VideoChatOnline-4B / trainer_state.json
hzp's picture
Upload checkpoint
9ab71d6 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9996886351842241,
"eval_steps": 500,
"global_step": 1376,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0007265179034769071,
"grad_norm": 2.140625,
"learning_rate": 2.3809523809523808e-06,
"loss": 1.0132,
"step": 1
},
{
"epoch": 0.0014530358069538142,
"grad_norm": 2.59375,
"learning_rate": 4.7619047619047615e-06,
"loss": 1.0295,
"step": 2
},
{
"epoch": 0.0021795537104307215,
"grad_norm": 2.046875,
"learning_rate": 7.142857142857143e-06,
"loss": 1.0052,
"step": 3
},
{
"epoch": 0.0029060716139076284,
"grad_norm": 1.9453125,
"learning_rate": 9.523809523809523e-06,
"loss": 0.9807,
"step": 4
},
{
"epoch": 0.0036325895173845357,
"grad_norm": 1.625,
"learning_rate": 1.1904761904761905e-05,
"loss": 0.9775,
"step": 5
},
{
"epoch": 0.004359107420861443,
"grad_norm": 1.1953125,
"learning_rate": 1.4285714285714285e-05,
"loss": 0.9196,
"step": 6
},
{
"epoch": 0.0050856253243383494,
"grad_norm": 0.96484375,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.9438,
"step": 7
},
{
"epoch": 0.005812143227815257,
"grad_norm": 0.9453125,
"learning_rate": 1.9047619047619046e-05,
"loss": 0.8652,
"step": 8
},
{
"epoch": 0.006538661131292164,
"grad_norm": 0.67578125,
"learning_rate": 2.1428571428571428e-05,
"loss": 0.8665,
"step": 9
},
{
"epoch": 0.007265179034769071,
"grad_norm": 0.546875,
"learning_rate": 2.380952380952381e-05,
"loss": 0.9098,
"step": 10
},
{
"epoch": 0.007991696938245979,
"grad_norm": 0.478515625,
"learning_rate": 2.6190476190476192e-05,
"loss": 0.8427,
"step": 11
},
{
"epoch": 0.008718214841722886,
"grad_norm": 0.447265625,
"learning_rate": 2.857142857142857e-05,
"loss": 0.8126,
"step": 12
},
{
"epoch": 0.009444732745199792,
"grad_norm": 0.453125,
"learning_rate": 3.095238095238095e-05,
"loss": 0.8305,
"step": 13
},
{
"epoch": 0.010171250648676699,
"grad_norm": 0.427734375,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.8383,
"step": 14
},
{
"epoch": 0.010897768552153606,
"grad_norm": 0.4140625,
"learning_rate": 3.571428571428572e-05,
"loss": 0.8411,
"step": 15
},
{
"epoch": 0.011624286455630514,
"grad_norm": 0.384765625,
"learning_rate": 3.809523809523809e-05,
"loss": 0.8177,
"step": 16
},
{
"epoch": 0.01235080435910742,
"grad_norm": 0.396484375,
"learning_rate": 4.047619047619048e-05,
"loss": 0.8327,
"step": 17
},
{
"epoch": 0.013077322262584328,
"grad_norm": 0.43359375,
"learning_rate": 4.2857142857142856e-05,
"loss": 0.8288,
"step": 18
},
{
"epoch": 0.013803840166061235,
"grad_norm": 0.392578125,
"learning_rate": 4.523809523809524e-05,
"loss": 0.8234,
"step": 19
},
{
"epoch": 0.014530358069538143,
"grad_norm": 0.36328125,
"learning_rate": 4.761904761904762e-05,
"loss": 0.7784,
"step": 20
},
{
"epoch": 0.01525687597301505,
"grad_norm": 0.404296875,
"learning_rate": 5e-05,
"loss": 0.779,
"step": 21
},
{
"epoch": 0.015983393876491957,
"grad_norm": 0.376953125,
"learning_rate": 5.2380952380952384e-05,
"loss": 0.7819,
"step": 22
},
{
"epoch": 0.016709911779968865,
"grad_norm": 0.361328125,
"learning_rate": 5.4761904761904766e-05,
"loss": 0.7925,
"step": 23
},
{
"epoch": 0.017436429683445772,
"grad_norm": 0.3828125,
"learning_rate": 5.714285714285714e-05,
"loss": 0.8064,
"step": 24
},
{
"epoch": 0.01816294758692268,
"grad_norm": 0.35546875,
"learning_rate": 5.9523809523809524e-05,
"loss": 0.7933,
"step": 25
},
{
"epoch": 0.018889465490399583,
"grad_norm": 0.376953125,
"learning_rate": 6.19047619047619e-05,
"loss": 0.7937,
"step": 26
},
{
"epoch": 0.01961598339387649,
"grad_norm": 0.369140625,
"learning_rate": 6.428571428571429e-05,
"loss": 0.816,
"step": 27
},
{
"epoch": 0.020342501297353398,
"grad_norm": 0.373046875,
"learning_rate": 6.666666666666667e-05,
"loss": 0.7783,
"step": 28
},
{
"epoch": 0.021069019200830305,
"grad_norm": 0.388671875,
"learning_rate": 6.904761904761905e-05,
"loss": 0.8131,
"step": 29
},
{
"epoch": 0.021795537104307212,
"grad_norm": 0.365234375,
"learning_rate": 7.142857142857143e-05,
"loss": 0.7988,
"step": 30
},
{
"epoch": 0.02252205500778412,
"grad_norm": 0.353515625,
"learning_rate": 7.380952380952382e-05,
"loss": 0.8071,
"step": 31
},
{
"epoch": 0.023248572911261027,
"grad_norm": 0.341796875,
"learning_rate": 7.619047619047618e-05,
"loss": 0.8158,
"step": 32
},
{
"epoch": 0.023975090814737934,
"grad_norm": 0.40234375,
"learning_rate": 7.857142857142858e-05,
"loss": 0.8166,
"step": 33
},
{
"epoch": 0.02470160871821484,
"grad_norm": 0.349609375,
"learning_rate": 8.095238095238096e-05,
"loss": 0.7689,
"step": 34
},
{
"epoch": 0.02542812662169175,
"grad_norm": 0.365234375,
"learning_rate": 8.333333333333334e-05,
"loss": 0.7977,
"step": 35
},
{
"epoch": 0.026154644525168656,
"grad_norm": 0.357421875,
"learning_rate": 8.571428571428571e-05,
"loss": 0.8024,
"step": 36
},
{
"epoch": 0.026881162428645564,
"grad_norm": 0.404296875,
"learning_rate": 8.80952380952381e-05,
"loss": 0.8454,
"step": 37
},
{
"epoch": 0.02760768033212247,
"grad_norm": 0.345703125,
"learning_rate": 9.047619047619048e-05,
"loss": 0.7782,
"step": 38
},
{
"epoch": 0.028334198235599378,
"grad_norm": 0.361328125,
"learning_rate": 9.285714285714286e-05,
"loss": 0.8165,
"step": 39
},
{
"epoch": 0.029060716139076286,
"grad_norm": 0.341796875,
"learning_rate": 9.523809523809524e-05,
"loss": 0.8042,
"step": 40
},
{
"epoch": 0.029787234042553193,
"grad_norm": 0.375,
"learning_rate": 9.761904761904762e-05,
"loss": 0.7814,
"step": 41
},
{
"epoch": 0.0305137519460301,
"grad_norm": 0.375,
"learning_rate": 0.0001,
"loss": 0.8138,
"step": 42
},
{
"epoch": 0.031240269849507004,
"grad_norm": 0.365234375,
"learning_rate": 9.999986134743949e-05,
"loss": 0.7679,
"step": 43
},
{
"epoch": 0.031966787752983915,
"grad_norm": 0.388671875,
"learning_rate": 9.99994453905269e-05,
"loss": 0.7785,
"step": 44
},
{
"epoch": 0.03269330565646082,
"grad_norm": 0.3984375,
"learning_rate": 9.99987521315692e-05,
"loss": 0.8373,
"step": 45
},
{
"epoch": 0.03341982355993773,
"grad_norm": 0.37109375,
"learning_rate": 9.999778157441127e-05,
"loss": 0.8188,
"step": 46
},
{
"epoch": 0.03414634146341464,
"grad_norm": 0.41796875,
"learning_rate": 9.99965337244359e-05,
"loss": 0.7892,
"step": 47
},
{
"epoch": 0.034872859366891544,
"grad_norm": 0.37109375,
"learning_rate": 9.999500858856381e-05,
"loss": 0.8207,
"step": 48
},
{
"epoch": 0.03559937727036845,
"grad_norm": 0.3671875,
"learning_rate": 9.999320617525356e-05,
"loss": 0.8033,
"step": 49
},
{
"epoch": 0.03632589517384536,
"grad_norm": 0.349609375,
"learning_rate": 9.999112649450153e-05,
"loss": 0.7654,
"step": 50
},
{
"epoch": 0.037052413077322266,
"grad_norm": 0.341796875,
"learning_rate": 9.998876955784183e-05,
"loss": 0.7591,
"step": 51
},
{
"epoch": 0.037778930980799166,
"grad_norm": 0.373046875,
"learning_rate": 9.998613537834624e-05,
"loss": 0.7809,
"step": 52
},
{
"epoch": 0.038505448884276074,
"grad_norm": 0.3515625,
"learning_rate": 9.998322397062425e-05,
"loss": 0.7573,
"step": 53
},
{
"epoch": 0.03923196678775298,
"grad_norm": 0.35546875,
"learning_rate": 9.998003535082279e-05,
"loss": 0.8222,
"step": 54
},
{
"epoch": 0.03995848469122989,
"grad_norm": 0.37109375,
"learning_rate": 9.997656953662627e-05,
"loss": 0.7745,
"step": 55
},
{
"epoch": 0.040685002594706796,
"grad_norm": 0.37890625,
"learning_rate": 9.997282654725646e-05,
"loss": 0.7563,
"step": 56
},
{
"epoch": 0.0414115204981837,
"grad_norm": 0.412109375,
"learning_rate": 9.996880640347235e-05,
"loss": 0.8236,
"step": 57
},
{
"epoch": 0.04213803840166061,
"grad_norm": 0.349609375,
"learning_rate": 9.99645091275701e-05,
"loss": 0.7766,
"step": 58
},
{
"epoch": 0.04286455630513752,
"grad_norm": 0.337890625,
"learning_rate": 9.99599347433828e-05,
"loss": 0.7795,
"step": 59
},
{
"epoch": 0.043591074208614425,
"grad_norm": 0.359375,
"learning_rate": 9.99550832762805e-05,
"loss": 0.7736,
"step": 60
},
{
"epoch": 0.04431759211209133,
"grad_norm": 0.34375,
"learning_rate": 9.994995475316989e-05,
"loss": 0.775,
"step": 61
},
{
"epoch": 0.04504411001556824,
"grad_norm": 0.3828125,
"learning_rate": 9.994454920249432e-05,
"loss": 0.7683,
"step": 62
},
{
"epoch": 0.04577062791904515,
"grad_norm": 0.341796875,
"learning_rate": 9.993886665423349e-05,
"loss": 0.7533,
"step": 63
},
{
"epoch": 0.046497145822522054,
"grad_norm": 0.373046875,
"learning_rate": 9.993290713990343e-05,
"loss": 0.8006,
"step": 64
},
{
"epoch": 0.04722366372599896,
"grad_norm": 0.36328125,
"learning_rate": 9.992667069255619e-05,
"loss": 0.7773,
"step": 65
},
{
"epoch": 0.04795018162947587,
"grad_norm": 0.388671875,
"learning_rate": 9.992015734677978e-05,
"loss": 0.8005,
"step": 66
},
{
"epoch": 0.048676699532952776,
"grad_norm": 0.337890625,
"learning_rate": 9.991336713869784e-05,
"loss": 0.7696,
"step": 67
},
{
"epoch": 0.04940321743642968,
"grad_norm": 0.361328125,
"learning_rate": 9.990630010596959e-05,
"loss": 0.7909,
"step": 68
},
{
"epoch": 0.05012973533990659,
"grad_norm": 0.365234375,
"learning_rate": 9.989895628778951e-05,
"loss": 0.8244,
"step": 69
},
{
"epoch": 0.0508562532433835,
"grad_norm": 0.349609375,
"learning_rate": 9.989133572488716e-05,
"loss": 0.7708,
"step": 70
},
{
"epoch": 0.051582771146860405,
"grad_norm": 0.40234375,
"learning_rate": 9.988343845952697e-05,
"loss": 0.7772,
"step": 71
},
{
"epoch": 0.05230928905033731,
"grad_norm": 0.353515625,
"learning_rate": 9.987526453550798e-05,
"loss": 0.791,
"step": 72
},
{
"epoch": 0.05303580695381422,
"grad_norm": 0.37109375,
"learning_rate": 9.98668139981636e-05,
"loss": 0.773,
"step": 73
},
{
"epoch": 0.05376232485729113,
"grad_norm": 0.3359375,
"learning_rate": 9.985808689436141e-05,
"loss": 0.7702,
"step": 74
},
{
"epoch": 0.054488842760768035,
"grad_norm": 0.33203125,
"learning_rate": 9.984908327250277e-05,
"loss": 0.7585,
"step": 75
},
{
"epoch": 0.05521536066424494,
"grad_norm": 0.400390625,
"learning_rate": 9.983980318252273e-05,
"loss": 0.8104,
"step": 76
},
{
"epoch": 0.05594187856772185,
"grad_norm": 0.341796875,
"learning_rate": 9.98302466758896e-05,
"loss": 0.7862,
"step": 77
},
{
"epoch": 0.056668396471198756,
"grad_norm": 0.384765625,
"learning_rate": 9.982041380560476e-05,
"loss": 0.8183,
"step": 78
},
{
"epoch": 0.057394914374675664,
"grad_norm": 0.322265625,
"learning_rate": 9.981030462620228e-05,
"loss": 0.7918,
"step": 79
},
{
"epoch": 0.05812143227815257,
"grad_norm": 0.376953125,
"learning_rate": 9.979991919374877e-05,
"loss": 0.8042,
"step": 80
},
{
"epoch": 0.05884795018162948,
"grad_norm": 0.3671875,
"learning_rate": 9.978925756584284e-05,
"loss": 0.799,
"step": 81
},
{
"epoch": 0.059574468085106386,
"grad_norm": 0.353515625,
"learning_rate": 9.977831980161499e-05,
"loss": 0.7606,
"step": 82
},
{
"epoch": 0.06030098598858329,
"grad_norm": 0.361328125,
"learning_rate": 9.976710596172721e-05,
"loss": 0.8021,
"step": 83
},
{
"epoch": 0.0610275038920602,
"grad_norm": 0.359375,
"learning_rate": 9.975561610837254e-05,
"loss": 0.7788,
"step": 84
},
{
"epoch": 0.06175402179553711,
"grad_norm": 0.3359375,
"learning_rate": 9.974385030527495e-05,
"loss": 0.7847,
"step": 85
},
{
"epoch": 0.06248053969901401,
"grad_norm": 0.365234375,
"learning_rate": 9.973180861768874e-05,
"loss": 0.7936,
"step": 86
},
{
"epoch": 0.06320705760249092,
"grad_norm": 0.361328125,
"learning_rate": 9.971949111239837e-05,
"loss": 0.7657,
"step": 87
},
{
"epoch": 0.06393357550596783,
"grad_norm": 0.37109375,
"learning_rate": 9.970689785771798e-05,
"loss": 0.7781,
"step": 88
},
{
"epoch": 0.06466009340944473,
"grad_norm": 0.33984375,
"learning_rate": 9.969402892349106e-05,
"loss": 0.8173,
"step": 89
},
{
"epoch": 0.06538661131292164,
"grad_norm": 0.32421875,
"learning_rate": 9.968088438109002e-05,
"loss": 0.7675,
"step": 90
},
{
"epoch": 0.06611312921639854,
"grad_norm": 0.359375,
"learning_rate": 9.966746430341583e-05,
"loss": 0.7902,
"step": 91
},
{
"epoch": 0.06683964711987546,
"grad_norm": 0.33984375,
"learning_rate": 9.965376876489765e-05,
"loss": 0.8026,
"step": 92
},
{
"epoch": 0.06756616502335236,
"grad_norm": 0.333984375,
"learning_rate": 9.963979784149231e-05,
"loss": 0.7807,
"step": 93
},
{
"epoch": 0.06829268292682927,
"grad_norm": 0.3359375,
"learning_rate": 9.962555161068399e-05,
"loss": 0.7725,
"step": 94
},
{
"epoch": 0.06901920083030617,
"grad_norm": 0.322265625,
"learning_rate": 9.961103015148376e-05,
"loss": 0.7731,
"step": 95
},
{
"epoch": 0.06974571873378309,
"grad_norm": 0.349609375,
"learning_rate": 9.95962335444291e-05,
"loss": 0.7684,
"step": 96
},
{
"epoch": 0.07047223663725999,
"grad_norm": 0.359375,
"learning_rate": 9.95811618715835e-05,
"loss": 0.7912,
"step": 97
},
{
"epoch": 0.0711987545407369,
"grad_norm": 0.353515625,
"learning_rate": 9.956581521653604e-05,
"loss": 0.8271,
"step": 98
},
{
"epoch": 0.0719252724442138,
"grad_norm": 0.365234375,
