EternalRecursion's picture
Training in progress, step 338, checkpoint
44138c4 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 50,
"global_step": 338,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.002962962962962963,
"grad_norm": 11.3371000289917,
"learning_rate": 0.0,
"loss": 1.3243,
"step": 1
},
{
"epoch": 0.005925925925925926,
"grad_norm": 12.801159858703613,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.5339,
"step": 2
},
{
"epoch": 0.008888888888888889,
"grad_norm": 10.644610404968262,
"learning_rate": 4.000000000000001e-06,
"loss": 1.367,
"step": 3
},
{
"epoch": 0.011851851851851851,
"grad_norm": 10.896141052246094,
"learning_rate": 6e-06,
"loss": 1.2596,
"step": 4
},
{
"epoch": 0.014814814814814815,
"grad_norm": 8.76422119140625,
"learning_rate": 8.000000000000001e-06,
"loss": 0.9669,
"step": 5
},
{
"epoch": 0.017777777777777778,
"grad_norm": 11.150997161865234,
"learning_rate": 1e-05,
"loss": 1.202,
"step": 6
},
{
"epoch": 0.02074074074074074,
"grad_norm": 13.492061614990234,
"learning_rate": 9.96996996996997e-06,
"loss": 1.0129,
"step": 7
},
{
"epoch": 0.023703703703703703,
"grad_norm": 10.329751968383789,
"learning_rate": 9.93993993993994e-06,
"loss": 0.8347,
"step": 8
},
{
"epoch": 0.02666666666666667,
"grad_norm": 7.28446626663208,
"learning_rate": 9.90990990990991e-06,
"loss": 0.5802,
"step": 9
},
{
"epoch": 0.02962962962962963,
"grad_norm": 6.310451030731201,
"learning_rate": 9.879879879879881e-06,
"loss": 0.5678,
"step": 10
},
{
"epoch": 0.03259259259259259,
"grad_norm": 4.07226037979126,
"learning_rate": 9.849849849849851e-06,
"loss": 0.4087,
"step": 11
},
{
"epoch": 0.035555555555555556,
"grad_norm": 5.995666980743408,
"learning_rate": 9.81981981981982e-06,
"loss": 0.5431,
"step": 12
},
{
"epoch": 0.03851851851851852,
"grad_norm": 2.8703126907348633,
"learning_rate": 9.78978978978979e-06,
"loss": 0.2719,
"step": 13
},
{
"epoch": 0.04148148148148148,
"grad_norm": 4.808892250061035,
"learning_rate": 9.75975975975976e-06,
"loss": 0.4298,
"step": 14
},
{
"epoch": 0.044444444444444446,
"grad_norm": 3.846687078475952,
"learning_rate": 9.729729729729732e-06,
"loss": 0.2783,
"step": 15
},
{
"epoch": 0.047407407407407405,
"grad_norm": 4.096401214599609,
"learning_rate": 9.699699699699701e-06,
"loss": 0.3686,
"step": 16
},
{
"epoch": 0.05037037037037037,
"grad_norm": 1.8531608581542969,
"learning_rate": 9.669669669669671e-06,
"loss": 0.3132,
"step": 17
},
{
"epoch": 0.05333333333333334,
"grad_norm": 1.7076753377914429,
"learning_rate": 9.63963963963964e-06,
"loss": 0.2203,
"step": 18
},
{
"epoch": 0.056296296296296296,
"grad_norm": 1.959383249282837,
"learning_rate": 9.60960960960961e-06,
"loss": 0.3382,
"step": 19
},
{
"epoch": 0.05925925925925926,
"grad_norm": 1.6060762405395508,
"learning_rate": 9.57957957957958e-06,
"loss": 0.3703,
"step": 20
},
{
"epoch": 0.06222222222222222,
"grad_norm": 1.372205376625061,
"learning_rate": 9.54954954954955e-06,
"loss": 0.2131,
"step": 21
},
{
"epoch": 0.06518518518518518,
"grad_norm": 2.090074062347412,
"learning_rate": 9.51951951951952e-06,
"loss": 0.3861,
"step": 22
},
{
"epoch": 0.06814814814814815,
"grad_norm": 1.5326591730117798,
"learning_rate": 9.489489489489491e-06,
"loss": 0.4017,
"step": 23
},
{
"epoch": 0.07111111111111111,
"grad_norm": 1.553800344467163,
"learning_rate": 9.45945945945946e-06,
"loss": 0.3871,
"step": 24
},
{
"epoch": 0.07407407407407407,
"grad_norm": 1.2676138877868652,
"learning_rate": 9.42942942942943e-06,
"loss": 0.2506,
"step": 25
},
{
"epoch": 0.07703703703703704,
"grad_norm": 1.4148956537246704,
"learning_rate": 9.3993993993994e-06,
"loss": 0.3275,
"step": 26
},
{
"epoch": 0.08,
"grad_norm": 1.628173589706421,
"learning_rate": 9.36936936936937e-06,
"loss": 0.3785,
"step": 27
},
{
"epoch": 0.08296296296296296,
"grad_norm": 1.551418662071228,
"learning_rate": 9.339339339339341e-06,
"loss": 0.4007,
"step": 28
},
{
"epoch": 0.08592592592592592,
"grad_norm": 1.2471089363098145,
"learning_rate": 9.30930930930931e-06,
"loss": 0.2917,
"step": 29
},
{
"epoch": 0.08888888888888889,
"grad_norm": 1.195343255996704,
"learning_rate": 9.27927927927928e-06,
"loss": 0.2419,
"step": 30
},
{
"epoch": 0.09185185185185185,
"grad_norm": 1.0216526985168457,
"learning_rate": 9.24924924924925e-06,
"loss": 0.1991,
"step": 31
},
{
"epoch": 0.09481481481481481,
"grad_norm": 0.6894762516021729,
"learning_rate": 9.21921921921922e-06,
"loss": 0.1065,
"step": 32
},
{
"epoch": 0.09777777777777778,
"grad_norm": 1.1006757020950317,
"learning_rate": 9.189189189189191e-06,
"loss": 0.1823,
"step": 33
},
{
"epoch": 0.10074074074074074,
"grad_norm": 1.1868857145309448,
"learning_rate": 9.15915915915916e-06,
"loss": 0.2261,
"step": 34
},
{
"epoch": 0.1037037037037037,
"grad_norm": 1.2749474048614502,
"learning_rate": 9.129129129129129e-06,
"loss": 0.3215,
"step": 35
},
{
"epoch": 0.10666666666666667,
"grad_norm": 1.1576004028320312,
"learning_rate": 9.0990990990991e-06,
"loss": 0.219,
"step": 36
},
{
"epoch": 0.10962962962962963,
"grad_norm": 1.1340727806091309,
"learning_rate": 9.06906906906907e-06,
"loss": 0.2596,
"step": 37
},
{
"epoch": 0.11259259259259259,
"grad_norm": 1.425715684890747,
"learning_rate": 9.03903903903904e-06,
"loss": 0.2553,
"step": 38
},
{
"epoch": 0.11555555555555555,
"grad_norm": 1.0939496755599976,
"learning_rate": 9.00900900900901e-06,
"loss": 0.1856,
"step": 39
},
{
"epoch": 0.11851851851851852,
"grad_norm": 1.0559018850326538,
"learning_rate": 8.97897897897898e-06,
"loss": 0.1976,
"step": 40
},
{
"epoch": 0.12148148148148148,
"grad_norm": 1.3287632465362549,
"learning_rate": 8.94894894894895e-06,
"loss": 0.283,
"step": 41
},
{
"epoch": 0.12444444444444444,
"grad_norm": 1.6757111549377441,
"learning_rate": 8.91891891891892e-06,
"loss": 0.3562,
"step": 42
},
{
"epoch": 0.1274074074074074,
"grad_norm": 0.9322190880775452,
"learning_rate": 8.888888888888888e-06,
