 9.486404833836857e-07,
"loss": 1.8626,
"step": 91
},
{
"epoch": 0.27721280602636533,
"grad_norm": 5.26611852645874,
"learning_rate": 9.48036253776435e-07,
"loss": 1.6375,
"step": 92
},
{
"epoch": 0.280225988700565,
"grad_norm": 4.380786895751953,
"learning_rate": 9.474320241691842e-07,
"loss": 1.7516,
"step": 93
},
{
"epoch": 0.2832391713747646,
"grad_norm": 4.630937099456787,
"learning_rate": 9.468277945619335e-07,
"loss": 1.6986,
"step": 94
},
{
"epoch": 0.2862523540489642,
"grad_norm": 4.607402801513672,
"learning_rate": 9.462235649546827e-07,
"loss": 1.717,
"step": 95
},
{
"epoch": 0.28926553672316385,
"grad_norm": 4.747241497039795,
"learning_rate": 9.45619335347432e-07,
"loss": 1.7993,
"step": 96
},
{
"epoch": 0.29227871939736344,
"grad_norm": 5.222727298736572,
"learning_rate": 9.450151057401811e-07,
"loss": 1.7622,
"step": 97
},
{
"epoch": 0.2952919020715631,
"grad_norm": 4.226417541503906,
"learning_rate": 9.444108761329305e-07,
"loss": 1.7105,
"step": 98
},
{
"epoch": 0.2983050847457627,
"grad_norm": 5.662446022033691,
"learning_rate": 9.438066465256798e-07,
"loss": 1.5551,
"step": 99
},
{
"epoch": 0.3013182674199623,
"grad_norm": 5.452689170837402,
"learning_rate": 9.432024169184289e-07,
"loss": 1.6254,
"step": 100
},
{
"epoch": 0.30433145009416196,
"grad_norm": 6.139257431030273,
"learning_rate": 9.425981873111783e-07,
"loss": 1.8607,
"step": 101
},
{
"epoch": 0.3073446327683616,
"grad_norm": 5.731149673461914,
"learning_rate": 9.419939577039274e-07,
"loss": 1.7846,
"step": 102
},
{
"epoch": 0.3103578154425612,
"grad_norm": 4.859795093536377,
"learning_rate": 9.413897280966767e-07,
"loss": 1.7599,
"step": 103
},
{
"epoch": 0.31337099811676083,
"grad_norm": 4.731764316558838,
"learning_rate": 9.407854984894259e-07,
"loss": 1.6824,
"step": 104
},
{
"epoch": 0.3163841807909605,
"grad_norm": 5.090848445892334,
"learning_rate": 9.401812688821752e-07,
"loss": 1.4966,
"step": 105
},
{
"epoch": 0.31939736346516007,
"grad_norm": 5.832790374755859,
"learning_rate": 9.395770392749243e-07,
"loss": 1.6723,
"step": 106
},
{
"epoch": 0.3224105461393597,
"grad_norm": 4.752500534057617,
"learning_rate": 9.389728096676737e-07,
"loss": 1.5952,
"step": 107
},
{
"epoch": 0.3254237288135593,
"grad_norm": 4.700122833251953,
"learning_rate": 9.383685800604229e-07,
"loss": 1.6605,
"step": 108
},
{
"epoch": 0.32843691148775894,
"grad_norm": 4.912515640258789,
"learning_rate": 9.377643504531722e-07,
"loss": 1.7009,
"step": 109
},
{
"epoch": 0.3314500941619586,
"grad_norm": 4.371939182281494,
"learning_rate": 9.371601208459214e-07,
"loss": 1.6983,
"step": 110
},
{
"epoch": 0.3344632768361582,
"grad_norm": 4.993189811706543,
"learning_rate": 9.365558912386706e-07,
"loss": 1.6657,
"step": 111
},
{
"epoch": 0.3374764595103578,
"grad_norm": 5.17345666885376,
"learning_rate": 9.3595166163142e-07,
"loss": 1.6463,
"step": 112
},
{
"epoch": 0.34048964218455746,
"grad_norm": 4.0338053703308105,
"learning_rate": 9.353474320241691e-07,
"loss": 1.6468,
"step": 113
},
{
"epoch": 0.34350282485875705,
"grad_norm": 4.444165229797363,
"learning_rate": 9.347432024169184e-07,
"loss": 1.6073,
"step": 114
},
{
"epoch": 0.3465160075329567,
"grad_norm": 5.414663791656494,
"learning_rate": 9.341389728096676e-07,
"loss": 1.751,
"step": 115
},
{
"epoch": 0.3495291902071563,
"grad_norm": 4.576066017150879,
"learning_rate": 9.335347432024169e-07,
"loss": 1.6533,
"step": 116
},
{
"epoch": 0.3525423728813559,
"grad_norm": 4.185419082641602,
"learning_rate": 9.329305135951662e-07,
"loss": 1.6802,
"step": 117
},
{
"epoch": 0.35555555555555557,
"grad_norm": 5.01163911819458,
"learning_rate": 9.323262839879154e-07,
"loss": 1.6024,
"step": 118
},
{
"epoch": 0.35856873822975516,
"grad_norm": 5.191035270690918,
"learning_rate": 9.317220543806646e-07,
"loss": 1.7589,
"step": 119
},
{
"epoch": 0.3615819209039548,
"grad_norm": 5.3965959548950195,
"learning_rate": 9.311178247734139e-07,
"loss": 1.5132,
"step": 120
},
{
"epoch": 0.36459510357815444,
"grad_norm": 5.428668022155762,
"learning_rate": 9.305135951661631e-07,
"loss": 1.8154,
"step": 121
},
{
"epoch": 0.36760828625235403,
"grad_norm": 4.524122714996338,
"learning_rate": 9.299093655589123e-07,
"loss": 1.6294,
"step": 122
},
{
"epoch": 0.3706214689265537,
"grad_norm": 7.043918132781982,
"learning_rate": 9.293051359516616e-07,
"loss": 1.6754,
"step": 123
},
{
"epoch": 0.3736346516007533,
"grad_norm": 5.170762538909912,
"learning_rate": 9.287009063444108e-07,
"loss": 1.6978,
"step": 124
},
{
"epoch": 0.3766478342749529,
"grad_norm": 4.266485691070557,
"learning_rate": 9.2809667673716e-07,
"loss": 1.6359,
"step": 125
},
{
"epoch": 0.37966101694915255,
"grad_norm": 5.6969685554504395,
"learning_rate": 9.274924471299094e-07,
"loss": 1.6604,
"step": 126
},
{
"epoch": 0.38267419962335214,
"grad_norm": 5.008423328399658,
"learning_rate": 9.268882175226585e-07,
"loss": 1.7061,
"step": 127
},
{
"epoch": 0.3856873822975518,
"grad_norm": 7.691641330718994,
"learning_rate": 9.262839879154078e-07,
"loss": 1.627,
"step": 128
},
{
"epoch": 0.3887005649717514,
"grad_norm": 5.625863552093506,
"learning_rate": 9.256797583081571e-07,
"loss": 1.5484,
"step": 129
},
{
"epoch": 0.391713747645951,
"grad_norm": 6.434806823730469,
"learning_rate": 9.250755287009063e-07,
"loss": 1.7078,
"step": 130
},
{
"epoch": 0.39472693032015066,
"grad_norm": 6.211691856384277,
"learning_rate": 9.244712990936556e-07,
"loss": 1.693,
"step": 131
},
{
"epoch": 0.3977401129943503,
"grad_norm": 5.0158467292785645,
"learning_rate": 9.238670694864048e-07,
"loss": 1.6616,
"step": 132
},
{
"epoch": 0.4007532956685499,
"grad_norm": 5.5790114402771,
"learning_rate": 9.23262839879154e-07,
"loss": 1.5867,
"step": 133
},
{
"epoch": 0.40376647834274954,
"grad_norm": 5.472513198852539,
"learning_rate": 9.226586102719033e-07,
"loss": 1.5356,
"step": 134
},
{
"epoch": 0.4067796610169492,
"grad_norm": 5.892872333526611,
"learning_rate": 9.220543806646526e-07,
"loss": 1.5713,
"step": 135
},
{
"epoch": 0.40979284369114877,
"grad_norm": 5.382603645324707,
"learning_rate": 9.214501510574017e-07,
"loss": 1.5487,
"step": 136
},
{
"epoch": 0.4128060263653484,
"grad_norm": 5.466237545013428,
"learning_rate": 9.208459214501511e-07,
"loss": 1.6959,
"step": 137
},
{
"epoch": 0.415819209039548,
"grad_norm": 6.329081058502197,
"learning_rate": 9.202416918429002e-07,
"loss": 1.5138,
"step": 138
},
{
"epoch": 0.41883239171374764,
"grad_norm": 4.847983360290527,
"learning_rate": 9.196374622356495e-07,
"loss": 1.5952,
"step": 139
},
{
"epoch": 0.4218455743879473,
"grad_norm": 5.410863876342773,
"learning_rate": 9.190332326283987e-07,
"loss": 1.5666,
"step": 140
},
{
"epoch": 0.4248587570621469,
"grad_norm": 5.97892427444458,
"learning_rate": 9.18429003021148e-07,
"loss": 1.5877,
"step": 141
},
{
"epoch": 0.4278719397363465,
"grad_norm": 6.052073001861572,
"learning_rate": 9.178247734138971e-07,
"loss": 1.619,
"step": 142
},
{
"epoch": 0.43088512241054616,
"grad_norm": 6.032132148742676,
"learning_rate": 9.172205438066465e-07,
"loss": 1.6091,
"step": 143
},
{
"epoch": 0.43389830508474575,
"grad_norm": 6.4606122970581055,
"learning_rate": 9.166163141993958e-07,
"loss": 1.4937,
"step": 144
},
{
"epoch": 0.4369114877589454,
"grad_norm": 4.8324995040893555,
"learning_rate": 9.16012084592145e-07,
"loss": 1.4955,
"step": 145
},
{
"epoch": 0.439924670433145,
"grad_norm": 7.679388046264648,
"learning_rate": 9.154078549848943e-07,
"loss": 1.6338,
"step": 146
},
{
"epoch": 0.4429378531073446,
"grad_norm": 5.446895122528076,
"learning_rate": 9.148036253776434e-07,
"loss": 1.6086,
"step": 147
},
{
"epoch": 0.44595103578154427,
"grad_norm": 6.193073749542236,
"learning_rate": 9.141993957703928e-07,
"loss": 1.6233,
"step": 148
},
{
"epoch": 0.44896421845574386,
"grad_norm": 5.870221138000488,
"learning_rate": 9.135951661631419e-07,
"loss": 1.6047,
"step": 149
},
{
"epoch": 0.4519774011299435,
"grad_norm": 5.440488338470459,
"learning_rate": 9.129909365558912e-07,
"loss": 1.5929,
"step": 150
},
{
"epoch": 0.45499058380414314,
"grad_norm": 5.8792805671691895,
"learning_rate": 9.123867069486404e-07,
"loss": 1.6988,
"step": 151
},
{
"epoch": 0.45800376647834273,
"grad_norm": 5.484136581420898,
"learning_rate": 9.117824773413897e-07,
"loss": 1.6668,
"step": 152
},
{
"epoch": 0.4610169491525424,
"grad_norm": 5.463471412658691,
"learning_rate": 9.111782477341389e-07,
"loss": 1.6386,
"step": 153
},
{
"epoch": 0.464030131826742,
"grad_norm": 5.9401373863220215,
"learning_rate": 9.105740181268882e-07,
"loss": 1.5446,
"step": 154
},
{
"epoch": 0.4670433145009416,
"grad_norm": 5.409419536590576,
"learning_rate": 9.099697885196374e-07,
"loss": 1.5491,
"step": 155
},
{
"epoch": 0.47005649717514125,
"grad_norm": 6.793614387512207,
"learning_rate": 9.093655589123867e-07,
"loss": 1.5701,
"step": 156
},
{
"epoch": 0.47306967984934084,
"grad_norm": 6.287842750549316,
"learning_rate": 9.087613293051359e-07,
"loss": 1.5029,
"step": 157
},
{
"epoch": 0.4760828625235405,
"grad_norm": 7.36419153213501,
"learning_rate": 9.081570996978851e-07,
"loss": 1.7923,
"step": 158
},
{
"epoch": 0.47909604519774013,
"grad_norm": 6.176687717437744,
"learning_rate": 9.075528700906345e-07,
"loss": 1.5927,
"step": 159
},
{
"epoch": 0.4821092278719397,
"grad_norm": 8.09927749633789,
"learning_rate": 9.069486404833836e-07,
"loss": 1.6368,
"step": 160
},
{
"epoch": 0.48512241054613936,
"grad_norm": 5.725100994110107,
"learning_rate": 9.063444108761329e-07,
"loss": 1.621,
"step": 161
},
{
"epoch": 0.488135593220339,
"grad_norm": 6.655712127685547,
"learning_rate": 9.057401812688822e-07,
"loss": 1.611,
"step": 162
},
{
"epoch": 0.4911487758945386,
"grad_norm": 7.28790283203125,
"learning_rate": 9.051359516616314e-07,
"loss": 1.7741,
"step": 163
},
{
"epoch": 0.49416195856873824,
"grad_norm": 6.514660358428955,
"learning_rate": 9.045317220543806e-07,
"loss": 1.6044,
"step": 164
},
{
"epoch": 0.4971751412429379,
"grad_norm": 6.514247417449951,
"learning_rate": 9.039274924471299e-07,
"loss": 1.5373,
"step": 165
},
{
"epoch": 0.5001883239171375,
"grad_norm": 5.70638370513916,
"learning_rate": 9.033232628398791e-07,
"loss": 1.4872,
"step": 166
},
{
"epoch": 0.5032015065913371,
"grad_norm": 8.311596870422363,
"learning_rate": 9.027190332326283e-07,
"loss": 1.667,
"step": 167
},
{
"epoch": 0.5062146892655367,
"grad_norm": 7.69071626663208,
"learning_rate": 9.021148036253776e-07,
"loss": 1.6485,
"step": 168
},
{
"epoch": 0.5092278719397364,
"grad_norm": 5.051042556762695,
"learning_rate": 9.015105740181268e-07,
"loss": 1.5039,
"step": 169
},
{
"epoch": 0.512241054613936,
"grad_norm": 5.553494930267334,
"learning_rate": 9.009063444108761e-07,
"loss": 1.5953,
"step": 170
},
{
"epoch": 0.5152542372881356,
"grad_norm": 8.505714416503906,
"learning_rate": 9.003021148036254e-07,
"loss": 1.6012,
"step": 171
},
{
"epoch": 0.5182674199623352,
"grad_norm": 8.109448432922363,
"learning_rate": 8.996978851963745e-07,
"loss": 1.5244,
"step": 172
},
{
"epoch": 0.5212806026365349,
"grad_norm": 5.802191734313965,
"learning_rate": 8.990936555891239e-07,
"loss": 1.4676,
"step": 173
},
{
"epoch": 0.5242937853107345,
"grad_norm": 5.986242294311523,
"learning_rate": 8.984894259818731e-07,
"loss": 1.5684,
"step": 174
},
{
"epoch": 0.527306967984934,
"grad_norm": 4.864075183868408,
"learning_rate": 8.978851963746223e-07,
"loss": 1.5974,
"step": 175
},
{
"epoch": 0.5303201506591337,
"grad_norm": 5.130259990692139,
"learning_rate": 8.972809667673716e-07,
"loss": 1.479,
"step": 176
},
{
"epoch": 0.5333333333333333,
"grad_norm": 7.681236743927002,
"learning_rate": 8.966767371601208e-07,
"loss": 1.6573,
"step": 177
},
{
"epoch": 0.5363465160075329,
"grad_norm": 6.221404075622559,
"learning_rate": 8.9607250755287e-07,
"loss": 1.4351,
"step": 178
},
{
"epoch": 0.5393596986817326,
"grad_norm": 8.46912956237793,
"learning_rate": 8.954682779456193e-07,
"loss": 1.7202,
"step": 179
},
{
"epoch": 0.5423728813559322,
"grad_norm": 5.749709606170654,
"learning_rate": 8.948640483383686e-07,
"loss": 1.5161,
"step": 180
},
{
"epoch": 0.5453860640301318,
"grad_norm": 6.005599498748779,
"learning_rate": 8.942598187311177e-07,
"loss": 1.4453,
"step": 181
},
{
"epoch": 0.5483992467043315,
"grad_norm": 6.749095916748047,
"learning_rate": 8.936555891238671e-07,
"loss": 1.5969,
"step": 182
},
{
"epoch": 0.5514124293785311,
"grad_norm": 6.684814929962158,
"learning_rate": 8.930513595166162e-07,
"loss": 1.5549,
"step": 183
},
{
"epoch": 0.5544256120527307,
"grad_norm": 7.206900119781494,
"learning_rate": 8.924471299093656e-07,
"loss": 1.6059,
"step": 184
},
{
"epoch": 0.5574387947269304,
"grad_norm": 7.277518272399902,
"learning_rate": 8.918429003021147e-07,
"loss": 1.6016,
"step": 185
},
{
"epoch": 0.56045197740113,
"grad_norm": 6.886972427368164,
"learning_rate": 8.91238670694864e-07,
"loss": 1.4321,
"step": 186
},
{
"epoch": 0.5634651600753295,
"grad_norm": 5.228976249694824,
"learning_rate": 8.906344410876132e-07,
"loss": 1.5728,
"step": 187
},
{
"epoch": 0.5664783427495292,
"grad_norm": 5.535543918609619,
"learning_rate": 8.900302114803625e-07,
"loss": 1.6334,
"step": 188
},
{
"epoch": 0.5694915254237288,
"grad_norm": 6.800729274749756,
"learning_rate": 8.894259818731118e-07,
"loss": 1.4861,
"step": 189
},
{
"epoch": 0.5725047080979284,
"grad_norm": 9.01477336883545,
"learning_rate": 8.88821752265861e-07,
"loss": 1.5952,
"step": 190
},
{
"epoch": 0.5755178907721281,
"grad_norm": 6.48466157913208,
"learning_rate": 8.882175226586103e-07,
"loss": 1.6768,
"step": 191
},
{
"epoch": 0.5785310734463277,
"grad_norm": 9.188112258911133,
"learning_rate": 8.876132930513594e-07,
"loss": 1.5059,
"step": 192
},
{
"epoch": 0.5815442561205273,
"grad_norm": 6.5499982833862305,
"learning_rate": 8.870090634441088e-07,
"loss": 1.461,
"step": 193
},
{
"epoch": 0.5845574387947269,
"grad_norm": 5.8452253341674805,
"learning_rate": 8.864048338368579e-07,
"loss": 1.4932,
"step": 194
},
{
"epoch": 0.5875706214689266,
"grad_norm": 7.008406162261963,
"learning_rate": 8.858006042296073e-07,
"loss": 1.512,
"step": 195
},
{
"epoch": 0.5905838041431262,
"grad_norm": 7.992347717285156,
"learning_rate": 8.851963746223564e-07,
"loss": 1.5753,
"step": 196
},
{
"epoch": 0.5935969868173258,
"grad_norm": 9.332303047180176,
"learning_rate": 8.845921450151057e-07,
"loss": 1.5802,
"step": 197
},
{
"epoch": 0.5966101694915255,
"grad_norm": 6.212387561798096,
"learning_rate": 8.839879154078549e-07,
"loss": 1.56,
"step": 198
},
{
"epoch": 0.599623352165725,
"grad_norm": 4.9587836265563965,
"learning_rate": 8.833836858006042e-07,
"loss": 1.6038,
"step": 199
},
{
"epoch": 0.6026365348399246,
"grad_norm": 8.691217422485352,
"learning_rate": 8.827794561933534e-07,
"loss": 1.4769,
"step": 200
},
{
"epoch": 0.6056497175141243,
"grad_norm": 7.946009635925293,
"learning_rate": 8.821752265861027e-07,
"loss": 1.4844,
"step": 201
},
{
"epoch": 0.6086629001883239,
"grad_norm": 7.402195453643799,
"learning_rate": 8.815709969788519e-07,
"loss": 1.5348,
"step": 202
},
{
"epoch": 0.6116760828625235,
"grad_norm": 6.194790840148926,
"learning_rate": 8.809667673716011e-07,
"loss": 1.5576,
"step": 203
},
{
"epoch": 0.6146892655367232,
"grad_norm": 10.788127899169922,
"learning_rate": 8.803625377643505e-07,
"loss": 1.5542,
"step": 204
},
{
"epoch": 0.6177024482109228,
"grad_norm": 6.447693824768066,
"learning_rate": 8.797583081570996e-07,
"loss": 1.6638,
"step": 205
},
{
"epoch": 0.6207156308851224,
"grad_norm": 6.808053016662598,
"learning_rate": 8.79154078549849e-07,
"loss": 1.3766,
"step": 206
},
{
"epoch": 0.6237288135593221,
"grad_norm": 6.570572376251221,
"learning_rate": 8.785498489425981e-07,
"loss": 1.4773,
"step": 207
},
{
"epoch": 0.6267419962335217,
"grad_norm": 6.888332843780518,
"learning_rate": 8.779456193353474e-07,
"loss": 1.6505,
"step": 208
},
{
"epoch": 0.6297551789077213,
"grad_norm": 7.269958019256592,
"learning_rate": 8.773413897280967e-07,
"loss": 1.5959,
"step": 209
},
{
"epoch": 0.632768361581921,
"grad_norm": 5.675526142120361,
"learning_rate": 8.767371601208459e-07,
"loss": 1.5648,
"step": 210
},
{
"epoch": 0.6357815442561205,
"grad_norm": 5.325082778930664,
"learning_rate": 8.761329305135951e-07,
"loss": 1.5648,
"step": 211
},
{
"epoch": 0.6387947269303201,
"grad_norm": 6.052435874938965,
"learning_rate": 8.755287009063444e-07,