"learning_rate": 9.955019366440082e-05,
"loss": 0.7561,
"step": 99
},
{
"epoch": 0.07265179034769072,
"grad_norm": 0.341796875,
"learning_rate": 9.953429730181653e-05,
"loss": 0.7733,
"step": 100
},
{
"epoch": 0.07337830825116762,
"grad_norm": 0.326171875,
"learning_rate": 9.951812621694609e-05,
"loss": 0.7822,
"step": 101
},
{
"epoch": 0.07410482615464453,
"grad_norm": 0.3671875,
"learning_rate": 9.950168049947596e-05,
"loss": 0.7892,
"step": 102
},
{
"epoch": 0.07483134405812143,
"grad_norm": 0.34375,
"learning_rate": 9.948496024061578e-05,
"loss": 0.7868,
"step": 103
},
{
"epoch": 0.07555786196159833,
"grad_norm": 0.318359375,
"learning_rate": 9.946796553309781e-05,
"loss": 0.7695,
"step": 104
},
{
"epoch": 0.07628437986507525,
"grad_norm": 0.341796875,
"learning_rate": 9.945069647117644e-05,
"loss": 0.7649,
"step": 105
},
{
"epoch": 0.07701089776855215,
"grad_norm": 0.373046875,
"learning_rate": 9.943315315062766e-05,
"loss": 0.7639,
"step": 106
},
{
"epoch": 0.07773741567202906,
"grad_norm": 0.349609375,
"learning_rate": 9.941533566874852e-05,
"loss": 0.7764,
"step": 107
},
{
"epoch": 0.07846393357550596,
"grad_norm": 0.31640625,
"learning_rate": 9.93972441243566e-05,
"loss": 0.8119,
"step": 108
},
{
"epoch": 0.07919045147898288,
"grad_norm": 0.37890625,
"learning_rate": 9.937887861778947e-05,
"loss": 0.7885,
"step": 109
},
{
"epoch": 0.07991696938245978,
"grad_norm": 0.375,
"learning_rate": 9.936023925090409e-05,
"loss": 0.7986,
"step": 110
},
{
"epoch": 0.08064348728593669,
"grad_norm": 0.37109375,
"learning_rate": 9.934132612707632e-05,
"loss": 0.8224,
"step": 111
},
{
"epoch": 0.08137000518941359,
"grad_norm": 0.32421875,
"learning_rate": 9.932213935120025e-05,
"loss": 0.7715,
"step": 112
},
{
"epoch": 0.0820965230928905,
"grad_norm": 0.37109375,
"learning_rate": 9.930267902968774e-05,
"loss": 0.7821,
"step": 113
},
{
"epoch": 0.0828230409963674,
"grad_norm": 0.3359375,
"learning_rate": 9.928294527046771e-05,
"loss": 0.7583,
"step": 114
},
{
"epoch": 0.08354955889984432,
"grad_norm": 0.34765625,
"learning_rate": 9.92629381829856e-05,
"loss": 0.7897,
"step": 115
},
{
"epoch": 0.08427607680332122,
"grad_norm": 0.33984375,
"learning_rate": 9.924265787820278e-05,
"loss": 0.7857,
"step": 116
},
{
"epoch": 0.08500259470679813,
"grad_norm": 0.35546875,
"learning_rate": 9.92221044685959e-05,
"loss": 0.7919,
"step": 117
},
{
"epoch": 0.08572911261027504,
"grad_norm": 0.328125,
"learning_rate": 9.920127806815627e-05,
"loss": 0.7853,
"step": 118
},
{
"epoch": 0.08645563051375195,
"grad_norm": 0.330078125,
"learning_rate": 9.918017879238923e-05,
"loss": 0.7467,
"step": 119
},
{
"epoch": 0.08718214841722885,
"grad_norm": 0.357421875,
"learning_rate": 9.915880675831353e-05,
"loss": 0.7656,
"step": 120
},
{
"epoch": 0.08790866632070576,
"grad_norm": 0.345703125,
"learning_rate": 9.913716208446066e-05,
"loss": 0.7742,
"step": 121
},
{
"epoch": 0.08863518422418266,
"grad_norm": 0.345703125,
"learning_rate": 9.911524489087421e-05,
"loss": 0.7765,
"step": 122
},
{
"epoch": 0.08936170212765958,
"grad_norm": 0.37109375,
"learning_rate": 9.909305529910917e-05,
"loss": 0.7723,
"step": 123
},
{
"epoch": 0.09008822003113648,
"grad_norm": 0.361328125,
"learning_rate": 9.907059343223128e-05,
"loss": 0.7599,
"step": 124
},
{
"epoch": 0.0908147379346134,
"grad_norm": 0.36328125,
"learning_rate": 9.904785941481637e-05,
"loss": 0.7664,
"step": 125
},
{
"epoch": 0.0915412558380903,
"grad_norm": 0.337890625,
"learning_rate": 9.902485337294965e-05,
"loss": 0.7775,
"step": 126
},
{
"epoch": 0.09226777374156721,
"grad_norm": 0.341796875,
"learning_rate": 9.900157543422492e-05,
"loss": 0.7916,
"step": 127
},
{
"epoch": 0.09299429164504411,
"grad_norm": 0.337890625,
"learning_rate": 9.897802572774406e-05,
"loss": 0.7767,
"step": 128
},
{
"epoch": 0.09372080954852102,
"grad_norm": 0.328125,
"learning_rate": 9.895420438411616e-05,
"loss": 0.7873,
"step": 129
},
{
"epoch": 0.09444732745199792,
"grad_norm": 0.337890625,
"learning_rate": 9.893011153545679e-05,
"loss": 0.7981,
"step": 130
},
{
"epoch": 0.09517384535547484,
"grad_norm": 0.314453125,
"learning_rate": 9.89057473153874e-05,
"loss": 0.7582,
"step": 131
},
{
"epoch": 0.09590036325895174,
"grad_norm": 0.359375,
"learning_rate": 9.888111185903441e-05,
"loss": 0.7431,
"step": 132
},
{
"epoch": 0.09662688116242865,
"grad_norm": 0.36328125,
"learning_rate": 9.885620530302864e-05,
"loss": 0.7787,
"step": 133
},
{
"epoch": 0.09735339906590555,
"grad_norm": 0.35546875,
"learning_rate": 9.883102778550434e-05,
"loss": 0.7752,
"step": 134
},
{
"epoch": 0.09807991696938247,
"grad_norm": 0.33984375,
"learning_rate": 9.880557944609863e-05,
"loss": 0.8004,
"step": 135
},
{
"epoch": 0.09880643487285937,
"grad_norm": 0.326171875,
"learning_rate": 9.877986042595062e-05,
"loss": 0.7753,
"step": 136
},
{
"epoch": 0.09953295277633628,
"grad_norm": 0.33203125,
"learning_rate": 9.875387086770059e-05,
"loss": 0.7903,
"step": 137
},
{
"epoch": 0.10025947067981318,
"grad_norm": 0.34375,
"learning_rate": 9.872761091548933e-05,
"loss": 0.8139,
"step": 138
},
{
"epoch": 0.10098598858329008,
"grad_norm": 0.330078125,
"learning_rate": 9.870108071495721e-05,
"loss": 0.7628,
"step": 139
},
{
"epoch": 0.101712506486767,
"grad_norm": 0.349609375,
"learning_rate": 9.867428041324344e-05,
"loss": 0.8121,
"step": 140
},
{
"epoch": 0.1024390243902439,
"grad_norm": 0.337890625,
"learning_rate": 9.864721015898523e-05,
"loss": 0.7859,
"step": 141
},
{
"epoch": 0.10316554229372081,
"grad_norm": 0.357421875,
"learning_rate": 9.861987010231702e-05,
"loss": 0.7762,
"step": 142
},
{
"epoch": 0.10389206019719771,
"grad_norm": 0.30859375,
"learning_rate": 9.859226039486949e-05,
"loss": 0.7674,
"step": 143
},
{
"epoch": 0.10461857810067463,
"grad_norm": 0.326171875,
"learning_rate": 9.856438118976899e-05,
"loss": 0.7817,
"step": 144
},
{
"epoch": 0.10534509600415153,
"grad_norm": 0.369140625,
"learning_rate": 9.853623264163639e-05,
"loss": 0.7743,
"step": 145
},
{
"epoch": 0.10607161390762844,
"grad_norm": 0.33984375,
"learning_rate": 9.850781490658642e-05,
"loss": 0.7647,
"step": 146
},
{
"epoch": 0.10679813181110534,
"grad_norm": 0.3671875,
"learning_rate": 9.84791281422268e-05,
"loss": 0.8197,
"step": 147
},
{
"epoch": 0.10752464971458225,
"grad_norm": 0.365234375,
"learning_rate": 9.845017250765721e-05,
"loss": 0.7995,
"step": 148
},
{
"epoch": 0.10825116761805915,
"grad_norm": 0.345703125,
"learning_rate": 9.84209481634686e-05,
"loss": 0.7803,
"step": 149
},
{
"epoch": 0.10897768552153607,
"grad_norm": 0.333984375,
"learning_rate": 9.839145527174215e-05,
"loss": 0.7709,
"step": 150
},
{
"epoch": 0.10970420342501297,
"grad_norm": 0.3359375,
"learning_rate": 9.836169399604847e-05,
"loss": 0.788,
"step": 151
},
{
"epoch": 0.11043072132848988,
"grad_norm": 0.341796875,
"learning_rate": 9.833166450144666e-05,
"loss": 0.7845,
"step": 152
},
{
"epoch": 0.11115723923196678,
"grad_norm": 0.322265625,
"learning_rate": 9.830136695448333e-05,
"loss": 0.7392,
"step": 153
},
{
"epoch": 0.1118837571354437,
"grad_norm": 0.38671875,
"learning_rate": 9.827080152319182e-05,
"loss": 0.7959,
"step": 154
},
{
"epoch": 0.1126102750389206,
"grad_norm": 0.314453125,
"learning_rate": 9.823996837709113e-05,
"loss": 0.7449,
"step": 155
},
{
"epoch": 0.11333679294239751,
"grad_norm": 0.41796875,
"learning_rate": 9.820886768718502e-05,
"loss": 0.7719,
"step": 156
},
{
"epoch": 0.11406331084587441,
"grad_norm": 0.359375,
"learning_rate": 9.817749962596115e-05,
"loss": 0.7882,
"step": 157
},
{
"epoch": 0.11478982874935133,
"grad_norm": 0.37109375,
"learning_rate": 9.814586436738998e-05,
"loss": 0.8004,
"step": 158
},
{
"epoch": 0.11551634665282823,
"grad_norm": 0.341796875,
"learning_rate": 9.811396208692387e-05,
"loss": 0.7709,
"step": 159
},
{
"epoch": 0.11624286455630514,
"grad_norm": 0.365234375,
"learning_rate": 9.808179296149616e-05,
"loss": 0.7887,
"step": 160
},
{
"epoch": 0.11696938245978204,
"grad_norm": 0.328125,
"learning_rate": 9.804935716952011e-05,
"loss": 0.7643,
"step": 161
},
{
"epoch": 0.11769590036325896,
"grad_norm": 0.337890625,
"learning_rate": 9.801665489088794e-05,
"loss": 0.7757,
"step": 162
},
{
"epoch": 0.11842241826673586,
"grad_norm": 0.33984375,
"learning_rate": 9.798368630696983e-05,
"loss": 0.766,
"step": 163
},
{
"epoch": 0.11914893617021277,
"grad_norm": 0.373046875,
"learning_rate": 9.795045160061295e-05,
"loss": 0.7741,
"step": 164
},
{
"epoch": 0.11987545407368967,
"grad_norm": 0.349609375,
"learning_rate": 9.791695095614035e-05,
"loss": 0.7788,
"step": 165
},
{
"epoch": 0.12060197197716659,
"grad_norm": 0.330078125,
"learning_rate": 9.788318455935007e-05,
"loss": 0.7778,
"step": 166
},
{
"epoch": 0.12132848988064349,
"grad_norm": 0.3125,
"learning_rate": 9.784915259751399e-05,
"loss": 0.7751,
"step": 167
},
{
"epoch": 0.1220550077841204,
"grad_norm": 0.32421875,
"learning_rate": 9.781485525937684e-05,
"loss": 0.7767,
"step": 168
},
{
"epoch": 0.1227815256875973,
"grad_norm": 0.341796875,
"learning_rate": 9.778029273515518e-05,
"loss": 0.7782,
"step": 169
},
{
"epoch": 0.12350804359107422,
"grad_norm": 0.32421875,
"learning_rate": 9.774546521653633e-05,
"loss": 0.7714,
"step": 170
},
{
"epoch": 0.12423456149455112,
"grad_norm": 0.33984375,
"learning_rate": 9.771037289667727e-05,
"loss": 0.7638,
"step": 171
},
{
"epoch": 0.12496107939802802,
"grad_norm": 0.326171875,
"learning_rate": 9.767501597020357e-05,
"loss": 0.7875,
"step": 172
},
{
"epoch": 0.12568759730150492,
"grad_norm": 0.33203125,
"learning_rate": 9.763939463320839e-05,
"loss": 0.7364,
"step": 173
},
{
"epoch": 0.12641411520498183,
"grad_norm": 0.349609375,
"learning_rate": 9.76035090832513e-05,
"loss": 0.767,
"step": 174
},
{
"epoch": 0.12714063310845874,
"grad_norm": 0.365234375,
"learning_rate": 9.756735951935725e-05,
"loss": 0.7817,
"step": 175
},
{
"epoch": 0.12786715101193566,
"grad_norm": 0.345703125,
"learning_rate": 9.753094614201541e-05,
"loss": 0.7789,
"step": 176
},
{
"epoch": 0.12859366891541255,
"grad_norm": 0.330078125,
"learning_rate": 9.749426915317812e-05,
"loss": 0.7702,
"step": 177
},
{
"epoch": 0.12932018681888946,
"grad_norm": 0.330078125,
"learning_rate": 9.745732875625971e-05,
"loss": 0.7681,
"step": 178
},
{
"epoch": 0.13004670472236637,
"grad_norm": 0.326171875,
"learning_rate": 9.742012515613537e-05,
"loss": 0.7466,
"step": 179
},
{
"epoch": 0.1307732226258433,
"grad_norm": 0.337890625,
"learning_rate": 9.738265855914013e-05,
"loss": 0.8001,
"step": 180
},
{
"epoch": 0.13149974052932017,
"grad_norm": 0.3125,
"learning_rate": 9.734492917306754e-05,
"loss": 0.7489,
"step": 181
},
{
"epoch": 0.1322262584327971,
"grad_norm": 0.326171875,
"learning_rate": 9.730693720716866e-05,
"loss": 0.7751,
"step": 182
},
{
"epoch": 0.132952776336274,
"grad_norm": 0.32421875,
"learning_rate": 9.72686828721508e-05,
"loss": 0.762,
"step": 183
},
{
"epoch": 0.13367929423975092,
"grad_norm": 0.326171875,
"learning_rate": 9.723016638017643e-05,
"loss": 0.7672,
"step": 184
},
{
"epoch": 0.1344058121432278,
"grad_norm": 0.32421875,
"learning_rate": 9.719138794486198e-05,
"loss": 0.7538,
"step": 185
},
{
"epoch": 0.13513233004670472,
"grad_norm": 0.359375,
"learning_rate": 9.715234778127659e-05,
"loss": 0.7822,
"step": 186
},
{
"epoch": 0.13585884795018163,
"grad_norm": 0.314453125,
"learning_rate": 9.711304610594104e-05,
"loss": 0.7686,
"step": 187
},
{
"epoch": 0.13658536585365855,
"grad_norm": 0.3359375,
"learning_rate": 9.70734831368264e-05,
"loss": 0.7779,
"step": 188
},
{
"epoch": 0.13731188375713543,
"grad_norm": 0.333984375,
"learning_rate": 9.7033659093353e-05,
"loss": 0.7792,
"step": 189
},
{
"epoch": 0.13803840166061235,
"grad_norm": 0.337890625,
"learning_rate": 9.699357419638904e-05,
"loss": 0.7894,
"step": 190
},
{
"epoch": 0.13876491956408926,
"grad_norm": 0.32421875,
"learning_rate": 9.695322866824947e-05,
"loss": 0.7705,
"step": 191
},
{
"epoch": 0.13949143746756618,
"grad_norm": 0.32421875,
"learning_rate": 9.691262273269471e-05,
"loss": 0.7551,
"step": 192
},
{
"epoch": 0.14021795537104306,
"grad_norm": 0.33984375,
"learning_rate": 9.687175661492944e-05,
"loss": 0.7776,
"step": 193
},
{
"epoch": 0.14094447327451998,
"grad_norm": 0.314453125,
"learning_rate": 9.683063054160135e-05,
"loss": 0.7667,
"step": 194
},
{
"epoch": 0.1416709911779969,
"grad_norm": 0.330078125,
"learning_rate": 9.678924474079985e-05,
"loss": 0.7554,
"step": 195
},
{
"epoch": 0.1423975090814738,
"grad_norm": 0.357421875,
"learning_rate": 9.67475994420548e-05,
"loss": 0.8083,
"step": 196
},
{
"epoch": 0.1431240269849507,
"grad_norm": 0.330078125,
"learning_rate": 9.670569487633534e-05,
"loss": 0.7444,
"step": 197
},
{
"epoch": 0.1438505448884276,
"grad_norm": 0.328125,
"learning_rate": 9.666353127604844e-05,
"loss": 0.7737,
"step": 198
},
{
"epoch": 0.14457706279190452,
"grad_norm": 0.33984375,