"loss": 0.1689,
"step": 43
},
{
"epoch": 0.13037037037037036,
"grad_norm": 1.035520315170288,
"learning_rate": 8.85885885885886e-06,
"loss": 0.1939,
"step": 44
},
{
"epoch": 0.13333333333333333,
"grad_norm": 1.4078480005264282,
"learning_rate": 8.82882882882883e-06,
"loss": 0.2571,
"step": 45
},
{
"epoch": 0.1362962962962963,
"grad_norm": 1.2980031967163086,
"learning_rate": 8.798798798798799e-06,
"loss": 0.2919,
"step": 46
},
{
"epoch": 0.13925925925925925,
"grad_norm": 1.7783174514770508,
"learning_rate": 8.768768768768769e-06,
"loss": 0.3939,
"step": 47
},
{
"epoch": 0.14222222222222222,
"grad_norm": 0.9576874375343323,
"learning_rate": 8.738738738738739e-06,
"loss": 0.151,
"step": 48
},
{
"epoch": 0.1451851851851852,
"grad_norm": 1.269023060798645,
"learning_rate": 8.70870870870871e-06,
"loss": 0.2183,
"step": 49
},
{
"epoch": 0.14814814814814814,
"grad_norm": 0.9194425940513611,
"learning_rate": 8.67867867867868e-06,
"loss": 0.1784,
"step": 50
},
{
"epoch": 0.14814814814814814,
"eval_loss": 0.2179427146911621,
"eval_runtime": 26.264,
"eval_samples_per_second": 22.845,
"eval_steps_per_second": 11.422,
"step": 50
},
{
"epoch": 0.1511111111111111,
"grad_norm": 1.4745863676071167,
"learning_rate": 8.64864864864865e-06,
"loss": 0.3137,
"step": 51
},
{
"epoch": 0.15407407407407409,
"grad_norm": 1.3270994424819946,
"learning_rate": 8.618618618618619e-06,
"loss": 0.2654,
"step": 52
},
{
"epoch": 0.15703703703703703,
"grad_norm": 1.2774759531021118,
"learning_rate": 8.588588588588589e-06,
"loss": 0.2876,
"step": 53
},
{
"epoch": 0.16,
"grad_norm": 1.5174992084503174,
"learning_rate": 8.55855855855856e-06,
"loss": 0.2627,
"step": 54
},
{
"epoch": 0.16296296296296298,
"grad_norm": 1.633291244506836,
"learning_rate": 8.52852852852853e-06,
"loss": 0.1577,
"step": 55
},
{
"epoch": 0.16592592592592592,
"grad_norm": 1.2609471082687378,
"learning_rate": 8.4984984984985e-06,
"loss": 0.2188,
"step": 56
},
{
"epoch": 0.1688888888888889,
"grad_norm": 1.1018271446228027,
"learning_rate": 8.46846846846847e-06,
"loss": 0.1847,
"step": 57
},
{
"epoch": 0.17185185185185184,
"grad_norm": 5.128139972686768,
"learning_rate": 8.438438438438439e-06,
"loss": 0.1202,
"step": 58
},
{
"epoch": 0.1748148148148148,
"grad_norm": 1.2842433452606201,
"learning_rate": 8.408408408408409e-06,
"loss": 0.2561,
"step": 59
},
{
"epoch": 0.17777777777777778,
"grad_norm": 1.0647783279418945,
"learning_rate": 8.378378378378378e-06,
"loss": 0.2169,
"step": 60
},
{
"epoch": 0.18074074074074073,
"grad_norm": 1.1153974533081055,
"learning_rate": 8.348348348348348e-06,
"loss": 0.2161,
"step": 61
},
{
"epoch": 0.1837037037037037,
"grad_norm": 1.042328953742981,
"learning_rate": 8.31831831831832e-06,
"loss": 0.1679,
"step": 62
},
{
"epoch": 0.18666666666666668,
"grad_norm": 1.312528133392334,
"learning_rate": 8.288288288288289e-06,
"loss": 0.2831,
"step": 63
},
{
"epoch": 0.18962962962962962,
"grad_norm": 1.0079033374786377,
"learning_rate": 8.258258258258259e-06,
"loss": 0.2167,
"step": 64
},
{
"epoch": 0.1925925925925926,
"grad_norm": 1.1558252573013306,
"learning_rate": 8.228228228228229e-06,
"loss": 0.228,
"step": 65
},
{
"epoch": 0.19555555555555557,
"grad_norm": 1.2176589965820312,
"learning_rate": 8.198198198198198e-06,
"loss": 0.1934,
"step": 66
},
{
"epoch": 0.1985185185185185,
"grad_norm": 1.2216565608978271,
"learning_rate": 8.16816816816817e-06,
"loss": 0.2861,
"step": 67
},
{
"epoch": 0.20148148148148148,
"grad_norm": 1.416286587715149,
"learning_rate": 8.13813813813814e-06,
"loss": 0.3126,
"step": 68
},
{
"epoch": 0.20444444444444446,
"grad_norm": 1.2522228956222534,
"learning_rate": 8.108108108108109e-06,
"loss": 0.2273,
"step": 69
},
{
"epoch": 0.2074074074074074,
"grad_norm": 0.9117985963821411,
"learning_rate": 8.078078078078079e-06,
"loss": 0.1377,
"step": 70
},
{
"epoch": 0.21037037037037037,
"grad_norm": 1.2130306959152222,
"learning_rate": 8.048048048048048e-06,
"loss": 0.2451,
"step": 71
},
{
"epoch": 0.21333333333333335,
"grad_norm": 1.5322959423065186,
"learning_rate": 8.018018018018018e-06,
"loss": 0.2618,
"step": 72
},
{
"epoch": 0.2162962962962963,
"grad_norm": 0.9832788109779358,
"learning_rate": 7.987987987987988e-06,
"loss": 0.1565,
"step": 73
},
{
"epoch": 0.21925925925925926,
"grad_norm": 0.8861773014068604,
"learning_rate": 7.95795795795796e-06,
"loss": 0.1292,
"step": 74
},
{
"epoch": 0.2222222222222222,
"grad_norm": 1.2317291498184204,
"learning_rate": 7.927927927927929e-06,
"loss": 0.1915,
"step": 75
},
{
"epoch": 0.22518518518518518,
"grad_norm": 1.2152000665664673,
"learning_rate": 7.897897897897899e-06,
"loss": 0.1967,
"step": 76
},
{
"epoch": 0.22814814814814816,
"grad_norm": 1.282239317893982,
"learning_rate": 7.867867867867868e-06,
"loss": 0.2483,
"step": 77
},
{
"epoch": 0.2311111111111111,
"grad_norm": 1.4242349863052368,
"learning_rate": 7.837837837837838e-06,
"loss": 0.2421,
"step": 78
},
{
"epoch": 0.23407407407407407,
"grad_norm": 0.9982733130455017,
"learning_rate": 7.807807807807808e-06,
"loss": 0.1474,
"step": 79
},
{
"epoch": 0.23703703703703705,
"grad_norm": 1.3020929098129272,
"learning_rate": 7.77777777777778e-06,
"loss": 0.2243,
"step": 80
},
{
"epoch": 0.24,
"grad_norm": 1.045766830444336,
"learning_rate": 7.747747747747749e-06,
"loss": 0.2096,
"step": 81
},
{
"epoch": 0.24296296296296296,
"grad_norm": 1.095937728881836,
"learning_rate": 7.717717717717719e-06,
"loss": 0.166,
"step": 82
},
{
"epoch": 0.24592592592592594,
"grad_norm": 1.053566575050354,
"learning_rate": 7.687687687687688e-06,
"loss": 0.156,
"step": 83
},
{
"epoch": 0.24888888888888888,
"grad_norm": 1.3010492324829102,
"learning_rate": 7.657657657657658e-06,
"loss": 0.2308,
"step": 84
},
{
"epoch": 0.2518518518518518,
"grad_norm": 1.3565430641174316,
"learning_rate": 7.6276276276276285e-06,
"loss": 0.2598,
"step": 85
},
{
"epoch": 0.2548148148148148,