"loss": 1.6068,
"step": 212
},
{
"epoch": 0.6418079096045197,
"grad_norm": 6.327192783355713,
"learning_rate": 8.749244712990936e-07,
"loss": 1.5738,
"step": 213
},
{
"epoch": 0.6448210922787194,
"grad_norm": 6.1447272300720215,
"learning_rate": 8.743202416918428e-07,
"loss": 1.5532,
"step": 214
},
{
"epoch": 0.647834274952919,
"grad_norm": 7.469200134277344,
"learning_rate": 8.737160120845921e-07,
"loss": 1.426,
"step": 215
},
{
"epoch": 0.6508474576271186,
"grad_norm": 4.781744003295898,
"learning_rate": 8.731117824773413e-07,
"loss": 1.5058,
"step": 216
},
{
"epoch": 0.6538606403013183,
"grad_norm": 5.519852161407471,
"learning_rate": 8.725075528700905e-07,
"loss": 1.4737,
"step": 217
},
{
"epoch": 0.6568738229755179,
"grad_norm": 5.2881035804748535,
"learning_rate": 8.719033232628399e-07,
"loss": 1.4697,
"step": 218
},
{
"epoch": 0.6598870056497175,
"grad_norm": 12.132883071899414,
"learning_rate": 8.712990936555891e-07,
"loss": 1.613,
"step": 219
},
{
"epoch": 0.6629001883239172,
"grad_norm": 8.0232572555542,
"learning_rate": 8.706948640483384e-07,
"loss": 1.4118,
"step": 220
},
{
"epoch": 0.6659133709981168,
"grad_norm": 5.796176910400391,
"learning_rate": 8.700906344410876e-07,
"loss": 1.5771,
"step": 221
},
{
"epoch": 0.6689265536723163,
"grad_norm": 6.733500957489014,
"learning_rate": 8.694864048338368e-07,
"loss": 1.4824,
"step": 222
},
{
"epoch": 0.671939736346516,
"grad_norm": 6.836402893066406,
"learning_rate": 8.688821752265861e-07,
"loss": 1.4314,
"step": 223
},
{
"epoch": 0.6749529190207156,
"grad_norm": 8.261625289916992,
"learning_rate": 8.682779456193353e-07,
"loss": 1.431,
"step": 224
},
{
"epoch": 0.6779661016949152,
"grad_norm": 6.64957857131958,
"learning_rate": 8.676737160120845e-07,
"loss": 1.4866,
"step": 225
},
{
"epoch": 0.6809792843691149,
"grad_norm": 8.183669090270996,
"learning_rate": 8.670694864048338e-07,
"loss": 1.5451,
"step": 226
},
{
"epoch": 0.6839924670433145,
"grad_norm": 4.453248977661133,
"learning_rate": 8.664652567975831e-07,
"loss": 1.449,
"step": 227
},
{
"epoch": 0.6870056497175141,
"grad_norm": 8.958436012268066,
"learning_rate": 8.658610271903322e-07,
"loss": 1.4439,
"step": 228
},
{
"epoch": 0.6900188323917138,
"grad_norm": 7.10236930847168,
"learning_rate": 8.652567975830816e-07,
"loss": 1.4938,
"step": 229
},
{
"epoch": 0.6930320150659134,
"grad_norm": 6.993839740753174,
"learning_rate": 8.646525679758307e-07,
"loss": 1.6116,
"step": 230
},
{
"epoch": 0.696045197740113,
"grad_norm": 8.513530731201172,
"learning_rate": 8.6404833836858e-07,
"loss": 1.5006,
"step": 231
},
{
"epoch": 0.6990583804143126,
"grad_norm": 6.418121337890625,
"learning_rate": 8.634441087613292e-07,
"loss": 1.4965,
"step": 232
},
{
"epoch": 0.7020715630885123,
"grad_norm": 5.647480010986328,
"learning_rate": 8.628398791540785e-07,
"loss": 1.5618,
"step": 233
},
{
"epoch": 0.7050847457627119,
"grad_norm": 7.730225563049316,
"learning_rate": 8.622356495468277e-07,
"loss": 1.5957,
"step": 234
},
{
"epoch": 0.7080979284369114,
"grad_norm": 6.108921051025391,
"learning_rate": 8.61631419939577e-07,
"loss": 1.5195,
"step": 235
},
{
"epoch": 0.7111111111111111,
"grad_norm": 9.409442901611328,
"learning_rate": 8.610271903323263e-07,
"loss": 1.6722,
"step": 236
},
{
"epoch": 0.7141242937853107,
"grad_norm": 7.018062114715576,
"learning_rate": 8.604229607250755e-07,
"loss": 1.6026,
"step": 237
},
{
"epoch": 0.7171374764595103,
"grad_norm": 5.681718349456787,
"learning_rate": 8.598187311178248e-07,
"loss": 1.5757,
"step": 238
},
{
"epoch": 0.72015065913371,
"grad_norm": 8.042954444885254,
"learning_rate": 8.592145015105739e-07,
"loss": 1.6127,
"step": 239
},
{
"epoch": 0.7231638418079096,
"grad_norm": 6.210933208465576,
"learning_rate": 8.586102719033233e-07,
"loss": 1.5256,
"step": 240
},
{
"epoch": 0.7261770244821092,
"grad_norm": 7.026112079620361,
"learning_rate": 8.580060422960724e-07,
"loss": 1.612,
"step": 241
},
{
"epoch": 0.7291902071563089,
"grad_norm": 5.423523426055908,
"learning_rate": 8.574018126888217e-07,
"loss": 1.5131,
"step": 242
},
{
"epoch": 0.7322033898305085,
"grad_norm": 8.194084167480469,
"learning_rate": 8.567975830815709e-07,
"loss": 1.3906,
"step": 243
},
{
"epoch": 0.7352165725047081,
"grad_norm": 6.695882320404053,
"learning_rate": 8.561933534743202e-07,
"loss": 1.6206,
"step": 244
},
{
"epoch": 0.7382297551789078,
"grad_norm": 7.198051929473877,
"learning_rate": 8.555891238670695e-07,
"loss": 1.6106,
"step": 245
},
{
"epoch": 0.7412429378531074,
"grad_norm": 4.882433891296387,
"learning_rate": 8.549848942598187e-07,
"loss": 1.5529,
"step": 246
},
{
"epoch": 0.7442561205273069,
"grad_norm": 4.953659534454346,
"learning_rate": 8.543806646525679e-07,
"loss": 1.5228,
"step": 247
},
{
"epoch": 0.7472693032015066,
"grad_norm": 5.135872840881348,
"learning_rate": 8.537764350453172e-07,
"loss": 1.4687,
"step": 248
},
{
"epoch": 0.7502824858757062,
"grad_norm": 4.615948677062988,
"learning_rate": 8.531722054380665e-07,
"loss": 1.548,
"step": 249
},
{
"epoch": 0.7532956685499058,
"grad_norm": 5.355706691741943,
"learning_rate": 8.525679758308156e-07,
"loss": 1.4623,
"step": 250
},
{
"epoch": 0.7563088512241055,
"grad_norm": 7.339105129241943,
"learning_rate": 8.51963746223565e-07,
"loss": 1.5565,
"step": 251
},
{
"epoch": 0.7593220338983051,
"grad_norm": 6.007565498352051,
"learning_rate": 8.513595166163141e-07,
"loss": 1.5154,
"step": 252
},
{
"epoch": 0.7623352165725047,
"grad_norm": 5.059671401977539,
"learning_rate": 8.507552870090634e-07,
"loss": 1.3948,
"step": 253
},
{
"epoch": 0.7653483992467043,
"grad_norm": 7.320003032684326,
"learning_rate": 8.501510574018127e-07,
"loss": 1.4797,
"step": 254
},
{
"epoch": 0.768361581920904,
"grad_norm": 6.245518684387207,
"learning_rate": 8.495468277945619e-07,
"loss": 1.6012,
"step": 255
},
{
"epoch": 0.7713747645951036,
"grad_norm": 5.943390369415283,
"learning_rate": 8.489425981873112e-07,
"loss": 1.5311,
"step": 256
},
{
"epoch": 0.7743879472693032,
"grad_norm": 8.189275741577148,
"learning_rate": 8.483383685800604e-07,
"loss": 1.6242,
"step": 257
},
{
"epoch": 0.7774011299435029,
"grad_norm": 7.5874199867248535,
"learning_rate": 8.477341389728096e-07,
"loss": 1.5804,
"step": 258
},
{
"epoch": 0.7804143126177024,
"grad_norm": 6.015980243682861,
"learning_rate": 8.471299093655589e-07,
"loss": 1.4812,
"step": 259
},
{
"epoch": 0.783427495291902,
"grad_norm": 6.392370700836182,
"learning_rate": 8.465256797583081e-07,
"loss": 1.4684,
"step": 260
},
{
"epoch": 0.7864406779661017,
"grad_norm": 8.292490005493164,
"learning_rate": 8.459214501510573e-07,
"loss": 1.5758,
"step": 261
},
{
"epoch": 0.7894538606403013,
"grad_norm": 7.845565319061279,
"learning_rate": 8.453172205438066e-07,
"loss": 1.5056,
"step": 262
},
{
"epoch": 0.7924670433145009,
"grad_norm": 6.539642810821533,
"learning_rate": 8.447129909365559e-07,
"loss": 1.6056,
"step": 263
},
{
"epoch": 0.7954802259887006,
"grad_norm": 5.963319778442383,
"learning_rate": 8.44108761329305e-07,
"loss": 1.5969,
"step": 264
},
{
"epoch": 0.7984934086629002,
"grad_norm": 6.1800055503845215,
"learning_rate": 8.435045317220544e-07,
"loss": 1.6895,
"step": 265
},
{
"epoch": 0.8015065913370998,
"grad_norm": 7.16093111038208,
"learning_rate": 8.429003021148036e-07,
"loss": 1.4832,
"step": 266
},
{
"epoch": 0.8045197740112995,
"grad_norm": 7.831375598907471,
"learning_rate": 8.422960725075528e-07,
"loss": 1.6119,
"step": 267
},
{
"epoch": 0.8075329566854991,
"grad_norm": 7.345058441162109,
"learning_rate": 8.416918429003021e-07,
"loss": 1.4166,
"step": 268
},
{
"epoch": 0.8105461393596987,
"grad_norm": 5.251908302307129,
"learning_rate": 8.410876132930513e-07,
"loss": 1.5507,
"step": 269
},
{
"epoch": 0.8135593220338984,
"grad_norm": 4.444120407104492,
"learning_rate": 8.404833836858006e-07,
"loss": 1.4939,
"step": 270
},
{
"epoch": 0.816572504708098,
"grad_norm": 6.49534273147583,
"learning_rate": 8.398791540785498e-07,
"loss": 1.5282,
"step": 271
},
{
"epoch": 0.8195856873822975,
"grad_norm": 7.334074020385742,
"learning_rate": 8.392749244712991e-07,
"loss": 1.459,
"step": 272
},
{
"epoch": 0.8225988700564971,
"grad_norm": 5.704728603363037,
"learning_rate": 8.386706948640483e-07,
"loss": 1.4058,
"step": 273
},
{
"epoch": 0.8256120527306968,
"grad_norm": 8.2361421585083,
"learning_rate": 8.380664652567976e-07,
"loss": 1.4003,
"step": 274
},
{
"epoch": 0.8286252354048964,
"grad_norm": 7.770495891571045,
"learning_rate": 8.374622356495467e-07,
"loss": 1.5165,
"step": 275
},
{
"epoch": 0.831638418079096,
"grad_norm": 7.955203533172607,
"learning_rate": 8.368580060422961e-07,
"loss": 1.6013,
"step": 276
},
{
"epoch": 0.8346516007532957,
"grad_norm": 6.4230828285217285,
"learning_rate": 8.362537764350452e-07,
"loss": 1.4329,
"step": 277
},
{
"epoch": 0.8376647834274953,
"grad_norm": 5.394540786743164,
"learning_rate": 8.356495468277945e-07,
"loss": 1.441,
"step": 278
},
{
"epoch": 0.8406779661016949,
"grad_norm": 7.356249809265137,
"learning_rate": 8.350453172205437e-07,
"loss": 1.4842,
"step": 279
},
{
"epoch": 0.8436911487758946,
"grad_norm": 7.684313774108887,
"learning_rate": 8.34441087613293e-07,
"loss": 1.492,
"step": 280
},
{
"epoch": 0.8467043314500942,
"grad_norm": 6.615567207336426,
"learning_rate": 8.338368580060424e-07,
"loss": 1.3746,
"step": 281
},
{
"epoch": 0.8497175141242937,
"grad_norm": 4.979093551635742,
"learning_rate": 8.332326283987915e-07,
"loss": 1.4832,
"step": 282
},
{
"epoch": 0.8527306967984934,
"grad_norm": 6.392155170440674,
"learning_rate": 8.326283987915408e-07,
"loss": 1.4993,
"step": 283
},
{
"epoch": 0.855743879472693,
"grad_norm": 5.286422252655029,
"learning_rate": 8.3202416918429e-07,
"loss": 1.501,
"step": 284
},
{
"epoch": 0.8587570621468926,
"grad_norm": 5.239201545715332,
"learning_rate": 8.314199395770393e-07,
"loss": 1.5111,
"step": 285
},
{
"epoch": 0.8617702448210923,
"grad_norm": 5.18308687210083,
"learning_rate": 8.308157099697884e-07,
"loss": 1.5012,
"step": 286
},
{
"epoch": 0.8647834274952919,
"grad_norm": 6.963190078735352,
"learning_rate": 8.302114803625378e-07,
"loss": 1.6271,
"step": 287
},
{
"epoch": 0.8677966101694915,
"grad_norm": 6.913437366485596,
"learning_rate": 8.296072507552869e-07,
"loss": 1.5469,
"step": 288
},
{
"epoch": 0.8708097928436912,
"grad_norm": 7.444077491760254,
"learning_rate": 8.290030211480362e-07,
"loss": 1.5648,
"step": 289
},
{
"epoch": 0.8738229755178908,
"grad_norm": 8.236980438232422,
"learning_rate": 8.283987915407855e-07,
"loss": 1.4712,
"step": 290
},
{
"epoch": 0.8768361581920904,
"grad_norm": 8.994156837463379,
"learning_rate": 8.277945619335347e-07,
"loss": 1.543,
"step": 291
},
{
"epoch": 0.87984934086629,
"grad_norm": 6.862576484680176,
"learning_rate": 8.271903323262839e-07,
"loss": 1.5007,
"step": 292
},
{
"epoch": 0.8828625235404897,
"grad_norm": 6.047828674316406,
"learning_rate": 8.265861027190332e-07,
"loss": 1.4253,
"step": 293
},
{
"epoch": 0.8858757062146893,
"grad_norm": 5.511521816253662,
"learning_rate": 8.259818731117824e-07,
"loss": 1.4789,
"step": 294
},
{
"epoch": 0.8888888888888888,
"grad_norm": 5.671835422515869,
"learning_rate": 8.253776435045317e-07,
"loss": 1.5623,
"step": 295
},
{
"epoch": 0.8919020715630885,
"grad_norm": 5.8705010414123535,
"learning_rate": 8.24773413897281e-07,
"loss": 1.3882,
"step": 296
},
{
"epoch": 0.8949152542372881,
"grad_norm": 5.783331394195557,
"learning_rate": 8.241691842900301e-07,
"loss": 1.4549,
"step": 297
},
{
"epoch": 0.8979284369114877,
"grad_norm": 4.781585693359375,
"learning_rate": 8.235649546827795e-07,
"loss": 1.4478,
"step": 298
},
{
"epoch": 0.9009416195856874,
"grad_norm": 5.374331951141357,
"learning_rate": 8.229607250755287e-07,
"loss": 1.502,
"step": 299
},
{
"epoch": 0.903954802259887,
"grad_norm": 5.809821128845215,
"learning_rate": 8.223564954682779e-07,
"loss": 1.4928,
"step": 300
},
{
"epoch": 0.9069679849340866,
"grad_norm": 6.391750335693359,
"learning_rate": 8.217522658610272e-07,
"loss": 1.5142,
"step": 301
},
{
"epoch": 0.9099811676082863,
"grad_norm": 5.688490390777588,
"learning_rate": 8.211480362537764e-07,
"loss": 1.3997,
"step": 302
},
{
"epoch": 0.9129943502824859,
"grad_norm": 8.432653427124023,
"learning_rate": 8.205438066465256e-07,
"loss": 1.6382,
"step": 303
},
{
"epoch": 0.9160075329566855,
"grad_norm": 7.900843143463135,
"learning_rate": 8.199395770392749e-07,
"loss": 1.6876,
"step": 304
},
{
"epoch": 0.9190207156308852,
"grad_norm": 7.336916923522949,
"learning_rate": 8.193353474320241e-07,
"loss": 1.422,
"step": 305
},
{
"epoch": 0.9220338983050848,
"grad_norm": 6.83461332321167,
"learning_rate": 8.187311178247733e-07,
"loss": 1.4121,
"step": 306
},
{
"epoch": 0.9250470809792843,
"grad_norm": 5.917620658874512,
"learning_rate": 8.181268882175226e-07,
"loss": 1.429,
"step": 307
},
{
"epoch": 0.928060263653484,
"grad_norm": 6.6068243980407715,
"learning_rate": 8.175226586102719e-07,
"loss": 1.4405,
"step": 308
},
{
"epoch": 0.9310734463276836,
"grad_norm": 5.454964637756348,
"learning_rate": 8.169184290030211e-07,
"loss": 1.6217,
"step": 309
},
{
"epoch": 0.9340866290018832,
"grad_norm": 5.495649337768555,
"learning_rate": 8.163141993957704e-07,
"loss": 1.4922,
"step": 310
},
{
"epoch": 0.9370998116760829,
"grad_norm": 4.083762168884277,
"learning_rate": 8.157099697885196e-07,
"loss": 1.3622,
"step": 311
},
{
"epoch": 0.9401129943502825,
"grad_norm": 4.942357540130615,
"learning_rate": 8.151057401812689e-07,
"loss": 1.4721,
"step": 312
},
{
"epoch": 0.9431261770244821,
"grad_norm": 5.29658317565918,
"learning_rate": 8.145015105740181e-07,
"loss": 1.5607,
"step": 313
},
{
"epoch": 0.9461393596986817,
"grad_norm": 5.887204647064209,
"learning_rate": 8.138972809667673e-07,
"loss": 1.4661,
"step": 314
},
{
"epoch": 0.9491525423728814,
"grad_norm": 7.6733574867248535,
"learning_rate": 8.132930513595166e-07,
"loss": 1.4322,
"step": 315
},
{
"epoch": 0.952165725047081,
"grad_norm": 5.148620128631592,
"learning_rate": 8.126888217522658e-07,
"loss": 1.3285,
"step": 316
},
{
"epoch": 0.9551789077212806,
"grad_norm": 6.739416599273682,
"learning_rate": 8.120845921450151e-07,
"loss": 1.5149,
"step": 317
},
{
"epoch": 0.9581920903954803,
"grad_norm": 6.18145227432251,
"learning_rate": 8.114803625377643e-07,
"loss": 1.5265,
"step": 318
},
{
"epoch": 0.9612052730696798,
"grad_norm": 6.958502292633057,
"learning_rate": 8.108761329305136e-07,
"loss": 1.516,
"step": 319
},
{
"epoch": 0.9642184557438794,
"grad_norm": 5.1808857917785645,
"learning_rate": 8.102719033232627e-07,
"loss": 1.4866,
"step": 320
},
{
"epoch": 0.9672316384180791,
"grad_norm": 6.208801746368408,
"learning_rate": 8.096676737160121e-07,
"loss": 1.6142,
"step": 321
},
{
"epoch": 0.9702448210922787,
"grad_norm": 5.780658721923828,
"learning_rate": 8.090634441087612e-07,
"loss": 1.4478,
"step": 322
},
{
"epoch": 0.9732580037664783,
"grad_norm": 6.446497440338135,
"learning_rate": 8.084592145015106e-07,
"loss": 1.4809,
"step": 323
},
{
"epoch": 0.976271186440678,
"grad_norm": 6.850809574127197,
"learning_rate": 8.078549848942597e-07,
"loss": 1.4693,
"step": 324
},
{
"epoch": 0.9792843691148776,
"grad_norm": 6.133167743682861,
"learning_rate": 8.07250755287009e-07,
"loss": 1.5469,
"step": 325
},
{
"epoch": 0.9822975517890772,
"grad_norm": 6.173937797546387,
"learning_rate": 8.066465256797583e-07,
"loss": 1.489,
"step": 326
},
{
"epoch": 0.9853107344632769,
"grad_norm": 6.194633483886719,
"learning_rate": 8.060422960725075e-07,
"loss": 1.45,
"step": 327
},
{
"epoch": 0.9883239171374765,
"grad_norm": 5.837034225463867,
"learning_rate": 8.054380664652568e-07,
"loss": 1.5201,
"step": 328
},
{
"epoch": 0.9913370998116761,
"grad_norm": 4.946648120880127,
"learning_rate": 8.04833836858006e-07,
"loss": 1.4982,
"step": 329
},
{
"epoch": 0.9943502824858758,
"grad_norm": 5.067462921142578,
"learning_rate": 8.042296072507553e-07,
"loss": 1.4429,
"step": 330
},
{
"epoch": 0.9973634651600753,
"grad_norm": 6.604504108428955,
"learning_rate": 8.036253776435044e-07,
"loss": 1.5087,
"step": 331
},
{
"epoch": 1.0,
"grad_norm": 6.244668483734131,
"learning_rate": 8.030211480362538e-07,
"loss": 1.3655,
"step": 332
},
{
"epoch": 1.0030131826741997,
"grad_norm": 4.467490196228027,
"learning_rate": 8.024169184290029e-07,
"loss": 1.4316,
"step": 333
},
{
"epoch": 1.0060263653483992,