"learning_rate": 9.662110887503779e-05,
"loss": 0.7883,
"step": 199
},
{
"epoch": 0.14530358069538143,
"grad_norm": 0.314453125,
"learning_rate": 9.657842790858234e-05,
"loss": 0.7233,
"step": 200
},
{
"epoch": 0.14603009859885832,
"grad_norm": 0.349609375,
"learning_rate": 9.65354886133951e-05,
"loss": 0.7707,
"step": 201
},
{
"epoch": 0.14675661650233524,
"grad_norm": 0.32421875,
"learning_rate": 9.64922912276218e-05,
"loss": 0.7688,
"step": 202
},
{
"epoch": 0.14748313440581215,
"grad_norm": 0.34375,
"learning_rate": 9.644883599083958e-05,
"loss": 0.7714,
"step": 203
},
{
"epoch": 0.14820965230928906,
"grad_norm": 0.3515625,
"learning_rate": 9.640512314405563e-05,
"loss": 0.7755,
"step": 204
},
{
"epoch": 0.14893617021276595,
"grad_norm": 0.33203125,
"learning_rate": 9.636115292970587e-05,
"loss": 0.8208,
"step": 205
},
{
"epoch": 0.14966268811624286,
"grad_norm": 0.34375,
"learning_rate": 9.63169255916536e-05,
"loss": 0.7688,
"step": 206
},
{
"epoch": 0.15038920601971978,
"grad_norm": 0.31640625,
"learning_rate": 9.62724413751882e-05,
"loss": 0.7456,
"step": 207
},
{
"epoch": 0.15111572392319667,
"grad_norm": 0.359375,
"learning_rate": 9.622770052702366e-05,
"loss": 0.7764,
"step": 208
},
{
"epoch": 0.15184224182667358,
"grad_norm": 0.357421875,
"learning_rate": 9.618270329529733e-05,
"loss": 0.7903,
"step": 209
},
{
"epoch": 0.1525687597301505,
"grad_norm": 0.32421875,
"learning_rate": 9.613744992956843e-05,
"loss": 0.7441,
"step": 210
},
{
"epoch": 0.1532952776336274,
"grad_norm": 0.3515625,
"learning_rate": 9.609194068081682e-05,
"loss": 0.7573,
"step": 211
},
{
"epoch": 0.1540217955371043,
"grad_norm": 0.3125,
"learning_rate": 9.604617580144139e-05,
"loss": 0.7693,
"step": 212
},
{
"epoch": 0.1547483134405812,
"grad_norm": 0.345703125,
"learning_rate": 9.600015554525889e-05,
"loss": 0.742,
"step": 213
},
{
"epoch": 0.15547483134405812,
"grad_norm": 0.353515625,
"learning_rate": 9.595388016750235e-05,
"loss": 0.7599,
"step": 214
},
{
"epoch": 0.15620134924753504,
"grad_norm": 0.32421875,
"learning_rate": 9.590734992481978e-05,
"loss": 0.7471,
"step": 215
},
{
"epoch": 0.15692786715101192,
"grad_norm": 0.3203125,
"learning_rate": 9.586056507527266e-05,
"loss": 0.7478,
"step": 216
},
{
"epoch": 0.15765438505448884,
"grad_norm": 0.337890625,
"learning_rate": 9.581352587833454e-05,
"loss": 0.7615,
"step": 217
},
{
"epoch": 0.15838090295796575,
"grad_norm": 0.32421875,
"learning_rate": 9.576623259488966e-05,
"loss": 0.7497,
"step": 218
},
{
"epoch": 0.15910742086144267,
"grad_norm": 0.302734375,
"learning_rate": 9.571868548723137e-05,
"loss": 0.7303,
"step": 219
},
{
"epoch": 0.15983393876491955,
"grad_norm": 0.33203125,
"learning_rate": 9.567088481906083e-05,
"loss": 0.763,
"step": 220
},
{
"epoch": 0.16056045666839647,
"grad_norm": 0.353515625,
"learning_rate": 9.562283085548545e-05,
"loss": 0.82,
"step": 221
},
{
"epoch": 0.16128697457187338,
"grad_norm": 0.333984375,
"learning_rate": 9.55745238630174e-05,
"loss": 0.7618,
"step": 222
},
{
"epoch": 0.1620134924753503,
"grad_norm": 0.345703125,
"learning_rate": 9.552596410957224e-05,
"loss": 0.8178,
"step": 223
},
{
"epoch": 0.16274001037882718,
"grad_norm": 0.341796875,
"learning_rate": 9.547715186446731e-05,
"loss": 0.7483,
"step": 224
},
{
"epoch": 0.1634665282823041,
"grad_norm": 0.345703125,
"learning_rate": 9.542808739842032e-05,
"loss": 0.764,
"step": 225
},
{
"epoch": 0.164193046185781,
"grad_norm": 0.330078125,
"learning_rate": 9.537877098354786e-05,
"loss": 0.7568,
"step": 226
},
{
"epoch": 0.16491956408925793,
"grad_norm": 0.421875,
"learning_rate": 9.532920289336378e-05,
"loss": 0.7691,
"step": 227
},
{
"epoch": 0.1656460819927348,
"grad_norm": 0.345703125,
"learning_rate": 9.52793834027778e-05,
"loss": 0.7859,
"step": 228
},
{
"epoch": 0.16637259989621173,
"grad_norm": 0.32421875,
"learning_rate": 9.522931278809392e-05,
"loss": 0.7231,
"step": 229
},
{
"epoch": 0.16709911779968864,
"grad_norm": 0.353515625,
"learning_rate": 9.517899132700889e-05,
"loss": 0.7475,
"step": 230
},
{
"epoch": 0.16782563570316555,
"grad_norm": 0.3515625,
"learning_rate": 9.51284192986107e-05,
"loss": 0.7755,
"step": 231
},
{
"epoch": 0.16855215360664244,
"grad_norm": 0.33984375,
"learning_rate": 9.507759698337697e-05,
"loss": 0.7867,
"step": 232
},
{
"epoch": 0.16927867151011936,
"grad_norm": 0.369140625,
"learning_rate": 9.50265246631735e-05,
"loss": 0.8128,
"step": 233
},
{
"epoch": 0.17000518941359627,
"grad_norm": 0.330078125,
"learning_rate": 9.49752026212526e-05,
"loss": 0.7842,
"step": 234
},
{
"epoch": 0.17073170731707318,
"grad_norm": 0.3359375,
"learning_rate": 9.492363114225155e-05,
"loss": 0.722,
"step": 235
},
{
"epoch": 0.17145822522055007,
"grad_norm": 0.359375,
"learning_rate": 9.487181051219107e-05,
"loss": 0.7531,
"step": 236
},
{
"epoch": 0.17218474312402698,
"grad_norm": 0.36328125,
"learning_rate": 9.48197410184737e-05,
"loss": 0.7854,
"step": 237
},
{
"epoch": 0.1729112610275039,
"grad_norm": 0.341796875,
"learning_rate": 9.476742294988214e-05,
"loss": 0.7672,
"step": 238
},
{
"epoch": 0.1736377789309808,
"grad_norm": 0.345703125,
"learning_rate": 9.471485659657781e-05,
"loss": 0.7605,
"step": 239
},
{
"epoch": 0.1743642968344577,
"grad_norm": 0.3359375,
"learning_rate": 9.466204225009905e-05,
"loss": 0.7672,
"step": 240
},
{
"epoch": 0.1750908147379346,
"grad_norm": 0.3671875,
"learning_rate": 9.460898020335964e-05,
"loss": 0.7913,
"step": 241
},
{
"epoch": 0.17581733264141153,
"grad_norm": 0.359375,
"learning_rate": 9.455567075064716e-05,
"loss": 0.7898,
"step": 242
},
{
"epoch": 0.17654385054488841,
"grad_norm": 0.314453125,
"learning_rate": 9.450211418762124e-05,
"loss": 0.7437,
"step": 243
},
{
"epoch": 0.17727036844836533,
"grad_norm": 0.33984375,
"learning_rate": 9.444831081131209e-05,
"loss": 0.7386,
"step": 244
},
{
"epoch": 0.17799688635184224,
"grad_norm": 0.333984375,
"learning_rate": 9.439426092011875e-05,
"loss": 0.7931,
"step": 245
},
{
"epoch": 0.17872340425531916,
"grad_norm": 0.326171875,
"learning_rate": 9.433996481380747e-05,
"loss": 0.7717,
"step": 246
},
{
"epoch": 0.17944992215879604,
"grad_norm": 0.345703125,
"learning_rate": 9.428542279351e-05,
"loss": 0.7768,
"step": 247
},
{
"epoch": 0.18017644006227296,
"grad_norm": 0.388671875,
"learning_rate": 9.423063516172195e-05,
"loss": 0.7962,
"step": 248
},
{
"epoch": 0.18090295796574987,
"grad_norm": 0.353515625,
"learning_rate": 9.417560222230115e-05,
"loss": 0.7777,
"step": 249
},
{
"epoch": 0.1816294758692268,
"grad_norm": 0.3203125,
"learning_rate": 9.412032428046594e-05,
"loss": 0.7721,
"step": 250
},
{
"epoch": 0.18235599377270367,
"grad_norm": 0.349609375,
"learning_rate": 9.40648016427934e-05,
"loss": 0.766,
"step": 251
},
{
"epoch": 0.1830825116761806,
"grad_norm": 0.3203125,
"learning_rate": 9.400903461721783e-05,
"loss": 0.7602,
"step": 252
},
{
"epoch": 0.1838090295796575,
"grad_norm": 0.3515625,
"learning_rate": 9.395302351302882e-05,
"loss": 0.7717,
"step": 253
},
{
"epoch": 0.18453554748313442,
"grad_norm": 0.32421875,
"learning_rate": 9.389676864086969e-05,
"loss": 0.7732,
"step": 254
},
{
"epoch": 0.1852620653866113,
"grad_norm": 0.32421875,
"learning_rate": 9.384027031273575e-05,
"loss": 0.7584,
"step": 255
},
{
"epoch": 0.18598858329008822,
"grad_norm": 0.345703125,
"learning_rate": 9.378352884197249e-05,
"loss": 0.772,
"step": 256
},
{
"epoch": 0.18671510119356513,
"grad_norm": 0.310546875,
"learning_rate": 9.372654454327393e-05,
"loss": 0.7012,
"step": 257
},
{
"epoch": 0.18744161909704204,
"grad_norm": 0.326171875,
"learning_rate": 9.366931773268082e-05,
"loss": 0.7558,
"step": 258
},
{
"epoch": 0.18816813700051893,
"grad_norm": 0.3046875,
"learning_rate": 9.361184872757894e-05,
"loss": 0.733,
"step": 259
},
{
"epoch": 0.18889465490399585,
"grad_norm": 0.349609375,
"learning_rate": 9.355413784669722e-05,
"loss": 0.78,
"step": 260
},
{
"epoch": 0.18962117280747276,
"grad_norm": 0.373046875,
"learning_rate": 9.349618541010616e-05,
"loss": 0.7784,
"step": 261
},
{
"epoch": 0.19034769071094967,
"grad_norm": 0.357421875,
"learning_rate": 9.343799173921592e-05,
"loss": 0.8008,
"step": 262
},
{
"epoch": 0.19107420861442656,
"grad_norm": 0.31640625,
"learning_rate": 9.337955715677452e-05,
"loss": 0.7713,
"step": 263
},
{
"epoch": 0.19180072651790347,
"grad_norm": 0.322265625,
"learning_rate": 9.332088198686617e-05,
"loss": 0.7816,
"step": 264
},
{
"epoch": 0.1925272444213804,
"grad_norm": 0.302734375,
"learning_rate": 9.326196655490935e-05,
"loss": 0.7611,
"step": 265
},
{
"epoch": 0.1932537623248573,
"grad_norm": 0.31640625,
"learning_rate": 9.320281118765509e-05,
"loss": 0.8111,
"step": 266
},
{
"epoch": 0.1939802802283342,
"grad_norm": 0.310546875,
"learning_rate": 9.314341621318512e-05,
"loss": 0.7739,
"step": 267
},
{
"epoch": 0.1947067981318111,
"grad_norm": 0.345703125,
"learning_rate": 9.308378196091005e-05,
"loss": 0.7973,
"step": 268
},
{
"epoch": 0.19543331603528802,
"grad_norm": 0.349609375,
"learning_rate": 9.302390876156755e-05,
"loss": 0.7643,
"step": 269
},
{
"epoch": 0.19615983393876493,
"grad_norm": 0.3359375,
"learning_rate": 9.296379694722051e-05,
"loss": 0.7533,
"step": 270
},
{
"epoch": 0.19688635184224182,
"grad_norm": 0.33203125,
"learning_rate": 9.29034468512552e-05,
"loss": 0.7358,
"step": 271
},
{
"epoch": 0.19761286974571873,
"grad_norm": 0.326171875,
"learning_rate": 9.284285880837946e-05,
"loss": 0.7721,
"step": 272
},
{
"epoch": 0.19833938764919565,
"grad_norm": 0.314453125,
"learning_rate": 9.278203315462078e-05,
"loss": 0.7492,
"step": 273
},
{
"epoch": 0.19906590555267256,
"grad_norm": 0.3359375,
"learning_rate": 9.272097022732443e-05,
"loss": 0.7713,
"step": 274
},
{
"epoch": 0.19979242345614945,
"grad_norm": 0.318359375,
"learning_rate": 9.265967036515169e-05,
"loss": 0.7322,
"step": 275
},
{
"epoch": 0.20051894135962636,
"grad_norm": 0.33203125,
"learning_rate": 9.259813390807787e-05,
"loss": 0.7863,
"step": 276
},
{
"epoch": 0.20124545926310328,
"grad_norm": 0.328125,
"learning_rate": 9.253636119739046e-05,
"loss": 0.7786,
"step": 277
},
{
"epoch": 0.20197197716658016,
"grad_norm": 0.34375,
"learning_rate": 9.247435257568724e-05,
"loss": 0.7775,
"step": 278
},
{
"epoch": 0.20269849507005708,
"grad_norm": 0.3125,
"learning_rate": 9.241210838687437e-05,
"loss": 0.7346,
"step": 279
},
{
"epoch": 0.203425012973534,
"grad_norm": 0.32421875,
"learning_rate": 9.23496289761645e-05,
"loss": 0.7301,
"step": 280
},
{
"epoch": 0.2041515308770109,
"grad_norm": 0.33203125,
"learning_rate": 9.228691469007487e-05,
"loss": 0.7649,
"step": 281
},
{
"epoch": 0.2048780487804878,
"grad_norm": 0.330078125,
"learning_rate": 9.222396587642528e-05,
"loss": 0.738,
"step": 282
},
{
"epoch": 0.2056045666839647,
"grad_norm": 0.33984375,
"learning_rate": 9.216078288433632e-05,
"loss": 0.7302,
"step": 283
},
{
"epoch": 0.20633108458744162,
"grad_norm": 0.322265625,
"learning_rate": 9.209736606422736e-05,
"loss": 0.7557,
"step": 284
},
{
"epoch": 0.20705760249091854,
"grad_norm": 0.30859375,
"learning_rate": 9.203371576781457e-05,
"loss": 0.7766,
"step": 285
},
{
"epoch": 0.20778412039439542,
"grad_norm": 0.3359375,
"learning_rate": 9.196983234810899e-05,
"loss": 0.7805,
"step": 286
},
{
"epoch": 0.20851063829787234,
"grad_norm": 0.322265625,
"learning_rate": 9.190571615941462e-05,
"loss": 0.7766,
"step": 287
},
{
"epoch": 0.20923715620134925,
"grad_norm": 0.330078125,
"learning_rate": 9.18413675573264e-05,
"loss": 0.7884,
"step": 288
},
{
"epoch": 0.20996367410482616,
"grad_norm": 0.333984375,
"learning_rate": 9.17767868987283e-05,
"loss": 0.7657,
"step": 289
},
{
"epoch": 0.21069019200830305,
"grad_norm": 0.35546875,
"learning_rate": 9.171197454179124e-05,
"loss": 0.814,
"step": 290
},
{
"epoch": 0.21141670991177997,
"grad_norm": 0.310546875,
"learning_rate": 9.16469308459712e-05,
"loss": 0.7597,
"step": 291
},
{
"epoch": 0.21214322781525688,
"grad_norm": 0.326171875,
"learning_rate": 9.158165617200717e-05,
"loss": 0.7497,
"step": 292
},
{
"epoch": 0.2128697457187338,
"grad_norm": 0.38671875,
"learning_rate": 9.151615088191918e-05,
"loss": 0.7765,
"step": 293
},
{
"epoch": 0.21359626362221068,
"grad_norm": 0.32421875,
"learning_rate": 9.145041533900628e-05,
"loss": 0.7765,
"step": 294
},
{
"epoch": 0.2143227815256876,
"grad_norm": 0.341796875,
"learning_rate": 9.138444990784453e-05,
"loss": 0.778,
"step": 295
},
{
"epoch": 0.2150492994291645,
"grad_norm": 0.33203125,
"learning_rate": 9.131825495428496e-05,
"loss": 0.7671,
"step": 296
},
{
"epoch": 0.21577581733264142,
"grad_norm": 0.35546875,
"learning_rate": 9.125183084545157e-05,
"loss": 0.7727,
"step": 297
},
{
"epoch": 0.2165023352361183,
"grad_norm": 0.328125,
"learning_rate": 9.118517794973926e-05,
"loss": 0.7337,
"step": 298
},
{
"epoch": 0.21722885313959522,
"grad_norm": 0.310546875,