"grad_norm": 0.9727479219436646,
"learning_rate": 7.597597597597598e-06,
"loss": 0.1833,
"step": 86
},
{
"epoch": 0.2577777777777778,
"grad_norm": 1.8599858283996582,
"learning_rate": 7.567567567567569e-06,
"loss": 0.3501,
"step": 87
},
{
"epoch": 0.2607407407407407,
"grad_norm": 1.3253231048583984,
"learning_rate": 7.5375375375375385e-06,
"loss": 0.2599,
"step": 88
},
{
"epoch": 0.2637037037037037,
"grad_norm": 0.9897385835647583,
"learning_rate": 7.507507507507507e-06,
"loss": 0.1556,
"step": 89
},
{
"epoch": 0.26666666666666666,
"grad_norm": 1.1445815563201904,
"learning_rate": 7.477477477477479e-06,
"loss": 0.1967,
"step": 90
},
{
"epoch": 0.2696296296296296,
"grad_norm": 1.2150932550430298,
"learning_rate": 7.447447447447448e-06,
"loss": 0.2604,
"step": 91
},
{
"epoch": 0.2725925925925926,
"grad_norm": 1.0080653429031372,
"learning_rate": 7.417417417417418e-06,
"loss": 0.169,
"step": 92
},
{
"epoch": 0.27555555555555555,
"grad_norm": 0.8388074040412903,
"learning_rate": 7.387387387387388e-06,
"loss": 0.1234,
"step": 93
},
{
"epoch": 0.2785185185185185,
"grad_norm": 1.3226969242095947,
"learning_rate": 7.3573573573573575e-06,
"loss": 0.3036,
"step": 94
},
{
"epoch": 0.2814814814814815,
"grad_norm": 1.1742416620254517,
"learning_rate": 7.327327327327328e-06,
"loss": 0.2219,
"step": 95
},
{
"epoch": 0.28444444444444444,
"grad_norm": 1.2756623029708862,
"learning_rate": 7.297297297297298e-06,
"loss": 0.2256,
"step": 96
},
{
"epoch": 0.2874074074074074,
"grad_norm": 1.2642868757247925,
"learning_rate": 7.267267267267268e-06,
"loss": 0.2593,
"step": 97
},
{
"epoch": 0.2903703703703704,
"grad_norm": 1.247946858406067,
"learning_rate": 7.237237237237238e-06,
"loss": 0.193,
"step": 98
},
{
"epoch": 0.29333333333333333,
"grad_norm": 1.4509199857711792,
"learning_rate": 7.207207207207208e-06,
"loss": 0.3564,
"step": 99
},
{
"epoch": 0.2962962962962963,
"grad_norm": 1.0693156719207764,
"learning_rate": 7.177177177177178e-06,
"loss": 0.2287,
"step": 100
},
{
"epoch": 0.2962962962962963,
"eval_loss": 0.19448572397232056,
"eval_runtime": 23.8735,
"eval_samples_per_second": 25.132,
"eval_steps_per_second": 12.566,
"step": 100
},
{
"epoch": 0.2992592592592593,
"grad_norm": 1.3502346277236938,
"learning_rate": 7.147147147147148e-06,
"loss": 0.1529,
"step": 101
},
{
"epoch": 0.3022222222222222,
"grad_norm": 1.2263582944869995,
"learning_rate": 7.117117117117117e-06,
"loss": 0.2126,
"step": 102
},
{
"epoch": 0.30518518518518517,
"grad_norm": 1.4411283731460571,
"learning_rate": 7.087087087087087e-06,
"loss": 0.2937,
"step": 103
},
{
"epoch": 0.30814814814814817,
"grad_norm": 1.1589494943618774,
"learning_rate": 7.057057057057057e-06,
"loss": 0.1865,
"step": 104
},
{
"epoch": 0.3111111111111111,
"grad_norm": 1.317421793937683,
"learning_rate": 7.027027027027028e-06,
"loss": 0.2869,
"step": 105
},
{
"epoch": 0.31407407407407406,
"grad_norm": 1.0805225372314453,
"learning_rate": 6.996996996996997e-06,
"loss": 0.1544,
"step": 106
},
{
"epoch": 0.31703703703703706,
"grad_norm": 1.4819189310073853,
"learning_rate": 6.966966966966967e-06,
"loss": 0.1942,
"step": 107
},
{
"epoch": 0.32,
"grad_norm": 1.0392121076583862,
"learning_rate": 6.936936936936938e-06,
"loss": 0.1886,
"step": 108
},
{
"epoch": 0.32296296296296295,
"grad_norm": 1.530296802520752,
"learning_rate": 6.906906906906907e-06,
"loss": 0.2398,
"step": 109
},
{
"epoch": 0.32592592592592595,
"grad_norm": 1.0972685813903809,
"learning_rate": 6.876876876876878e-06,
"loss": 0.2197,
"step": 110
},
{
"epoch": 0.3288888888888889,
"grad_norm": 1.4250812530517578,
"learning_rate": 6.846846846846848e-06,
"loss": 0.2369,
"step": 111
},
{
"epoch": 0.33185185185185184,
"grad_norm": 1.0383516550064087,
"learning_rate": 6.816816816816817e-06,
"loss": 0.1976,
"step": 112
},
{
"epoch": 0.3348148148148148,
"grad_norm": 0.9757740497589111,
"learning_rate": 6.786786786786788e-06,
"loss": 0.1687,
"step": 113
},
{
"epoch": 0.3377777777777778,
"grad_norm": 1.2417925596237183,
"learning_rate": 6.7567567567567575e-06,
"loss": 0.251,
"step": 114
},
{
"epoch": 0.34074074074074073,
"grad_norm": 1.1182583570480347,
"learning_rate": 6.726726726726728e-06,
"loss": 0.1992,
"step": 115
},
{
"epoch": 0.3437037037037037,
"grad_norm": 1.467090368270874,
"learning_rate": 6.696696696696697e-06,
"loss": 0.2976,
"step": 116
},
{
"epoch": 0.3466666666666667,
"grad_norm": 1.3952428102493286,
"learning_rate": 6.666666666666667e-06,
"loss": 0.1878,
"step": 117
},
{
"epoch": 0.3496296296296296,
"grad_norm": 1.5462948083877563,
"learning_rate": 6.636636636636637e-06,
"loss": 0.2699,
"step": 118
},
{
"epoch": 0.35259259259259257,
"grad_norm": 1.3345576524734497,
"learning_rate": 6.606606606606607e-06,
"loss": 0.2817,
"step": 119
},
{
"epoch": 0.35555555555555557,
"grad_norm": 1.076418161392212,
"learning_rate": 6.5765765765765775e-06,
"loss": 0.2011,
"step": 120
},
{
"epoch": 0.3585185185185185,
"grad_norm": 1.1570076942443848,
"learning_rate": 6.546546546546547e-06,
"loss": 0.2349,
"step": 121
},
{
"epoch": 0.36148148148148146,
"grad_norm": 0.9971967339515686,
"learning_rate": 6.516516516516517e-06,
"loss": 0.1879,
"step": 122
},
{
"epoch": 0.36444444444444446,
"grad_norm": 1.1504583358764648,
"learning_rate": 6.486486486486487e-06,
"loss": 0.1983,
"step": 123
},
{
"epoch": 0.3674074074074074,
"grad_norm": 1.6223655939102173,
"learning_rate": 6.456456456456457e-06,
"loss": 0.302,
"step": 124
},
{
"epoch": 0.37037037037037035,
"grad_norm": 1.222901463508606,
"learning_rate": 6.426426426426427e-06,
"loss": 0.2145,
"step": 125
},
{
"epoch": 0.37333333333333335,
"grad_norm": 1.4153494834899902,
"learning_rate": 6.396396396396397e-06,
"loss": 0.2699,
"step": 126
},
{
"epoch": 0.3762962962962963,
"grad_norm": 1.0600813627243042,
"learning_rate": 6.366366366366366e-06,
"loss": 0.1698,
"step": 127
},
{
"epoch": 0.37925925925925924,
"grad_norm": 0.9981789588928223,