"grad_norm": 6.296884536743164,
"learning_rate": 8.018126888217523e-07,
"loss": 1.4275,
"step": 334
},
{
"epoch": 1.0090395480225989,
"grad_norm": 7.04038143157959,
"learning_rate": 8.012084592145014e-07,
"loss": 1.4458,
"step": 335
},
{
"epoch": 1.0120527306967986,
"grad_norm": 7.556911468505859,
"learning_rate": 8.006042296072507e-07,
"loss": 1.5214,
"step": 336
},
{
"epoch": 1.015065913370998,
"grad_norm": 8.293994903564453,
"learning_rate": 8e-07,
"loss": 1.515,
"step": 337
},
{
"epoch": 1.0180790960451978,
"grad_norm": 5.978755950927734,
"learning_rate": 7.993957703927492e-07,
"loss": 1.3552,
"step": 338
},
{
"epoch": 1.0210922787193975,
"grad_norm": 5.53171968460083,
"learning_rate": 7.987915407854984e-07,
"loss": 1.3732,
"step": 339
},
{
"epoch": 1.024105461393597,
"grad_norm": 5.102609634399414,
"learning_rate": 7.981873111782477e-07,
"loss": 1.4378,
"step": 340
},
{
"epoch": 1.0271186440677966,
"grad_norm": 8.573832511901855,
"learning_rate": 7.97583081570997e-07,
"loss": 1.5285,
"step": 341
},
{
"epoch": 1.0301318267419963,
"grad_norm": 6.137781143188477,
"learning_rate": 7.969788519637461e-07,
"loss": 1.4345,
"step": 342
},
{
"epoch": 1.0331450094161958,
"grad_norm": 5.788732528686523,
"learning_rate": 7.963746223564955e-07,
"loss": 1.4061,
"step": 343
},
{
"epoch": 1.0361581920903955,
"grad_norm": 6.551296234130859,
"learning_rate": 7.957703927492446e-07,
"loss": 1.5064,
"step": 344
},
{
"epoch": 1.0391713747645952,
"grad_norm": 6.626697063446045,
"learning_rate": 7.95166163141994e-07,
"loss": 1.4849,
"step": 345
},
{
"epoch": 1.0421845574387947,
"grad_norm": 7.8492631912231445,
"learning_rate": 7.945619335347432e-07,
"loss": 1.5365,
"step": 346
},
{
"epoch": 1.0451977401129944,
"grad_norm": 10.96153450012207,
"learning_rate": 7.939577039274924e-07,
"loss": 1.4231,
"step": 347
},
{
"epoch": 1.048210922787194,
"grad_norm": 8.36257266998291,
"learning_rate": 7.933534743202417e-07,
"loss": 1.4906,
"step": 348
},
{
"epoch": 1.0512241054613936,
"grad_norm": 6.522828578948975,
"learning_rate": 7.927492447129909e-07,
"loss": 1.4316,
"step": 349
},
{
"epoch": 1.0542372881355933,
"grad_norm": 5.135219097137451,
"learning_rate": 7.921450151057401e-07,
"loss": 1.4789,
"step": 350
},
{
"epoch": 1.0572504708097927,
"grad_norm": 7.572334289550781,
"learning_rate": 7.915407854984894e-07,
"loss": 1.5181,
"step": 351
},
{
"epoch": 1.0602636534839924,
"grad_norm": 5.472777843475342,
"learning_rate": 7.909365558912386e-07,
"loss": 1.5157,
"step": 352
},
{
"epoch": 1.0632768361581921,
"grad_norm": 6.605233192443848,
"learning_rate": 7.903323262839878e-07,
"loss": 1.6803,
"step": 353
},
{
"epoch": 1.0662900188323916,
"grad_norm": 8.083072662353516,
"learning_rate": 7.897280966767371e-07,
"loss": 1.4954,
"step": 354
},
{
"epoch": 1.0693032015065913,
"grad_norm": 6.5436859130859375,
"learning_rate": 7.891238670694864e-07,
"loss": 1.3769,
"step": 355
},
{
"epoch": 1.072316384180791,
"grad_norm": 6.924417018890381,
"learning_rate": 7.885196374622356e-07,
"loss": 1.4738,
"step": 356
},
{
"epoch": 1.0753295668549905,
"grad_norm": 6.195346355438232,
"learning_rate": 7.879154078549849e-07,
"loss": 1.3856,
"step": 357
},
{
"epoch": 1.0783427495291902,
"grad_norm": 6.597601413726807,
"learning_rate": 7.873111782477341e-07,
"loss": 1.5945,
"step": 358
},
{
"epoch": 1.0813559322033899,
"grad_norm": 7.515981197357178,
"learning_rate": 7.867069486404834e-07,
"loss": 1.38,
"step": 359
},
{
"epoch": 1.0843691148775894,
"grad_norm": 4.861922740936279,
"learning_rate": 7.861027190332326e-07,
"loss": 1.5156,
"step": 360
},
{
"epoch": 1.087382297551789,
"grad_norm": 5.297628402709961,
"learning_rate": 7.854984894259818e-07,
"loss": 1.4665,
"step": 361
},
{
"epoch": 1.0903954802259888,
"grad_norm": 5.723709583282471,
"learning_rate": 7.848942598187311e-07,
"loss": 1.4795,
"step": 362
},
{
"epoch": 1.0934086629001882,
"grad_norm": 7.437093734741211,
"learning_rate": 7.842900302114803e-07,
"loss": 1.3805,
"step": 363
},
{
"epoch": 1.096421845574388,
"grad_norm": 5.3132476806640625,
"learning_rate": 7.836858006042296e-07,
"loss": 1.4352,
"step": 364
},
{
"epoch": 1.0994350282485876,
"grad_norm": 5.235926151275635,
"learning_rate": 7.830815709969788e-07,
"loss": 1.4481,
"step": 365
},
{
"epoch": 1.102448210922787,
"grad_norm": 5.392710208892822,
"learning_rate": 7.824773413897281e-07,
"loss": 1.4496,
"step": 366
},
{
"epoch": 1.1054613935969868,
"grad_norm": 7.049579620361328,
"learning_rate": 7.818731117824772e-07,
"loss": 1.5239,
"step": 367
},
{
"epoch": 1.1084745762711865,
"grad_norm": 4.965340614318848,
"learning_rate": 7.812688821752266e-07,
"loss": 1.4552,
"step": 368
},
{
"epoch": 1.111487758945386,
"grad_norm": 5.697866916656494,
"learning_rate": 7.806646525679757e-07,
"loss": 1.4332,
"step": 369
},
{
"epoch": 1.1145009416195857,
"grad_norm": 6.33465576171875,
"learning_rate": 7.80060422960725e-07,
"loss": 1.5326,
"step": 370
},
{
"epoch": 1.1175141242937854,
"grad_norm": 6.2289276123046875,
"learning_rate": 7.794561933534742e-07,
"loss": 1.3593,
"step": 371
},
{
"epoch": 1.1205273069679849,
"grad_norm": 5.588104724884033,
"learning_rate": 7.788519637462235e-07,
"loss": 1.5042,
"step": 372
},
{
"epoch": 1.1235404896421846,
"grad_norm": 5.868190765380859,
"learning_rate": 7.782477341389729e-07,
"loss": 1.4732,
"step": 373
},
{
"epoch": 1.1265536723163843,
"grad_norm": 5.766890048980713,
"learning_rate": 7.77643504531722e-07,
"loss": 1.4918,
"step": 374
},
{
"epoch": 1.1295668549905837,
"grad_norm": 5.5379133224487305,
"learning_rate": 7.770392749244713e-07,
"loss": 1.6178,
"step": 375
},
{
"epoch": 1.1325800376647834,
"grad_norm": 7.331387519836426,
"learning_rate": 7.764350453172205e-07,
"loss": 1.3317,
"step": 376
},
{
"epoch": 1.1355932203389831,
"grad_norm": 6.548041343688965,
"learning_rate": 7.758308157099698e-07,
"loss": 1.5441,
"step": 377
},
{
"epoch": 1.1386064030131826,
"grad_norm": 5.313483238220215,
"learning_rate": 7.752265861027189e-07,
"loss": 1.5561,
"step": 378
},
{
"epoch": 1.1416195856873823,
"grad_norm": 5.601877212524414,
"learning_rate": 7.746223564954683e-07,
"loss": 1.5529,
"step": 379
},
{
"epoch": 1.144632768361582,
"grad_norm": 5.99515962600708,
"learning_rate": 7.740181268882174e-07,
"loss": 1.5021,
"step": 380
},
{
"epoch": 1.1476459510357815,
"grad_norm": 6.389265060424805,
"learning_rate": 7.734138972809667e-07,
"loss": 1.4541,
"step": 381
},
{
"epoch": 1.1506591337099812,
"grad_norm": 5.451423645019531,
"learning_rate": 7.72809667673716e-07,
"loss": 1.5272,
"step": 382
},
{
"epoch": 1.1536723163841809,
"grad_norm": 6.803645133972168,
"learning_rate": 7.722054380664652e-07,
"loss": 1.4324,
"step": 383
},
{
"epoch": 1.1566854990583804,
"grad_norm": 6.200608253479004,
"learning_rate": 7.716012084592145e-07,
"loss": 1.4426,
"step": 384
},
{
"epoch": 1.15969868173258,
"grad_norm": 5.176392555236816,
"learning_rate": 7.709969788519637e-07,
"loss": 1.3608,
"step": 385
},
{
"epoch": 1.1627118644067798,
"grad_norm": 8.1022367477417,
"learning_rate": 7.70392749244713e-07,
"loss": 1.4524,
"step": 386
},
{
"epoch": 1.1657250470809792,
"grad_norm": 8.393830299377441,
"learning_rate": 7.697885196374622e-07,
"loss": 1.3483,
"step": 387
},
{
"epoch": 1.168738229755179,
"grad_norm": 5.789231300354004,
"learning_rate": 7.691842900302115e-07,
"loss": 1.5301,
"step": 388
},
{
"epoch": 1.1717514124293786,
"grad_norm": 5.6079559326171875,
"learning_rate": 7.685800604229606e-07,
"loss": 1.4417,
"step": 389
},
{
"epoch": 1.1747645951035781,
"grad_norm": 7.824696063995361,
"learning_rate": 7.6797583081571e-07,
"loss": 1.497,
"step": 390
},
{
"epoch": 1.1777777777777778,
"grad_norm": 6.026281833648682,
"learning_rate": 7.673716012084592e-07,
"loss": 1.5102,
"step": 391
},
{
"epoch": 1.1807909604519775,
"grad_norm": 7.385575294494629,
"learning_rate": 7.667673716012084e-07,
"loss": 1.689,
"step": 392
},
{
"epoch": 1.183804143126177,
"grad_norm": 6.165759086608887,
"learning_rate": 7.661631419939577e-07,
"loss": 1.4588,
"step": 393
},
{
"epoch": 1.1868173258003767,
"grad_norm": 5.655641078948975,
"learning_rate": 7.655589123867069e-07,
"loss": 1.4996,
"step": 394
},
{
"epoch": 1.1898305084745764,
"grad_norm": 5.622771739959717,
"learning_rate": 7.649546827794562e-07,
"loss": 1.533,
"step": 395
},
{
"epoch": 1.1928436911487759,
"grad_norm": 5.785812854766846,
"learning_rate": 7.643504531722054e-07,
"loss": 1.4503,
"step": 396
},
{
"epoch": 1.1958568738229756,
"grad_norm": 4.814526557922363,
"learning_rate": 7.637462235649546e-07,
"loss": 1.4046,
"step": 397
},
{
"epoch": 1.1988700564971753,
"grad_norm": 6.786997318267822,
"learning_rate": 7.631419939577039e-07,
"loss": 1.4258,
"step": 398
},
{
"epoch": 1.2018832391713747,
"grad_norm": 8.599371910095215,
"learning_rate": 7.625377643504531e-07,
"loss": 1.4855,
"step": 399
},
{
"epoch": 1.2048964218455744,
"grad_norm": 6.268576145172119,
"learning_rate": 7.619335347432024e-07,
"loss": 1.4865,
"step": 400
},
{
"epoch": 1.207909604519774,
"grad_norm": 5.0782084465026855,
"learning_rate": 7.613293051359517e-07,
"loss": 1.5071,
"step": 401
},
{
"epoch": 1.2109227871939736,
"grad_norm": 5.930427074432373,
"learning_rate": 7.607250755287009e-07,
"loss": 1.5052,
"step": 402
},
{
"epoch": 1.2139359698681733,
"grad_norm": 6.130629062652588,
"learning_rate": 7.601208459214501e-07,
"loss": 1.3685,
"step": 403
},
{
"epoch": 1.2169491525423728,
"grad_norm": 5.17104434967041,
"learning_rate": 7.595166163141994e-07,
"loss": 1.5282,
"step": 404
},
{
"epoch": 1.2199623352165725,
"grad_norm": 6.357630252838135,
"learning_rate": 7.589123867069486e-07,
"loss": 1.5413,
"step": 405
},
{
"epoch": 1.2229755178907722,
"grad_norm": 5.158059120178223,
"learning_rate": 7.583081570996978e-07,
"loss": 1.4363,
"step": 406
},
{
"epoch": 1.2259887005649717,
"grad_norm": 7.064553260803223,
"learning_rate": 7.577039274924471e-07,
"loss": 1.516,
"step": 407
},
{
"epoch": 1.2290018832391714,
"grad_norm": 5.152454853057861,
"learning_rate": 7.570996978851963e-07,
"loss": 1.4774,
"step": 408
},
{
"epoch": 1.232015065913371,
"grad_norm": 4.66790771484375,
"learning_rate": 7.564954682779457e-07,
"loss": 1.5289,
"step": 409
},
{
"epoch": 1.2350282485875705,
"grad_norm": 5.234610557556152,
"learning_rate": 7.558912386706948e-07,
"loss": 1.4726,
"step": 410
},
{
"epoch": 1.2380414312617702,
"grad_norm": 6.0115156173706055,
"learning_rate": 7.552870090634441e-07,
"loss": 1.5175,
"step": 411
},
{
"epoch": 1.24105461393597,
"grad_norm": 6.490240097045898,
"learning_rate": 7.546827794561933e-07,
"loss": 1.4239,
"step": 412
},
{
"epoch": 1.2440677966101694,
"grad_norm": 5.694466590881348,
"learning_rate": 7.540785498489426e-07,
"loss": 1.5157,
"step": 413
},
{
"epoch": 1.2470809792843691,
"grad_norm": 5.529226779937744,
"learning_rate": 7.534743202416917e-07,
"loss": 1.4068,
"step": 414
},
{
"epoch": 1.2500941619585688,
"grad_norm": 5.583081245422363,
"learning_rate": 7.528700906344411e-07,
"loss": 1.401,
"step": 415
},
{
"epoch": 1.2531073446327683,
"grad_norm": 4.854590892791748,
"learning_rate": 7.522658610271902e-07,
"loss": 1.3146,
"step": 416
},
{
"epoch": 1.256120527306968,
"grad_norm": 4.061290264129639,
"learning_rate": 7.516616314199395e-07,
"loss": 1.4698,
"step": 417
},
{
"epoch": 1.2591337099811675,
"grad_norm": 4.967966079711914,
"learning_rate": 7.510574018126889e-07,
"loss": 1.395,
"step": 418
},
{
"epoch": 1.2621468926553672,
"grad_norm": 4.872391223907471,
"learning_rate": 7.50453172205438e-07,
"loss": 1.3768,
"step": 419
},
{
"epoch": 1.2651600753295669,
"grad_norm": 4.683777332305908,
"learning_rate": 7.498489425981874e-07,
"loss": 1.4286,
"step": 420
},
{
"epoch": 1.2681732580037663,
"grad_norm": 7.127167701721191,
"learning_rate": 7.492447129909365e-07,
"loss": 1.475,
"step": 421
},
{
"epoch": 1.271186440677966,
"grad_norm": 5.692124366760254,
"learning_rate": 7.486404833836858e-07,
"loss": 1.4027,
"step": 422
},
{
"epoch": 1.2741996233521657,
"grad_norm": 5.0434699058532715,
"learning_rate": 7.48036253776435e-07,
"loss": 1.3496,
"step": 423
},
{
"epoch": 1.2772128060263652,
"grad_norm": 5.898393630981445,
"learning_rate": 7.474320241691843e-07,
"loss": 1.481,
"step": 424
},
{
"epoch": 1.280225988700565,
"grad_norm": 7.333285331726074,
"learning_rate": 7.468277945619334e-07,
"loss": 1.5249,
"step": 425
},
{
"epoch": 1.2832391713747646,
"grad_norm": 4.917825698852539,
"learning_rate": 7.462235649546828e-07,
"loss": 1.4124,
"step": 426
},
{
"epoch": 1.286252354048964,
"grad_norm": 5.303079128265381,
"learning_rate": 7.45619335347432e-07,
"loss": 1.4667,
"step": 427
},
{
"epoch": 1.2892655367231638,
"grad_norm": 6.22338342666626,
"learning_rate": 7.450151057401812e-07,
"loss": 1.3717,
"step": 428
},
{
"epoch": 1.2922787193973635,
"grad_norm": 5.587646484375,
"learning_rate": 7.444108761329305e-07,
"loss": 1.5644,
"step": 429
},
{
"epoch": 1.295291902071563,
"grad_norm": 5.007399559020996,
"learning_rate": 7.438066465256797e-07,
"loss": 1.4556,
"step": 430
},
{
"epoch": 1.2983050847457627,
"grad_norm": 5.113317966461182,
"learning_rate": 7.43202416918429e-07,
"loss": 1.5206,
"step": 431
},
{
"epoch": 1.3013182674199624,
"grad_norm": 5.745063781738281,
"learning_rate": 7.425981873111782e-07,
"loss": 1.6043,
"step": 432
},
{
"epoch": 1.3043314500941618,
"grad_norm": 5.018908977508545,
"learning_rate": 7.419939577039275e-07,
"loss": 1.4842,
"step": 433
},
{
"epoch": 1.3073446327683615,
"grad_norm": 6.297757148742676,
"learning_rate": 7.413897280966767e-07,
"loss": 1.4591,
"step": 434
},
{
"epoch": 1.3103578154425612,
"grad_norm": 6.9438982009887695,
"learning_rate": 7.40785498489426e-07,
"loss": 1.3976,
"step": 435
},
{
"epoch": 1.3133709981167607,
"grad_norm": 5.57979154586792,
"learning_rate": 7.401812688821752e-07,
"loss": 1.5316,
"step": 436
},
{
"epoch": 1.3163841807909604,
"grad_norm": 5.123766899108887,
"learning_rate": 7.395770392749245e-07,
"loss": 1.6012,
"step": 437
},
{
"epoch": 1.3193973634651601,
"grad_norm": 5.855531215667725,
"learning_rate": 7.389728096676737e-07,
"loss": 1.4202,
"step": 438
},
{
"epoch": 1.3224105461393596,
"grad_norm": 6.032529830932617,
"learning_rate": 7.383685800604229e-07,
"loss": 1.412,
"step": 439
},
{
"epoch": 1.3254237288135593,
"grad_norm": 5.293960094451904,
"learning_rate": 7.377643504531722e-07,
"loss": 1.556,
"step": 440
},
{
"epoch": 1.328436911487759,
"grad_norm": 6.7965803146362305,
"learning_rate": 7.371601208459214e-07,
"loss": 1.4496,
"step": 441
},
{
"epoch": 1.3314500941619585,
"grad_norm": 7.592730522155762,
"learning_rate": 7.365558912386706e-07,
"loss": 1.5965,
"step": 442
},
{
"epoch": 1.3344632768361582,
"grad_norm": 5.725823879241943,
"learning_rate": 7.359516616314199e-07,
"loss": 1.456,
"step": 443
},
{
"epoch": 1.3374764595103579,
"grad_norm": 5.557275295257568,
"learning_rate": 7.353474320241691e-07,
"loss": 1.4534,
"step": 444
},
{
"epoch": 1.3404896421845574,
"grad_norm": 5.644491672515869,
"learning_rate": 7.347432024169185e-07,
"loss": 1.3903,
"step": 445
},
{
"epoch": 1.343502824858757,
"grad_norm": 4.930250644683838,
"learning_rate": 7.341389728096676e-07,
"loss": 1.5251,
"step": 446
},
{
"epoch": 1.3465160075329567,
"grad_norm": 7.409116268157959,
"learning_rate": 7.335347432024169e-07,
"loss": 1.4062,
"step": 447
},
{
"epoch": 1.3495291902071562,
"grad_norm": 5.850759983062744,
"learning_rate": 7.329305135951662e-07,
"loss": 1.3804,
"step": 448
},
{
"epoch": 1.352542372881356,
"grad_norm": 5.160429000854492,
"learning_rate": 7.323262839879154e-07,
"loss": 1.5141,
"step": 449
},
{
"epoch": 1.3555555555555556,
"grad_norm": 6.901113033294678,
"learning_rate": 7.317220543806646e-07,
"loss": 1.3898,
"step": 450
},
{
"epoch": 1.358568738229755,
"grad_norm": 6.2050557136535645,
"learning_rate": 7.311178247734139e-07,
"loss": 1.4045,
"step": 451
},
{
"epoch": 1.3615819209039548,
"grad_norm": 6.413991928100586,
"learning_rate": 7.305135951661631e-07,
"loss": 1.3447,
"step": 452
},
{
"epoch": 1.3645951035781545,
"grad_norm": 5.251416206359863,
"learning_rate": 7.299093655589123e-07,
"loss": 1.4523,
"step": 453
},
{
"epoch": 1.367608286252354,
"grad_norm": 5.234088897705078,
"learning_rate": 7.293051359516616e-07,
"loss": 1.4367,
"step": 454
},
{
"epoch": 1.3706214689265537,
"grad_norm": 5.005328178405762,
"learning_rate": 7.287009063444108e-07,