"learning_rate": 9.111829663681181e-05,
"loss": 0.7726,
"step": 299
},
{
"epoch": 0.21795537104307214,
"grad_norm": 0.3203125,
"learning_rate": 9.105118727759985e-05,
"loss": 0.7114,
"step": 300
},
{
"epoch": 0.21868188894654905,
"grad_norm": 0.3359375,
"learning_rate": 9.098385024429875e-05,
"loss": 0.7853,
"step": 301
},
{
"epoch": 0.21940840685002594,
"grad_norm": 0.35546875,
"learning_rate": 9.091628591036661e-05,
"loss": 0.7678,
"step": 302
},
{
"epoch": 0.22013492475350285,
"grad_norm": 0.34375,
"learning_rate": 9.08484946505221e-05,
"loss": 0.7632,
"step": 303
},
{
"epoch": 0.22086144265697977,
"grad_norm": 0.345703125,
"learning_rate": 9.078047684074255e-05,
"loss": 0.7378,
"step": 304
},
{
"epoch": 0.22158796056045668,
"grad_norm": 0.302734375,
"learning_rate": 9.071223285826165e-05,
"loss": 0.7567,
"step": 305
},
{
"epoch": 0.22231447846393357,
"grad_norm": 0.318359375,
"learning_rate": 9.064376308156754e-05,
"loss": 0.7308,
"step": 306
},
{
"epoch": 0.22304099636741048,
"grad_norm": 0.310546875,
"learning_rate": 9.057506789040064e-05,
"loss": 0.7288,
"step": 307
},
{
"epoch": 0.2237675142708874,
"grad_norm": 0.337890625,
"learning_rate": 9.050614766575146e-05,
"loss": 0.7287,
"step": 308
},
{
"epoch": 0.22449403217436428,
"grad_norm": 0.328125,
"learning_rate": 9.043700278985868e-05,
"loss": 0.7559,
"step": 309
},
{
"epoch": 0.2252205500778412,
"grad_norm": 0.314453125,
"learning_rate": 9.036763364620679e-05,
"loss": 0.7632,
"step": 310
},
{
"epoch": 0.2259470679813181,
"grad_norm": 0.32421875,
"learning_rate": 9.029804061952425e-05,
"loss": 0.7549,
"step": 311
},
{
"epoch": 0.22667358588479503,
"grad_norm": 0.33984375,
"learning_rate": 9.022822409578105e-05,
"loss": 0.7744,
"step": 312
},
{
"epoch": 0.2274001037882719,
"grad_norm": 0.328125,
"learning_rate": 9.015818446218682e-05,
"loss": 0.7641,
"step": 313
},
{
"epoch": 0.22812662169174883,
"grad_norm": 0.33984375,
"learning_rate": 9.008792210718853e-05,
"loss": 0.7743,
"step": 314
},
{
"epoch": 0.22885313959522574,
"grad_norm": 0.3125,
"learning_rate": 9.001743742046839e-05,
"loss": 0.766,
"step": 315
},
{
"epoch": 0.22957965749870266,
"grad_norm": 0.326171875,
"learning_rate": 8.994673079294171e-05,
"loss": 0.7728,
"step": 316
},
{
"epoch": 0.23030617540217954,
"grad_norm": 0.3125,
"learning_rate": 8.987580261675465e-05,
"loss": 0.7459,
"step": 317
},
{
"epoch": 0.23103269330565646,
"grad_norm": 0.341796875,
"learning_rate": 8.980465328528219e-05,
"loss": 0.7609,
"step": 318
},
{
"epoch": 0.23175921120913337,
"grad_norm": 0.3046875,
"learning_rate": 8.973328319312577e-05,
"loss": 0.7334,
"step": 319
},
{
"epoch": 0.23248572911261028,
"grad_norm": 0.349609375,
"learning_rate": 8.966169273611125e-05,
"loss": 0.8078,
"step": 320
},
{
"epoch": 0.23321224701608717,
"grad_norm": 0.330078125,
"learning_rate": 8.958988231128664e-05,
"loss": 0.7582,
"step": 321
},
{
"epoch": 0.23393876491956409,
"grad_norm": 0.35546875,
"learning_rate": 8.95178523169199e-05,
"loss": 0.7539,
"step": 322
},
{
"epoch": 0.234665282823041,
"grad_norm": 0.341796875,
"learning_rate": 8.944560315249675e-05,
"loss": 0.7647,
"step": 323
},
{
"epoch": 0.2353918007265179,
"grad_norm": 0.330078125,
"learning_rate": 8.937313521871846e-05,
"loss": 0.7817,
"step": 324
},
{
"epoch": 0.2361183186299948,
"grad_norm": 0.310546875,
"learning_rate": 8.930044891749962e-05,
"loss": 0.765,
"step": 325
},
{
"epoch": 0.23684483653347171,
"grad_norm": 0.34765625,
"learning_rate": 8.922754465196591e-05,
"loss": 0.7674,
"step": 326
},
{
"epoch": 0.23757135443694863,
"grad_norm": 0.314453125,
"learning_rate": 8.915442282645184e-05,
"loss": 0.7319,
"step": 327
},
{
"epoch": 0.23829787234042554,
"grad_norm": 0.365234375,
"learning_rate": 8.908108384649855e-05,
"loss": 0.7707,
"step": 328
},
{
"epoch": 0.23902439024390243,
"grad_norm": 0.337890625,
"learning_rate": 8.900752811885152e-05,
"loss": 0.7503,
"step": 329
},
{
"epoch": 0.23975090814737934,
"grad_norm": 0.349609375,
"learning_rate": 8.893375605145836e-05,
"loss": 0.8007,
"step": 330
},
{
"epoch": 0.24047742605085626,
"grad_norm": 0.330078125,
"learning_rate": 8.885976805346651e-05,
"loss": 0.772,
"step": 331
},
{
"epoch": 0.24120394395433317,
"grad_norm": 0.3359375,
"learning_rate": 8.8785564535221e-05,
"loss": 0.7938,
"step": 332
},
{
"epoch": 0.24193046185781006,
"grad_norm": 0.3359375,
"learning_rate": 8.87111459082621e-05,
"loss": 0.7481,
"step": 333
},
{
"epoch": 0.24265697976128697,
"grad_norm": 0.33203125,
"learning_rate": 8.86365125853232e-05,
"loss": 0.7492,
"step": 334
},
{
"epoch": 0.2433834976647639,
"grad_norm": 0.345703125,
"learning_rate": 8.85616649803283e-05,
"loss": 0.7573,
"step": 335
},
{
"epoch": 0.2441100155682408,
"grad_norm": 0.322265625,
"learning_rate": 8.84866035083899e-05,
"loss": 0.7671,
"step": 336
},
{
"epoch": 0.2448365334717177,
"grad_norm": 0.33984375,
"learning_rate": 8.841132858580661e-05,
"loss": 0.7434,
"step": 337
},
{
"epoch": 0.2455630513751946,
"grad_norm": 0.337890625,
"learning_rate": 8.833584063006087e-05,
"loss": 0.7638,
"step": 338
},
{
"epoch": 0.24628956927867152,
"grad_norm": 0.3515625,
"learning_rate": 8.826014005981661e-05,
"loss": 0.792,
"step": 339
},
{
"epoch": 0.24701608718214843,
"grad_norm": 0.349609375,
"learning_rate": 8.818422729491693e-05,
"loss": 0.7902,
"step": 340
},
{
"epoch": 0.24774260508562532,
"grad_norm": 0.333984375,
"learning_rate": 8.810810275638183e-05,
"loss": 0.7458,
"step": 341
},
{
"epoch": 0.24846912298910223,
"grad_norm": 0.32421875,
"learning_rate": 8.803176686640577e-05,
"loss": 0.7372,
"step": 342
},
{
"epoch": 0.24919564089257915,
"grad_norm": 0.330078125,
"learning_rate": 8.795522004835543e-05,
"loss": 0.7533,
"step": 343
},
{
"epoch": 0.24992215879605603,
"grad_norm": 0.3359375,
"learning_rate": 8.787846272676728e-05,
"loss": 0.7808,
"step": 344
},
{
"epoch": 0.25064867669953295,
"grad_norm": 0.328125,
"learning_rate": 8.780149532734532e-05,
"loss": 0.7348,
"step": 345
},
{
"epoch": 0.25137519460300983,
"grad_norm": 0.318359375,
"learning_rate": 8.772431827695861e-05,
"loss": 0.7803,
"step": 346
},
{
"epoch": 0.2521017125064868,
"grad_norm": 0.33203125,
"learning_rate": 8.764693200363897e-05,
"loss": 0.7639,
"step": 347
},
{
"epoch": 0.25282823040996366,
"grad_norm": 0.34765625,
"learning_rate": 8.756933693657863e-05,
"loss": 0.7761,
"step": 348
},
{
"epoch": 0.2535547483134406,
"grad_norm": 0.330078125,
"learning_rate": 8.749153350612774e-05,
"loss": 0.771,
"step": 349
},
{
"epoch": 0.2542812662169175,
"grad_norm": 0.322265625,
"learning_rate": 8.741352214379211e-05,
"loss": 0.7412,
"step": 350
},
{
"epoch": 0.2550077841203944,
"grad_norm": 0.36328125,
"learning_rate": 8.733530328223075e-05,
"loss": 0.7706,
"step": 351
},
{
"epoch": 0.2557343020238713,
"grad_norm": 0.328125,
"learning_rate": 8.725687735525348e-05,
"loss": 0.7705,
"step": 352
},
{
"epoch": 0.2564608199273482,
"grad_norm": 0.365234375,
"learning_rate": 8.717824479781852e-05,
"loss": 0.7495,
"step": 353
},
{
"epoch": 0.2571873378308251,
"grad_norm": 0.3203125,
"learning_rate": 8.709940604603007e-05,
"loss": 0.7362,
"step": 354
},
{
"epoch": 0.25791385573430203,
"grad_norm": 0.326171875,
"learning_rate": 8.702036153713593e-05,
"loss": 0.7826,
"step": 355
},
{
"epoch": 0.2586403736377789,
"grad_norm": 0.345703125,
"learning_rate": 8.694111170952507e-05,
"loss": 0.7692,
"step": 356
},
{
"epoch": 0.25936689154125586,
"grad_norm": 0.306640625,
"learning_rate": 8.686165700272513e-05,
"loss": 0.7611,
"step": 357
},
{
"epoch": 0.26009340944473275,
"grad_norm": 0.3203125,
"learning_rate": 8.678199785740003e-05,
"loss": 0.7561,
"step": 358
},
{
"epoch": 0.26081992734820963,
"grad_norm": 0.326171875,
"learning_rate": 8.670213471534759e-05,
"loss": 0.7475,
"step": 359
},
{
"epoch": 0.2615464452516866,
"grad_norm": 0.337890625,
"learning_rate": 8.662206801949695e-05,
"loss": 0.7872,
"step": 360
},
{
"epoch": 0.26227296315516346,
"grad_norm": 0.314453125,
"learning_rate": 8.654179821390621e-05,
"loss": 0.7695,
"step": 361
},
{
"epoch": 0.26299948105864035,
"grad_norm": 0.318359375,
"learning_rate": 8.646132574375994e-05,
"loss": 0.747,
"step": 362
},
{
"epoch": 0.2637259989621173,
"grad_norm": 0.3203125,
"learning_rate": 8.638065105536668e-05,
"loss": 0.7394,
"step": 363
},
{
"epoch": 0.2644525168655942,
"grad_norm": 0.349609375,
"learning_rate": 8.629977459615655e-05,
"loss": 0.7879,
"step": 364
},
{
"epoch": 0.2651790347690711,
"grad_norm": 0.3359375,
"learning_rate": 8.621869681467865e-05,
"loss": 0.7738,
"step": 365
},
{
"epoch": 0.265905552672548,
"grad_norm": 0.306640625,
"learning_rate": 8.613741816059866e-05,
"loss": 0.7312,
"step": 366
},
{
"epoch": 0.2666320705760249,
"grad_norm": 0.296875,
"learning_rate": 8.605593908469633e-05,
"loss": 0.7396,
"step": 367
},
{
"epoch": 0.26735858847950184,
"grad_norm": 0.314453125,
"learning_rate": 8.597426003886295e-05,
"loss": 0.7828,
"step": 368
},
{
"epoch": 0.2680851063829787,
"grad_norm": 0.322265625,
"learning_rate": 8.58923814760989e-05,
"loss": 0.7612,
"step": 369
},
{
"epoch": 0.2688116242864556,
"grad_norm": 0.359375,
"learning_rate": 8.581030385051106e-05,
"loss": 0.7672,
"step": 370
},
{
"epoch": 0.26953814218993255,
"grad_norm": 0.32421875,
"learning_rate": 8.572802761731031e-05,
"loss": 0.7782,
"step": 371
},
{
"epoch": 0.27026466009340944,
"grad_norm": 0.330078125,
"learning_rate": 8.564555323280913e-05,
"loss": 0.7253,
"step": 372
},
{
"epoch": 0.2709911779968864,
"grad_norm": 0.31640625,
"learning_rate": 8.556288115441886e-05,
"loss": 0.7142,
"step": 373
},
{
"epoch": 0.27171769590036327,
"grad_norm": 0.31640625,
"learning_rate": 8.548001184064733e-05,
"loss": 0.7538,
"step": 374
},
{
"epoch": 0.27244421380384015,
"grad_norm": 0.333984375,
"learning_rate": 8.539694575109625e-05,
"loss": 0.7604,
"step": 375
},
{
"epoch": 0.2731707317073171,
"grad_norm": 0.318359375,
"learning_rate": 8.531368334645864e-05,
"loss": 0.7597,
"step": 376
},
{
"epoch": 0.273897249610794,
"grad_norm": 0.3203125,
"learning_rate": 8.523022508851633e-05,
"loss": 0.7657,
"step": 377
},
{
"epoch": 0.27462376751427087,
"grad_norm": 0.31640625,
"learning_rate": 8.514657144013738e-05,
"loss": 0.7529,
"step": 378
},
{
"epoch": 0.2753502854177478,
"grad_norm": 0.330078125,
"learning_rate": 8.506272286527346e-05,
"loss": 0.7563,
"step": 379
},
{
"epoch": 0.2760768033212247,
"grad_norm": 0.34375,
"learning_rate": 8.497867982895741e-05,
"loss": 0.7891,
"step": 380
},
{
"epoch": 0.2768033212247016,
"grad_norm": 0.34765625,
"learning_rate": 8.489444279730046e-05,
"loss": 0.7271,
"step": 381
},
{
"epoch": 0.2775298391281785,
"grad_norm": 0.310546875,
"learning_rate": 8.481001223748985e-05,
"loss": 0.7456,
"step": 382
},
{
"epoch": 0.2782563570316554,
"grad_norm": 0.349609375,
"learning_rate": 8.472538861778609e-05,
"loss": 0.7883,
"step": 383
},
{
"epoch": 0.27898287493513235,
"grad_norm": 0.341796875,
"learning_rate": 8.464057240752046e-05,
"loss": 0.7665,
"step": 384
},
{
"epoch": 0.27970939283860924,
"grad_norm": 0.33203125,
"learning_rate": 8.455556407709235e-05,
"loss": 0.7459,
"step": 385
},
{
"epoch": 0.2804359107420861,
"grad_norm": 0.3203125,
"learning_rate": 8.447036409796664e-05,
"loss": 0.7487,
"step": 386
},
{
"epoch": 0.28116242864556307,
"grad_norm": 0.3125,
"learning_rate": 8.438497294267117e-05,
"loss": 0.8181,
"step": 387
},
{
"epoch": 0.28188894654903995,
"grad_norm": 0.32421875,
"learning_rate": 8.429939108479403e-05,
"loss": 0.739,
"step": 388
},
{
"epoch": 0.28261546445251684,
"grad_norm": 0.318359375,
"learning_rate": 8.421361899898095e-05,
"loss": 0.7695,
"step": 389
},
{
"epoch": 0.2833419823559938,
"grad_norm": 0.34375,
"learning_rate": 8.412765716093272e-05,
"loss": 0.7912,
"step": 390
},
{
"epoch": 0.28406850025947067,
"grad_norm": 0.34375,
"learning_rate": 8.404150604740249e-05,
"loss": 0.7798,
"step": 391
},
{
"epoch": 0.2847950181629476,
"grad_norm": 0.3359375,
"learning_rate": 8.395516613619316e-05,
"loss": 0.7703,
"step": 392
},
{
"epoch": 0.2855215360664245,
"grad_norm": 0.345703125,
"learning_rate": 8.386863790615472e-05,
"loss": 0.7709,
"step": 393
},
{
"epoch": 0.2862480539699014,
"grad_norm": 0.326171875,
"learning_rate": 8.378192183718158e-05,
"loss": 0.7453,
"step": 394
},
{
"epoch": 0.2869745718733783,
"grad_norm": 0.322265625,
"learning_rate": 8.369501841020999e-05,
"loss": 0.7592,
"step": 395
},
{
"epoch": 0.2877010897768552,
"grad_norm": 0.32421875,
"learning_rate": 8.360792810721521e-05,
"loss": 0.7557,
"step": 396
},
{
"epoch": 0.2884276076803321,
"grad_norm": 0.33984375,
"learning_rate": 8.352065141120902e-05,
"loss": 0.7671,
"step": 397
},
{
"epoch": 0.28915412558380904,
"grad_norm": 0.345703125,
"learning_rate": 8.343318880623688e-05,
"loss": 0.7635,
"step": 398
},
{
"epoch": 0.2898806434872859,
"grad_norm": 0.306640625,
"learning_rate": 8.334554077737534e-05,