"learning_rate": 6.336336336336338e-06,
"loss": 0.1644,
"step": 128
},
{
"epoch": 0.38222222222222224,
"grad_norm": 1.2153654098510742,
"learning_rate": 6.3063063063063065e-06,
"loss": 0.1686,
"step": 129
},
{
"epoch": 0.3851851851851852,
"grad_norm": 1.1575673818588257,
"learning_rate": 6.276276276276276e-06,
"loss": 0.1425,
"step": 130
},
{
"epoch": 0.38814814814814813,
"grad_norm": 1.3473142385482788,
"learning_rate": 6.246246246246247e-06,
"loss": 0.222,
"step": 131
},
{
"epoch": 0.39111111111111113,
"grad_norm": 1.2329224348068237,
"learning_rate": 6.2162162162162164e-06,
"loss": 0.1989,
"step": 132
},
{
"epoch": 0.3940740740740741,
"grad_norm": 1.3736624717712402,
"learning_rate": 6.186186186186187e-06,
"loss": 0.2583,
"step": 133
},
{
"epoch": 0.397037037037037,
"grad_norm": 1.344009518623352,
"learning_rate": 6.156156156156157e-06,
"loss": 0.2501,
"step": 134
},
{
"epoch": 0.4,
"grad_norm": 1.1183502674102783,
"learning_rate": 6.126126126126126e-06,
"loss": 0.2099,
"step": 135
},
{
"epoch": 0.40296296296296297,
"grad_norm": 1.0197062492370605,
"learning_rate": 6.096096096096097e-06,
"loss": 0.1413,
"step": 136
},
{
"epoch": 0.4059259259259259,
"grad_norm": 1.2187565565109253,
"learning_rate": 6.066066066066067e-06,
"loss": 0.1505,
"step": 137
},
{
"epoch": 0.4088888888888889,
"grad_norm": 1.1941757202148438,
"learning_rate": 6.036036036036037e-06,
"loss": 0.1716,
"step": 138
},
{
"epoch": 0.41185185185185186,
"grad_norm": 1.1741786003112793,
"learning_rate": 6.006006006006007e-06,
"loss": 0.2038,
"step": 139
},
{
"epoch": 0.4148148148148148,
"grad_norm": 1.9440799951553345,
"learning_rate": 5.975975975975976e-06,
"loss": 0.3251,
"step": 140
},
{
"epoch": 0.4177777777777778,
"grad_norm": 1.3958055973052979,
"learning_rate": 5.945945945945947e-06,
"loss": 0.2683,
"step": 141
},
{
"epoch": 0.42074074074074075,
"grad_norm": 1.2900551557540894,
"learning_rate": 5.915915915915916e-06,
"loss": 0.1459,
"step": 142
},
{
"epoch": 0.4237037037037037,
"grad_norm": 1.3513091802597046,
"learning_rate": 5.885885885885886e-06,
"loss": 0.2561,
"step": 143
},
{
"epoch": 0.4266666666666667,
"grad_norm": 1.291257381439209,
"learning_rate": 5.855855855855856e-06,
"loss": 0.2224,
"step": 144
},
{
"epoch": 0.42962962962962964,
"grad_norm": 1.3259387016296387,
"learning_rate": 5.825825825825826e-06,
"loss": 0.1657,
"step": 145
},
{
"epoch": 0.4325925925925926,
"grad_norm": 0.9156279563903809,
"learning_rate": 5.7957957957957965e-06,
"loss": 0.1085,
"step": 146
},
{
"epoch": 0.43555555555555553,
"grad_norm": 1.070117712020874,
"learning_rate": 5.765765765765766e-06,
"loss": 0.166,
"step": 147
},
{
"epoch": 0.43851851851851853,
"grad_norm": 1.1252092123031616,
"learning_rate": 5.735735735735736e-06,
"loss": 0.2035,
"step": 148
},
{
"epoch": 0.4414814814814815,
"grad_norm": 1.2120965719223022,
"learning_rate": 5.7057057057057065e-06,
"loss": 0.213,
"step": 149
},
{
"epoch": 0.4444444444444444,
"grad_norm": 1.370896577835083,
"learning_rate": 5.675675675675676e-06,
"loss": 0.2586,
"step": 150
},
{
"epoch": 0.4444444444444444,
"eval_loss": 0.18571805953979492,
"eval_runtime": 23.9059,
"eval_samples_per_second": 25.098,
"eval_steps_per_second": 12.549,
"step": 150
},
{
"epoch": 0.4474074074074074,
"grad_norm": 1.6352787017822266,
"learning_rate": 5.645645645645647e-06,
"loss": 0.2708,
"step": 151
},
{
"epoch": 0.45037037037037037,
"grad_norm": 1.0235956907272339,
"learning_rate": 5.615615615615616e-06,
"loss": 0.1541,
"step": 152
},
{
"epoch": 0.4533333333333333,
"grad_norm": 1.20542573928833,
"learning_rate": 5.585585585585585e-06,
"loss": 0.1611,
"step": 153
},
{
"epoch": 0.4562962962962963,
"grad_norm": 1.3218120336532593,
"learning_rate": 5.555555555555557e-06,
"loss": 0.2094,
"step": 154
},
{
"epoch": 0.45925925925925926,
"grad_norm": 0.9487716555595398,
"learning_rate": 5.5255255255255255e-06,
"loss": 0.1332,
"step": 155
},
{
"epoch": 0.4622222222222222,
"grad_norm": 0.5763458609580994,
"learning_rate": 5.495495495495496e-06,
"loss": 0.0568,
"step": 156
},
{
"epoch": 0.4651851851851852,
"grad_norm": 1.3980292081832886,
"learning_rate": 5.465465465465466e-06,
"loss": 0.2442,
"step": 157
},
{
"epoch": 0.46814814814814815,
"grad_norm": 0.9683685898780823,
"learning_rate": 5.4354354354354355e-06,
"loss": 0.1605,
"step": 158
},
{
"epoch": 0.4711111111111111,
"grad_norm": 1.2993813753128052,
"learning_rate": 5.405405405405406e-06,
"loss": 0.2494,
"step": 159
},
{
"epoch": 0.4740740740740741,
"grad_norm": 1.0891103744506836,
"learning_rate": 5.375375375375376e-06,
"loss": 0.1469,
"step": 160
},
{
"epoch": 0.47703703703703704,
"grad_norm": 1.1268359422683716,
"learning_rate": 5.345345345345346e-06,
"loss": 0.2085,
"step": 161
},
{
"epoch": 0.48,
"grad_norm": 1.3577607870101929,
"learning_rate": 5.315315315315316e-06,
"loss": 0.1503,
"step": 162
},
{
"epoch": 0.482962962962963,
"grad_norm": 1.2231824398040771,
"learning_rate": 5.285285285285286e-06,
"loss": 0.2081,
"step": 163
},
{
"epoch": 0.48592592592592593,
"grad_norm": 1.0802165269851685,
"learning_rate": 5.255255255255256e-06,
"loss": 0.1258,
"step": 164
},
{
"epoch": 0.4888888888888889,
"grad_norm": 1.182357668876648,
"learning_rate": 5.225225225225226e-06,
"loss": 0.207,
"step": 165
},
{
"epoch": 0.4918518518518519,
"grad_norm": 1.003881812095642,
"learning_rate": 5.195195195195195e-06,
"loss": 0.143,
"step": 166
},
{
"epoch": 0.4948148148148148,
"grad_norm": 1.1116942167282104,
"learning_rate": 5.165165165165165e-06,
"loss": 0.1625,
"step": 167
},
{
"epoch": 0.49777777777777776,
"grad_norm": 1.533279299736023,
"learning_rate": 5.135135135135135e-06,
"loss": 0.2987,
"step": 168
},
{
"epoch": 0.5007407407407407,
"grad_norm": 1.104600191116333,
"learning_rate": 5.105105105105106e-06,
"loss": 0.1881,
"step": 169
},
{
"epoch": 0.5037037037037037,
"grad_norm": 1.2864400148391724,