"loss": 1.3826,
"step": 455
},
{
"epoch": 1.3736346516007534,
"grad_norm": 5.171993732452393,
"learning_rate": 7.280966767371601e-07,
"loss": 1.4407,
"step": 456
},
{
"epoch": 1.3766478342749529,
"grad_norm": 5.298288345336914,
"learning_rate": 7.274924471299093e-07,
"loss": 1.4663,
"step": 457
},
{
"epoch": 1.3796610169491526,
"grad_norm": 5.139895439147949,
"learning_rate": 7.268882175226586e-07,
"loss": 1.3168,
"step": 458
},
{
"epoch": 1.3826741996233523,
"grad_norm": 4.685584545135498,
"learning_rate": 7.262839879154077e-07,
"loss": 1.3457,
"step": 459
},
{
"epoch": 1.3856873822975517,
"grad_norm": 4.778255462646484,
"learning_rate": 7.256797583081571e-07,
"loss": 1.3638,
"step": 460
},
{
"epoch": 1.3887005649717514,
"grad_norm": 7.220554351806641,
"learning_rate": 7.250755287009062e-07,
"loss": 1.344,
"step": 461
},
{
"epoch": 1.3917137476459511,
"grad_norm": 5.174147605895996,
"learning_rate": 7.244712990936556e-07,
"loss": 1.3162,
"step": 462
},
{
"epoch": 1.3947269303201506,
"grad_norm": 5.388669967651367,
"learning_rate": 7.238670694864048e-07,
"loss": 1.4031,
"step": 463
},
{
"epoch": 1.3977401129943503,
"grad_norm": 5.195096015930176,
"learning_rate": 7.23262839879154e-07,
"loss": 1.3972,
"step": 464
},
{
"epoch": 1.40075329566855,
"grad_norm": 8.188602447509766,
"learning_rate": 7.226586102719034e-07,
"loss": 1.4762,
"step": 465
},
{
"epoch": 1.4037664783427495,
"grad_norm": 7.0600104331970215,
"learning_rate": 7.220543806646525e-07,
"loss": 1.461,
"step": 466
},
{
"epoch": 1.4067796610169492,
"grad_norm": 5.993371963500977,
"learning_rate": 7.214501510574018e-07,
"loss": 1.42,
"step": 467
},
{
"epoch": 1.4097928436911489,
"grad_norm": 6.568065643310547,
"learning_rate": 7.20845921450151e-07,
"loss": 1.505,
"step": 468
},
{
"epoch": 1.4128060263653484,
"grad_norm": 5.151662349700928,
"learning_rate": 7.202416918429003e-07,
"loss": 1.5105,
"step": 469
},
{
"epoch": 1.415819209039548,
"grad_norm": 5.1942009925842285,
"learning_rate": 7.196374622356494e-07,
"loss": 1.5293,
"step": 470
},
{
"epoch": 1.4188323917137478,
"grad_norm": 5.3867387771606445,
"learning_rate": 7.190332326283988e-07,
"loss": 1.3749,
"step": 471
},
{
"epoch": 1.4218455743879472,
"grad_norm": 4.629281520843506,
"learning_rate": 7.184290030211479e-07,
"loss": 1.426,
"step": 472
},
{
"epoch": 1.424858757062147,
"grad_norm": 7.186618804931641,
"learning_rate": 7.178247734138973e-07,
"loss": 1.3155,
"step": 473
},
{
"epoch": 1.4278719397363466,
"grad_norm": 4.487481594085693,
"learning_rate": 7.172205438066465e-07,
"loss": 1.5398,
"step": 474
},
{
"epoch": 1.430885122410546,
"grad_norm": 6.537076473236084,
"learning_rate": 7.166163141993957e-07,
"loss": 1.3386,
"step": 475
},
{
"epoch": 1.4338983050847458,
"grad_norm": 5.330569267272949,
"learning_rate": 7.16012084592145e-07,
"loss": 1.4076,
"step": 476
},
{
"epoch": 1.4369114877589455,
"grad_norm": 6.147136211395264,
"learning_rate": 7.154078549848942e-07,
"loss": 1.4184,
"step": 477
},
{
"epoch": 1.439924670433145,
"grad_norm": 5.484400749206543,
"learning_rate": 7.148036253776435e-07,
"loss": 1.3983,
"step": 478
},
{
"epoch": 1.4429378531073447,
"grad_norm": 5.467801094055176,
"learning_rate": 7.141993957703927e-07,
"loss": 1.5122,
"step": 479
},
{
"epoch": 1.4459510357815444,
"grad_norm": 5.399661064147949,
"learning_rate": 7.13595166163142e-07,
"loss": 1.3758,
"step": 480
},
{
"epoch": 1.4489642184557439,
"grad_norm": 5.076383590698242,
"learning_rate": 7.129909365558911e-07,
"loss": 1.4967,
"step": 481
},
{
"epoch": 1.4519774011299436,
"grad_norm": 5.443070411682129,
"learning_rate": 7.123867069486405e-07,
"loss": 1.3773,
"step": 482
},
{
"epoch": 1.4549905838041433,
"grad_norm": 5.821800708770752,
"learning_rate": 7.117824773413897e-07,
"loss": 1.4446,
"step": 483
},
{
"epoch": 1.4580037664783427,
"grad_norm": 6.820368766784668,
"learning_rate": 7.11178247734139e-07,
"loss": 1.4646,
"step": 484
},
{
"epoch": 1.4610169491525424,
"grad_norm": 5.108595848083496,
"learning_rate": 7.105740181268882e-07,
"loss": 1.3969,
"step": 485
},
{
"epoch": 1.4640301318267421,
"grad_norm": 5.136443614959717,
"learning_rate": 7.099697885196374e-07,
"loss": 1.3959,
"step": 486
},
{
"epoch": 1.4670433145009416,
"grad_norm": 5.6289286613464355,
"learning_rate": 7.093655589123867e-07,
"loss": 1.3887,
"step": 487
},
{
"epoch": 1.4700564971751413,
"grad_norm": 5.159824371337891,
"learning_rate": 7.087613293051359e-07,
"loss": 1.4145,
"step": 488
},
{
"epoch": 1.4730696798493408,
"grad_norm": 5.452634334564209,
"learning_rate": 7.081570996978851e-07,
"loss": 1.3945,
"step": 489
},
{
"epoch": 1.4760828625235405,
"grad_norm": 5.129777908325195,
"learning_rate": 7.075528700906344e-07,
"loss": 1.5507,
"step": 490
},
{
"epoch": 1.4790960451977402,
"grad_norm": 5.247596740722656,
"learning_rate": 7.069486404833836e-07,
"loss": 1.4331,
"step": 491
},
{
"epoch": 1.4821092278719397,
"grad_norm": 6.178140163421631,
"learning_rate": 7.063444108761329e-07,
"loss": 1.4418,
"step": 492
},
{
"epoch": 1.4851224105461394,
"grad_norm": 6.076567649841309,
"learning_rate": 7.057401812688822e-07,
"loss": 1.3777,
"step": 493
},
{
"epoch": 1.488135593220339,
"grad_norm": 5.229823112487793,
"learning_rate": 7.051359516616314e-07,
"loss": 1.3608,
"step": 494
},
{
"epoch": 1.4911487758945385,
"grad_norm": 6.000827312469482,
"learning_rate": 7.045317220543806e-07,
"loss": 1.4285,
"step": 495
},
{
"epoch": 1.4941619585687382,
"grad_norm": 6.488296031951904,
"learning_rate": 7.039274924471299e-07,
"loss": 1.396,
"step": 496
},
{
"epoch": 1.497175141242938,
"grad_norm": 6.797378063201904,
"learning_rate": 7.033232628398791e-07,
"loss": 1.6419,
"step": 497
},
{
"epoch": 1.5001883239171376,
"grad_norm": 5.642067909240723,
"learning_rate": 7.027190332326284e-07,
"loss": 1.4001,
"step": 498
},
{
"epoch": 1.503201506591337,
"grad_norm": 7.238025665283203,
"learning_rate": 7.021148036253776e-07,
"loss": 1.5748,
"step": 499
},
{
"epoch": 1.5062146892655366,
"grad_norm": 4.841119766235352,
"learning_rate": 7.015105740181268e-07,
"loss": 1.4002,
"step": 500
},
{
"epoch": 1.5092278719397365,
"grad_norm": 7.108461856842041,
"learning_rate": 7.009063444108762e-07,
"loss": 1.457,
"step": 501
},
{
"epoch": 1.512241054613936,
"grad_norm": 5.759829521179199,
"learning_rate": 7.003021148036253e-07,
"loss": 1.4616,
"step": 502
},
{
"epoch": 1.5152542372881355,
"grad_norm": 5.384749889373779,
"learning_rate": 6.996978851963746e-07,
"loss": 1.4173,
"step": 503
},
{
"epoch": 1.5182674199623352,
"grad_norm": 5.466532230377197,
"learning_rate": 6.990936555891238e-07,
"loss": 1.353,
"step": 504
},
{
"epoch": 1.5212806026365349,
"grad_norm": 9.823829650878906,
"learning_rate": 6.984894259818731e-07,
"loss": 1.44,
"step": 505
},
{
"epoch": 1.5242937853107343,
"grad_norm": 5.307360649108887,
"learning_rate": 6.978851963746222e-07,
"loss": 1.3811,
"step": 506
},
{
"epoch": 1.527306967984934,
"grad_norm": 5.112379550933838,
"learning_rate": 6.972809667673716e-07,
"loss": 1.3994,
"step": 507
},
{
"epoch": 1.5303201506591337,
"grad_norm": 5.7161359786987305,
"learning_rate": 6.966767371601208e-07,
"loss": 1.479,
"step": 508
},
{
"epoch": 1.5333333333333332,
"grad_norm": 5.918424606323242,
"learning_rate": 6.9607250755287e-07,
"loss": 1.5487,
"step": 509
},
{
"epoch": 1.536346516007533,
"grad_norm": 4.992625713348389,
"learning_rate": 6.954682779456194e-07,
"loss": 1.3757,
"step": 510
},
{
"epoch": 1.5393596986817326,
"grad_norm": 4.293216228485107,
"learning_rate": 6.948640483383685e-07,
"loss": 1.4065,
"step": 511
},
{
"epoch": 1.542372881355932,
"grad_norm": 5.834140300750732,
"learning_rate": 6.942598187311179e-07,
"loss": 1.4839,
"step": 512
},
{
"epoch": 1.5453860640301318,
"grad_norm": 5.41923189163208,
"learning_rate": 6.93655589123867e-07,
"loss": 1.4985,
"step": 513
},
{
"epoch": 1.5483992467043315,
"grad_norm": 5.158897876739502,
"learning_rate": 6.930513595166163e-07,
"loss": 1.4512,
"step": 514
},
{
"epoch": 1.551412429378531,
"grad_norm": 6.274599552154541,
"learning_rate": 6.924471299093655e-07,
"loss": 1.4295,
"step": 515
},
{
"epoch": 1.5544256120527307,
"grad_norm": 5.780722141265869,
"learning_rate": 6.918429003021148e-07,
"loss": 1.4675,
"step": 516
},
{
"epoch": 1.5574387947269304,
"grad_norm": 6.4688520431518555,
"learning_rate": 6.912386706948639e-07,
"loss": 1.4375,
"step": 517
},
{
"epoch": 1.5604519774011298,
"grad_norm": 6.904114723205566,
"learning_rate": 6.906344410876133e-07,
"loss": 1.3001,
"step": 518
},
{
"epoch": 1.5634651600753295,
"grad_norm": 7.99424934387207,
"learning_rate": 6.900302114803625e-07,
"loss": 1.3876,
"step": 519
},
{
"epoch": 1.5664783427495292,
"grad_norm": 4.946364879608154,
"learning_rate": 6.894259818731117e-07,
"loss": 1.4967,
"step": 520
},
{
"epoch": 1.5694915254237287,
"grad_norm": 4.895719051361084,
"learning_rate": 6.88821752265861e-07,
"loss": 1.4387,
"step": 521
},
{
"epoch": 1.5725047080979284,
"grad_norm": 5.683162689208984,
"learning_rate": 6.882175226586102e-07,
"loss": 1.4157,
"step": 522
},
{
"epoch": 1.5755178907721281,
"grad_norm": 6.254124164581299,
"learning_rate": 6.876132930513596e-07,
"loss": 1.3239,
"step": 523
},
{
"epoch": 1.5785310734463276,
"grad_norm": 5.455890655517578,
"learning_rate": 6.870090634441087e-07,
"loss": 1.4771,
"step": 524
},
{
"epoch": 1.5815442561205273,
"grad_norm": 5.1645307540893555,
"learning_rate": 6.86404833836858e-07,
"loss": 1.4606,
"step": 525
},
{
"epoch": 1.584557438794727,
"grad_norm": 5.679819107055664,
"learning_rate": 6.858006042296072e-07,
"loss": 1.4379,
"step": 526
},
{
"epoch": 1.5875706214689265,
"grad_norm": 5.951003074645996,
"learning_rate": 6.851963746223565e-07,
"loss": 1.4842,
"step": 527
},
{
"epoch": 1.5905838041431262,
"grad_norm": 5.812933921813965,
"learning_rate": 6.845921450151057e-07,
"loss": 1.4825,
"step": 528
},
{
"epoch": 1.5935969868173259,
"grad_norm": 5.2482218742370605,
"learning_rate": 6.83987915407855e-07,
"loss": 1.488,
"step": 529
},
{
"epoch": 1.5966101694915253,
"grad_norm": 5.172732830047607,
"learning_rate": 6.833836858006042e-07,
"loss": 1.3151,
"step": 530
},
{
"epoch": 1.599623352165725,
"grad_norm": 5.541701793670654,
"learning_rate": 6.827794561933534e-07,
"loss": 1.3685,
"step": 531
},
{
"epoch": 1.6026365348399247,
"grad_norm": 4.998197555541992,
"learning_rate": 6.821752265861027e-07,
"loss": 1.4423,
"step": 532
},
{
"epoch": 1.6056497175141242,
"grad_norm": 5.002514839172363,
"learning_rate": 6.815709969788519e-07,
"loss": 1.4232,
"step": 533
},
{
"epoch": 1.608662900188324,
"grad_norm": 7.178779125213623,
"learning_rate": 6.809667673716012e-07,
"loss": 1.5029,
"step": 534
},
{
"epoch": 1.6116760828625236,
"grad_norm": 6.734219551086426,
"learning_rate": 6.803625377643504e-07,
"loss": 1.4361,
"step": 535
},
{
"epoch": 1.614689265536723,
"grad_norm": 6.7906494140625,
"learning_rate": 6.797583081570996e-07,
"loss": 1.2748,
"step": 536
},
{
"epoch": 1.6177024482109228,
"grad_norm": 4.756163120269775,
"learning_rate": 6.79154078549849e-07,
"loss": 1.4651,
"step": 537
},
{
"epoch": 1.6207156308851225,
"grad_norm": 6.231260776519775,
"learning_rate": 6.785498489425982e-07,
"loss": 1.4384,
"step": 538
},
{
"epoch": 1.623728813559322,
"grad_norm": 5.305384635925293,
"learning_rate": 6.779456193353474e-07,
"loss": 1.4345,
"step": 539
},
{
"epoch": 1.6267419962335217,
"grad_norm": 4.599124431610107,
"learning_rate": 6.773413897280967e-07,
"loss": 1.4567,
"step": 540
},
{
"epoch": 1.6297551789077214,
"grad_norm": 5.924282073974609,
"learning_rate": 6.767371601208459e-07,
"loss": 1.3263,
"step": 541
},
{
"epoch": 1.6327683615819208,
"grad_norm": 6.763551235198975,
"learning_rate": 6.761329305135951e-07,
"loss": 1.432,
"step": 542
},
{
"epoch": 1.6357815442561205,
"grad_norm": 5.712234973907471,
"learning_rate": 6.755287009063444e-07,
"loss": 1.4291,
"step": 543
},
{
"epoch": 1.6387947269303202,
"grad_norm": 5.8092360496521,
"learning_rate": 6.749244712990936e-07,
"loss": 1.3997,
"step": 544
},
{
"epoch": 1.6418079096045197,
"grad_norm": 5.469808101654053,
"learning_rate": 6.743202416918428e-07,
"loss": 1.3896,
"step": 545
},
{
"epoch": 1.6448210922787194,
"grad_norm": 5.859208106994629,
"learning_rate": 6.737160120845922e-07,
"loss": 1.4631,
"step": 546
},
{
"epoch": 1.6478342749529191,
"grad_norm": 5.414376735687256,
"learning_rate": 6.731117824773413e-07,
"loss": 1.3612,
"step": 547
},
{
"epoch": 1.6508474576271186,
"grad_norm": 5.3840460777282715,
"learning_rate": 6.725075528700907e-07,
"loss": 1.3608,
"step": 548
},
{
"epoch": 1.6538606403013183,
"grad_norm": 4.658404350280762,
"learning_rate": 6.719033232628398e-07,
"loss": 1.5127,
"step": 549
},
{
"epoch": 1.656873822975518,
"grad_norm": 4.918388366699219,
"learning_rate": 6.712990936555891e-07,
"loss": 1.4597,
"step": 550
},
{
"epoch": 1.6598870056497175,
"grad_norm": 6.723229885101318,
"learning_rate": 6.706948640483383e-07,
"loss": 1.3722,
"step": 551
},
{
"epoch": 1.6629001883239172,
"grad_norm": 5.890351295471191,
"learning_rate": 6.700906344410876e-07,
"loss": 1.4422,
"step": 552
},
{
"epoch": 1.6659133709981169,
"grad_norm": 6.722075939178467,
"learning_rate": 6.694864048338367e-07,
"loss": 1.4273,
"step": 553
},
{
"epoch": 1.6689265536723163,
"grad_norm": 6.511855125427246,
"learning_rate": 6.688821752265861e-07,
"loss": 1.6251,
"step": 554
},
{
"epoch": 1.671939736346516,
"grad_norm": 5.096655368804932,
"learning_rate": 6.682779456193354e-07,
"loss": 1.4326,
"step": 555
},
{
"epoch": 1.6749529190207157,
"grad_norm": 5.17719841003418,
"learning_rate": 6.676737160120845e-07,
"loss": 1.2426,
"step": 556
},
{
"epoch": 1.6779661016949152,
"grad_norm": 6.523287773132324,
"learning_rate": 6.670694864048339e-07,
"loss": 1.3799,
"step": 557
},
{
"epoch": 1.680979284369115,
"grad_norm": 5.452298641204834,
"learning_rate": 6.66465256797583e-07,
"loss": 1.3897,
"step": 558
},
{
"epoch": 1.6839924670433146,
"grad_norm": 5.382078647613525,
"learning_rate": 6.658610271903324e-07,
"loss": 1.3989,
"step": 559
},
{
"epoch": 1.687005649717514,
"grad_norm": 6.651437759399414,
"learning_rate": 6.652567975830815e-07,
"loss": 1.5026,
"step": 560
},
{
"epoch": 1.6900188323917138,
"grad_norm": 4.4180145263671875,
"learning_rate": 6.646525679758308e-07,
"loss": 1.3469,
"step": 561
},
{
"epoch": 1.6930320150659135,
"grad_norm": 4.69598388671875,
"learning_rate": 6.6404833836858e-07,
"loss": 1.4108,
"step": 562
},
{
"epoch": 1.696045197740113,
"grad_norm": 4.863903999328613,
"learning_rate": 6.634441087613293e-07,
"loss": 1.5132,
"step": 563
},
{
"epoch": 1.6990583804143125,
"grad_norm": 5.178380966186523,
"learning_rate": 6.628398791540785e-07,
"loss": 1.5195,
"step": 564
},
{
"epoch": 1.7020715630885124,
"grad_norm": 6.061720848083496,
"learning_rate": 6.622356495468278e-07,
"loss": 1.3956,
"step": 565
},
{
"epoch": 1.7050847457627119,
"grad_norm": 4.397692680358887,
"learning_rate": 6.61631419939577e-07,
"loss": 1.3829,
"step": 566
},
{
"epoch": 1.7080979284369113,
"grad_norm": 5.247250556945801,
"learning_rate": 6.610271903323262e-07,
"loss": 1.4632,
"step": 567
},
{
"epoch": 1.7111111111111112,
"grad_norm": 5.468592643737793,
"learning_rate": 6.604229607250756e-07,
"loss": 1.3197,
"step": 568
},
{
"epoch": 1.7141242937853107,
"grad_norm": 4.7552385330200195,
"learning_rate": 6.598187311178247e-07,
"loss": 1.4925,
"step": 569
},
{
"epoch": 1.7171374764595102,
"grad_norm": 5.632788181304932,
"learning_rate": 6.59214501510574e-07,
"loss": 1.4752,
"step": 570
},
{
"epoch": 1.7201506591337101,
"grad_norm": 4.604435443878174,
"learning_rate": 6.586102719033232e-07,
"loss": 1.4336,
"step": 571
},
{
"epoch": 1.7231638418079096,
"grad_norm": 5.476536273956299,
"learning_rate": 6.580060422960725e-07,
"loss": 1.4693,
"step": 572
},
{
"epoch": 1.726177024482109,
"grad_norm": 4.73729944229126,
"learning_rate": 6.574018126888218e-07,
"loss": 1.454,
"step": 573
},
{
"epoch": 1.729190207156309,
"grad_norm": 5.8851847648620605,
"learning_rate": 6.56797583081571e-07,
"loss": 1.4858,
"step": 574
},
{
"epoch": 1.7322033898305085,
"grad_norm": 5.509660720825195,
"learning_rate": 6.561933534743202e-07,
"loss": 1.5265,
"step": 575
},
{
"epoch": 1.735216572504708,
"grad_norm": 5.304653167724609,
"learning_rate": 6.555891238670695e-07,
"loss": 1.3569,
"step": 576
},
{
"epoch": 1.7382297551789079,