"loss": 0.7413,
"step": 399
},
{
"epoch": 0.29060716139076287,
"grad_norm": 0.3359375,
"learning_rate": 8.325770781072939e-05,
"loss": 0.7853,
"step": 400
},
{
"epoch": 0.29133367929423976,
"grad_norm": 0.322265625,
"learning_rate": 8.316969039342963e-05,
"loss": 0.7264,
"step": 401
},
{
"epoch": 0.29206019719771664,
"grad_norm": 0.31640625,
"learning_rate": 8.308148901362969e-05,
"loss": 0.7638,
"step": 402
},
{
"epoch": 0.2927867151011936,
"grad_norm": 0.32421875,
"learning_rate": 8.299310416050346e-05,
"loss": 0.7771,
"step": 403
},
{
"epoch": 0.29351323300467047,
"grad_norm": 0.322265625,
"learning_rate": 8.290453632424236e-05,
"loss": 0.7364,
"step": 404
},
{
"epoch": 0.29423975090814736,
"grad_norm": 0.3203125,
"learning_rate": 8.281578599605268e-05,
"loss": 0.7548,
"step": 405
},
{
"epoch": 0.2949662688116243,
"grad_norm": 0.3125,
"learning_rate": 8.272685366815287e-05,
"loss": 0.7057,
"step": 406
},
{
"epoch": 0.2956927867151012,
"grad_norm": 0.341796875,
"learning_rate": 8.26377398337707e-05,
"loss": 0.7544,
"step": 407
},
{
"epoch": 0.2964193046185781,
"grad_norm": 0.33203125,
"learning_rate": 8.254844498714061e-05,
"loss": 0.7809,
"step": 408
},
{
"epoch": 0.297145822522055,
"grad_norm": 0.3046875,
"learning_rate": 8.2458969623501e-05,
"loss": 0.7358,
"step": 409
},
{
"epoch": 0.2978723404255319,
"grad_norm": 0.341796875,
"learning_rate": 8.236931423909138e-05,
"loss": 0.7568,
"step": 410
},
{
"epoch": 0.29859885832900884,
"grad_norm": 0.32421875,
"learning_rate": 8.227947933114971e-05,
"loss": 0.7273,
"step": 411
},
{
"epoch": 0.29932537623248573,
"grad_norm": 0.337890625,
"learning_rate": 8.218946539790958e-05,
"loss": 0.802,
"step": 412
},
{
"epoch": 0.3000518941359626,
"grad_norm": 0.333984375,
"learning_rate": 8.209927293859745e-05,
"loss": 0.773,
"step": 413
},
{
"epoch": 0.30077841203943956,
"grad_norm": 0.318359375,
"learning_rate": 8.200890245342998e-05,
"loss": 0.7754,
"step": 414
},
{
"epoch": 0.30150492994291644,
"grad_norm": 0.330078125,
"learning_rate": 8.191835444361114e-05,
"loss": 0.8057,
"step": 415
},
{
"epoch": 0.30223144784639333,
"grad_norm": 0.33203125,
"learning_rate": 8.182762941132944e-05,
"loss": 0.7943,
"step": 416
},
{
"epoch": 0.3029579657498703,
"grad_norm": 0.353515625,
"learning_rate": 8.173672785975522e-05,
"loss": 0.8197,
"step": 417
},
{
"epoch": 0.30368448365334716,
"grad_norm": 0.3203125,
"learning_rate": 8.164565029303778e-05,
"loss": 0.7861,
"step": 418
},
{
"epoch": 0.3044110015568241,
"grad_norm": 0.3359375,
"learning_rate": 8.155439721630264e-05,
"loss": 0.7669,
"step": 419
},
{
"epoch": 0.305137519460301,
"grad_norm": 0.3359375,
"learning_rate": 8.146296913564873e-05,
"loss": 0.7549,
"step": 420
},
{
"epoch": 0.3058640373637779,
"grad_norm": 0.3359375,
"learning_rate": 8.13713665581455e-05,
"loss": 0.7398,
"step": 421
},
{
"epoch": 0.3065905552672548,
"grad_norm": 0.333984375,
"learning_rate": 8.127958999183027e-05,
"loss": 0.7686,
"step": 422
},
{
"epoch": 0.3073170731707317,
"grad_norm": 0.32421875,
"learning_rate": 8.118763994570527e-05,
"loss": 0.7191,
"step": 423
},
{
"epoch": 0.3080435910742086,
"grad_norm": 0.318359375,
"learning_rate": 8.109551692973487e-05,
"loss": 0.7567,
"step": 424
},
{
"epoch": 0.30877010897768553,
"grad_norm": 0.33984375,
"learning_rate": 8.100322145484274e-05,
"loss": 0.7625,
"step": 425
},
{
"epoch": 0.3094966268811624,
"grad_norm": 0.3203125,
"learning_rate": 8.091075403290905e-05,
"loss": 0.7572,
"step": 426
},
{
"epoch": 0.31022314478463936,
"grad_norm": 0.3125,
"learning_rate": 8.081811517676759e-05,
"loss": 0.7155,
"step": 427
},
{
"epoch": 0.31094966268811625,
"grad_norm": 0.31640625,
"learning_rate": 8.072530540020293e-05,
"loss": 0.7208,
"step": 428
},
{
"epoch": 0.31167618059159313,
"grad_norm": 0.333984375,
"learning_rate": 8.063232521794762e-05,
"loss": 0.7276,
"step": 429
},
{
"epoch": 0.3124026984950701,
"grad_norm": 0.31640625,
"learning_rate": 8.053917514567927e-05,
"loss": 0.7622,
"step": 430
},
{
"epoch": 0.31312921639854696,
"grad_norm": 0.322265625,
"learning_rate": 8.04458557000177e-05,
"loss": 0.7444,
"step": 431
},
{
"epoch": 0.31385573430202385,
"grad_norm": 0.322265625,
"learning_rate": 8.035236739852215e-05,
"loss": 0.7455,
"step": 432
},
{
"epoch": 0.3145822522055008,
"grad_norm": 0.318359375,
"learning_rate": 8.025871075968828e-05,
"loss": 0.7521,
"step": 433
},
{
"epoch": 0.3153087701089777,
"grad_norm": 0.3203125,
"learning_rate": 8.016488630294538e-05,
"loss": 0.7201,
"step": 434
},
{
"epoch": 0.3160352880124546,
"grad_norm": 0.330078125,
"learning_rate": 8.007089454865357e-05,
"loss": 0.7981,
"step": 435
},
{
"epoch": 0.3167618059159315,
"grad_norm": 0.306640625,
"learning_rate": 7.997673601810071e-05,
"loss": 0.7712,
"step": 436
},
{
"epoch": 0.3174883238194084,
"grad_norm": 0.33203125,
"learning_rate": 7.988241123349964e-05,
"loss": 0.7684,
"step": 437
},
{
"epoch": 0.31821484172288533,
"grad_norm": 0.318359375,
"learning_rate": 7.978792071798529e-05,
"loss": 0.7441,
"step": 438
},
{
"epoch": 0.3189413596263622,
"grad_norm": 0.31640625,
"learning_rate": 7.969326499561174e-05,
"loss": 0.7547,
"step": 439
},
{
"epoch": 0.3196678775298391,
"grad_norm": 0.322265625,
"learning_rate": 7.959844459134931e-05,
"loss": 0.7555,
"step": 440
},
{
"epoch": 0.32039439543331605,
"grad_norm": 0.322265625,
"learning_rate": 7.950346003108167e-05,
"loss": 0.7753,
"step": 441
},
{
"epoch": 0.32112091333679293,
"grad_norm": 0.306640625,
"learning_rate": 7.940831184160294e-05,
"loss": 0.7677,
"step": 442
},
{
"epoch": 0.3218474312402699,
"grad_norm": 0.330078125,
"learning_rate": 7.931300055061471e-05,
"loss": 0.7286,
"step": 443
},
{
"epoch": 0.32257394914374676,
"grad_norm": 0.34375,
"learning_rate": 7.921752668672316e-05,
"loss": 0.7747,
"step": 444
},
{
"epoch": 0.32330046704722365,
"grad_norm": 0.34375,
"learning_rate": 7.912189077943612e-05,
"loss": 0.7769,
"step": 445
},
{
"epoch": 0.3240269849507006,
"grad_norm": 0.328125,
"learning_rate": 7.902609335916015e-05,
"loss": 0.7447,
"step": 446
},
{
"epoch": 0.3247535028541775,
"grad_norm": 0.3515625,
"learning_rate": 7.893013495719751e-05,
"loss": 0.8011,
"step": 447
},
{
"epoch": 0.32548002075765436,
"grad_norm": 0.32421875,
"learning_rate": 7.883401610574336e-05,
"loss": 0.7505,
"step": 448
},
{
"epoch": 0.3262065386611313,
"grad_norm": 0.326171875,
"learning_rate": 7.873773733788267e-05,
"loss": 0.7716,
"step": 449
},
{
"epoch": 0.3269330565646082,
"grad_norm": 0.326171875,
"learning_rate": 7.864129918758738e-05,
"loss": 0.7329,
"step": 450
},
{
"epoch": 0.3276595744680851,
"grad_norm": 0.3203125,
"learning_rate": 7.854470218971333e-05,
"loss": 0.7637,
"step": 451
},
{
"epoch": 0.328386092371562,
"grad_norm": 0.333984375,
"learning_rate": 7.844794687999736e-05,
"loss": 0.7592,
"step": 452
},
{
"epoch": 0.3291126102750389,
"grad_norm": 0.3203125,
"learning_rate": 7.835103379505433e-05,
"loss": 0.7567,
"step": 453
},
{
"epoch": 0.32983912817851585,
"grad_norm": 0.3046875,
"learning_rate": 7.825396347237413e-05,
"loss": 0.6992,
"step": 454
},
{
"epoch": 0.33056564608199274,
"grad_norm": 0.341796875,
"learning_rate": 7.815673645031871e-05,
"loss": 0.7546,
"step": 455
},
{
"epoch": 0.3312921639854696,
"grad_norm": 0.369140625,
"learning_rate": 7.805935326811912e-05,
"loss": 0.7565,
"step": 456
},
{
"epoch": 0.33201868188894657,
"grad_norm": 0.30078125,
"learning_rate": 7.796181446587244e-05,
"loss": 0.7159,
"step": 457
},
{
"epoch": 0.33274519979242345,
"grad_norm": 0.359375,
"learning_rate": 7.786412058453885e-05,
"loss": 0.7793,
"step": 458
},
{
"epoch": 0.33347171769590034,
"grad_norm": 0.310546875,
"learning_rate": 7.776627216593863e-05,
"loss": 0.7442,
"step": 459
},
{
"epoch": 0.3341982355993773,
"grad_norm": 0.33984375,
"learning_rate": 7.766826975274914e-05,
"loss": 0.7297,
"step": 460
},
{
"epoch": 0.33492475350285417,
"grad_norm": 0.33984375,
"learning_rate": 7.757011388850181e-05,
"loss": 0.7745,
"step": 461
},
{
"epoch": 0.3356512714063311,
"grad_norm": 0.294921875,
"learning_rate": 7.747180511757908e-05,
"loss": 0.7579,
"step": 462
},
{
"epoch": 0.336377789309808,
"grad_norm": 0.326171875,
"learning_rate": 7.737334398521148e-05,
"loss": 0.7753,
"step": 463
},
{
"epoch": 0.3371043072132849,
"grad_norm": 0.330078125,
"learning_rate": 7.727473103747455e-05,
"loss": 0.7729,
"step": 464
},
{
"epoch": 0.3378308251167618,
"grad_norm": 0.3359375,
"learning_rate": 7.717596682128578e-05,
"loss": 0.7771,
"step": 465
},
{
"epoch": 0.3385573430202387,
"grad_norm": 0.31640625,
"learning_rate": 7.707705188440164e-05,
"loss": 0.7638,
"step": 466
},
{
"epoch": 0.3392838609237156,
"grad_norm": 0.33984375,
"learning_rate": 7.697798677541449e-05,
"loss": 0.7327,
"step": 467
},
{
"epoch": 0.34001037882719254,
"grad_norm": 0.302734375,
"learning_rate": 7.687877204374957e-05,
"loss": 0.7252,
"step": 468
},
{
"epoch": 0.3407368967306694,
"grad_norm": 0.349609375,
"learning_rate": 7.677940823966196e-05,
"loss": 0.7819,
"step": 469
},
{
"epoch": 0.34146341463414637,
"grad_norm": 0.361328125,
"learning_rate": 7.667989591423348e-05,
"loss": 0.7737,
"step": 470
},
{
"epoch": 0.34218993253762325,
"grad_norm": 0.306640625,
"learning_rate": 7.658023561936967e-05,
"loss": 0.7507,
"step": 471
},
{
"epoch": 0.34291645044110014,
"grad_norm": 0.30859375,
"learning_rate": 7.648042790779676e-05,
"loss": 0.7396,
"step": 472
},
{
"epoch": 0.3436429683445771,
"grad_norm": 0.330078125,
"learning_rate": 7.638047333305852e-05,
"loss": 0.7355,
"step": 473
},
{
"epoch": 0.34436948624805397,
"grad_norm": 0.3515625,
"learning_rate": 7.628037244951327e-05,
"loss": 0.7484,
"step": 474
},
{
"epoch": 0.34509600415153086,
"grad_norm": 0.3359375,
"learning_rate": 7.618012581233076e-05,
"loss": 0.7648,
"step": 475
},
{
"epoch": 0.3458225220550078,
"grad_norm": 0.35546875,
"learning_rate": 7.607973397748909e-05,
"loss": 0.7961,
"step": 476
},
{
"epoch": 0.3465490399584847,
"grad_norm": 0.333984375,
"learning_rate": 7.597919750177168e-05,
"loss": 0.7673,
"step": 477
},
{
"epoch": 0.3472755578619616,
"grad_norm": 0.337890625,
"learning_rate": 7.587851694276412e-05,
"loss": 0.7426,
"step": 478
},
{
"epoch": 0.3480020757654385,
"grad_norm": 0.3359375,
"learning_rate": 7.577769285885109e-05,
"loss": 0.7576,
"step": 479
},
{
"epoch": 0.3487285936689154,
"grad_norm": 0.30078125,
"learning_rate": 7.56767258092133e-05,
"loss": 0.7013,
"step": 480
},
{
"epoch": 0.34945511157239234,
"grad_norm": 0.302734375,
"learning_rate": 7.557561635382434e-05,
"loss": 0.7063,
"step": 481
},
{
"epoch": 0.3501816294758692,
"grad_norm": 0.314453125,
"learning_rate": 7.54743650534476e-05,
"loss": 0.7621,
"step": 482
},
{
"epoch": 0.3509081473793461,
"grad_norm": 0.314453125,
"learning_rate": 7.537297246963316e-05,
"loss": 0.7824,
"step": 483
},
{
"epoch": 0.35163466528282306,
"grad_norm": 0.322265625,
"learning_rate": 7.527143916471469e-05,
"loss": 0.7389,
"step": 484
},
{
"epoch": 0.35236118318629994,
"grad_norm": 0.30078125,
"learning_rate": 7.516976570180629e-05,
"loss": 0.7406,
"step": 485
},
{
"epoch": 0.35308770108977683,
"grad_norm": 0.306640625,
"learning_rate": 7.506795264479941e-05,
"loss": 0.7216,
"step": 486
},
{
"epoch": 0.35381421899325377,
"grad_norm": 0.337890625,
"learning_rate": 7.496600055835967e-05,
"loss": 0.7746,
"step": 487
},
{
"epoch": 0.35454073689673066,
"grad_norm": 0.35546875,
"learning_rate": 7.486391000792378e-05,
"loss": 0.729,
"step": 488
},
{
"epoch": 0.3552672548002076,
"grad_norm": 0.36328125,
"learning_rate": 7.476168155969643e-05,
"loss": 0.7182,
"step": 489
},
{
"epoch": 0.3559937727036845,
"grad_norm": 0.328125,
"learning_rate": 7.465931578064704e-05,
"loss": 0.7292,
"step": 490
},
{
"epoch": 0.35672029060716137,
"grad_norm": 0.3125,
"learning_rate": 7.455681323850668e-05,
"loss": 0.751,
"step": 491
},
{
"epoch": 0.3574468085106383,
"grad_norm": 0.3203125,
"learning_rate": 7.4454174501765e-05,
"loss": 0.7603,
"step": 492
},
{
"epoch": 0.3581733264141152,
"grad_norm": 0.341796875,
"learning_rate": 7.435140013966689e-05,
"loss": 0.7735,
"step": 493
},
{
"epoch": 0.3588998443175921,
"grad_norm": 0.3203125,
"learning_rate": 7.424849072220953e-05,
"loss": 0.7379,
"step": 494
},
{
"epoch": 0.35962636222106903,
"grad_norm": 0.32421875,
"learning_rate": 7.414544682013906e-05,
"loss": 0.7601,
"step": 495
},
{
"epoch": 0.3603528801245459,
"grad_norm": 0.322265625,
"learning_rate": 7.404226900494753e-05,
"loss": 0.7459,
"step": 496
},
{
"epoch": 0.36107939802802286,
"grad_norm": 0.349609375,
"learning_rate": 7.393895784886969e-05,
"loss": 0.7464,
"step": 497
},
{
"epoch": 0.36180591593149974,
"grad_norm": 0.310546875,
"learning_rate": 7.383551392487976e-05,
"loss": 0.7381,
"step": 498
},
{
"epoch": 0.36253243383497663,
"grad_norm": 0.326171875,
"learning_rate": 7.373193780668835e-05,
"loss": 0.7532,