"learning_rate": 5.075075075075075e-06,
"loss": 0.2471,
"step": 170
},
{
"epoch": 0.5066666666666667,
"grad_norm": 1.2904927730560303,
"learning_rate": 5.045045045045045e-06,
"loss": 0.2277,
"step": 171
},
{
"epoch": 0.5096296296296297,
"grad_norm": 1.5207302570343018,
"learning_rate": 5.0150150150150156e-06,
"loss": 0.2567,
"step": 172
},
{
"epoch": 0.5125925925925926,
"grad_norm": 1.2911041975021362,
"learning_rate": 4.984984984984985e-06,
"loss": 0.2412,
"step": 173
},
{
"epoch": 0.5155555555555555,
"grad_norm": 1.3439834117889404,
"learning_rate": 4.954954954954955e-06,
"loss": 0.2162,
"step": 174
},
{
"epoch": 0.5185185185185185,
"grad_norm": 1.1687285900115967,
"learning_rate": 4.9249249249249255e-06,
"loss": 0.1896,
"step": 175
},
{
"epoch": 0.5214814814814814,
"grad_norm": 1.4640212059020996,
"learning_rate": 4.894894894894895e-06,
"loss": 0.2475,
"step": 176
},
{
"epoch": 0.5244444444444445,
"grad_norm": 1.0062167644500732,
"learning_rate": 4.864864864864866e-06,
"loss": 0.1369,
"step": 177
},
{
"epoch": 0.5274074074074074,
"grad_norm": 1.2928881645202637,
"learning_rate": 4.8348348348348355e-06,
"loss": 0.1962,
"step": 178
},
{
"epoch": 0.5303703703703704,
"grad_norm": 1.2557439804077148,
"learning_rate": 4.804804804804805e-06,
"loss": 0.2165,
"step": 179
},
{
"epoch": 0.5333333333333333,
"grad_norm": 0.9841265678405762,
"learning_rate": 4.774774774774775e-06,
"loss": 0.1646,
"step": 180
},
{
"epoch": 0.5362962962962963,
"grad_norm": 1.0929591655731201,
"learning_rate": 4.7447447447447454e-06,
"loss": 0.1904,
"step": 181
},
{
"epoch": 0.5392592592592592,
"grad_norm": 1.2781792879104614,
"learning_rate": 4.714714714714715e-06,
"loss": 0.1737,
"step": 182
},
{
"epoch": 0.5422222222222223,
"grad_norm": 1.1512343883514404,
"learning_rate": 4.684684684684685e-06,
"loss": 0.1504,
"step": 183
},
{
"epoch": 0.5451851851851852,
"grad_norm": 1.399990200996399,
"learning_rate": 4.654654654654655e-06,
"loss": 0.2874,
"step": 184
},
{
"epoch": 0.5481481481481482,
"grad_norm": 0.9561607837677002,
"learning_rate": 4.624624624624625e-06,
"loss": 0.1256,
"step": 185
},
{
"epoch": 0.5511111111111111,
"grad_norm": 1.375466227531433,
"learning_rate": 4.594594594594596e-06,
"loss": 0.2313,
"step": 186
},
{
"epoch": 0.554074074074074,
"grad_norm": 1.3498553037643433,
"learning_rate": 4.5645645645645645e-06,
"loss": 0.269,
"step": 187
},
{
"epoch": 0.557037037037037,
"grad_norm": 1.0630544424057007,
"learning_rate": 4.534534534534535e-06,
"loss": 0.184,
"step": 188
},
{
"epoch": 0.56,
"grad_norm": 1.4239861965179443,
"learning_rate": 4.504504504504505e-06,
"loss": 0.2222,
"step": 189
},
{
"epoch": 0.562962962962963,
"grad_norm": 1.7471421957015991,
"learning_rate": 4.474474474474475e-06,
"loss": 0.2216,
"step": 190
},
{
"epoch": 0.5659259259259259,
"grad_norm": 1.0986744165420532,
"learning_rate": 4.444444444444444e-06,
"loss": 0.1841,
"step": 191
},
{
"epoch": 0.5688888888888889,
"grad_norm": 1.0935932397842407,
"learning_rate": 4.414414414414415e-06,
"loss": 0.1434,
"step": 192
},
{
"epoch": 0.5718518518518518,
"grad_norm": 1.2842414379119873,
"learning_rate": 4.384384384384384e-06,
"loss": 0.2624,
"step": 193
},
{
"epoch": 0.5748148148148148,
"grad_norm": 1.2077158689498901,
"learning_rate": 4.354354354354355e-06,
"loss": 0.2381,
"step": 194
},
{
"epoch": 0.5777777777777777,
"grad_norm": 1.1203219890594482,
"learning_rate": 4.324324324324325e-06,
"loss": 0.1577,
"step": 195
},
{
"epoch": 0.5807407407407408,
"grad_norm": 0.9772409796714783,
"learning_rate": 4.294294294294294e-06,
"loss": 0.1524,
"step": 196
},
{
"epoch": 0.5837037037037037,
"grad_norm": 1.0411548614501953,
"learning_rate": 4.264264264264265e-06,
"loss": 0.2033,
"step": 197
},
{
"epoch": 0.5866666666666667,
"grad_norm": 1.2207049131393433,
"learning_rate": 4.234234234234235e-06,
"loss": 0.2064,
"step": 198
},
{
"epoch": 0.5896296296296296,
"grad_norm": 1.0652477741241455,
"learning_rate": 4.204204204204204e-06,
"loss": 0.1747,
"step": 199
},
{
"epoch": 0.5925925925925926,
"grad_norm": 0.955497145652771,
"learning_rate": 4.174174174174174e-06,
"loss": 0.1373,
"step": 200
},
{
"epoch": 0.5925925925925926,
"eval_loss": 0.18103553354740143,
"eval_runtime": 23.8535,
"eval_samples_per_second": 25.154,
"eval_steps_per_second": 12.577,
"step": 200
},
{
"epoch": 0.5955555555555555,
"grad_norm": 1.7014416456222534,
"learning_rate": 4.1441441441441446e-06,
"loss": 0.332,
"step": 201
},
{
"epoch": 0.5985185185185186,
"grad_norm": 1.1033849716186523,
"learning_rate": 4.114114114114114e-06,
"loss": 0.1832,
"step": 202
},
{
"epoch": 0.6014814814814815,
"grad_norm": 0.8649323582649231,
"learning_rate": 4.084084084084085e-06,
"loss": 0.1175,
"step": 203
},
{
"epoch": 0.6044444444444445,
"grad_norm": 1.6363075971603394,
"learning_rate": 4.0540540540540545e-06,
"loss": 0.2817,
"step": 204
},
{
"epoch": 0.6074074074074074,
"grad_norm": 1.5028653144836426,
"learning_rate": 4.024024024024024e-06,
"loss": 0.2674,
"step": 205
},
{
"epoch": 0.6103703703703703,
"grad_norm": 0.9459887146949768,
"learning_rate": 3.993993993993994e-06,
"loss": 0.1497,
"step": 206
},
{
"epoch": 0.6133333333333333,
"grad_norm": 0.9247708320617676,
"learning_rate": 3.9639639639639645e-06,
"loss": 0.095,
"step": 207
},
{
"epoch": 0.6162962962962963,
"grad_norm": 0.9643094539642334,
"learning_rate": 3.933933933933934e-06,
"loss": 0.1395,
"step": 208
},
{
"epoch": 0.6192592592592593,
"grad_norm": 0.973877489566803,
"learning_rate": 3.903903903903904e-06,
"loss": 0.1929,
"step": 209
},
{
"epoch": 0.6222222222222222,
"grad_norm": 1.095645785331726,
"learning_rate": 3.8738738738738744e-06,
"loss": 0.2016,
"step": 210
},
{
"epoch": 0.6251851851851852,
"grad_norm": 1.261592984199524,
"learning_rate": 3.843843843843844e-06,
"loss": 0.2307,
"step": 211
},
{
"epoch": 0.6281481481481481,
"grad_norm": 1.310593843460083,
"learning_rate": 3.8138138138138143e-06,