"grad_norm": 5.039734840393066,
"learning_rate": 6.549848942598187e-07,
"loss": 1.419,
"step": 577
},
{
"epoch": 1.7412429378531074,
"grad_norm": 6.974076271057129,
"learning_rate": 6.543806646525679e-07,
"loss": 1.5582,
"step": 578
},
{
"epoch": 1.7442561205273068,
"grad_norm": 6.748344898223877,
"learning_rate": 6.537764350453172e-07,
"loss": 1.5854,
"step": 579
},
{
"epoch": 1.7472693032015068,
"grad_norm": 5.640841960906982,
"learning_rate": 6.531722054380664e-07,
"loss": 1.4451,
"step": 580
},
{
"epoch": 1.7502824858757062,
"grad_norm": 5.6795454025268555,
"learning_rate": 6.525679758308156e-07,
"loss": 1.4107,
"step": 581
},
{
"epoch": 1.7532956685499057,
"grad_norm": 5.71448278427124,
"learning_rate": 6.519637462235649e-07,
"loss": 1.4481,
"step": 582
},
{
"epoch": 1.7563088512241056,
"grad_norm": 5.561422824859619,
"learning_rate": 6.513595166163141e-07,
"loss": 1.5204,
"step": 583
},
{
"epoch": 1.759322033898305,
"grad_norm": 4.414923667907715,
"learning_rate": 6.507552870090635e-07,
"loss": 1.4593,
"step": 584
},
{
"epoch": 1.7623352165725046,
"grad_norm": 5.140356540679932,
"learning_rate": 6.501510574018127e-07,
"loss": 1.4937,
"step": 585
},
{
"epoch": 1.7653483992467043,
"grad_norm": 7.388606071472168,
"learning_rate": 6.495468277945619e-07,
"loss": 1.4052,
"step": 586
},
{
"epoch": 1.768361581920904,
"grad_norm": 5.832814693450928,
"learning_rate": 6.489425981873112e-07,
"loss": 1.4518,
"step": 587
},
{
"epoch": 1.7713747645951035,
"grad_norm": 4.214459419250488,
"learning_rate": 6.483383685800604e-07,
"loss": 1.4523,
"step": 588
},
{
"epoch": 1.7743879472693032,
"grad_norm": 5.070772171020508,
"learning_rate": 6.477341389728096e-07,
"loss": 1.3983,
"step": 589
},
{
"epoch": 1.7774011299435029,
"grad_norm": 5.3739800453186035,
"learning_rate": 6.471299093655589e-07,
"loss": 1.4219,
"step": 590
},
{
"epoch": 1.7804143126177023,
"grad_norm": 6.607515335083008,
"learning_rate": 6.465256797583081e-07,
"loss": 1.3319,
"step": 591
},
{
"epoch": 1.783427495291902,
"grad_norm": 5.779582500457764,
"learning_rate": 6.459214501510573e-07,
"loss": 1.3368,
"step": 592
},
{
"epoch": 1.7864406779661017,
"grad_norm": 4.628208160400391,
"learning_rate": 6.453172205438067e-07,
"loss": 1.4129,
"step": 593
},
{
"epoch": 1.7894538606403012,
"grad_norm": 5.075791835784912,
"learning_rate": 6.447129909365558e-07,
"loss": 1.3953,
"step": 594
},
{
"epoch": 1.792467043314501,
"grad_norm": 5.970827102661133,
"learning_rate": 6.441087613293051e-07,
"loss": 1.4621,
"step": 595
},
{
"epoch": 1.7954802259887006,
"grad_norm": 5.0847883224487305,
"learning_rate": 6.435045317220543e-07,
"loss": 1.45,
"step": 596
},
{
"epoch": 1.7984934086629,
"grad_norm": 5.330321311950684,
"learning_rate": 6.429003021148036e-07,
"loss": 1.3755,
"step": 597
},
{
"epoch": 1.8015065913370998,
"grad_norm": 5.063493251800537,
"learning_rate": 6.422960725075527e-07,
"loss": 1.4522,
"step": 598
},
{
"epoch": 1.8045197740112995,
"grad_norm": 5.650209903717041,
"learning_rate": 6.416918429003021e-07,
"loss": 1.3714,
"step": 599
},
{
"epoch": 1.807532956685499,
"grad_norm": 5.014791965484619,
"learning_rate": 6.410876132930513e-07,
"loss": 1.4091,
"step": 600
},
{
"epoch": 1.8105461393596987,
"grad_norm": 4.727352142333984,
"learning_rate": 6.404833836858006e-07,
"loss": 1.4282,
"step": 601
},
{
"epoch": 1.8135593220338984,
"grad_norm": 5.757930755615234,
"learning_rate": 6.398791540785499e-07,
"loss": 1.4752,
"step": 602
},
{
"epoch": 1.8165725047080978,
"grad_norm": 5.246910095214844,
"learning_rate": 6.39274924471299e-07,
"loss": 1.4855,
"step": 603
},
{
"epoch": 1.8195856873822975,
"grad_norm": 6.4755682945251465,
"learning_rate": 6.386706948640484e-07,
"loss": 1.5642,
"step": 604
},
{
"epoch": 1.8225988700564972,
"grad_norm": 5.53103494644165,
"learning_rate": 6.380664652567975e-07,
"loss": 1.4201,
"step": 605
},
{
"epoch": 1.8256120527306967,
"grad_norm": 6.595399379730225,
"learning_rate": 6.374622356495468e-07,
"loss": 1.4027,
"step": 606
},
{
"epoch": 1.8286252354048964,
"grad_norm": 5.8376359939575195,
"learning_rate": 6.36858006042296e-07,
"loss": 1.5129,
"step": 607
},
{
"epoch": 1.831638418079096,
"grad_norm": 6.222456455230713,
"learning_rate": 6.362537764350453e-07,
"loss": 1.4368,
"step": 608
},
{
"epoch": 1.8346516007532956,
"grad_norm": 6.442774772644043,
"learning_rate": 6.356495468277944e-07,
"loss": 1.3926,
"step": 609
},
{
"epoch": 1.8376647834274953,
"grad_norm": 5.401163101196289,
"learning_rate": 6.350453172205438e-07,
"loss": 1.4971,
"step": 610
},
{
"epoch": 1.840677966101695,
"grad_norm": 5.267601490020752,
"learning_rate": 6.34441087613293e-07,
"loss": 1.4403,
"step": 611
},
{
"epoch": 1.8436911487758945,
"grad_norm": 5.1611714363098145,
"learning_rate": 6.338368580060423e-07,
"loss": 1.4001,
"step": 612
},
{
"epoch": 1.8467043314500942,
"grad_norm": 4.236810207366943,
"learning_rate": 6.332326283987916e-07,
"loss": 1.4281,
"step": 613
},
{
"epoch": 1.8497175141242939,
"grad_norm": 5.382960796356201,
"learning_rate": 6.326283987915407e-07,
"loss": 1.4978,
"step": 614
},
{
"epoch": 1.8527306967984933,
"grad_norm": 5.151810169219971,
"learning_rate": 6.320241691842901e-07,
"loss": 1.4408,
"step": 615
},
{
"epoch": 1.855743879472693,
"grad_norm": 6.229462623596191,
"learning_rate": 6.314199395770392e-07,
"loss": 1.4,
"step": 616
},
{
"epoch": 1.8587570621468927,
"grad_norm": 5.40347146987915,
"learning_rate": 6.308157099697885e-07,
"loss": 1.4664,
"step": 617
},
{
"epoch": 1.8617702448210922,
"grad_norm": 5.364798069000244,
"learning_rate": 6.302114803625377e-07,
"loss": 1.3194,
"step": 618
},
{
"epoch": 1.864783427495292,
"grad_norm": 4.928649425506592,
"learning_rate": 6.29607250755287e-07,
"loss": 1.4539,
"step": 619
},
{
"epoch": 1.8677966101694916,
"grad_norm": 5.486970901489258,
"learning_rate": 6.290030211480362e-07,
"loss": 1.5761,
"step": 620
},
{
"epoch": 1.870809792843691,
"grad_norm": 5.141716957092285,
"learning_rate": 6.283987915407855e-07,
"loss": 1.5517,
"step": 621
},
{
"epoch": 1.8738229755178908,
"grad_norm": 5.570183277130127,
"learning_rate": 6.277945619335347e-07,
"loss": 1.4369,
"step": 622
},
{
"epoch": 1.8768361581920905,
"grad_norm": 5.514773368835449,
"learning_rate": 6.27190332326284e-07,
"loss": 1.3528,
"step": 623
},
{
"epoch": 1.87984934086629,
"grad_norm": 4.866400718688965,
"learning_rate": 6.265861027190332e-07,
"loss": 1.4558,
"step": 624
},
{
"epoch": 1.8828625235404897,
"grad_norm": 5.65744161605835,
"learning_rate": 6.259818731117824e-07,
"loss": 1.4621,
"step": 625
},
{
"epoch": 1.8858757062146894,
"grad_norm": 4.45788049697876,
"learning_rate": 6.253776435045317e-07,
"loss": 1.4233,
"step": 626
},
{
"epoch": 1.8888888888888888,
"grad_norm": 4.6774468421936035,
"learning_rate": 6.247734138972809e-07,
"loss": 1.3827,
"step": 627
},
{
"epoch": 1.8919020715630885,
"grad_norm": 5.3839240074157715,
"learning_rate": 6.241691842900301e-07,
"loss": 1.3881,
"step": 628
},
{
"epoch": 1.8949152542372882,
"grad_norm": 5.282009601593018,
"learning_rate": 6.235649546827795e-07,
"loss": 1.5081,
"step": 629
},
{
"epoch": 1.8979284369114877,
"grad_norm": 5.900636672973633,
"learning_rate": 6.229607250755287e-07,
"loss": 1.3394,
"step": 630
},
{
"epoch": 1.9009416195856874,
"grad_norm": 5.5449604988098145,
"learning_rate": 6.223564954682779e-07,
"loss": 1.4728,
"step": 631
},
{
"epoch": 1.9039548022598871,
"grad_norm": 5.975988864898682,
"learning_rate": 6.217522658610272e-07,
"loss": 1.4423,
"step": 632
},
{
"epoch": 1.9069679849340866,
"grad_norm": 5.850360870361328,
"learning_rate": 6.211480362537764e-07,
"loss": 1.4192,
"step": 633
},
{
"epoch": 1.9099811676082863,
"grad_norm": 5.3933424949646,
"learning_rate": 6.205438066465256e-07,
"loss": 1.4928,
"step": 634
},
{
"epoch": 1.912994350282486,
"grad_norm": 5.343086242675781,
"learning_rate": 6.199395770392749e-07,
"loss": 1.4382,
"step": 635
},
{
"epoch": 1.9160075329566855,
"grad_norm": 5.127535820007324,
"learning_rate": 6.193353474320241e-07,
"loss": 1.3975,
"step": 636
},
{
"epoch": 1.9190207156308852,
"grad_norm": 6.427939414978027,
"learning_rate": 6.187311178247734e-07,
"loss": 1.4685,
"step": 637
},
{
"epoch": 1.9220338983050849,
"grad_norm": 5.146970748901367,
"learning_rate": 6.181268882175227e-07,
"loss": 1.3038,
"step": 638
},
{
"epoch": 1.9250470809792843,
"grad_norm": 5.896442890167236,
"learning_rate": 6.175226586102718e-07,
"loss": 1.4573,
"step": 639
},
{
"epoch": 1.928060263653484,
"grad_norm": 5.2345356941223145,
"learning_rate": 6.169184290030212e-07,
"loss": 1.4047,
"step": 640
},
{
"epoch": 1.9310734463276837,
"grad_norm": 5.183843612670898,
"learning_rate": 6.163141993957703e-07,
"loss": 1.5048,
"step": 641
},
{
"epoch": 1.9340866290018832,
"grad_norm": 6.291079998016357,
"learning_rate": 6.157099697885196e-07,
"loss": 1.3371,
"step": 642
},
{
"epoch": 1.937099811676083,
"grad_norm": 6.718411922454834,
"learning_rate": 6.151057401812688e-07,
"loss": 1.4606,
"step": 643
},
{
"epoch": 1.9401129943502826,
"grad_norm": 6.028992176055908,
"learning_rate": 6.145015105740181e-07,
"loss": 1.5625,
"step": 644
},
{
"epoch": 1.943126177024482,
"grad_norm": 5.395115852355957,
"learning_rate": 6.138972809667673e-07,
"loss": 1.4054,
"step": 645
},
{
"epoch": 1.9461393596986816,
"grad_norm": 4.531974792480469,
"learning_rate": 6.132930513595166e-07,
"loss": 1.433,
"step": 646
},
{
"epoch": 1.9491525423728815,
"grad_norm": 5.246399402618408,
"learning_rate": 6.126888217522659e-07,
"loss": 1.4677,
"step": 647
},
{
"epoch": 1.952165725047081,
"grad_norm": 8.41258430480957,
"learning_rate": 6.12084592145015e-07,
"loss": 1.4845,
"step": 648
},
{
"epoch": 1.9551789077212804,
"grad_norm": 5.498213291168213,
"learning_rate": 6.114803625377644e-07,
"loss": 1.434,
"step": 649
},
{
"epoch": 1.9581920903954804,
"grad_norm": 5.884972095489502,
"learning_rate": 6.108761329305135e-07,
"loss": 1.3248,
"step": 650
},
{
"epoch": 1.9612052730696798,
"grad_norm": 5.844563961029053,
"learning_rate": 6.102719033232629e-07,
"loss": 1.3895,
"step": 651
},
{
"epoch": 1.9642184557438793,
"grad_norm": 4.956814765930176,
"learning_rate": 6.09667673716012e-07,
"loss": 1.3546,
"step": 652
},
{
"epoch": 1.9672316384180792,
"grad_norm": 6.289551258087158,
"learning_rate": 6.090634441087613e-07,
"loss": 1.3619,
"step": 653
},
{
"epoch": 1.9702448210922787,
"grad_norm": 4.80326509475708,
"learning_rate": 6.084592145015105e-07,
"loss": 1.4339,
"step": 654
},
{
"epoch": 1.9732580037664782,
"grad_norm": 4.916763782501221,
"learning_rate": 6.078549848942598e-07,
"loss": 1.4357,
"step": 655
},
{
"epoch": 1.9762711864406781,
"grad_norm": 5.264612674713135,
"learning_rate": 6.07250755287009e-07,
"loss": 1.3895,
"step": 656
},
{
"epoch": 1.9792843691148776,
"grad_norm": 4.559102535247803,
"learning_rate": 6.066465256797583e-07,
"loss": 1.3428,
"step": 657
},
{
"epoch": 1.982297551789077,
"grad_norm": 4.3896589279174805,
"learning_rate": 6.060422960725075e-07,
"loss": 1.2766,
"step": 658
},
{
"epoch": 1.985310734463277,
"grad_norm": 5.347879886627197,
"learning_rate": 6.054380664652567e-07,
"loss": 1.4443,
"step": 659
},
{
"epoch": 1.9883239171374765,
"grad_norm": 5.088440895080566,
"learning_rate": 6.048338368580061e-07,
"loss": 1.4539,
"step": 660
},
{
"epoch": 1.991337099811676,
"grad_norm": 5.309561729431152,
"learning_rate": 6.042296072507552e-07,
"loss": 1.4494,
"step": 661
},
{
"epoch": 1.9943502824858759,
"grad_norm": 6.114358901977539,
"learning_rate": 6.036253776435046e-07,
"loss": 1.3435,
"step": 662
},
{
"epoch": 1.9973634651600753,
"grad_norm": 4.403398036956787,
"learning_rate": 6.030211480362537e-07,
"loss": 1.3779,
"step": 663
},
{
"epoch": 2.0,
"grad_norm": 4.7274346351623535,
"learning_rate": 6.02416918429003e-07,
"loss": 1.4645,
"step": 664
},
{
"epoch": 2.0030131826741995,
"grad_norm": 6.506847381591797,
"learning_rate": 6.018126888217523e-07,
"loss": 1.5385,
"step": 665
},
{
"epoch": 2.0060263653483994,
"grad_norm": 7.451054096221924,
"learning_rate": 6.012084592145015e-07,
"loss": 1.4049,
"step": 666
},
{
"epoch": 2.009039548022599,
"grad_norm": 4.383606433868408,
"learning_rate": 6.006042296072507e-07,
"loss": 1.4833,
"step": 667
},
{
"epoch": 2.0120527306967984,
"grad_norm": 5.063993453979492,
"learning_rate": 6e-07,
"loss": 1.3355,
"step": 668
},
{
"epoch": 2.0150659133709983,
"grad_norm": 5.351034641265869,
"learning_rate": 5.993957703927492e-07,
"loss": 1.3882,
"step": 669
},
{
"epoch": 2.0180790960451978,
"grad_norm": 7.559557914733887,
"learning_rate": 5.987915407854984e-07,
"loss": 1.4989,
"step": 670
},
{
"epoch": 2.0210922787193972,
"grad_norm": 5.76372766494751,
"learning_rate": 5.981873111782477e-07,
"loss": 1.3548,
"step": 671
},
{
"epoch": 2.024105461393597,
"grad_norm": 5.260524749755859,
"learning_rate": 5.975830815709969e-07,
"loss": 1.4599,
"step": 672
},
{
"epoch": 2.0271186440677966,
"grad_norm": 5.199622631072998,
"learning_rate": 5.969788519637462e-07,
"loss": 1.4346,
"step": 673
},
{
"epoch": 2.030131826741996,
"grad_norm": 5.199345588684082,
"learning_rate": 5.963746223564955e-07,
"loss": 1.4608,
"step": 674
},
{
"epoch": 2.033145009416196,
"grad_norm": 4.905064582824707,
"learning_rate": 5.957703927492447e-07,
"loss": 1.4167,
"step": 675
},
{
"epoch": 2.0361581920903955,
"grad_norm": 5.352112293243408,
"learning_rate": 5.95166163141994e-07,
"loss": 1.5008,
"step": 676
},
{
"epoch": 2.039171374764595,
"grad_norm": 5.230722427368164,
"learning_rate": 5.945619335347432e-07,
"loss": 1.4865,
"step": 677
},
{
"epoch": 2.042184557438795,
"grad_norm": 6.2545647621154785,
"learning_rate": 5.939577039274924e-07,
"loss": 1.4017,
"step": 678
},
{
"epoch": 2.0451977401129944,
"grad_norm": 5.609623908996582,
"learning_rate": 5.933534743202417e-07,
"loss": 1.4035,
"step": 679
},
{
"epoch": 2.048210922787194,
"grad_norm": 4.778747081756592,
"learning_rate": 5.927492447129909e-07,
"loss": 1.4581,
"step": 680
},
{
"epoch": 2.0512241054613938,
"grad_norm": 5.225364685058594,
"learning_rate": 5.921450151057401e-07,
"loss": 1.4524,
"step": 681
},
{
"epoch": 2.0542372881355933,
"grad_norm": 5.3008222579956055,
"learning_rate": 5.915407854984894e-07,
"loss": 1.5256,
"step": 682
},
{
"epoch": 2.0572504708097927,
"grad_norm": 4.803897857666016,
"learning_rate": 5.909365558912387e-07,
"loss": 1.3641,
"step": 683
},
{
"epoch": 2.0602636534839927,
"grad_norm": 5.865955829620361,
"learning_rate": 5.903323262839878e-07,
"loss": 1.5513,
"step": 684
},
{
"epoch": 2.063276836158192,
"grad_norm": 5.892612934112549,
"learning_rate": 5.897280966767372e-07,
"loss": 1.3533,
"step": 685
},
{
"epoch": 2.0662900188323916,
"grad_norm": 6.444551467895508,
"learning_rate": 5.891238670694863e-07,
"loss": 1.3951,
"step": 686
},
{
"epoch": 2.0693032015065915,
"grad_norm": 4.745134353637695,
"learning_rate": 5.885196374622357e-07,
"loss": 1.3467,
"step": 687
},
{
"epoch": 2.072316384180791,
"grad_norm": 4.58413028717041,
"learning_rate": 5.879154078549848e-07,
"loss": 1.4109,
"step": 688
},
{
"epoch": 2.0753295668549905,
"grad_norm": 7.045490264892578,
"learning_rate": 5.873111782477341e-07,
"loss": 1.2779,
"step": 689
},
{
"epoch": 2.0783427495291904,
"grad_norm": 4.938101291656494,
"learning_rate": 5.867069486404834e-07,
"loss": 1.4159,
"step": 690
},
{
"epoch": 2.08135593220339,
"grad_norm": 5.45305871963501,
"learning_rate": 5.861027190332326e-07,
"loss": 1.4708,
"step": 691
},
{
"epoch": 2.0843691148775894,
"grad_norm": 5.357665061950684,
"learning_rate": 5.854984894259819e-07,
"loss": 1.4104,
"step": 692
},
{
"epoch": 2.0873822975517893,
"grad_norm": 5.973804950714111,
"learning_rate": 5.848942598187311e-07,
"loss": 1.4934,
"step": 693
},
{
"epoch": 2.0903954802259888,
"grad_norm": 5.5561370849609375,
"learning_rate": 5.842900302114804e-07,
"loss": 1.4021,
"step": 694
},
{
"epoch": 2.0934086629001882,
"grad_norm": 6.015888690948486,
"learning_rate": 5.836858006042295e-07,
"loss": 1.3318,
"step": 695
},
{
"epoch": 2.096421845574388,
"grad_norm": 5.203176498413086,
"learning_rate": 5.830815709969789e-07,
"loss": 1.3799,
"step": 696
},
{
"epoch": 2.0994350282485876,
"grad_norm": 5.700403213500977,
"learning_rate": 5.82477341389728e-07,
"loss": 1.4465,
"step": 697
},
{
"epoch": 2.102448210922787,
"grad_norm": 5.27009391784668,
"learning_rate": 5.818731117824774e-07,