"step": 499
},
{
"epoch": 0.3632589517384536,
"grad_norm": 0.3046875,
"learning_rate": 7.36282300687392e-05,
"loss": 0.7572,
"step": 500
},
{
"epoch": 0.36398546964193046,
"grad_norm": 0.333984375,
"learning_rate": 7.35243912862061e-05,
"loss": 0.7314,
"step": 501
},
{
"epoch": 0.36471198754540735,
"grad_norm": 0.34765625,
"learning_rate": 7.342042203498951e-05,
"loss": 0.7737,
"step": 502
},
{
"epoch": 0.3654385054488843,
"grad_norm": 0.3203125,
"learning_rate": 7.33163228917136e-05,
"loss": 0.718,
"step": 503
},
{
"epoch": 0.3661650233523612,
"grad_norm": 0.31640625,
"learning_rate": 7.321209443372283e-05,
"loss": 0.7614,
"step": 504
},
{
"epoch": 0.3668915412558381,
"grad_norm": 0.359375,
"learning_rate": 7.310773723907894e-05,
"loss": 0.8015,
"step": 505
},
{
"epoch": 0.367618059159315,
"grad_norm": 0.33984375,
"learning_rate": 7.300325188655761e-05,
"loss": 0.7695,
"step": 506
},
{
"epoch": 0.3683445770627919,
"grad_norm": 0.322265625,
"learning_rate": 7.28986389556453e-05,
"loss": 0.7359,
"step": 507
},
{
"epoch": 0.36907109496626883,
"grad_norm": 0.32421875,
"learning_rate": 7.279389902653606e-05,
"loss": 0.7895,
"step": 508
},
{
"epoch": 0.3697976128697457,
"grad_norm": 0.29296875,
"learning_rate": 7.268903268012822e-05,
"loss": 0.7159,
"step": 509
},
{
"epoch": 0.3705241307732226,
"grad_norm": 0.33984375,
"learning_rate": 7.258404049802134e-05,
"loss": 0.7505,
"step": 510
},
{
"epoch": 0.37125064867669955,
"grad_norm": 0.314453125,
"learning_rate": 7.247892306251276e-05,
"loss": 0.7407,
"step": 511
},
{
"epoch": 0.37197716658017643,
"grad_norm": 0.294921875,
"learning_rate": 7.237368095659459e-05,
"loss": 0.7457,
"step": 512
},
{
"epoch": 0.3727036844836534,
"grad_norm": 0.32421875,
"learning_rate": 7.226831476395028e-05,
"loss": 0.7664,
"step": 513
},
{
"epoch": 0.37343020238713026,
"grad_norm": 0.35546875,
"learning_rate": 7.216282506895155e-05,
"loss": 0.7593,
"step": 514
},
{
"epoch": 0.37415672029060715,
"grad_norm": 0.3359375,
"learning_rate": 7.205721245665506e-05,
"loss": 0.7726,
"step": 515
},
{
"epoch": 0.3748832381940841,
"grad_norm": 0.3359375,
"learning_rate": 7.195147751279915e-05,
"loss": 0.7415,
"step": 516
},
{
"epoch": 0.375609756097561,
"grad_norm": 0.30078125,
"learning_rate": 7.184562082380068e-05,
"loss": 0.7199,
"step": 517
},
{
"epoch": 0.37633627400103786,
"grad_norm": 0.328125,
"learning_rate": 7.173964297675167e-05,
"loss": 0.7185,
"step": 518
},
{
"epoch": 0.3770627919045148,
"grad_norm": 0.33984375,
"learning_rate": 7.163354455941614e-05,
"loss": 0.7538,
"step": 519
},
{
"epoch": 0.3777893098079917,
"grad_norm": 0.31640625,
"learning_rate": 7.152732616022675e-05,
"loss": 0.7348,
"step": 520
},
{
"epoch": 0.3785158277114686,
"grad_norm": 0.318359375,
"learning_rate": 7.142098836828162e-05,
"loss": 0.75,
"step": 521
},
{
"epoch": 0.3792423456149455,
"grad_norm": 0.3203125,
"learning_rate": 7.131453177334103e-05,
"loss": 0.7516,
"step": 522
},
{
"epoch": 0.3799688635184224,
"grad_norm": 0.333984375,
"learning_rate": 7.120795696582418e-05,
"loss": 0.7261,
"step": 523
},
{
"epoch": 0.38069538142189935,
"grad_norm": 0.3359375,
"learning_rate": 7.110126453680588e-05,
"loss": 0.7555,
"step": 524
},
{
"epoch": 0.38142189932537623,
"grad_norm": 0.314453125,
"learning_rate": 7.099445507801323e-05,
"loss": 0.7287,
"step": 525
},
{
"epoch": 0.3821484172288531,
"grad_norm": 0.322265625,
"learning_rate": 7.088752918182247e-05,
"loss": 0.7696,
"step": 526
},
{
"epoch": 0.38287493513233006,
"grad_norm": 0.32421875,
"learning_rate": 7.078048744125553e-05,
"loss": 0.7772,
"step": 527
},
{
"epoch": 0.38360145303580695,
"grad_norm": 0.349609375,
"learning_rate": 7.067333044997688e-05,
"loss": 0.7393,
"step": 528
},
{
"epoch": 0.38432797093928384,
"grad_norm": 0.3046875,
"learning_rate": 7.056605880229019e-05,
"loss": 0.7493,
"step": 529
},
{
"epoch": 0.3850544888427608,
"grad_norm": 0.330078125,
"learning_rate": 7.045867309313499e-05,
"loss": 0.7553,
"step": 530
},
{
"epoch": 0.38578100674623766,
"grad_norm": 0.30859375,
"learning_rate": 7.035117391808342e-05,
"loss": 0.7285,
"step": 531
},
{
"epoch": 0.3865075246497146,
"grad_norm": 0.294921875,
"learning_rate": 7.024356187333692e-05,
"loss": 0.7359,
"step": 532
},
{
"epoch": 0.3872340425531915,
"grad_norm": 0.3125,
"learning_rate": 7.013583755572289e-05,
"loss": 0.7739,
"step": 533
},
{
"epoch": 0.3879605604566684,
"grad_norm": 0.318359375,
"learning_rate": 7.002800156269146e-05,
"loss": 0.7624,
"step": 534
},
{
"epoch": 0.3886870783601453,
"grad_norm": 0.314453125,
"learning_rate": 6.992005449231208e-05,
"loss": 0.7447,
"step": 535
},
{
"epoch": 0.3894135962636222,
"grad_norm": 0.34375,
"learning_rate": 6.981199694327025e-05,
"loss": 0.7479,
"step": 536
},
{
"epoch": 0.3901401141670991,
"grad_norm": 0.322265625,
"learning_rate": 6.970382951486421e-05,
"loss": 0.7678,
"step": 537
},
{
"epoch": 0.39086663207057604,
"grad_norm": 0.31640625,
"learning_rate": 6.959555280700162e-05,
"loss": 0.7309,
"step": 538
},
{
"epoch": 0.3915931499740529,
"grad_norm": 0.33984375,
"learning_rate": 6.948716742019615e-05,
"loss": 0.7764,
"step": 539
},
{
"epoch": 0.39231966787752987,
"grad_norm": 0.3359375,
"learning_rate": 6.937867395556427e-05,
"loss": 0.7222,
"step": 540
},
{
"epoch": 0.39304618578100675,
"grad_norm": 0.32421875,
"learning_rate": 6.927007301482187e-05,
"loss": 0.7239,
"step": 541
},
{
"epoch": 0.39377270368448364,
"grad_norm": 0.3359375,
"learning_rate": 6.916136520028088e-05,
"loss": 0.7608,
"step": 542
},
{
"epoch": 0.3944992215879606,
"grad_norm": 0.314453125,
"learning_rate": 6.905255111484591e-05,
"loss": 0.7411,
"step": 543
},
{
"epoch": 0.39522573949143747,
"grad_norm": 0.322265625,
"learning_rate": 6.894363136201114e-05,
"loss": 0.7556,
"step": 544
},
{
"epoch": 0.39595225739491435,
"grad_norm": 0.3203125,
"learning_rate": 6.883460654585659e-05,
"loss": 0.7263,
"step": 545
},
{
"epoch": 0.3966787752983913,
"grad_norm": 0.33203125,
"learning_rate": 6.872547727104508e-05,
"loss": 0.735,
"step": 546
},
{
"epoch": 0.3974052932018682,
"grad_norm": 0.310546875,
"learning_rate": 6.861624414281875e-05,
"loss": 0.7292,
"step": 547
},
{
"epoch": 0.3981318111053451,
"grad_norm": 0.322265625,
"learning_rate": 6.850690776699573e-05,
"loss": 0.7518,
"step": 548
},
{
"epoch": 0.398858329008822,
"grad_norm": 0.33203125,
"learning_rate": 6.839746874996673e-05,
"loss": 0.7106,
"step": 549
},
{
"epoch": 0.3995848469122989,
"grad_norm": 0.3125,
"learning_rate": 6.828792769869174e-05,
"loss": 0.7337,
"step": 550
},
{
"epoch": 0.40031136481577584,
"grad_norm": 0.306640625,
"learning_rate": 6.817828522069668e-05,
"loss": 0.719,
"step": 551
},
{
"epoch": 0.4010378827192527,
"grad_norm": 0.33203125,
"learning_rate": 6.806854192406995e-05,
"loss": 0.7715,
"step": 552
},
{
"epoch": 0.4017644006227296,
"grad_norm": 0.357421875,
"learning_rate": 6.795869841745912e-05,
"loss": 0.7482,
"step": 553
},
{
"epoch": 0.40249091852620655,
"grad_norm": 0.32421875,
"learning_rate": 6.78487553100675e-05,
"loss": 0.7614,
"step": 554
},
{
"epoch": 0.40321743642968344,
"grad_norm": 0.318359375,
"learning_rate": 6.773871321165088e-05,
"loss": 0.7424,
"step": 555
},
{
"epoch": 0.4039439543331603,
"grad_norm": 0.322265625,
"learning_rate": 6.762857273251396e-05,
"loss": 0.7505,
"step": 556
},
{
"epoch": 0.40467047223663727,
"grad_norm": 0.322265625,
"learning_rate": 6.751833448350713e-05,
"loss": 0.7551,
"step": 557
},
{
"epoch": 0.40539699014011416,
"grad_norm": 0.330078125,
"learning_rate": 6.740799907602302e-05,
"loss": 0.7839,
"step": 558
},
{
"epoch": 0.4061235080435911,
"grad_norm": 0.3359375,
"learning_rate": 6.729756712199309e-05,
"loss": 0.7463,
"step": 559
},
{
"epoch": 0.406850025947068,
"grad_norm": 0.392578125,
"learning_rate": 6.718703923388427e-05,
"loss": 0.7268,
"step": 560
},
{
"epoch": 0.40757654385054487,
"grad_norm": 0.31640625,
"learning_rate": 6.707641602469555e-05,
"loss": 0.7148,
"step": 561
},
{
"epoch": 0.4083030617540218,
"grad_norm": 0.349609375,
"learning_rate": 6.696569810795456e-05,
"loss": 0.7716,
"step": 562
},
{
"epoch": 0.4090295796574987,
"grad_norm": 0.3203125,
"learning_rate": 6.685488609771423e-05,
"loss": 0.7612,
"step": 563
},
{
"epoch": 0.4097560975609756,
"grad_norm": 0.328125,
"learning_rate": 6.674398060854931e-05,
"loss": 0.775,
"step": 564
},
{
"epoch": 0.4104826154644525,
"grad_norm": 0.318359375,
"learning_rate": 6.6632982255553e-05,
"loss": 0.7265,
"step": 565
},
{
"epoch": 0.4112091333679294,
"grad_norm": 0.32421875,
"learning_rate": 6.652189165433356e-05,
"loss": 0.7463,
"step": 566
},
{
"epoch": 0.41193565127140636,
"grad_norm": 0.33984375,
"learning_rate": 6.64107094210108e-05,
"loss": 0.7819,
"step": 567
},
{
"epoch": 0.41266216917488324,
"grad_norm": 0.314453125,
"learning_rate": 6.629943617221279e-05,
"loss": 0.7567,
"step": 568
},
{
"epoch": 0.41338868707836013,
"grad_norm": 0.322265625,
"learning_rate": 6.618807252507237e-05,
"loss": 0.7453,
"step": 569
},
{
"epoch": 0.41411520498183707,
"grad_norm": 0.322265625,
"learning_rate": 6.607661909722373e-05,
"loss": 0.7314,
"step": 570
},
{
"epoch": 0.41484172288531396,
"grad_norm": 0.3125,
"learning_rate": 6.5965076506799e-05,
"loss": 0.7493,
"step": 571
},
{
"epoch": 0.41556824078879084,
"grad_norm": 0.333984375,
"learning_rate": 6.58534453724248e-05,
"loss": 0.7524,
"step": 572
},
{
"epoch": 0.4162947586922678,
"grad_norm": 0.33984375,
"learning_rate": 6.574172631321886e-05,
"loss": 0.7884,
"step": 573
},
{
"epoch": 0.41702127659574467,
"grad_norm": 0.322265625,
"learning_rate": 6.562991994878649e-05,
"loss": 0.7652,
"step": 574
},
{
"epoch": 0.4177477944992216,
"grad_norm": 0.333984375,
"learning_rate": 6.551802689921726e-05,
"loss": 0.7624,
"step": 575
},
{
"epoch": 0.4184743124026985,
"grad_norm": 0.314453125,
"learning_rate": 6.540604778508148e-05,
"loss": 0.736,
"step": 576
},
{
"epoch": 0.4192008303061754,
"grad_norm": 0.33203125,
"learning_rate": 6.529398322742676e-05,
"loss": 0.7719,
"step": 577
},
{
"epoch": 0.41992734820965233,
"grad_norm": 0.314453125,
"learning_rate": 6.518183384777468e-05,
"loss": 0.7395,
"step": 578
},
{
"epoch": 0.4206538661131292,
"grad_norm": 0.3203125,
"learning_rate": 6.506960026811711e-05,
"loss": 0.7325,
"step": 579
},
{
"epoch": 0.4213803840166061,
"grad_norm": 0.33984375,
"learning_rate": 6.495728311091303e-05,
"loss": 0.7714,
"step": 580
},
{
"epoch": 0.42210690192008304,
"grad_norm": 0.310546875,
"learning_rate": 6.484488299908487e-05,
"loss": 0.7297,
"step": 581
},
{
"epoch": 0.42283341982355993,
"grad_norm": 0.337890625,
"learning_rate": 6.473240055601517e-05,
"loss": 0.7465,
"step": 582
},
{
"epoch": 0.4235599377270368,
"grad_norm": 0.31640625,
"learning_rate": 6.46198364055431e-05,
"loss": 0.7514,
"step": 583
},
{
"epoch": 0.42428645563051376,
"grad_norm": 0.3359375,
"learning_rate": 6.450719117196094e-05,
"loss": 0.7263,
"step": 584
},
{
"epoch": 0.42501297353399065,
"grad_norm": 0.322265625,
"learning_rate": 6.439446548001069e-05,
"loss": 0.7547,
"step": 585
},
{
"epoch": 0.4257394914374676,
"grad_norm": 0.34375,
"learning_rate": 6.42816599548806e-05,
"loss": 0.7512,
"step": 586
},
{
"epoch": 0.4264660093409445,
"grad_norm": 0.345703125,
"learning_rate": 6.416877522220166e-05,
"loss": 0.779,
"step": 587
},
{
"epoch": 0.42719252724442136,
"grad_norm": 0.33203125,
"learning_rate": 6.405581190804417e-05,
"loss": 0.7534,
"step": 588
},
{
"epoch": 0.4279190451478983,
"grad_norm": 0.337890625,
"learning_rate": 6.394277063891422e-05,
"loss": 0.7626,
"step": 589
},
{
"epoch": 0.4286455630513752,
"grad_norm": 0.31640625,
"learning_rate": 6.382965204175027e-05,
"loss": 0.7223,
"step": 590
},
{
"epoch": 0.4293720809548521,
"grad_norm": 0.314453125,
"learning_rate": 6.371645674391966e-05,
"loss": 0.7598,
"step": 591
},
{
"epoch": 0.430098598858329,
"grad_norm": 0.333984375,
"learning_rate": 6.36031853732151e-05,
"loss": 0.7687,
"step": 592
},
{
"epoch": 0.4308251167618059,
"grad_norm": 0.322265625,
"learning_rate": 6.348983855785121e-05,
"loss": 0.7599,
"step": 593
},
{
"epoch": 0.43155163466528285,
"grad_norm": 0.328125,
"learning_rate": 6.337641692646106e-05,
"loss": 0.7675,
"step": 594
},
{
"epoch": 0.43227815256875973,
"grad_norm": 0.306640625,
"learning_rate": 6.326292110809258e-05,
"loss": 0.7487,
"step": 595
},
{
"epoch": 0.4330046704722366,
"grad_norm": 0.31640625,
"learning_rate": 6.314935173220524e-05,
"loss": 0.7455,
"step": 596
},
{
"epoch": 0.43373118837571356,
"grad_norm": 0.333984375,
"learning_rate": 6.303570942866643e-05,
"loss": 0.7231,
"step": 597
},
{
"epoch": 0.43445770627919045,
"grad_norm": 0.310546875,
"learning_rate": 6.2921994827748e-05,
"loss": 0.7462,
"step": 598
},
{
"epoch": 0.43518422418266733,
"grad_norm": 0.349609375,
"learning_rate": 6.280820856012277e-05,
"loss": 0.7566,
"step": 599
},
{
"epoch": 0.4359107420861443,