"loss": 0.2168,
"step": 212
},
{
"epoch": 0.6311111111111111,
"grad_norm": 1.293213129043579,
"learning_rate": 3.7837837837837844e-06,
"loss": 0.2149,
"step": 213
},
{
"epoch": 0.6340740740740741,
"grad_norm": 1.0491732358932495,
"learning_rate": 3.7537537537537537e-06,
"loss": 0.165,
"step": 214
},
{
"epoch": 0.6370370370370371,
"grad_norm": 1.0517427921295166,
"learning_rate": 3.723723723723724e-06,
"loss": 0.1388,
"step": 215
},
{
"epoch": 0.64,
"grad_norm": 1.0244203805923462,
"learning_rate": 3.693693693693694e-06,
"loss": 0.1736,
"step": 216
},
{
"epoch": 0.642962962962963,
"grad_norm": 1.0759280920028687,
"learning_rate": 3.663663663663664e-06,
"loss": 0.1762,
"step": 217
},
{
"epoch": 0.6459259259259259,
"grad_norm": 1.0782538652420044,
"learning_rate": 3.633633633633634e-06,
"loss": 0.137,
"step": 218
},
{
"epoch": 0.6488888888888888,
"grad_norm": 1.3638719320297241,
"learning_rate": 3.603603603603604e-06,
"loss": 0.2473,
"step": 219
},
{
"epoch": 0.6518518518518519,
"grad_norm": 1.0736602544784546,
"learning_rate": 3.573573573573574e-06,
"loss": 0.1665,
"step": 220
},
{
"epoch": 0.6548148148148148,
"grad_norm": 1.1971744298934937,
"learning_rate": 3.5435435435435437e-06,
"loss": 0.1958,
"step": 221
},
{
"epoch": 0.6577777777777778,
"grad_norm": 1.2904586791992188,
"learning_rate": 3.513513513513514e-06,
"loss": 0.1976,
"step": 222
},
{
"epoch": 0.6607407407407407,
"grad_norm": 1.1217589378356934,
"learning_rate": 3.4834834834834835e-06,
"loss": 0.1682,
"step": 223
},
{
"epoch": 0.6637037037037037,
"grad_norm": 1.0893889665603638,
"learning_rate": 3.4534534534534537e-06,
"loss": 0.1156,
"step": 224
},
{
"epoch": 0.6666666666666666,
"grad_norm": 1.0684195756912231,
"learning_rate": 3.423423423423424e-06,
"loss": 0.1328,
"step": 225
},
{
"epoch": 0.6696296296296296,
"grad_norm": 1.3466291427612305,
"learning_rate": 3.393393393393394e-06,
"loss": 0.1595,
"step": 226
},
{
"epoch": 0.6725925925925926,
"grad_norm": 1.7177739143371582,
"learning_rate": 3.363363363363364e-06,
"loss": 0.2979,
"step": 227
},
{
"epoch": 0.6755555555555556,
"grad_norm": 0.8278678059577942,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.1115,
"step": 228
},
{
"epoch": 0.6785185185185185,
"grad_norm": 0.8506137728691101,
"learning_rate": 3.3033033033033035e-06,
"loss": 0.1131,
"step": 229
},
{
"epoch": 0.6814814814814815,
"grad_norm": 0.9570547342300415,
"learning_rate": 3.2732732732732736e-06,
"loss": 0.1404,
"step": 230
},
{
"epoch": 0.6844444444444444,
"grad_norm": 1.4363343715667725,
"learning_rate": 3.2432432432432437e-06,
"loss": 0.2583,
"step": 231
},
{
"epoch": 0.6874074074074074,
"grad_norm": 1.147659420967102,
"learning_rate": 3.2132132132132134e-06,
"loss": 0.1775,
"step": 232
},
{
"epoch": 0.6903703703703704,
"grad_norm": 1.0482374429702759,
"learning_rate": 3.183183183183183e-06,
"loss": 0.1609,
"step": 233
},
{
"epoch": 0.6933333333333334,
"grad_norm": 1.1560864448547363,
"learning_rate": 3.1531531531531532e-06,
"loss": 0.1102,
"step": 234
},
{
"epoch": 0.6962962962962963,
"grad_norm": 1.6406065225601196,
"learning_rate": 3.1231231231231234e-06,
"loss": 0.2131,
"step": 235
},
{
"epoch": 0.6992592592592592,
"grad_norm": 1.3609254360198975,
"learning_rate": 3.0930930930930935e-06,
"loss": 0.213,
"step": 236
},
{
"epoch": 0.7022222222222222,
"grad_norm": 1.3128950595855713,
"learning_rate": 3.063063063063063e-06,
"loss": 0.2121,
"step": 237
},
{
"epoch": 0.7051851851851851,
"grad_norm": 1.3306642770767212,
"learning_rate": 3.0330330330330333e-06,
"loss": 0.1847,
"step": 238
},
{
"epoch": 0.7081481481481482,
"grad_norm": 1.104454755783081,
"learning_rate": 3.0030030030030034e-06,
"loss": 0.1415,
"step": 239
},
{
"epoch": 0.7111111111111111,
"grad_norm": 1.406089186668396,
"learning_rate": 2.9729729729729736e-06,
"loss": 0.2269,
"step": 240
},
{
"epoch": 0.7140740740740741,
"grad_norm": 1.2940478324890137,
"learning_rate": 2.942942942942943e-06,
"loss": 0.208,
"step": 241
},
{
"epoch": 0.717037037037037,
"grad_norm": 1.162065863609314,
"learning_rate": 2.912912912912913e-06,
"loss": 0.1807,
"step": 242
},
{
"epoch": 0.72,
"grad_norm": 1.3046311140060425,
"learning_rate": 2.882882882882883e-06,
"loss": 0.2562,
"step": 243
},
{
"epoch": 0.7229629629629629,
"grad_norm": 1.0760042667388916,
"learning_rate": 2.8528528528528532e-06,
"loss": 0.1447,
"step": 244
},
{
"epoch": 0.725925925925926,
"grad_norm": 0.935987651348114,
"learning_rate": 2.8228228228228234e-06,
"loss": 0.113,
"step": 245
},
{
"epoch": 0.7288888888888889,
"grad_norm": 1.2913446426391602,
"learning_rate": 2.7927927927927926e-06,
"loss": 0.2269,
"step": 246
},
{
"epoch": 0.7318518518518519,
"grad_norm": 1.0510679483413696,
"learning_rate": 2.7627627627627628e-06,
"loss": 0.1293,
"step": 247
},
{
"epoch": 0.7348148148148148,
"grad_norm": 1.0901553630828857,
"learning_rate": 2.732732732732733e-06,
"loss": 0.146,
"step": 248
},
{
"epoch": 0.7377777777777778,
"grad_norm": 1.4486427307128906,
"learning_rate": 2.702702702702703e-06,
"loss": 0.265,
"step": 249
},
{
"epoch": 0.7407407407407407,
"grad_norm": 1.237182855606079,
"learning_rate": 2.672672672672673e-06,
"loss": 0.2151,
"step": 250
},
{
"epoch": 0.7407407407407407,
"eval_loss": 0.17773914337158203,
"eval_runtime": 23.9072,
"eval_samples_per_second": 25.097,
"eval_steps_per_second": 12.548,
"step": 250
},
{
"epoch": 0.7437037037037038,
"grad_norm": 1.1155471801757812,
"learning_rate": 2.642642642642643e-06,
"loss": 0.1662,
"step": 251
},
{
"epoch": 0.7466666666666667,
"grad_norm": 1.0092755556106567,
"learning_rate": 2.612612612612613e-06,
"loss": 0.1511,
"step": 252
},
{
"epoch": 0.7496296296296296,
"grad_norm": 1.4825466871261597,
"learning_rate": 2.5825825825825827e-06,
"loss": 0.2112,
"step": 253
},
{
"epoch": 0.7525925925925926,
"grad_norm": 1.237218976020813,
"learning_rate": 2.552552552552553e-06,
"loss": 0.1658,
"step": 254