"loss": 1.4464,
"step": 698
},
{
"epoch": 2.105461393596987,
"grad_norm": 4.3890838623046875,
"learning_rate": 5.812688821752265e-07,
"loss": 1.3357,
"step": 699
},
{
"epoch": 2.1084745762711865,
"grad_norm": 5.063640117645264,
"learning_rate": 5.806646525679758e-07,
"loss": 1.3312,
"step": 700
},
{
"epoch": 2.111487758945386,
"grad_norm": 5.567170143127441,
"learning_rate": 5.800604229607251e-07,
"loss": 1.443,
"step": 701
},
{
"epoch": 2.1145009416195855,
"grad_norm": 4.773354530334473,
"learning_rate": 5.794561933534743e-07,
"loss": 1.4135,
"step": 702
},
{
"epoch": 2.1175141242937854,
"grad_norm": 5.5113205909729,
"learning_rate": 5.788519637462235e-07,
"loss": 1.4001,
"step": 703
},
{
"epoch": 2.120527306967985,
"grad_norm": 6.3716840744018555,
"learning_rate": 5.782477341389728e-07,
"loss": 1.551,
"step": 704
},
{
"epoch": 2.123540489642185,
"grad_norm": 6.4553046226501465,
"learning_rate": 5.776435045317221e-07,
"loss": 1.5445,
"step": 705
},
{
"epoch": 2.1265536723163843,
"grad_norm": 6.153264045715332,
"learning_rate": 5.770392749244712e-07,
"loss": 1.4689,
"step": 706
},
{
"epoch": 2.1295668549905837,
"grad_norm": 6.04611873626709,
"learning_rate": 5.764350453172206e-07,
"loss": 1.3696,
"step": 707
},
{
"epoch": 2.132580037664783,
"grad_norm": 5.727451801300049,
"learning_rate": 5.758308157099697e-07,
"loss": 1.3972,
"step": 708
},
{
"epoch": 2.135593220338983,
"grad_norm": 5.192663192749023,
"learning_rate": 5.75226586102719e-07,
"loss": 1.3843,
"step": 709
},
{
"epoch": 2.1386064030131826,
"grad_norm": 4.959181308746338,
"learning_rate": 5.746223564954682e-07,
"loss": 1.3187,
"step": 710
},
{
"epoch": 2.1416195856873825,
"grad_norm": 6.960421085357666,
"learning_rate": 5.740181268882175e-07,
"loss": 1.3501,
"step": 711
},
{
"epoch": 2.144632768361582,
"grad_norm": 6.067958831787109,
"learning_rate": 5.734138972809668e-07,
"loss": 1.3431,
"step": 712
},
{
"epoch": 2.1476459510357815,
"grad_norm": 6.101826190948486,
"learning_rate": 5.72809667673716e-07,
"loss": 1.3915,
"step": 713
},
{
"epoch": 2.150659133709981,
"grad_norm": 5.134862899780273,
"learning_rate": 5.722054380664652e-07,
"loss": 1.3667,
"step": 714
},
{
"epoch": 2.153672316384181,
"grad_norm": 5.357845783233643,
"learning_rate": 5.716012084592145e-07,
"loss": 1.461,
"step": 715
},
{
"epoch": 2.1566854990583804,
"grad_norm": 5.645199775695801,
"learning_rate": 5.709969788519637e-07,
"loss": 1.4587,
"step": 716
},
{
"epoch": 2.15969868173258,
"grad_norm": 4.612567901611328,
"learning_rate": 5.703927492447129e-07,
"loss": 1.3755,
"step": 717
},
{
"epoch": 2.1627118644067798,
"grad_norm": 5.404798984527588,
"learning_rate": 5.697885196374622e-07,
"loss": 1.397,
"step": 718
},
{
"epoch": 2.1657250470809792,
"grad_norm": 6.823877334594727,
"learning_rate": 5.691842900302114e-07,
"loss": 1.5049,
"step": 719
},
{
"epoch": 2.1687382297551787,
"grad_norm": 4.873520851135254,
"learning_rate": 5.685800604229607e-07,
"loss": 1.3848,
"step": 720
},
{
"epoch": 2.1717514124293786,
"grad_norm": 4.607947826385498,
"learning_rate": 5.6797583081571e-07,
"loss": 1.3787,
"step": 721
},
{
"epoch": 2.174764595103578,
"grad_norm": 4.3039045333862305,
"learning_rate": 5.673716012084592e-07,
"loss": 1.4073,
"step": 722
},
{
"epoch": 2.1777777777777776,
"grad_norm": 6.4014081954956055,
"learning_rate": 5.667673716012085e-07,
"loss": 1.4743,
"step": 723
},
{
"epoch": 2.1807909604519775,
"grad_norm": 5.704488277435303,
"learning_rate": 5.661631419939577e-07,
"loss": 1.3492,
"step": 724
},
{
"epoch": 2.183804143126177,
"grad_norm": 5.089229583740234,
"learning_rate": 5.655589123867069e-07,
"loss": 1.3759,
"step": 725
},
{
"epoch": 2.1868173258003765,
"grad_norm": 5.573424816131592,
"learning_rate": 5.649546827794562e-07,
"loss": 1.3611,
"step": 726
},
{
"epoch": 2.1898305084745764,
"grad_norm": 5.113455772399902,
"learning_rate": 5.643504531722054e-07,
"loss": 1.2688,
"step": 727
},
{
"epoch": 2.192843691148776,
"grad_norm": 5.637343406677246,
"learning_rate": 5.637462235649546e-07,
"loss": 1.2778,
"step": 728
},
{
"epoch": 2.1958568738229753,
"grad_norm": 5.297298908233643,
"learning_rate": 5.631419939577039e-07,
"loss": 1.3677,
"step": 729
},
{
"epoch": 2.1988700564971753,
"grad_norm": 5.349950790405273,
"learning_rate": 5.625377643504532e-07,
"loss": 1.3514,
"step": 730
},
{
"epoch": 2.2018832391713747,
"grad_norm": 5.5406575202941895,
"learning_rate": 5.619335347432023e-07,
"loss": 1.4946,
"step": 731
},
{
"epoch": 2.204896421845574,
"grad_norm": 5.90025520324707,
"learning_rate": 5.613293051359517e-07,
"loss": 1.3405,
"step": 732
},
{
"epoch": 2.207909604519774,
"grad_norm": 6.53027868270874,
"learning_rate": 5.607250755287008e-07,
"loss": 1.364,
"step": 733
},
{
"epoch": 2.2109227871939736,
"grad_norm": 6.908459663391113,
"learning_rate": 5.601208459214501e-07,
"loss": 1.4171,
"step": 734
},
{
"epoch": 2.213935969868173,
"grad_norm": 6.314930438995361,
"learning_rate": 5.595166163141993e-07,
"loss": 1.4053,
"step": 735
},
{
"epoch": 2.216949152542373,
"grad_norm": 5.039096355438232,
"learning_rate": 5.589123867069486e-07,
"loss": 1.4515,
"step": 736
},
{
"epoch": 2.2199623352165725,
"grad_norm": 5.380539894104004,
"learning_rate": 5.583081570996979e-07,
"loss": 1.3262,
"step": 737
},
{
"epoch": 2.222975517890772,
"grad_norm": 5.479008197784424,
"learning_rate": 5.577039274924471e-07,
"loss": 1.4381,
"step": 738
},
{
"epoch": 2.225988700564972,
"grad_norm": 5.449029922485352,
"learning_rate": 5.570996978851964e-07,
"loss": 1.5548,
"step": 739
},
{
"epoch": 2.2290018832391714,
"grad_norm": 6.784027576446533,
"learning_rate": 5.564954682779456e-07,
"loss": 1.4505,
"step": 740
},
{
"epoch": 2.232015065913371,
"grad_norm": 5.272122859954834,
"learning_rate": 5.558912386706949e-07,
"loss": 1.4236,
"step": 741
},
{
"epoch": 2.2350282485875708,
"grad_norm": 5.2925848960876465,
"learning_rate": 5.55287009063444e-07,
"loss": 1.4045,
"step": 742
},
{
"epoch": 2.2380414312617702,
"grad_norm": 5.430851459503174,
"learning_rate": 5.546827794561934e-07,
"loss": 1.3611,
"step": 743
},
{
"epoch": 2.2410546139359697,
"grad_norm": 6.0691819190979,
"learning_rate": 5.540785498489425e-07,
"loss": 1.3461,
"step": 744
},
{
"epoch": 2.2440677966101696,
"grad_norm": 6.548588752746582,
"learning_rate": 5.534743202416918e-07,
"loss": 1.5202,
"step": 745
},
{
"epoch": 2.247080979284369,
"grad_norm": 4.588008880615234,
"learning_rate": 5.52870090634441e-07,
"loss": 1.3955,
"step": 746
},
{
"epoch": 2.2500941619585686,
"grad_norm": 4.85317850112915,
"learning_rate": 5.522658610271903e-07,
"loss": 1.3379,
"step": 747
},
{
"epoch": 2.2531073446327685,
"grad_norm": 5.505369186401367,
"learning_rate": 5.516616314199396e-07,
"loss": 1.2991,
"step": 748
},
{
"epoch": 2.256120527306968,
"grad_norm": 5.266923427581787,
"learning_rate": 5.510574018126888e-07,
"loss": 1.4563,
"step": 749
},
{
"epoch": 2.2591337099811675,
"grad_norm": 4.722748279571533,
"learning_rate": 5.504531722054381e-07,
"loss": 1.3144,
"step": 750
},
{
"epoch": 2.2621468926553674,
"grad_norm": 5.333494663238525,
"learning_rate": 5.498489425981873e-07,
"loss": 1.3694,
"step": 751
},
{
"epoch": 2.265160075329567,
"grad_norm": 5.768506050109863,
"learning_rate": 5.492447129909366e-07,
"loss": 1.3551,
"step": 752
},
{
"epoch": 2.2681732580037663,
"grad_norm": 5.590920448303223,
"learning_rate": 5.486404833836857e-07,
"loss": 1.4318,
"step": 753
},
{
"epoch": 2.2711864406779663,
"grad_norm": 5.287954330444336,
"learning_rate": 5.480362537764351e-07,
"loss": 1.4571,
"step": 754
},
{
"epoch": 2.2741996233521657,
"grad_norm": 5.73705530166626,
"learning_rate": 5.474320241691842e-07,
"loss": 1.4492,
"step": 755
},
{
"epoch": 2.277212806026365,
"grad_norm": 4.944558620452881,
"learning_rate": 5.468277945619335e-07,
"loss": 1.3898,
"step": 756
},
{
"epoch": 2.280225988700565,
"grad_norm": 5.280138969421387,
"learning_rate": 5.462235649546828e-07,
"loss": 1.3925,
"step": 757
},
{
"epoch": 2.2832391713747646,
"grad_norm": 5.228864669799805,
"learning_rate": 5.45619335347432e-07,
"loss": 1.316,
"step": 758
},
{
"epoch": 2.286252354048964,
"grad_norm": 5.202868938446045,
"learning_rate": 5.450151057401812e-07,
"loss": 1.5104,
"step": 759
},
{
"epoch": 2.289265536723164,
"grad_norm": 5.165500640869141,
"learning_rate": 5.444108761329305e-07,
"loss": 1.4511,
"step": 760
},
{
"epoch": 2.2922787193973635,
"grad_norm": 5.167695045471191,
"learning_rate": 5.438066465256797e-07,
"loss": 1.4157,
"step": 761
},
{
"epoch": 2.295291902071563,
"grad_norm": 5.771923542022705,
"learning_rate": 5.43202416918429e-07,
"loss": 1.4223,
"step": 762
},
{
"epoch": 2.298305084745763,
"grad_norm": 6.398752212524414,
"learning_rate": 5.425981873111782e-07,
"loss": 1.2413,
"step": 763
},
{
"epoch": 2.3013182674199624,
"grad_norm": 4.828259468078613,
"learning_rate": 5.419939577039274e-07,
"loss": 1.4065,
"step": 764
},
{
"epoch": 2.304331450094162,
"grad_norm": 4.799897193908691,
"learning_rate": 5.413897280966767e-07,
"loss": 1.4111,
"step": 765
},
{
"epoch": 2.3073446327683618,
"grad_norm": 4.8980278968811035,
"learning_rate": 5.40785498489426e-07,
"loss": 1.4593,
"step": 766
},
{
"epoch": 2.3103578154425612,
"grad_norm": 6.555448532104492,
"learning_rate": 5.401812688821752e-07,
"loss": 1.5678,
"step": 767
},
{
"epoch": 2.3133709981167607,
"grad_norm": 5.026364803314209,
"learning_rate": 5.395770392749245e-07,
"loss": 1.3852,
"step": 768
},
{
"epoch": 2.3163841807909606,
"grad_norm": 5.971618175506592,
"learning_rate": 5.389728096676737e-07,
"loss": 1.4891,
"step": 769
},
{
"epoch": 2.31939736346516,
"grad_norm": 5.163649559020996,
"learning_rate": 5.383685800604229e-07,
"loss": 1.4324,
"step": 770
},
{
"epoch": 2.3224105461393596,
"grad_norm": 5.030628204345703,
"learning_rate": 5.377643504531722e-07,
"loss": 1.4346,
"step": 771
},
{
"epoch": 2.3254237288135595,
"grad_norm": 6.850794792175293,
"learning_rate": 5.371601208459214e-07,
"loss": 1.2893,
"step": 772
},
{
"epoch": 2.328436911487759,
"grad_norm": 4.461858749389648,
"learning_rate": 5.365558912386706e-07,
"loss": 1.3034,
"step": 773
},
{
"epoch": 2.3314500941619585,
"grad_norm": 4.366841793060303,
"learning_rate": 5.359516616314199e-07,
"loss": 1.3536,
"step": 774
},
{
"epoch": 2.334463276836158,
"grad_norm": 5.5118727684021,
"learning_rate": 5.353474320241692e-07,
"loss": 1.4047,
"step": 775
},
{
"epoch": 2.337476459510358,
"grad_norm": 5.083255767822266,
"learning_rate": 5.347432024169184e-07,
"loss": 1.3084,
"step": 776
},
{
"epoch": 2.3404896421845574,
"grad_norm": 5.434283256530762,
"learning_rate": 5.341389728096677e-07,
"loss": 1.3846,
"step": 777
},
{
"epoch": 2.3435028248587573,
"grad_norm": 4.90469217300415,
"learning_rate": 5.335347432024168e-07,
"loss": 1.4139,
"step": 778
},
{
"epoch": 2.3465160075329567,
"grad_norm": 6.241771221160889,
"learning_rate": 5.329305135951662e-07,
"loss": 1.4582,
"step": 779
},
{
"epoch": 2.3495291902071562,
"grad_norm": 5.895584583282471,
"learning_rate": 5.323262839879153e-07,
"loss": 1.3051,
"step": 780
},
{
"epoch": 2.3525423728813557,
"grad_norm": 5.881920337677002,
"learning_rate": 5.317220543806646e-07,
"loss": 1.4703,
"step": 781
},
{
"epoch": 2.3555555555555556,
"grad_norm": 5.702391624450684,
"learning_rate": 5.311178247734139e-07,
"loss": 1.3757,
"step": 782
},
{
"epoch": 2.358568738229755,
"grad_norm": 5.143468856811523,
"learning_rate": 5.305135951661631e-07,
"loss": 1.3637,
"step": 783
},
{
"epoch": 2.361581920903955,
"grad_norm": 4.814526081085205,
"learning_rate": 5.299093655589125e-07,
"loss": 1.257,
"step": 784
},
{
"epoch": 2.3645951035781545,
"grad_norm": 6.0213751792907715,
"learning_rate": 5.293051359516616e-07,
"loss": 1.5238,
"step": 785
},
{
"epoch": 2.367608286252354,
"grad_norm": 4.7446489334106445,
"learning_rate": 5.287009063444109e-07,
"loss": 1.3483,
"step": 786
},
{
"epoch": 2.3706214689265535,
"grad_norm": 5.7863616943359375,
"learning_rate": 5.2809667673716e-07,
"loss": 1.4076,
"step": 787
},
{
"epoch": 2.3736346516007534,
"grad_norm": 4.720901966094971,
"learning_rate": 5.274924471299094e-07,
"loss": 1.3956,
"step": 788
},
{
"epoch": 2.376647834274953,
"grad_norm": 4.803937911987305,
"learning_rate": 5.268882175226585e-07,
"loss": 1.3972,
"step": 789
},
{
"epoch": 2.3796610169491528,
"grad_norm": 6.049300670623779,
"learning_rate": 5.262839879154079e-07,
"loss": 1.2986,
"step": 790
},
{
"epoch": 2.3826741996233523,
"grad_norm": 5.316163539886475,
"learning_rate": 5.25679758308157e-07,
"loss": 1.3263,
"step": 791
},
{
"epoch": 2.3856873822975517,
"grad_norm": 5.801413059234619,
"learning_rate": 5.250755287009063e-07,
"loss": 1.4789,
"step": 792
},
{
"epoch": 2.388700564971751,
"grad_norm": 5.5726165771484375,
"learning_rate": 5.244712990936556e-07,
"loss": 1.4595,
"step": 793
},
{
"epoch": 2.391713747645951,
"grad_norm": 5.9866156578063965,
"learning_rate": 5.238670694864048e-07,
"loss": 1.4622,
"step": 794
},
{
"epoch": 2.3947269303201506,
"grad_norm": 4.857815265655518,
"learning_rate": 5.23262839879154e-07,
"loss": 1.2981,
"step": 795
},
{
"epoch": 2.3977401129943505,
"grad_norm": 5.8389058113098145,
"learning_rate": 5.226586102719033e-07,
"loss": 1.3678,
"step": 796
},
{
"epoch": 2.40075329566855,
"grad_norm": 6.6678996086120605,
"learning_rate": 5.220543806646526e-07,
"loss": 1.3378,
"step": 797
},
{
"epoch": 2.4037664783427495,
"grad_norm": 5.256933212280273,
"learning_rate": 5.214501510574017e-07,
"loss": 1.4176,
"step": 798
},
{
"epoch": 2.406779661016949,
"grad_norm": 4.508882522583008,
"learning_rate": 5.208459214501511e-07,
"loss": 1.3573,
"step": 799
},
{
"epoch": 2.409792843691149,
"grad_norm": 4.6468186378479,
"learning_rate": 5.202416918429002e-07,
"loss": 1.2596,
"step": 800
},
{
"epoch": 2.4128060263653484,
"grad_norm": 5.40158224105835,
"learning_rate": 5.196374622356496e-07,
"loss": 1.4059,
"step": 801
},
{
"epoch": 2.415819209039548,
"grad_norm": 6.531670570373535,
"learning_rate": 5.190332326283988e-07,
"loss": 1.3649,
"step": 802
},
{
"epoch": 2.4188323917137478,
"grad_norm": 5.398077487945557,
"learning_rate": 5.18429003021148e-07,
"loss": 1.3326,
"step": 803
},
{
"epoch": 2.4218455743879472,
"grad_norm": 5.232184410095215,
"learning_rate": 5.178247734138973e-07,
"loss": 1.438,
"step": 804
},
{
"epoch": 2.4248587570621467,
"grad_norm": 5.577856063842773,
"learning_rate": 5.172205438066465e-07,
"loss": 1.2982,
"step": 805
},
{
"epoch": 2.4278719397363466,
"grad_norm": 4.479556083679199,
"learning_rate": 5.166163141993957e-07,
"loss": 1.3887,
"step": 806
},
{
"epoch": 2.430885122410546,
"grad_norm": 4.324286460876465,
"learning_rate": 5.16012084592145e-07,
"loss": 1.3925,
"step": 807
},
{
"epoch": 2.4338983050847456,
"grad_norm": 4.672438621520996,
"learning_rate": 5.154078549848942e-07,
"loss": 1.2739,
"step": 808
},
{
"epoch": 2.4369114877589455,
"grad_norm": 6.77756929397583,
"learning_rate": 5.148036253776434e-07,
"loss": 1.4571,
"step": 809
},
{
"epoch": 2.439924670433145,
"grad_norm": 5.18680477142334,
"learning_rate": 5.141993957703927e-07,
"loss": 1.4374,
"step": 810
},
{
"epoch": 2.4429378531073445,
"grad_norm": 4.846097946166992,
"learning_rate": 5.13595166163142e-07,
"loss": 1.3009,
"step": 811
},
{
"epoch": 2.4459510357815444,
"grad_norm": 4.986232757568359,
"learning_rate": 5.129909365558913e-07,
"loss": 1.4091,
"step": 812
},
{
"epoch": 2.448964218455744,
"grad_norm": 4.635514259338379,
"learning_rate": 5.123867069486405e-07,
"loss": 1.4438,
"step": 813
},
{
"epoch": 2.4519774011299433,
"grad_norm": 4.925203323364258,
"learning_rate": 5.117824773413897e-07,
"loss": 1.3924,
"step": 814
},
{
"epoch": 2.4549905838041433,
"grad_norm": 5.646998405456543,
"learning_rate": 5.11178247734139e-07,
"loss": 1.4767,
"step": 815
},
{
"epoch": 2.4580037664783427,
"grad_norm": 4.781537055969238,
"learning_rate": 5.105740181268882e-07,
"loss": 1.3645,
"step": 816
},
{
"epoch": 2.461016949152542,
"grad_norm": 5.457485675811768,
"learning_rate": 5.099697885196374e-07,
"loss": 1.4672,
"step": 817
},
{
"epoch": 2.464030131826742,
"grad_norm": 4.934605598449707,
"learning_rate": 5.093655589123867e-07,
"loss": 1.3191,
"step": 818
},
{
"epoch": 2.4670433145009416,
"grad_norm": 5.155109405517578,
"learning_rate": 5.087613293051359e-07,
"loss": 1.323,
"step": 819
},
{
"epoch": 2.470056497175141,
"grad_norm": 6.053231239318848,