"grad_norm": 0.33203125,
"learning_rate": 6.269435125686105e-05,
"loss": 0.7655,
"step": 600
},
{
"epoch": 0.43663725998962116,
"grad_norm": 0.3359375,
"learning_rate": 6.258042354942709e-05,
"loss": 0.7687,
"step": 601
},
{
"epoch": 0.4373637778930981,
"grad_norm": 0.3125,
"learning_rate": 6.246642606967562e-05,
"loss": 0.7094,
"step": 602
},
{
"epoch": 0.438090295796575,
"grad_norm": 0.306640625,
"learning_rate": 6.235235944984835e-05,
"loss": 0.7351,
"step": 603
},
{
"epoch": 0.4388168137000519,
"grad_norm": 0.314453125,
"learning_rate": 6.223822432257043e-05,
"loss": 0.7317,
"step": 604
},
{
"epoch": 0.4395433316035288,
"grad_norm": 0.30859375,
"learning_rate": 6.212402132084697e-05,
"loss": 0.7361,
"step": 605
},
{
"epoch": 0.4402698495070057,
"grad_norm": 0.298828125,
"learning_rate": 6.200975107805951e-05,
"loss": 0.7379,
"step": 606
},
{
"epoch": 0.4409963674104826,
"grad_norm": 0.302734375,
"learning_rate": 6.189541422796253e-05,
"loss": 0.7096,
"step": 607
},
{
"epoch": 0.44172288531395953,
"grad_norm": 0.322265625,
"learning_rate": 6.17810114046799e-05,
"loss": 0.76,
"step": 608
},
{
"epoch": 0.4424494032174364,
"grad_norm": 0.326171875,
"learning_rate": 6.16665432427014e-05,
"loss": 0.7522,
"step": 609
},
{
"epoch": 0.44317592112091336,
"grad_norm": 0.341796875,
"learning_rate": 6.155201037687916e-05,
"loss": 0.7226,
"step": 610
},
{
"epoch": 0.44390243902439025,
"grad_norm": 0.330078125,
"learning_rate": 6.143741344242423e-05,
"loss": 0.7665,
"step": 611
},
{
"epoch": 0.44462895692786714,
"grad_norm": 0.322265625,
"learning_rate": 6.13227530749029e-05,
"loss": 0.7544,
"step": 612
},
{
"epoch": 0.4453554748313441,
"grad_norm": 0.32421875,
"learning_rate": 6.120802991023335e-05,
"loss": 0.7623,
"step": 613
},
{
"epoch": 0.44608199273482096,
"grad_norm": 0.314453125,
"learning_rate": 6.109324458468197e-05,
"loss": 0.7307,
"step": 614
},
{
"epoch": 0.44680851063829785,
"grad_norm": 0.306640625,
"learning_rate": 6.097839773485995e-05,
"loss": 0.7118,
"step": 615
},
{
"epoch": 0.4475350285417748,
"grad_norm": 0.330078125,
"learning_rate": 6.086348999771967e-05,
"loss": 0.7421,
"step": 616
},
{
"epoch": 0.4482615464452517,
"grad_norm": 0.30859375,
"learning_rate": 6.0748522010551215e-05,
"loss": 0.7538,
"step": 617
},
{
"epoch": 0.44898806434872857,
"grad_norm": 0.3046875,
"learning_rate": 6.0633494410978805e-05,
"loss": 0.6916,
"step": 618
},
{
"epoch": 0.4497145822522055,
"grad_norm": 0.31640625,
"learning_rate": 6.051840783695731e-05,
"loss": 0.7397,
"step": 619
},
{
"epoch": 0.4504411001556824,
"grad_norm": 0.3046875,
"learning_rate": 6.040326292676866e-05,
"loss": 0.7065,
"step": 620
},
{
"epoch": 0.45116761805915934,
"grad_norm": 0.32421875,
"learning_rate": 6.028806031901829e-05,
"loss": 0.7355,
"step": 621
},
{
"epoch": 0.4518941359626362,
"grad_norm": 0.330078125,
"learning_rate": 6.01728006526317e-05,
"loss": 0.7655,
"step": 622
},
{
"epoch": 0.4526206538661131,
"grad_norm": 0.3203125,
"learning_rate": 6.0057484566850774e-05,
"loss": 0.7436,
"step": 623
},
{
"epoch": 0.45334717176959005,
"grad_norm": 0.341796875,
"learning_rate": 5.9942112701230336e-05,
"loss": 0.7925,
"step": 624
},
{
"epoch": 0.45407368967306694,
"grad_norm": 0.322265625,
"learning_rate": 5.9826685695634576e-05,
"loss": 0.7802,
"step": 625
},
{
"epoch": 0.4548002075765438,
"grad_norm": 0.306640625,
"learning_rate": 5.971120419023349e-05,
"loss": 0.7478,
"step": 626
},
{
"epoch": 0.45552672548002077,
"grad_norm": 0.314453125,
"learning_rate": 5.959566882549935e-05,
"loss": 0.7245,
"step": 627
},
{
"epoch": 0.45625324338349765,
"grad_norm": 0.318359375,
"learning_rate": 5.948008024220311e-05,
"loss": 0.7402,
"step": 628
},
{
"epoch": 0.4569797612869746,
"grad_norm": 0.3359375,
"learning_rate": 5.9364439081410875e-05,
"loss": 0.7434,
"step": 629
},
{
"epoch": 0.4577062791904515,
"grad_norm": 0.310546875,
"learning_rate": 5.924874598448038e-05,
"loss": 0.7071,
"step": 630
},
{
"epoch": 0.45843279709392837,
"grad_norm": 0.34765625,
"learning_rate": 5.91330015930574e-05,
"loss": 0.7509,
"step": 631
},
{
"epoch": 0.4591593149974053,
"grad_norm": 0.333984375,
"learning_rate": 5.9017206549072165e-05,
"loss": 0.7606,
"step": 632
},
{
"epoch": 0.4598858329008822,
"grad_norm": 0.294921875,
"learning_rate": 5.8901361494735876e-05,
"loss": 0.6963,
"step": 633
},
{
"epoch": 0.4606123508043591,
"grad_norm": 0.3515625,
"learning_rate": 5.878546707253704e-05,
"loss": 0.7474,
"step": 634
},
{
"epoch": 0.461338868707836,
"grad_norm": 0.326171875,
"learning_rate": 5.8669523925238e-05,
"loss": 0.7504,
"step": 635
},
{
"epoch": 0.4620653866113129,
"grad_norm": 0.30859375,
"learning_rate": 5.855353269587134e-05,
"loss": 0.7707,
"step": 636
},
{
"epoch": 0.46279190451478985,
"grad_norm": 0.34375,
"learning_rate": 5.8437494027736285e-05,
"loss": 0.7771,
"step": 637
},
{
"epoch": 0.46351842241826674,
"grad_norm": 0.32421875,
"learning_rate": 5.8321408564395165e-05,
"loss": 0.7385,
"step": 638
},
{
"epoch": 0.4642449403217436,
"grad_norm": 0.306640625,
"learning_rate": 5.8205276949669885e-05,
"loss": 0.7328,
"step": 639
},
{
"epoch": 0.46497145822522057,
"grad_norm": 0.2890625,
"learning_rate": 5.808909982763825e-05,
"loss": 0.7144,
"step": 640
},
{
"epoch": 0.46569797612869746,
"grad_norm": 0.31640625,
"learning_rate": 5.797287784263047e-05,
"loss": 0.6975,
"step": 641
},
{
"epoch": 0.46642449403217434,
"grad_norm": 0.33984375,
"learning_rate": 5.785661163922558e-05,
"loss": 0.7628,
"step": 642
},
{
"epoch": 0.4671510119356513,
"grad_norm": 0.30859375,
"learning_rate": 5.774030186224786e-05,
"loss": 0.7302,
"step": 643
},
{
"epoch": 0.46787752983912817,
"grad_norm": 0.32421875,
"learning_rate": 5.7623949156763243e-05,
"loss": 0.7411,
"step": 644
},
{
"epoch": 0.4686040477426051,
"grad_norm": 0.3046875,
"learning_rate": 5.750755416807575e-05,
"loss": 0.6969,
"step": 645
},
{
"epoch": 0.469330565646082,
"grad_norm": 0.310546875,
"learning_rate": 5.739111754172391e-05,
"loss": 0.7367,
"step": 646
},
{
"epoch": 0.4700570835495589,
"grad_norm": 0.314453125,
"learning_rate": 5.727463992347719e-05,
"loss": 0.7444,
"step": 647
},
{
"epoch": 0.4707836014530358,
"grad_norm": 0.3203125,
"learning_rate": 5.715812195933238e-05,
"loss": 0.7739,
"step": 648
},
{
"epoch": 0.4715101193565127,
"grad_norm": 0.349609375,
"learning_rate": 5.7041564295510044e-05,
"loss": 0.7067,
"step": 649
},
{
"epoch": 0.4722366372599896,
"grad_norm": 0.369140625,
"learning_rate": 5.692496757845091e-05,
"loss": 0.7615,
"step": 650
},
{
"epoch": 0.47296315516346654,
"grad_norm": 0.318359375,
"learning_rate": 5.680833245481234e-05,
"loss": 0.7334,
"step": 651
},
{
"epoch": 0.47368967306694343,
"grad_norm": 0.337890625,
"learning_rate": 5.669165957146465e-05,
"loss": 0.7697,
"step": 652
},
{
"epoch": 0.4744161909704203,
"grad_norm": 0.326171875,
"learning_rate": 5.6574949575487615e-05,
"loss": 0.7671,
"step": 653
},
{
"epoch": 0.47514270887389726,
"grad_norm": 0.341796875,
"learning_rate": 5.645820311416681e-05,
"loss": 0.7352,
"step": 654
},
{
"epoch": 0.47586922677737414,
"grad_norm": 0.302734375,
"learning_rate": 5.63414208349901e-05,
"loss": 0.7562,
"step": 655
},
{
"epoch": 0.4765957446808511,
"grad_norm": 0.326171875,
"learning_rate": 5.622460338564393e-05,
"loss": 0.7599,
"step": 656
},
{
"epoch": 0.47732226258432797,
"grad_norm": 0.345703125,
"learning_rate": 5.6107751414009855e-05,
"loss": 0.7337,
"step": 657
},
{
"epoch": 0.47804878048780486,
"grad_norm": 0.333984375,
"learning_rate": 5.5990865568160885e-05,
"loss": 0.7619,
"step": 658
},
{
"epoch": 0.4787752983912818,
"grad_norm": 0.33203125,
"learning_rate": 5.5873946496357885e-05,
"loss": 0.7645,
"step": 659
},
{
"epoch": 0.4795018162947587,
"grad_norm": 0.32421875,
"learning_rate": 5.5756994847046e-05,
"loss": 0.7206,
"step": 660
},
{
"epoch": 0.4802283341982356,
"grad_norm": 0.333984375,
"learning_rate": 5.5640011268851055e-05,
"loss": 0.7875,
"step": 661
},
{
"epoch": 0.4809548521017125,
"grad_norm": 0.353515625,
"learning_rate": 5.552299641057596e-05,
"loss": 0.7625,
"step": 662
},
{
"epoch": 0.4816813700051894,
"grad_norm": 0.322265625,
"learning_rate": 5.540595092119709e-05,
"loss": 0.7381,
"step": 663
},
{
"epoch": 0.48240788790866634,
"grad_norm": 0.33203125,
"learning_rate": 5.528887544986075e-05,
"loss": 0.7245,
"step": 664
},
{
"epoch": 0.48313440581214323,
"grad_norm": 0.318359375,
"learning_rate": 5.517177064587945e-05,
"loss": 0.7131,
"step": 665
},
{
"epoch": 0.4838609237156201,
"grad_norm": 0.326171875,
"learning_rate": 5.505463715872846e-05,
"loss": 0.7399,
"step": 666
},
{
"epoch": 0.48458744161909706,
"grad_norm": 0.314453125,
"learning_rate": 5.49374756380421e-05,
"loss": 0.7137,
"step": 667
},
{
"epoch": 0.48531395952257395,
"grad_norm": 0.310546875,
"learning_rate": 5.482028673361015e-05,
"loss": 0.7459,
"step": 668
},
{
"epoch": 0.48604047742605083,
"grad_norm": 0.33984375,
"learning_rate": 5.470307109537427e-05,
"loss": 0.7234,
"step": 669
},
{
"epoch": 0.4867669953295278,
"grad_norm": 0.3359375,
"learning_rate": 5.45858293734244e-05,
"loss": 0.7735,
"step": 670
},
{
"epoch": 0.48749351323300466,
"grad_norm": 0.30078125,
"learning_rate": 5.446856221799514e-05,
"loss": 0.7411,
"step": 671
},
{
"epoch": 0.4882200311364816,
"grad_norm": 0.318359375,
"learning_rate": 5.435127027946215e-05,
"loss": 0.7561,
"step": 672
},
{
"epoch": 0.4889465490399585,
"grad_norm": 0.298828125,
"learning_rate": 5.4233954208338525e-05,
"loss": 0.7025,
"step": 673
},
{
"epoch": 0.4896730669434354,
"grad_norm": 0.328125,
"learning_rate": 5.411661465527123e-05,
"loss": 0.7601,
"step": 674
},
{
"epoch": 0.4903995848469123,
"grad_norm": 0.328125,
"learning_rate": 5.39992522710374e-05,
"loss": 0.7072,
"step": 675
},
{
"epoch": 0.4911261027503892,
"grad_norm": 0.333984375,
"learning_rate": 5.38818677065409e-05,
"loss": 0.7202,
"step": 676
},
{
"epoch": 0.4918526206538661,
"grad_norm": 0.322265625,
"learning_rate": 5.3764461612808507e-05,
"loss": 0.7266,
"step": 677
},
{
"epoch": 0.49257913855734303,
"grad_norm": 0.30859375,
"learning_rate": 5.3647034640986446e-05,
"loss": 0.7272,
"step": 678
},
{
"epoch": 0.4933056564608199,
"grad_norm": 0.31640625,
"learning_rate": 5.352958744233673e-05,
"loss": 0.7271,
"step": 679
},
{
"epoch": 0.49403217436429686,
"grad_norm": 0.322265625,
"learning_rate": 5.341212066823355e-05,
"loss": 0.7336,
"step": 680
},
{
"epoch": 0.49475869226777375,
"grad_norm": 0.333984375,
"learning_rate": 5.3294634970159685e-05,
"loss": 0.7235,
"step": 681
},
{
"epoch": 0.49548521017125063,
"grad_norm": 0.3203125,
"learning_rate": 5.317713099970283e-05,
"loss": 0.7457,
"step": 682
},
{
"epoch": 0.4962117280747276,
"grad_norm": 0.3203125,
"learning_rate": 5.3059609408552045e-05,
"loss": 0.7232,
"step": 683
},
{
"epoch": 0.49693824597820446,
"grad_norm": 0.333984375,
"learning_rate": 5.294207084849412e-05,
"loss": 0.7323,
"step": 684
},
{
"epoch": 0.49766476388168135,
"grad_norm": 0.326171875,
"learning_rate": 5.282451597140994e-05,
"loss": 0.7046,
"step": 685
},
{
"epoch": 0.4983912817851583,
"grad_norm": 0.296875,
"learning_rate": 5.270694542927088e-05,
"loss": 0.7062,
"step": 686
},
{
"epoch": 0.4991177996886352,
"grad_norm": 0.328125,
"learning_rate": 5.258935987413523e-05,
"loss": 0.757,
"step": 687
},
{
"epoch": 0.49984431759211206,
"grad_norm": 0.310546875,
"learning_rate": 5.2471759958144516e-05,
"loss": 0.7407,
"step": 688
},
{
"epoch": 0.500570835495589,
"grad_norm": 0.32421875,
"learning_rate": 5.2354146333519914e-05,
"loss": 0.8009,
"step": 689
},
{
"epoch": 0.5012973533990659,
"grad_norm": 0.318359375,
"learning_rate": 5.2236519652558634e-05,
"loss": 0.7722,
"step": 690
},
{
"epoch": 0.5020238713025428,
"grad_norm": 0.33203125,
"learning_rate": 5.211888056763029e-05,
"loss": 0.7563,
"step": 691
},
{
"epoch": 0.5027503892060197,
"grad_norm": 0.314453125,
"learning_rate": 5.200122973117329e-05,
"loss": 0.7207,
"step": 692
},
{
"epoch": 0.5034769071094967,
"grad_norm": 0.30859375,
"learning_rate": 5.188356779569125e-05,
"loss": 0.7423,
"step": 693
},
{
"epoch": 0.5042034250129735,
"grad_norm": 0.296875,
"learning_rate": 5.176589541374929e-05,
"loss": 0.7113,
"step": 694
},
{
"epoch": 0.5049299429164504,
"grad_norm": 0.326171875,
"learning_rate": 5.164821323797051e-05,
"loss": 0.7369,
"step": 695
},
{
"epoch": 0.5056564608199273,
"grad_norm": 0.314453125,
"learning_rate": 5.15305219210323e-05,
"loss": 0.7331,
"step": 696
},
{
"epoch": 0.5063829787234042,
"grad_norm": 0.3203125,
"learning_rate": 5.141282211566275e-05,
"loss": 0.7092,
"step": 697
},
{
"epoch": 0.5071094966268812,
"grad_norm": 0.33984375,
"learning_rate": 5.1295114474637054e-05,
"loss": 0.7626,
"step": 698
},
{
"epoch": 0.5078360145303581,
"grad_norm": 0.3125,
"learning_rate": 5.1177399650773814e-05,
"loss": 0.7152,
"step": 699
},
{