},
{
"epoch": 0.7555555555555555,
"grad_norm": 1.3147841691970825,
"learning_rate": 2.5225225225225225e-06,
"loss": 0.2195,
"step": 255
},
{
"epoch": 0.7585185185185185,
"grad_norm": 1.2130299806594849,
"learning_rate": 2.4924924924924926e-06,
"loss": 0.1948,
"step": 256
},
{
"epoch": 0.7614814814814815,
"grad_norm": 1.0403757095336914,
"learning_rate": 2.4624624624624628e-06,
"loss": 0.2153,
"step": 257
},
{
"epoch": 0.7644444444444445,
"grad_norm": 1.1891593933105469,
"learning_rate": 2.432432432432433e-06,
"loss": 0.2152,
"step": 258
},
{
"epoch": 0.7674074074074074,
"grad_norm": 1.3501454591751099,
"learning_rate": 2.4024024024024026e-06,
"loss": 0.2112,
"step": 259
},
{
"epoch": 0.7703703703703704,
"grad_norm": 1.1462842226028442,
"learning_rate": 2.3723723723723727e-06,
"loss": 0.1755,
"step": 260
},
{
"epoch": 0.7733333333333333,
"grad_norm": 1.4402129650115967,
"learning_rate": 2.3423423423423424e-06,
"loss": 0.2469,
"step": 261
},
{
"epoch": 0.7762962962962963,
"grad_norm": 1.5388565063476562,
"learning_rate": 2.3123123123123125e-06,
"loss": 0.2386,
"step": 262
},
{
"epoch": 0.7792592592592592,
"grad_norm": 1.5926933288574219,
"learning_rate": 2.2822822822822822e-06,
"loss": 0.2768,
"step": 263
},
{
"epoch": 0.7822222222222223,
"grad_norm": 1.0447241067886353,
"learning_rate": 2.2522522522522524e-06,
"loss": 0.131,
"step": 264
},
{
"epoch": 0.7851851851851852,
"grad_norm": 1.0833740234375,
"learning_rate": 2.222222222222222e-06,
"loss": 0.1305,
"step": 265
},
{
"epoch": 0.7881481481481482,
"grad_norm": 0.9263427257537842,
"learning_rate": 2.192192192192192e-06,
"loss": 0.1405,
"step": 266
},
{
"epoch": 0.7911111111111111,
"grad_norm": 1.18036687374115,
"learning_rate": 2.1621621621621623e-06,
"loss": 0.208,
"step": 267
},
{
"epoch": 0.794074074074074,
"grad_norm": 1.2910195589065552,
"learning_rate": 2.1321321321321325e-06,
"loss": 0.1776,
"step": 268
},
{
"epoch": 0.797037037037037,
"grad_norm": 1.4620945453643799,
"learning_rate": 2.102102102102102e-06,
"loss": 0.2105,
"step": 269
},
{
"epoch": 0.8,
"grad_norm": 1.750665307044983,
"learning_rate": 2.0720720720720723e-06,
"loss": 0.3037,
"step": 270
},
{
"epoch": 0.802962962962963,
"grad_norm": 1.2664645910263062,
"learning_rate": 2.0420420420420424e-06,
"loss": 0.1815,
"step": 271
},
{
"epoch": 0.8059259259259259,
"grad_norm": 1.2720537185668945,
"learning_rate": 2.012012012012012e-06,
"loss": 0.2134,
"step": 272
},
{
"epoch": 0.8088888888888889,
"grad_norm": 1.7047117948532104,
"learning_rate": 1.9819819819819822e-06,
"loss": 0.2941,
"step": 273
},
{
"epoch": 0.8118518518518518,
"grad_norm": 0.8581114411354065,
"learning_rate": 1.951951951951952e-06,
"loss": 0.1009,
"step": 274
},
{
"epoch": 0.8148148148148148,
"grad_norm": 1.3319694995880127,
"learning_rate": 1.921921921921922e-06,
"loss": 0.2247,
"step": 275
},
{
"epoch": 0.8177777777777778,
"grad_norm": 1.5772552490234375,
"learning_rate": 1.8918918918918922e-06,
"loss": 0.2679,
"step": 276
},
{
"epoch": 0.8207407407407408,
"grad_norm": 1.1886117458343506,
"learning_rate": 1.861861861861862e-06,
"loss": 0.1925,
"step": 277
},
{
"epoch": 0.8237037037037037,
"grad_norm": 0.9228101372718811,
"learning_rate": 1.831831831831832e-06,
"loss": 0.1038,
"step": 278
},
{
"epoch": 0.8266666666666667,
"grad_norm": 1.1413522958755493,
"learning_rate": 1.801801801801802e-06,
"loss": 0.1564,
"step": 279
},
{
"epoch": 0.8296296296296296,
"grad_norm": 1.5371259450912476,
"learning_rate": 1.7717717717717719e-06,
"loss": 0.2599,
"step": 280
},
{
"epoch": 0.8325925925925926,
"grad_norm": 0.9771330952644348,
"learning_rate": 1.7417417417417418e-06,
"loss": 0.1194,
"step": 281
},
{
"epoch": 0.8355555555555556,
"grad_norm": 1.459544062614441,
"learning_rate": 1.711711711711712e-06,
"loss": 0.2399,
"step": 282
},
{
"epoch": 0.8385185185185186,
"grad_norm": 1.1008762121200562,
"learning_rate": 1.681681681681682e-06,
"loss": 0.1801,
"step": 283
},
{
"epoch": 0.8414814814814815,
"grad_norm": 1.2950160503387451,
"learning_rate": 1.6516516516516517e-06,
"loss": 0.182,
"step": 284
},
{
"epoch": 0.8444444444444444,
"grad_norm": 1.1448296308517456,
"learning_rate": 1.6216216216216219e-06,
"loss": 0.1332,
"step": 285
},
{
"epoch": 0.8474074074074074,
"grad_norm": 0.9305551648139954,
"learning_rate": 1.5915915915915916e-06,
"loss": 0.1343,
"step": 286
},
{
"epoch": 0.8503703703703703,
"grad_norm": 1.1336984634399414,
"learning_rate": 1.5615615615615617e-06,
"loss": 0.1312,
"step": 287
},
{
"epoch": 0.8533333333333334,
"grad_norm": 1.0160270929336548,
"learning_rate": 1.5315315315315316e-06,
"loss": 0.1264,
"step": 288
},
{
"epoch": 0.8562962962962963,
"grad_norm": 1.1759402751922607,
"learning_rate": 1.5015015015015017e-06,
"loss": 0.1821,
"step": 289
},
{
"epoch": 0.8592592592592593,
"grad_norm": 1.0062414407730103,
"learning_rate": 1.4714714714714714e-06,
"loss": 0.1044,
"step": 290
},
{
"epoch": 0.8622222222222222,
"grad_norm": 1.1093711853027344,
"learning_rate": 1.4414414414414416e-06,
"loss": 0.1459,
"step": 291
},
{
"epoch": 0.8651851851851852,
"grad_norm": 1.0098477602005005,
"learning_rate": 1.4114114114114117e-06,
"loss": 0.1439,
"step": 292
},
{
"epoch": 0.8681481481481481,
"grad_norm": 1.1199849843978882,
"learning_rate": 1.3813813813813814e-06,
"loss": 0.1245,
"step": 293
},
{
"epoch": 0.8711111111111111,
"grad_norm": 1.4643607139587402,
"learning_rate": 1.3513513513513515e-06,
"loss": 0.2517,
"step": 294
},
{
"epoch": 0.8740740740740741,
"grad_norm": 0.9493430256843567,
"learning_rate": 1.3213213213213214e-06,
"loss": 0.1411,
"step": 295
},
{
"epoch": 0.8770370370370371,
"grad_norm": 1.235182523727417,
"learning_rate": 1.2912912912912913e-06,
"loss": 0.1854,
"step": 296
},
{
"epoch": 0.88,
"grad_norm": 1.1145265102386475,
"learning_rate": 1.2612612612612613e-06,
"loss": 0.1585,
"step": 297
},
{
"epoch": 0.882962962962963,
"grad_norm": 1.1541376113891602,