"learning_rate": 5.081570996978852e-07,
"loss": 1.3896,
"step": 820
},
{
"epoch": 2.473069679849341,
"grad_norm": 5.602438449859619,
"learning_rate": 5.075528700906344e-07,
"loss": 1.3991,
"step": 821
},
{
"epoch": 2.4760828625235405,
"grad_norm": 6.6072235107421875,
"learning_rate": 5.069486404833837e-07,
"loss": 1.3277,
"step": 822
},
{
"epoch": 2.47909604519774,
"grad_norm": 5.839221000671387,
"learning_rate": 5.063444108761328e-07,
"loss": 1.3465,
"step": 823
},
{
"epoch": 2.48210922787194,
"grad_norm": 5.864413261413574,
"learning_rate": 5.057401812688822e-07,
"loss": 1.3285,
"step": 824
},
{
"epoch": 2.4851224105461394,
"grad_norm": 4.84779691696167,
"learning_rate": 5.051359516616313e-07,
"loss": 1.379,
"step": 825
},
{
"epoch": 2.488135593220339,
"grad_norm": 4.586862564086914,
"learning_rate": 5.045317220543807e-07,
"loss": 1.3847,
"step": 826
},
{
"epoch": 2.4911487758945388,
"grad_norm": 6.357424736022949,
"learning_rate": 5.039274924471299e-07,
"loss": 1.51,
"step": 827
},
{
"epoch": 2.4941619585687382,
"grad_norm": 5.194407939910889,
"learning_rate": 5.033232628398791e-07,
"loss": 1.3787,
"step": 828
},
{
"epoch": 2.4971751412429377,
"grad_norm": 4.970487117767334,
"learning_rate": 5.027190332326285e-07,
"loss": 1.3422,
"step": 829
},
{
"epoch": 2.5001883239171376,
"grad_norm": 5.828860282897949,
"learning_rate": 5.021148036253776e-07,
"loss": 1.3608,
"step": 830
},
{
"epoch": 2.503201506591337,
"grad_norm": 4.613931179046631,
"learning_rate": 5.015105740181269e-07,
"loss": 1.373,
"step": 831
},
{
"epoch": 2.5062146892655366,
"grad_norm": 5.8415985107421875,
"learning_rate": 5.009063444108761e-07,
"loss": 1.3869,
"step": 832
},
{
"epoch": 2.5092278719397365,
"grad_norm": 5.232382297515869,
"learning_rate": 5.003021148036254e-07,
"loss": 1.2892,
"step": 833
},
{
"epoch": 2.512241054613936,
"grad_norm": 4.9899492263793945,
"learning_rate": 4.996978851963746e-07,
"loss": 1.3713,
"step": 834
},
{
"epoch": 2.5152542372881355,
"grad_norm": 5.91182279586792,
"learning_rate": 4.990936555891239e-07,
"loss": 1.3652,
"step": 835
},
{
"epoch": 2.518267419962335,
"grad_norm": 5.414116859436035,
"learning_rate": 4.984894259818731e-07,
"loss": 1.4621,
"step": 836
},
{
"epoch": 2.521280602636535,
"grad_norm": 6.548119068145752,
"learning_rate": 4.978851963746224e-07,
"loss": 1.527,
"step": 837
},
{
"epoch": 2.5242937853107343,
"grad_norm": 4.411587238311768,
"learning_rate": 4.972809667673716e-07,
"loss": 1.4071,
"step": 838
},
{
"epoch": 2.5273069679849343,
"grad_norm": 5.227695941925049,
"learning_rate": 4.966767371601208e-07,
"loss": 1.3503,
"step": 839
},
{
"epoch": 2.5303201506591337,
"grad_norm": 4.4931960105896,
"learning_rate": 4.960725075528701e-07,
"loss": 1.4042,
"step": 840
},
{
"epoch": 2.533333333333333,
"grad_norm": 5.4123406410217285,
"learning_rate": 4.954682779456193e-07,
"loss": 1.4937,
"step": 841
},
{
"epoch": 2.5363465160075327,
"grad_norm": 4.782264232635498,
"learning_rate": 4.948640483383685e-07,
"loss": 1.4335,
"step": 842
},
{
"epoch": 2.5393596986817326,
"grad_norm": 5.6392693519592285,
"learning_rate": 4.942598187311179e-07,
"loss": 1.3021,
"step": 843
},
{
"epoch": 2.542372881355932,
"grad_norm": 4.517958164215088,
"learning_rate": 4.936555891238671e-07,
"loss": 1.3187,
"step": 844
},
{
"epoch": 2.545386064030132,
"grad_norm": 5.458770751953125,
"learning_rate": 4.930513595166163e-07,
"loss": 1.4001,
"step": 845
},
{
"epoch": 2.5483992467043315,
"grad_norm": 4.532254695892334,
"learning_rate": 4.924471299093656e-07,
"loss": 1.3851,
"step": 846
},
{
"epoch": 2.551412429378531,
"grad_norm": 4.643901824951172,
"learning_rate": 4.918429003021148e-07,
"loss": 1.4623,
"step": 847
},
{
"epoch": 2.5544256120527304,
"grad_norm": 4.74837589263916,
"learning_rate": 4.91238670694864e-07,
"loss": 1.4195,
"step": 848
},
{
"epoch": 2.5574387947269304,
"grad_norm": 5.033172130584717,
"learning_rate": 4.906344410876133e-07,
"loss": 1.3541,
"step": 849
},
{
"epoch": 2.56045197740113,
"grad_norm": 5.355044364929199,
"learning_rate": 4.900302114803625e-07,
"loss": 1.3985,
"step": 850
},
{
"epoch": 2.5634651600753298,
"grad_norm": 5.097663879394531,
"learning_rate": 4.894259818731118e-07,
"loss": 1.4036,
"step": 851
},
{
"epoch": 2.5664783427495292,
"grad_norm": 4.603138446807861,
"learning_rate": 4.88821752265861e-07,
"loss": 1.3395,
"step": 852
},
{
"epoch": 2.5694915254237287,
"grad_norm": 4.3714070320129395,
"learning_rate": 4.882175226586102e-07,
"loss": 1.4366,
"step": 853
},
{
"epoch": 2.572504708097928,
"grad_norm": 5.633694648742676,
"learning_rate": 4.876132930513595e-07,
"loss": 1.456,
"step": 854
},
{
"epoch": 2.575517890772128,
"grad_norm": 5.291596412658691,
"learning_rate": 4.870090634441087e-07,
"loss": 1.4473,
"step": 855
},
{
"epoch": 2.5785310734463276,
"grad_norm": 4.71557092666626,
"learning_rate": 4.864048338368579e-07,
"loss": 1.361,
"step": 856
},
{
"epoch": 2.5815442561205275,
"grad_norm": 5.6157426834106445,
"learning_rate": 4.858006042296073e-07,
"loss": 1.3313,
"step": 857
},
{
"epoch": 2.584557438794727,
"grad_norm": 4.893215179443359,
"learning_rate": 4.851963746223565e-07,
"loss": 1.3823,
"step": 858
},
{
"epoch": 2.5875706214689265,
"grad_norm": 5.11285400390625,
"learning_rate": 4.845921450151057e-07,
"loss": 1.3059,
"step": 859
},
{
"epoch": 2.590583804143126,
"grad_norm": 5.747056007385254,
"learning_rate": 4.83987915407855e-07,
"loss": 1.4338,
"step": 860
},
{
"epoch": 2.593596986817326,
"grad_norm": 5.899341106414795,
"learning_rate": 4.833836858006042e-07,
"loss": 1.3658,
"step": 861
},
{
"epoch": 2.5966101694915253,
"grad_norm": 4.324906349182129,
"learning_rate": 4.827794561933535e-07,
"loss": 1.3912,
"step": 862
},
{
"epoch": 2.5996233521657253,
"grad_norm": 4.909964561462402,
"learning_rate": 4.821752265861027e-07,
"loss": 1.3919,
"step": 863
},
{
"epoch": 2.6026365348399247,
"grad_norm": 5.210026264190674,
"learning_rate": 4.815709969788519e-07,
"loss": 1.4038,
"step": 864
},
{
"epoch": 2.605649717514124,
"grad_norm": 5.408275604248047,
"learning_rate": 4.809667673716012e-07,
"loss": 1.4682,
"step": 865
},
{
"epoch": 2.6086629001883237,
"grad_norm": 5.552017688751221,
"learning_rate": 4.803625377643504e-07,
"loss": 1.2967,
"step": 866
},
{
"epoch": 2.6116760828625236,
"grad_norm": 7.799774169921875,
"learning_rate": 4.797583081570996e-07,
"loss": 1.426,
"step": 867
},
{
"epoch": 2.614689265536723,
"grad_norm": 6.884754180908203,
"learning_rate": 4.791540785498489e-07,
"loss": 1.3881,
"step": 868
},
{
"epoch": 2.617702448210923,
"grad_norm": 7.83217191696167,
"learning_rate": 4.785498489425981e-07,
"loss": 1.418,
"step": 869
},
{
"epoch": 2.6207156308851225,
"grad_norm": 5.122860431671143,
"learning_rate": 4.779456193353473e-07,
"loss": 1.3091,
"step": 870
},
{
"epoch": 2.623728813559322,
"grad_norm": 5.722933292388916,
"learning_rate": 4.773413897280967e-07,
"loss": 1.362,
"step": 871
},
{
"epoch": 2.6267419962335214,
"grad_norm": 4.507980823516846,
"learning_rate": 4.767371601208459e-07,
"loss": 1.4246,
"step": 872
},
{
"epoch": 2.6297551789077214,
"grad_norm": 5.295544624328613,
"learning_rate": 4.7613293051359515e-07,
"loss": 1.4139,
"step": 873
},
{
"epoch": 2.632768361581921,
"grad_norm": 4.21176815032959,
"learning_rate": 4.755287009063444e-07,
"loss": 1.3874,
"step": 874
},
{
"epoch": 2.6357815442561208,
"grad_norm": 4.981658935546875,
"learning_rate": 4.749244712990936e-07,
"loss": 1.3805,
"step": 875
},
{
"epoch": 2.6387947269303202,
"grad_norm": 4.418703556060791,
"learning_rate": 4.7432024169184286e-07,
"loss": 1.29,
"step": 876
},
{
"epoch": 2.6418079096045197,
"grad_norm": 6.650477409362793,
"learning_rate": 4.737160120845921e-07,
"loss": 1.4507,
"step": 877
},
{
"epoch": 2.644821092278719,
"grad_norm": 4.820608139038086,
"learning_rate": 4.731117824773413e-07,
"loss": 1.2432,
"step": 878
},
{
"epoch": 2.647834274952919,
"grad_norm": 5.358329772949219,
"learning_rate": 4.7250755287009056e-07,
"loss": 1.3021,
"step": 879
},
{
"epoch": 2.6508474576271186,
"grad_norm": 4.207238674163818,
"learning_rate": 4.719033232628399e-07,
"loss": 1.405,
"step": 880
},
{
"epoch": 2.6538606403013185,
"grad_norm": 5.843127250671387,
"learning_rate": 4.7129909365558914e-07,
"loss": 1.3403,
"step": 881
},
{
"epoch": 2.656873822975518,
"grad_norm": 6.023222923278809,
"learning_rate": 4.706948640483384e-07,
"loss": 1.4879,
"step": 882
},
{
"epoch": 2.6598870056497175,
"grad_norm": 5.1860857009887695,
"learning_rate": 4.700906344410876e-07,
"loss": 1.4778,
"step": 883
},
{
"epoch": 2.662900188323917,
"grad_norm": 5.576006889343262,
"learning_rate": 4.6948640483383684e-07,
"loss": 1.3816,
"step": 884
},
{
"epoch": 2.665913370998117,
"grad_norm": 5.2130045890808105,
"learning_rate": 4.688821752265861e-07,
"loss": 1.2855,
"step": 885
},
{
"epoch": 2.6689265536723163,
"grad_norm": 4.84255838394165,
"learning_rate": 4.682779456193353e-07,
"loss": 1.4034,
"step": 886
},
{
"epoch": 2.6719397363465163,
"grad_norm": 5.544811725616455,
"learning_rate": 4.6767371601208455e-07,
"loss": 1.3905,
"step": 887
},
{
"epoch": 2.6749529190207157,
"grad_norm": 4.909422874450684,
"learning_rate": 4.670694864048338e-07,
"loss": 1.3772,
"step": 888
},
{
"epoch": 2.6779661016949152,
"grad_norm": 6.080364227294922,
"learning_rate": 4.664652567975831e-07,
"loss": 1.387,
"step": 889
},
{
"epoch": 2.6809792843691147,
"grad_norm": 4.797935962677002,
"learning_rate": 4.658610271903323e-07,
"loss": 1.4102,
"step": 890
},
{
"epoch": 2.6839924670433146,
"grad_norm": 5.779572010040283,
"learning_rate": 4.6525679758308155e-07,
"loss": 1.4343,
"step": 891
},
{
"epoch": 2.687005649717514,
"grad_norm": 5.506649971008301,
"learning_rate": 4.646525679758308e-07,
"loss": 1.4558,
"step": 892
},
{
"epoch": 2.690018832391714,
"grad_norm": 5.0597052574157715,
"learning_rate": 4.6404833836858e-07,
"loss": 1.3169,
"step": 893
},
{
"epoch": 2.6930320150659135,
"grad_norm": 5.385110378265381,
"learning_rate": 4.6344410876132925e-07,
"loss": 1.3916,
"step": 894
},
{
"epoch": 2.696045197740113,
"grad_norm": 6.406915187835693,
"learning_rate": 4.6283987915407854e-07,
"loss": 1.3749,
"step": 895
},
{
"epoch": 2.6990583804143125,
"grad_norm": 5.116516590118408,
"learning_rate": 4.622356495468278e-07,
"loss": 1.3157,
"step": 896
},
{
"epoch": 2.7020715630885124,
"grad_norm": 5.402820110321045,
"learning_rate": 4.61631419939577e-07,
"loss": 1.5401,
"step": 897
},
{
"epoch": 2.705084745762712,
"grad_norm": 5.761125564575195,
"learning_rate": 4.610271903323263e-07,
"loss": 1.3589,
"step": 898
},
{
"epoch": 2.7080979284369113,
"grad_norm": 5.445271015167236,
"learning_rate": 4.6042296072507554e-07,
"loss": 1.3288,
"step": 899
},
{
"epoch": 2.7111111111111112,
"grad_norm": 4.508528709411621,
"learning_rate": 4.5981873111782477e-07,
"loss": 1.3436,
"step": 900
},
{
"epoch": 2.7141242937853107,
"grad_norm": 4.843202590942383,
"learning_rate": 4.59214501510574e-07,
"loss": 1.4008,
"step": 901
},
{
"epoch": 2.71713747645951,
"grad_norm": 4.8625335693359375,
"learning_rate": 4.5861027190332324e-07,
"loss": 1.4299,
"step": 902
},
{
"epoch": 2.72015065913371,
"grad_norm": 5.369333267211914,
"learning_rate": 4.580060422960725e-07,
"loss": 1.4505,
"step": 903
},
{
"epoch": 2.7231638418079096,
"grad_norm": 6.931520462036133,
"learning_rate": 4.574018126888217e-07,
"loss": 1.3121,
"step": 904
},
{
"epoch": 2.726177024482109,
"grad_norm": 6.4634623527526855,
"learning_rate": 4.5679758308157095e-07,
"loss": 1.3854,
"step": 905
},
{
"epoch": 2.729190207156309,
"grad_norm": 5.996848106384277,
"learning_rate": 4.561933534743202e-07,
"loss": 1.348,
"step": 906
},
{
"epoch": 2.7322033898305085,
"grad_norm": 5.70857048034668,
"learning_rate": 4.5558912386706947e-07,
"loss": 1.2956,
"step": 907
},
{
"epoch": 2.735216572504708,
"grad_norm": 5.584412097930908,
"learning_rate": 4.549848942598187e-07,
"loss": 1.379,
"step": 908
},
{
"epoch": 2.738229755178908,
"grad_norm": 6.666832447052002,
"learning_rate": 4.5438066465256794e-07,
"loss": 1.4878,
"step": 909
},
{
"epoch": 2.7412429378531074,
"grad_norm": 5.557536602020264,
"learning_rate": 4.5377643504531723e-07,
"loss": 1.3061,
"step": 910
},
{
"epoch": 2.744256120527307,
"grad_norm": 6.849345684051514,
"learning_rate": 4.5317220543806647e-07,
"loss": 1.547,
"step": 911
},
{
"epoch": 2.7472693032015068,
"grad_norm": 5.811504364013672,
"learning_rate": 4.525679758308157e-07,
"loss": 1.4129,
"step": 912
},
{
"epoch": 2.7502824858757062,
"grad_norm": 6.68612003326416,
"learning_rate": 4.5196374622356494e-07,
"loss": 1.3288,
"step": 913
},
{
"epoch": 2.7532956685499057,
"grad_norm": 5.305330753326416,
"learning_rate": 4.5135951661631417e-07,
"loss": 1.407,
"step": 914
},
{
"epoch": 2.7563088512241056,
"grad_norm": 5.111266613006592,
"learning_rate": 4.507552870090634e-07,
"loss": 1.3197,
"step": 915
},
{
"epoch": 2.759322033898305,
"grad_norm": 5.044455051422119,
"learning_rate": 4.501510574018127e-07,
"loss": 1.3481,
"step": 916
},
{
"epoch": 2.7623352165725046,
"grad_norm": 5.4864091873168945,
"learning_rate": 4.4954682779456193e-07,
"loss": 1.4862,
"step": 917
},
{
"epoch": 2.7653483992467045,
"grad_norm": 5.183647632598877,
"learning_rate": 4.4894259818731117e-07,
"loss": 1.4012,
"step": 918
},
{
"epoch": 2.768361581920904,
"grad_norm": 5.264411926269531,
"learning_rate": 4.483383685800604e-07,
"loss": 1.4432,
"step": 919
},
{
"epoch": 2.7713747645951035,
"grad_norm": 5.036288738250732,
"learning_rate": 4.4773413897280964e-07,
"loss": 1.4567,
"step": 920
},
{
"epoch": 2.774387947269303,
"grad_norm": 4.618870735168457,
"learning_rate": 4.471299093655589e-07,
"loss": 1.3392,
"step": 921
},
{
"epoch": 2.777401129943503,
"grad_norm": 5.67301607131958,
"learning_rate": 4.465256797583081e-07,
"loss": 1.3805,
"step": 922
},
{
"epoch": 2.7804143126177023,
"grad_norm": 6.1921706199646,
"learning_rate": 4.4592145015105735e-07,
"loss": 1.2438,
"step": 923
},
{
"epoch": 2.7834274952919023,
"grad_norm": 4.661489963531494,
"learning_rate": 4.453172205438066e-07,
"loss": 1.323,
"step": 924
},
{
"epoch": 2.7864406779661017,
"grad_norm": 5.9292216300964355,
"learning_rate": 4.447129909365559e-07,
"loss": 1.3986,
"step": 925
},
{
"epoch": 2.789453860640301,
"grad_norm": 4.722766876220703,
"learning_rate": 4.4410876132930516e-07,
"loss": 1.4888,
"step": 926
},
{
"epoch": 2.7924670433145007,
"grad_norm": 5.00396203994751,
"learning_rate": 4.435045317220544e-07,
"loss": 1.4067,
"step": 927
},
{
"epoch": 2.7954802259887006,
"grad_norm": 5.182219505310059,
"learning_rate": 4.4290030211480363e-07,
"loss": 1.337,
"step": 928
},
{
"epoch": 2.7984934086629,
"grad_norm": 5.727806091308594,
"learning_rate": 4.4229607250755286e-07,
"loss": 1.3156,
"step": 929
},
{
"epoch": 2.8015065913371,
"grad_norm": 5.534318447113037,
"learning_rate": 4.416918429003021e-07,
"loss": 1.3646,
"step": 930
},
{
"epoch": 2.8045197740112995,
"grad_norm": 4.730491638183594,
"learning_rate": 4.4108761329305134e-07,
"loss": 1.3839,
"step": 931
},
{
"epoch": 2.807532956685499,
"grad_norm": 4.715068817138672,
"learning_rate": 4.4048338368580057e-07,
"loss": 1.3194,
"step": 932
},
{
"epoch": 2.8105461393596984,
"grad_norm": 4.534972667694092,
"learning_rate": 4.398791540785498e-07,
"loss": 1.3764,
"step": 933
},
{
"epoch": 2.8135593220338984,
"grad_norm": 4.85308313369751,
"learning_rate": 4.3927492447129904e-07,
"loss": 1.3973,
"step": 934
},
{
"epoch": 2.816572504708098,
"grad_norm": 5.348034858703613,
"learning_rate": 4.3867069486404833e-07,
"loss": 1.3229,
"step": 935
},
{
"epoch": 2.8195856873822978,
"grad_norm": 6.930526256561279,
"learning_rate": 4.3806646525679757e-07,
"loss": 1.4855,
"step": 936
},
{
"epoch": 2.8225988700564972,
"grad_norm": 5.733300685882568,
"learning_rate": 4.374622356495468e-07,
"loss": 1.3428,
"step": 937
},
{
"epoch": 2.8256120527306967,
"grad_norm": 4.497043609619141,
"learning_rate": 4.3685800604229604e-07,
"loss": 1.2583,
"step": 938
},
{
"epoch": 2.828625235404896,
"grad_norm": 5.137788772583008,
"learning_rate": 4.3625377643504527e-07,
"loss": 1.3998,
"step": 939
},
{
"epoch": 2.831638418079096,
"grad_norm": 5.27037239074707,
"learning_rate": 4.3564954682779456e-07,
"loss": 1.408,
"step": 940
},
{
"epoch": 2.8346516007532956,
"grad_norm": 5.4238152503967285,
"learning_rate": 4.350453172205438e-07,
"loss": 1.4005,
"step": 941
},
{
"epoch": 2.8376647834274955,
"grad_norm": 5.701737880706787,
"learning_rate": 4.3444108761329303e-07,
"loss": 1.3428,
"step": 942
},
{
"epoch": 2.840677966101695,
"grad_norm": 4.339885711669922,
"learning_rate": 4.3383685800604227e-07,
"loss": 1.4307,
"step": 943
},
{
"epoch": 2.8436911487758945,
"grad_norm": 5.742118835449219,
"learning_rate": 4.3323262839879155e-07,
"loss": 1.4677,
"step": 944
},
{
"epoch": 2.846704331450094,
"grad_norm": 5.369758605957031,
"learning_rate": 4.326283987915408e-07,
"loss": 1.3123,
"step": 945
},
{
"epoch": 2.849717514124294,
"grad_norm": 4.570165634155273,
"learning_rate": 4.3202416918429e-07,
"loss": 1.523,
"step": 946
},
{
"epoch": 2.8527306967984933,
"grad_norm": 5.12955379486084,
"learning_rate": 4.3141993957703926e-07,
"loss": 1.2585,
"step": 947
},
{
"epoch": 2.8557438794726933,
"grad_norm": 5.771577835083008,
"learning_rate": 4.308157099697885e-07,
"loss": 1.161,
"step": 948
},
{
"epoch": 2.8587570621468927,
"grad_norm": 5.594604015350342,
"learning_rate": 4.3021148036253773e-07,
"loss": 1.3644,
"step": 949
},
{
"epoch": 2.861770244821092,
"grad_norm": 5.8950700759887695,
"learning_rate": 4.2960725075528697e-07,
"loss": 1.3926,
"step": 950
},
{
"epoch": 2.8647834274952917,
"grad_norm": 6.498231410980225,
"learning_rate": 4.290030211480362e-07,
"loss": 1.3941,
"step": 951
},
{
"epoch": 2.8677966101694916,
"grad_norm": 4.38367223739624,
"learning_rate": 4.2839879154078544e-07,
"loss": 1.3824,
"step": 952
},
{
"epoch": 2.870809792843691,
"grad_norm": 6.300016403198242,
"learning_rate": 4.2779456193353473e-07,
"loss": 1.3675,
"step": 953
},
{
"epoch": 2.873822975517891,
"grad_norm": 5.853883266448975,
"learning_rate": 4.2719033232628396e-07,
"loss": 1.4628,
"step": 954
},
{
"epoch": 2.8768361581920905,
"grad_norm": 4.957842826843262,
"learning_rate": 4.2658610271903325e-07,
"loss": 1.4033,
"step": 955
},
{
"epoch": 2.87984934086629,
"grad_norm": 4.800219535827637,
"learning_rate": 4.259818731117825e-07,
"loss": 1.2881,
"step": 956
},
{
"epoch": 2.8828625235404894,
"grad_norm": 5.728854179382324,
"learning_rate": 4.253776435045317e-07,
"loss": 1.39,
"step": 957
},
{
"epoch": 2.8858757062146894,
"grad_norm": 5.591170310974121,
"learning_rate": 4.2477341389728096e-07,
"loss": 1.3108,
"step": 958
},
{
"epoch": 2.888888888888889,
"grad_norm": 5.233771800994873,
"learning_rate": 4.241691842900302e-07,
"loss": 1.3804,
"step": 959
},
{
"epoch": 2.8919020715630888,
"grad_norm": 4.858612060546875,
"learning_rate": 4.2356495468277943e-07,
"loss": 1.369,
"step": 960
},
{
"epoch": 2.8949152542372882,
"grad_norm": 6.213875770568848,
"learning_rate": 4.2296072507552866e-07,
"loss": 1.3103,
"step": 961
},
{
"epoch": 2.8979284369114877,
"grad_norm": 5.499582290649414,
"learning_rate": 4.2235649546827795e-07,
"loss": 1.4543,
"step": 962
},
{
"epoch": 2.900941619585687,
"grad_norm": 4.72174072265625,
"learning_rate": 4.217522658610272e-07,
"loss": 1.3417,
"step": 963
},
{
"epoch": 2.903954802259887,
"grad_norm": 5.060640335083008,
"learning_rate": 4.211480362537764e-07,
"loss": 1.3713,
"step": 964
},
{
"epoch": 2.9069679849340866,
"grad_norm": 5.321628570556641,
"learning_rate": 4.2054380664652566e-07,
"loss": 1.3485,
"step": 965
},
{
"epoch": 2.9099811676082865,
"grad_norm": 6.256387233734131,
"learning_rate": 4.199395770392749e-07,
"loss": 1.4791,
"step": 966
},
{
"epoch": 2.912994350282486,
"grad_norm": 4.677583694458008,
"learning_rate": 4.1933534743202413e-07,
"loss": 1.4334,
"step": 967
},
{
"epoch": 2.9160075329566855,
"grad_norm": 4.438000679016113,
"learning_rate": 4.1873111782477336e-07,
"loss": 1.3218,
"step": 968
},
{
"epoch": 2.919020715630885,
"grad_norm": 5.72012996673584,
"learning_rate": 4.181268882175226e-07,
"loss": 1.5547,
"step": 969
},
{
"epoch": 2.922033898305085,
"grad_norm": 5.33144474029541,
"learning_rate": 4.1752265861027184e-07,
"loss": 1.4333,
"step": 970
},
{
"epoch": 2.9250470809792843,
"grad_norm": 4.570855140686035,
"learning_rate": 4.169184290030212e-07,
"loss": 1.4132,
"step": 971
},
{
"epoch": 2.9280602636534843,
"grad_norm": 5.121436595916748,
"learning_rate": 4.163141993957704e-07,
"loss": 1.414,
"step": 972
},
{
"epoch": 2.9310734463276837,
"grad_norm": 5.1723222732543945,
"learning_rate": 4.1570996978851965e-07,
"loss": 1.3499,
"step": 973
},
{
"epoch": 2.934086629001883,
"grad_norm": 4.78765344619751,
"learning_rate": 4.151057401812689e-07,
"loss": 1.2727,
"step": 974
},
{
"epoch": 2.9370998116760827,
"grad_norm": 5.11204195022583,
"learning_rate": 4.145015105740181e-07,
"loss": 1.3183,
"step": 975
},
{
"epoch": 2.9401129943502826,
"grad_norm": 5.006422519683838,
"learning_rate": 4.1389728096676735e-07,
"loss": 1.3286,
"step": 976
},
{
"epoch": 2.943126177024482,
"grad_norm": 5.531855583190918,
"learning_rate": 4.132930513595166e-07,
"loss": 1.3885,
"step": 977
},
{
"epoch": 2.9461393596986816,
"grad_norm": 4.342312335968018,
"learning_rate": 4.126888217522658e-07,
"loss": 1.2971,
"step": 978
},
{
"epoch": 2.9491525423728815,
"grad_norm": 5.590865612030029,
"learning_rate": 4.1208459214501506e-07,
"loss": 1.4025,
"step": 979
},
{
"epoch": 2.952165725047081,
"grad_norm": 5.830648899078369,
"learning_rate": 4.1148036253776435e-07,
"loss": 1.4031,
"step": 980
},
{
"epoch": 2.9551789077212804,
"grad_norm": 4.93297815322876,
"learning_rate": 4.108761329305136e-07,
"loss": 1.2535,
"step": 981
},
{
"epoch": 2.9581920903954804,
"grad_norm": 5.593379497528076,
"learning_rate": 4.102719033232628e-07,
"loss": 1.2898,
"step": 982
},
{
"epoch": 2.96120527306968,
"grad_norm": 5.680592060089111,
"learning_rate": 4.0966767371601206e-07,
"loss": 1.3898,
"step": 983
},
{
"epoch": 2.9642184557438793,
"grad_norm": 7.401136875152588,
"learning_rate": 4.090634441087613e-07,
"loss": 1.4972,
"step": 984
},
{
"epoch": 2.9672316384180792,
"grad_norm": 5.317058086395264,
"learning_rate": 4.0845921450151053e-07,
"loss": 1.3956,
"step": 985
},
{
"epoch": 2.9702448210922787,
"grad_norm": 4.717957496643066,
"learning_rate": 4.078549848942598e-07,
"loss": 1.3377,
"step": 986
},
{
"epoch": 2.973258003766478,
"grad_norm": 5.769641876220703,
"learning_rate": 4.0725075528700905e-07,
"loss": 1.3407,
"step": 987
},
{
"epoch": 2.976271186440678,
"grad_norm": 7.250093460083008,
"learning_rate": 4.066465256797583e-07,
"loss": 1.4534,
"step": 988
},
{
"epoch": 2.9792843691148776,
"grad_norm": 4.991407871246338,
"learning_rate": 4.060422960725076e-07,
"loss": 1.3179,
"step": 989
},
{
"epoch": 2.982297551789077,
"grad_norm": 4.5322980880737305,
"learning_rate": 4.054380664652568e-07,
"loss": 1.294,
"step": 990
},
{
"epoch": 2.985310734463277,
"grad_norm": 5.788262367248535,
"learning_rate": 4.0483383685800605e-07,
"loss": 1.3344,
"step": 991
},
{
"epoch": 2.9883239171374765,
"grad_norm": 5.948826789855957,
"learning_rate": 4.042296072507553e-07,
"loss": 1.3195,
"step": 992
},
{
"epoch": 2.991337099811676,
"grad_norm": 5.251885414123535,
"learning_rate": 4.036253776435045e-07,
"loss": 1.3783,
"step": 993
},
{
"epoch": 2.994350282485876,
"grad_norm": 5.911839962005615,
"learning_rate": 4.0302114803625375e-07,
"loss": 1.3643,
"step": 994
},
{
"epoch": 2.9973634651600753,
"grad_norm": 4.559868812561035,
"learning_rate": 4.02416918429003e-07,
"loss": 1.3504,
"step": 995
},
{
"epoch": 3.0,
"grad_norm": 4.937360763549805,
"learning_rate": 4.018126888217522e-07,
"loss": 1.2505,
"step": 996
},
{
"epoch": 3.0030131826741995,
"grad_norm": 6.265735626220703,
"learning_rate": 4.0120845921450146e-07,
"loss": 1.3716,
"step": 997
},
{
"epoch": 3.0060263653483994,
"grad_norm": 5.515944004058838,
"learning_rate": 4.006042296072507e-07,
"loss": 1.3743,
"step": 998
},
{
"epoch": 3.009039548022599,
"grad_norm": 4.209858417510986,
"learning_rate": 4e-07,
"loss": 1.3081,
"step": 999
},
{
"epoch": 3.0120527306967984,
"grad_norm": 4.728229522705078,
"learning_rate": 3.993957703927492e-07,
"loss": 1.3707,
"step": 1000
},
{
"epoch": 3.0150659133709983,
"grad_norm": 4.642185211181641,
"learning_rate": 3.987915407854985e-07,
"loss": 1.3156,
"step": 1001
},
{
"epoch": 3.0180790960451978,
"grad_norm": 4.265927791595459,
"learning_rate": 3.9818731117824774e-07,
"loss": 1.3349,
"step": 1002
},
{
"epoch": 3.0210922787193972,
"grad_norm": 4.554968357086182,
"learning_rate": 3.97583081570997e-07,
"loss": 1.4295,
"step": 1003
},
{
"epoch": 3.024105461393597,
"grad_norm": 6.320156097412109,
"learning_rate": 3.969788519637462e-07,
"loss": 1.4345,
"step": 1004
},
{
"epoch": 3.0271186440677966,
"grad_norm": 5.13922643661499,
"learning_rate": 3.9637462235649545e-07,
"loss": 1.414,
"step": 1005
},
{
"epoch": 3.030131826741996,
"grad_norm": 5.429257392883301,
"learning_rate": 3.957703927492447e-07,
"loss": 1.3601,
"step": 1006
},
{
"epoch": 3.033145009416196,
"grad_norm": 5.341658115386963,
"learning_rate": 3.951661631419939e-07,
"loss": 1.4078,
"step": 1007
},
{
"epoch": 3.0361581920903955,
"grad_norm": 5.2500433921813965,
"learning_rate": 3.945619335347432e-07,
"loss": 1.3362,
"step": 1008
},
{
"epoch": 3.039171374764595,
"grad_norm": 4.797705173492432,
"learning_rate": 3.9395770392749244e-07,
"loss": 1.3936,
"step": 1009
},
{
"epoch": 3.042184557438795,
"grad_norm": 6.012185573577881,
"learning_rate": 3.933534743202417e-07,
"loss": 1.5112,
"step": 1010
},
{
"epoch": 3.0451977401129944,
"grad_norm": 5.856369972229004,
"learning_rate": 3.927492447129909e-07,
"loss": 1.259,
"step": 1011
},
{
"epoch": 3.048210922787194,
"grad_norm": 4.568045616149902,
"learning_rate": 3.9214501510574015e-07,
"loss": 1.4061,
"step": 1012
},
{
"epoch": 3.0512241054613938,
"grad_norm": 5.07448673248291,
"learning_rate": 3.915407854984894e-07,
"loss": 1.4891,
"step": 1013
},
{
"epoch": 3.0542372881355933,
"grad_norm": 6.176218032836914,
"learning_rate": 3.909365558912386e-07,
"loss": 1.4924,
"step": 1014
},
{
"epoch": 3.0572504708097927,
"grad_norm": 5.526464939117432,
"learning_rate": 3.9033232628398786e-07,
"loss": 1.3928,
"step": 1015
},
{
"epoch": 3.0602636534839927,
"grad_norm": 5.0440192222595215,
"learning_rate": 3.897280966767371e-07,
"loss": 1.3097,
"step": 1016
},
{
"epoch": 3.063276836158192,
"grad_norm": 5.838516712188721,
"learning_rate": 3.8912386706948643e-07,
"loss": 1.3283,
"step": 1017
},
{
"epoch": 3.0662900188323916,
"grad_norm": 4.818419933319092,
"learning_rate": 3.8851963746223567e-07,
"loss": 1.3688,
"step": 1018
},
{
"epoch": 3.0693032015065915,
"grad_norm": 4.810229301452637,
"learning_rate": 3.879154078549849e-07,
"loss": 1.2191,
"step": 1019
},
{
"epoch": 3.072316384180791,
"grad_norm": 5.7492594718933105,
"learning_rate": 3.8731117824773414e-07,
"loss": 1.2977,
"step": 1020
},
{
"epoch": 3.0753295668549905,
"grad_norm": 4.548093318939209,
"learning_rate": 3.867069486404834e-07,
"loss": 1.3439,
"step": 1021
},
{
"epoch": 3.0783427495291904,
"grad_norm": 4.916570663452148,
"learning_rate": 3.861027190332326e-07,
"loss": 1.2329,
"step": 1022
},
{
"epoch": 3.08135593220339,
"grad_norm": 5.817365646362305,
"learning_rate": 3.8549848942598184e-07,
"loss": 1.3656,
"step": 1023
},
{
"epoch": 3.0843691148775894,
"grad_norm": 5.2817254066467285,
"learning_rate": 3.848942598187311e-07,
"loss": 1.3226,
"step": 1024
},
{
"epoch": 3.0873822975517893,
"grad_norm": 7.269449710845947,
"learning_rate": 3.842900302114803e-07,
"loss": 1.4445,
"step": 1025
},
{
"epoch": 3.0903954802259888,
"grad_norm": 5.553394317626953,
"learning_rate": 3.836858006042296e-07,
"loss": 1.2573,
"step": 1026
},
{
"epoch": 3.0934086629001882,
"grad_norm": 5.7581634521484375,
"learning_rate": 3.8308157099697884e-07,
"loss": 1.3977,
"step": 1027
},
{
"epoch": 3.096421845574388,
"grad_norm": 5.1239118576049805,
"learning_rate": 3.824773413897281e-07,
"loss": 1.417,
"step": 1028
},
{
"epoch": 3.0994350282485876,
"grad_norm": 5.5828094482421875,
"learning_rate": 3.818731117824773e-07,
"loss": 1.3681,
"step": 1029
},
{
"epoch": 3.102448210922787,
"grad_norm": 5.310403347015381,
"learning_rate": 3.8126888217522655e-07,
"loss": 1.3408,
"step": 1030
},
{
"epoch": 3.105461393596987,
"grad_norm": 4.930902481079102,
"learning_rate": 3.8066465256797583e-07,
"loss": 1.4034,
"step": 1031
},
{
"epoch": 3.1084745762711865,
"grad_norm": 4.8793840408325195,
"learning_rate": 3.8006042296072507e-07,
"loss": 1.3755,
"step": 1032
},
{
"epoch": 3.111487758945386,
"grad_norm": 5.215387344360352,
"learning_rate": 3.794561933534743e-07,
"loss": 1.2071,
"step": 1033
},
{
"epoch": 3.1145009416195855,
"grad_norm": 4.731071949005127,
"learning_rate": 3.7885196374622354e-07,
"loss": 1.2409,
"step": 1034
},
{
"epoch": 3.1175141242937854,
"grad_norm": 4.49262809753418,
"learning_rate": 3.7824773413897283e-07,
"loss": 1.3407,
"step": 1035
},
{
"epoch": 3.120527306967985,
"grad_norm": 6.764143943786621,
"learning_rate": 3.7764350453172206e-07,
"loss": 1.4285,
"step": 1036
},
{
"epoch": 3.123540489642185,
"grad_norm": 4.908986568450928,
"learning_rate": 3.770392749244713e-07,
"loss": 1.3841,
"step": 1037
},
{
"epoch": 3.1265536723163843,
"grad_norm": 5.709153652191162,
"learning_rate": 3.7643504531722054e-07,
"loss": 1.4646,
"step": 1038
},
{
"epoch": 3.1295668549905837,
"grad_norm": 5.032353401184082,
"learning_rate": 3.7583081570996977e-07,
"loss": 1.3858,
"step": 1039
},
{
"epoch": 3.132580037664783,
"grad_norm": 4.8558268547058105,
"learning_rate": 3.75226586102719e-07,
"loss": 1.256,
"step": 1040
},
{
"epoch": 3.135593220338983,
"grad_norm": 5.294119834899902,
"learning_rate": 3.7462235649546824e-07,
"loss": 1.3622,
"step": 1041
},
{
"epoch": 3.1386064030131826,
"grad_norm": 5.285462856292725,
"learning_rate": 3.740181268882175e-07,
"loss": 1.3741,
"step": 1042
},
{
"epoch": 3.1416195856873825,
"grad_norm": 5.080116271972656,
"learning_rate": 3.734138972809667e-07,
"loss": 1.3484,
"step": 1043
},
{
"epoch": 3.144632768361582,
"grad_norm": 6.381402492523193,
"learning_rate": 3.72809667673716e-07,
"loss": 1.4131,
"step": 1044
},
{
"epoch": 3.1476459510357815,
"grad_norm": 5.436094760894775,
"learning_rate": 3.7220543806646524e-07,
"loss": 1.4764,
"step": 1045
},
{
"epoch": 3.150659133709981,
"grad_norm": 5.257254600524902,
"learning_rate": 3.716012084592145e-07,
"loss": 1.3854,
"step": 1046
},
{
"epoch": 3.153672316384181,
"grad_norm": 4.668705463409424,
"learning_rate": 3.7099697885196376e-07,
"loss": 1.3192,
"step": 1047
},
{
"epoch": 3.1566854990583804,
"grad_norm": 6.393636703491211,
"learning_rate": 3.70392749244713e-07,
"loss": 1.522,
"step": 1048
},
{
"epoch": 3.15969868173258,
"grad_norm": 5.2552690505981445,
"learning_rate": 3.6978851963746223e-07,
"loss": 1.4212,
"step": 1049
},
{
"epoch": 3.1627118644067798,
"grad_norm": 5.195391654968262,
"learning_rate": 3.6918429003021147e-07,
"loss": 1.3469,
"step": 1050
},
{
"epoch": 3.1657250470809792,
"grad_norm": 5.488234996795654,
"learning_rate": 3.685800604229607e-07,
"loss": 1.3399,
"step": 1051
},
{
"epoch": 3.1687382297551787,
"grad_norm": 5.200152397155762,
"learning_rate": 3.6797583081570994e-07,
"loss": 1.3312,
"step": 1052
},
{
"epoch": 3.1717514124293786,
"grad_norm": 4.748150825500488,
"learning_rate": 3.673716012084592e-07,
"loss": 1.3778,
"step": 1053
},
{
"epoch": 3.174764595103578,
"grad_norm": 4.560179233551025,
"learning_rate": 3.6676737160120846e-07,
"loss": 1.3159,
"step": 1054
},
{
"epoch": 3.1777777777777776,
"grad_norm": 6.017602443695068,
"learning_rate": 3.661631419939577e-07,
"loss": 1.322,
"step": 1055
},
{
"epoch": 3.1807909604519775,
"grad_norm": 5.199182510375977,
"learning_rate": 3.6555891238670693e-07,
"loss": 1.3151,
"step": 1056
},
{
"epoch": 3.183804143126177,
"grad_norm": 4.5492401123046875,
"learning_rate": 3.6495468277945617e-07,
"loss": 1.2823,
"step": 1057
},
{
"epoch": 3.1868173258003765,
"grad_norm": 4.5472540855407715,
"learning_rate": 3.643504531722054e-07,
"loss": 1.3764,
"step": 1058
},
{
"epoch": 3.1898305084745764,
"grad_norm": 5.612013339996338,
"learning_rate": 3.6374622356495464e-07,
"loss": 1.5466,
"step": 1059
},
{
"epoch": 3.192843691148776,
"grad_norm": 4.775079727172852,
"learning_rate": 3.631419939577039e-07,
"loss": 1.3381,
"step": 1060
}
],
"logging_steps": 1,
"max_steps": 1660,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 10,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.3012958560280166e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}