"learning_rate": 1.2312312312312314e-06,
"loss": 0.1935,
"step": 298
},
{
"epoch": 0.8859259259259259,
"grad_norm": 1.0467174053192139,
"learning_rate": 1.2012012012012013e-06,
"loss": 0.1663,
"step": 299
},
{
"epoch": 0.8888888888888888,
"grad_norm": 1.0621838569641113,
"learning_rate": 1.1711711711711712e-06,
"loss": 0.1353,
"step": 300
},
{
"epoch": 0.8888888888888888,
"eval_loss": 0.17575983703136444,
"eval_runtime": 23.9675,
"eval_samples_per_second": 25.034,
"eval_steps_per_second": 12.517,
"step": 300
},
{
"epoch": 0.8918518518518519,
"grad_norm": 1.259453535079956,
"learning_rate": 1.1411411411411411e-06,
"loss": 0.1965,
"step": 301
},
{
"epoch": 0.8948148148148148,
"grad_norm": 1.3410152196884155,
"learning_rate": 1.111111111111111e-06,
"loss": 0.1863,
"step": 302
},
{
"epoch": 0.8977777777777778,
"grad_norm": 0.9149288535118103,
"learning_rate": 1.0810810810810812e-06,
"loss": 0.0953,
"step": 303
},
{
"epoch": 0.9007407407407407,
"grad_norm": 1.2499077320098877,
"learning_rate": 1.051051051051051e-06,
"loss": 0.2253,
"step": 304
},
{
"epoch": 0.9037037037037037,
"grad_norm": 1.1862951517105103,
"learning_rate": 1.0210210210210212e-06,
"loss": 0.1313,
"step": 305
},
{
"epoch": 0.9066666666666666,
"grad_norm": 1.379338026046753,
"learning_rate": 9.909909909909911e-07,
"loss": 0.1507,
"step": 306
},
{
"epoch": 0.9096296296296297,
"grad_norm": 0.9425829648971558,
"learning_rate": 9.60960960960961e-07,
"loss": 0.1207,
"step": 307
},
{
"epoch": 0.9125925925925926,
"grad_norm": 1.3688846826553345,
"learning_rate": 9.30930930930931e-07,
"loss": 0.2376,
"step": 308
},
{
"epoch": 0.9155555555555556,
"grad_norm": 1.4492270946502686,
"learning_rate": 9.00900900900901e-07,
"loss": 0.2451,
"step": 309
},
{
"epoch": 0.9185185185185185,
"grad_norm": 1.3633449077606201,
"learning_rate": 8.708708708708709e-07,
"loss": 0.1856,
"step": 310
},
{
"epoch": 0.9214814814814815,
"grad_norm": 0.7758963108062744,
"learning_rate": 8.40840840840841e-07,
"loss": 0.1013,
"step": 311
},
{
"epoch": 0.9244444444444444,
"grad_norm": 1.075621485710144,
"learning_rate": 8.108108108108109e-07,
"loss": 0.1367,
"step": 312
},
{
"epoch": 0.9274074074074075,
"grad_norm": 1.3161863088607788,
"learning_rate": 7.807807807807808e-07,
"loss": 0.2022,
"step": 313
},
{
"epoch": 0.9303703703703704,
"grad_norm": 1.0019944906234741,
"learning_rate": 7.507507507507509e-07,
"loss": 0.1104,
"step": 314
},
{
"epoch": 0.9333333333333333,
"grad_norm": 1.2972002029418945,
"learning_rate": 7.207207207207208e-07,
"loss": 0.2025,
"step": 315
},
{
"epoch": 0.9362962962962963,
"grad_norm": 1.1284160614013672,
"learning_rate": 6.906906906906907e-07,
"loss": 0.2142,
"step": 316
},
{
"epoch": 0.9392592592592592,
"grad_norm": 1.2063133716583252,
"learning_rate": 6.606606606606607e-07,
"loss": 0.1616,
"step": 317
},
{
"epoch": 0.9422222222222222,
"grad_norm": 1.1671180725097656,
"learning_rate": 6.306306306306306e-07,
"loss": 0.1575,
"step": 318
},
{
"epoch": 0.9451851851851852,
"grad_norm": 1.1023907661437988,
"learning_rate": 6.006006006006006e-07,
"loss": 0.1809,
"step": 319
},
{
"epoch": 0.9481481481481482,
"grad_norm": 1.1849286556243896,
"learning_rate": 5.705705705705706e-07,
"loss": 0.1565,
"step": 320
},
{
"epoch": 0.9511111111111111,
"grad_norm": 1.0859187841415405,
"learning_rate": 5.405405405405406e-07,
"loss": 0.1653,
"step": 321
},
{
"epoch": 0.9540740740740741,
"grad_norm": 1.1001648902893066,
"learning_rate": 5.105105105105106e-07,
"loss": 0.1744,
"step": 322
},
{
"epoch": 0.957037037037037,
"grad_norm": 0.9560665488243103,
"learning_rate": 4.804804804804805e-07,
"loss": 0.1548,
"step": 323
},
{
"epoch": 0.96,
"grad_norm": 1.0510227680206299,
"learning_rate": 4.504504504504505e-07,
"loss": 0.12,
"step": 324
},
{
"epoch": 0.9629629629629629,
"grad_norm": 0.7929470539093018,
"learning_rate": 4.204204204204205e-07,
"loss": 0.1139,
"step": 325
},
{
"epoch": 0.965925925925926,
"grad_norm": 1.40009605884552,
"learning_rate": 3.903903903903904e-07,
"loss": 0.2319,
"step": 326
},
{
"epoch": 0.9688888888888889,
"grad_norm": 0.9116257429122925,
"learning_rate": 3.603603603603604e-07,
"loss": 0.1162,
"step": 327
},
{
"epoch": 0.9718518518518519,
"grad_norm": 1.2207261323928833,
"learning_rate": 3.3033033033033036e-07,
"loss": 0.2028,
"step": 328
},
{
"epoch": 0.9748148148148148,
"grad_norm": 1.3603975772857666,
"learning_rate": 3.003003003003003e-07,
"loss": 0.2003,
"step": 329
},
{
"epoch": 0.9777777777777777,
"grad_norm": 1.1170819997787476,
"learning_rate": 2.702702702702703e-07,
"loss": 0.1221,
"step": 330
},
{
"epoch": 0.9807407407407407,
"grad_norm": 1.5130791664123535,
"learning_rate": 2.4024024024024026e-07,
"loss": 0.2615,
"step": 331
},
{
"epoch": 0.9837037037037037,
"grad_norm": 1.032984972000122,
"learning_rate": 2.1021021021021025e-07,
"loss": 0.1762,
"step": 332
},
{
"epoch": 0.9866666666666667,
"grad_norm": 0.953294038772583,
"learning_rate": 1.801801801801802e-07,
"loss": 0.1318,
"step": 333
},
{
"epoch": 0.9896296296296296,
"grad_norm": 0.879710853099823,
"learning_rate": 1.5015015015015016e-07,
"loss": 0.1204,
"step": 334
},
{
"epoch": 0.9925925925925926,
"grad_norm": 1.2884814739227295,
"learning_rate": 1.2012012012012013e-07,
"loss": 0.2094,
"step": 335
},
{
"epoch": 0.9955555555555555,
"grad_norm": 1.3783299922943115,
"learning_rate": 9.00900900900901e-08,
"loss": 0.2275,
"step": 336
},
{
"epoch": 0.9985185185185185,
"grad_norm": 1.4565948247909546,
"learning_rate": 6.006006006006006e-08,
"loss": 0.1978,
"step": 337
},
{
"epoch": 1.0,
"grad_norm": 1.7989568710327148,
"learning_rate": 3.003003003003003e-08,
"loss": 0.191,
"step": 338
}
],
"logging_steps": 1,
"max_steps": 338,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 10000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 6.726445731029606e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}