"epoch": 0.508562532433835,
"grad_norm": 0.318359375,
"learning_rate": 5.105967829693155e-05,
"loss": 0.7452,
"step": 700
},
{
"epoch": 0.5092890503373119,
"grad_norm": 0.294921875,
"learning_rate": 5.09419510660049e-05,
"loss": 0.7235,
"step": 701
},
{
"epoch": 0.5100155682407888,
"grad_norm": 0.3203125,
"learning_rate": 5.082421861092116e-05,
"loss": 0.7361,
"step": 702
},
{
"epoch": 0.5107420861442658,
"grad_norm": 0.330078125,
"learning_rate": 5.07064815846366e-05,
"loss": 0.7436,
"step": 703
},
{
"epoch": 0.5114686040477426,
"grad_norm": 0.3125,
"learning_rate": 5.0588740640132805e-05,
"loss": 0.7247,
"step": 704
},
{
"epoch": 0.5121951219512195,
"grad_norm": 0.318359375,
"learning_rate": 5.047099643041312e-05,
"loss": 0.742,
"step": 705
},
{
"epoch": 0.5129216398546964,
"grad_norm": 0.345703125,
"learning_rate": 5.0353249608499e-05,
"loss": 0.7425,
"step": 706
},
{
"epoch": 0.5136481577581733,
"grad_norm": 0.369140625,
"learning_rate": 5.023550082742636e-05,
"loss": 0.7404,
"step": 707
},
{
"epoch": 0.5143746756616502,
"grad_norm": 0.31640625,
"learning_rate": 5.011775074024202e-05,
"loss": 0.7423,
"step": 708
},
{
"epoch": 0.5151011935651272,
"grad_norm": 0.32421875,
"learning_rate": 5e-05,
"loss": 0.7223,
"step": 709
},
{
"epoch": 0.5158277114686041,
"grad_norm": 0.306640625,
"learning_rate": 4.9882249259758e-05,
"loss": 0.7415,
"step": 710
},
{
"epoch": 0.516554229372081,
"grad_norm": 0.326171875,
"learning_rate": 4.976449917257365e-05,
"loss": 0.7294,
"step": 711
},
{
"epoch": 0.5172807472755578,
"grad_norm": 0.349609375,
"learning_rate": 4.964675039150102e-05,
"loss": 0.7614,
"step": 712
},
{
"epoch": 0.5180072651790347,
"grad_norm": 0.322265625,
"learning_rate": 4.952900356958689e-05,
"loss": 0.7135,
"step": 713
},
{
"epoch": 0.5187337830825117,
"grad_norm": 0.326171875,
"learning_rate": 4.9411259359867206e-05,
"loss": 0.7487,
"step": 714
},
{
"epoch": 0.5194603009859886,
"grad_norm": 0.302734375,
"learning_rate": 4.9293518415363416e-05,
"loss": 0.6762,
"step": 715
},
{
"epoch": 0.5201868188894655,
"grad_norm": 0.322265625,
"learning_rate": 4.917578138907884e-05,
"loss": 0.7272,
"step": 716
},
{
"epoch": 0.5209133367929424,
"grad_norm": 0.31640625,
"learning_rate": 4.9058048933995104e-05,
"loss": 0.7129,
"step": 717
},
{
"epoch": 0.5216398546964193,
"grad_norm": 0.330078125,
"learning_rate": 4.8940321703068456e-05,
"loss": 0.7171,
"step": 718
},
{
"epoch": 0.5223663725998963,
"grad_norm": 0.3203125,
"learning_rate": 4.8822600349226184e-05,
"loss": 0.7611,
"step": 719
},
{
"epoch": 0.5230928905033732,
"grad_norm": 0.333984375,
"learning_rate": 4.870488552536296e-05,
"loss": 0.7344,
"step": 720
},
{
"epoch": 0.52381940840685,
"grad_norm": 0.361328125,
"learning_rate": 4.858717788433725e-05,
"loss": 0.7636,
"step": 721
},
{
"epoch": 0.5245459263103269,
"grad_norm": 0.318359375,
"learning_rate": 4.846947807896771e-05,
"loss": 0.7569,
"step": 722
},
{
"epoch": 0.5252724442138038,
"grad_norm": 0.31640625,
"learning_rate": 4.835178676202949e-05,
"loss": 0.743,
"step": 723
},
{
"epoch": 0.5259989621172807,
"grad_norm": 0.30859375,
"learning_rate": 4.8234104586250724e-05,
"loss": 0.7491,
"step": 724
},
{
"epoch": 0.5267254800207577,
"grad_norm": 0.34375,
"learning_rate": 4.8116432204308765e-05,
"loss": 0.7511,
"step": 725
},
{
"epoch": 0.5274519979242346,
"grad_norm": 0.318359375,
"learning_rate": 4.799877026882672e-05,
"loss": 0.7343,
"step": 726
},
{
"epoch": 0.5281785158277115,
"grad_norm": 0.330078125,
"learning_rate": 4.788111943236973e-05,
"loss": 0.7397,
"step": 727
},
{
"epoch": 0.5289050337311884,
"grad_norm": 0.34765625,
"learning_rate": 4.776348034744139e-05,
"loss": 0.743,
"step": 728
},
{
"epoch": 0.5296315516346652,
"grad_norm": 0.314453125,
"learning_rate": 4.7645853666480104e-05,
"loss": 0.7117,
"step": 729
},
{
"epoch": 0.5303580695381422,
"grad_norm": 0.3203125,
"learning_rate": 4.752824004185548e-05,
"loss": 0.7163,
"step": 730
},
{
"epoch": 0.5310845874416191,
"grad_norm": 0.3515625,
"learning_rate": 4.741064012586478e-05,
"loss": 0.7346,
"step": 731
},
{
"epoch": 0.531811105345096,
"grad_norm": 0.361328125,
"learning_rate": 4.729305457072913e-05,
"loss": 0.7207,
"step": 732
},
{
"epoch": 0.5325376232485729,
"grad_norm": 0.328125,
"learning_rate": 4.717548402859008e-05,
"loss": 0.7337,
"step": 733
},
{
"epoch": 0.5332641411520498,
"grad_norm": 0.3359375,
"learning_rate": 4.705792915150589e-05,
"loss": 0.7503,
"step": 734
},
{
"epoch": 0.5339906590555267,
"grad_norm": 0.3203125,
"learning_rate": 4.694039059144797e-05,
"loss": 0.6965,
"step": 735
},
{
"epoch": 0.5347171769590037,
"grad_norm": 0.302734375,
"learning_rate": 4.6822869000297184e-05,
"loss": 0.7021,
"step": 736
},
{
"epoch": 0.5354436948624806,
"grad_norm": 0.65234375,
"learning_rate": 4.6705365029840326e-05,
"loss": 0.7188,
"step": 737
},
{
"epoch": 0.5361702127659574,
"grad_norm": 0.31640625,
"learning_rate": 4.658787933176646e-05,
"loss": 0.7253,
"step": 738
},
{
"epoch": 0.5368967306694343,
"grad_norm": 0.333984375,
"learning_rate": 4.647041255766329e-05,
"loss": 0.7376,
"step": 739
},
{
"epoch": 0.5376232485729112,
"grad_norm": 0.32421875,
"learning_rate": 4.635296535901357e-05,
"loss": 0.7336,
"step": 740
},
{
"epoch": 0.5383497664763882,
"grad_norm": 0.310546875,
"learning_rate": 4.623553838719151e-05,
"loss": 0.7244,
"step": 741
},
{
"epoch": 0.5390762843798651,
"grad_norm": 0.310546875,
"learning_rate": 4.6118132293459114e-05,
"loss": 0.7673,
"step": 742
},
{
"epoch": 0.539802802283342,
"grad_norm": 0.330078125,
"learning_rate": 4.60007477289626e-05,
"loss": 0.7618,
"step": 743
},
{
"epoch": 0.5405293201868189,
"grad_norm": 0.3125,
"learning_rate": 4.5883385344728777e-05,
"loss": 0.7252,
"step": 744
},
{
"epoch": 0.5412558380902958,
"grad_norm": 0.349609375,
"learning_rate": 4.5766045791661473e-05,
"loss": 0.7356,
"step": 745
},
{
"epoch": 0.5419823559937728,
"grad_norm": 0.310546875,
"learning_rate": 4.5648729720537855e-05,
"loss": 0.7257,
"step": 746
},
{
"epoch": 0.5427088738972496,
"grad_norm": 0.30078125,
"learning_rate": 4.553143778200486e-05,
"loss": 0.7505,
"step": 747
},
{
"epoch": 0.5434353918007265,
"grad_norm": 0.31640625,
"learning_rate": 4.541417062657561e-05,
"loss": 0.7125,
"step": 748
},
{
"epoch": 0.5441619097042034,
"grad_norm": 0.3515625,
"learning_rate": 4.529692890462574e-05,
"loss": 0.7592,
"step": 749
},
{
"epoch": 0.5448884276076803,
"grad_norm": 0.32421875,
"learning_rate": 4.517971326638986e-05,
"loss": 0.7521,
"step": 750
},
{
"epoch": 0.5456149455111572,
"grad_norm": 0.3203125,
"learning_rate": 4.5062524361957903e-05,
"loss": 0.7578,
"step": 751
},
{
"epoch": 0.5463414634146342,
"grad_norm": 0.326171875,
"learning_rate": 4.494536284127155e-05,
"loss": 0.721,
"step": 752
},
{
"epoch": 0.5470679813181111,
"grad_norm": 0.341796875,
"learning_rate": 4.482822935412056e-05,
"loss": 0.7652,
"step": 753
},
{
"epoch": 0.547794499221588,
"grad_norm": 0.3203125,
"learning_rate": 4.471112455013928e-05,
"loss": 0.7733,
"step": 754
},
{
"epoch": 0.5485210171250648,
"grad_norm": 0.31640625,
"learning_rate": 4.4594049078802925e-05,
"loss": 0.7405,
"step": 755
},
{
"epoch": 0.5492475350285417,
"grad_norm": 0.3203125,
"learning_rate": 4.447700358942407e-05,
"loss": 0.7008,
"step": 756
},
{
"epoch": 0.5499740529320187,
"grad_norm": 0.318359375,
"learning_rate": 4.435998873114895e-05,
"loss": 0.7298,
"step": 757
},
{
"epoch": 0.5507005708354956,
"grad_norm": 0.32421875,
"learning_rate": 4.4243005152954e-05,
"loss": 0.7372,
"step": 758
},
{
"epoch": 0.5514270887389725,
"grad_norm": 0.3359375,
"learning_rate": 4.412605350364213e-05,
"loss": 0.7593,
"step": 759
},
{
"epoch": 0.5521536066424494,
"grad_norm": 0.32421875,
"learning_rate": 4.4009134431839126e-05,
"loss": 0.7226,
"step": 760
},
{
"epoch": 0.5528801245459263,
"grad_norm": 0.30859375,
"learning_rate": 4.389224858599015e-05,
"loss": 0.7192,
"step": 761
},
{
"epoch": 0.5536066424494032,
"grad_norm": 0.33203125,
"learning_rate": 4.3775396614356077e-05,
"loss": 0.7394,
"step": 762
},
{
"epoch": 0.5543331603528802,
"grad_norm": 0.310546875,
"learning_rate": 4.365857916500992e-05,
"loss": 0.742,
"step": 763
},
{
"epoch": 0.555059678256357,
"grad_norm": 0.32421875,
"learning_rate": 4.3541796885833195e-05,
"loss": 0.7296,
"step": 764
},
{
"epoch": 0.5557861961598339,
"grad_norm": 0.30078125,
"learning_rate": 4.34250504245124e-05,
"loss": 0.7094,
"step": 765
},
{
"epoch": 0.5565127140633108,
"grad_norm": 0.33203125,
"learning_rate": 4.3308340428535364e-05,
"loss": 0.7469,
"step": 766
},
{
"epoch": 0.5572392319667877,
"grad_norm": 0.31640625,
"learning_rate": 4.319166754518768e-05,
"loss": 0.7476,
"step": 767
},
{
"epoch": 0.5579657498702647,
"grad_norm": 0.3359375,
"learning_rate": 4.30750324215491e-05,
"loss": 0.7595,
"step": 768
},
{
"epoch": 0.5586922677737416,
"grad_norm": 0.33203125,
"learning_rate": 4.2958435704489975e-05,
"loss": 0.7061,
"step": 769
},
{
"epoch": 0.5594187856772185,
"grad_norm": 0.357421875,
"learning_rate": 4.284187804066763e-05,
"loss": 0.7331,
"step": 770
},
{
"epoch": 0.5601453035806954,
"grad_norm": 0.310546875,
"learning_rate": 4.27253600765228e-05,
"loss": 0.7492,
"step": 771
},
{
"epoch": 0.5608718214841723,
"grad_norm": 0.357421875,
"learning_rate": 4.260888245827608e-05,
"loss": 0.7856,
"step": 772
},
{
"epoch": 0.5615983393876492,
"grad_norm": 0.349609375,
"learning_rate": 4.249244583192425e-05,
"loss": 0.7691,
"step": 773
},
{
"epoch": 0.5623248572911261,
"grad_norm": 0.341796875,
"learning_rate": 4.237605084323676e-05,
"loss": 0.756,
"step": 774
},
{
"epoch": 0.563051375194603,
"grad_norm": 0.30859375,
"learning_rate": 4.225969813775215e-05,
"loss": 0.7256,
"step": 775
},
{
"epoch": 0.5637778930980799,
"grad_norm": 0.341796875,
"learning_rate": 4.2143388360774433e-05,
"loss": 0.7483,
"step": 776
},
{
"epoch": 0.5645044110015568,
"grad_norm": 0.310546875,
"learning_rate": 4.202712215736955e-05,
"loss": 0.7153,
"step": 777
},
{
"epoch": 0.5652309289050337,
"grad_norm": 0.33203125,
"learning_rate": 4.1910900172361764e-05,
"loss": 0.754,
"step": 778
},
{
"epoch": 0.5659574468085107,
"grad_norm": 0.365234375,
"learning_rate": 4.179472305033012e-05,
"loss": 0.7603,
"step": 779
},
{
"epoch": 0.5666839647119876,
"grad_norm": 0.302734375,
"learning_rate": 4.167859143560484e-05,
"loss": 0.7032,
"step": 780
},
{
"epoch": 0.5674104826154645,
"grad_norm": 0.318359375,
"learning_rate": 4.1562505972263734e-05,
"loss": 0.7417,
"step": 781
},
{
"epoch": 0.5681370005189413,
"grad_norm": 0.330078125,
"learning_rate": 4.1446467304128684e-05,
"loss": 0.7222,
"step": 782
},
{
"epoch": 0.5688635184224182,
"grad_norm": 0.310546875,
"learning_rate": 4.133047607476202e-05,
"loss": 0.7,
"step": 783
},
{
"epoch": 0.5695900363258952,
"grad_norm": 0.353515625,
"learning_rate": 4.1214532927462965e-05,
"loss": 0.7571,
"step": 784
},
{
"epoch": 0.5703165542293721,
"grad_norm": 0.302734375,
"learning_rate": 4.109863850526413e-05,
"loss": 0.7431,
"step": 785
},
{
"epoch": 0.571043072132849,
"grad_norm": 0.310546875,
"learning_rate": 4.098279345092783e-05,
"loss": 0.6975,
"step": 786
},
{
"epoch": 0.5717695900363259,
"grad_norm": 0.31640625,
"learning_rate": 4.0866998406942615e-05,
"loss": 0.7665,
"step": 787
},
{
"epoch": 0.5724961079398028,
"grad_norm": 0.310546875,
"learning_rate": 4.075125401551963e-05,
"loss": 0.7613,
"step": 788
},
{
"epoch": 0.5732226258432797,
"grad_norm": 0.31640625,
"learning_rate": 4.063556091858914e-05,
"loss": 0.7615,
"step": 789
},
{
"epoch": 0.5739491437467567,
"grad_norm": 0.287109375,
"learning_rate": 4.051991975779691e-05,
"loss": 0.7539,
"step": 790
},
{
"epoch": 0.5746756616502335,
"grad_norm": 0.30078125,
"learning_rate": 4.040433117450066e-05,
"loss": 0.7241,
"step": 791
},
{
"epoch": 0.5754021795537104,
"grad_norm": 0.3515625,
"learning_rate": 4.028879580976651e-05,
"loss": 0.7401,
"step": 792
},
{
"epoch": 0.5761286974571873,
"grad_norm": 0.306640625,
"learning_rate": 4.0173314304365435e-05,
"loss": 0.7177,
"step": 793
},
{
"epoch": 0.5768552153606642,
"grad_norm": 0.310546875,
"learning_rate": 4.005788729876968e-05,
"loss": 0.7267,
"step": 794
},
{
"epoch": 0.5775817332641412,
"grad_norm": 0.302734375,
"learning_rate": 3.994251543314925e-05,
"loss": 0.7157,
"step": 795
},
{
"epoch": 0.5783082511676181,
"grad_norm": 0.33984375,
"learning_rate": 3.982719934736832e-05,
"loss": 0.7561,
"step": 796
},
{
"epoch": 0.579034769071095,
"grad_norm": 0.30859375,
"learning_rate": 3.971193968098172e-05,
"loss": 0.7468,
"step": 797
},
{
"epoch": 0.5797612869745719,
"grad_norm": 0.306640625,
"learning_rate": 3.9596737073231346e-05,
"loss": 0.7231,
"step": 798
},
{
"epoch": 0.5804878048780487,
"grad_norm": 0.32421875,
"learning_rate": 3.9481592163042685e-05,
"loss": 0.7106,
"step": 799
},
{
"epoch": 0.5812143227815257,
"grad_norm": 0.310546875,
"learning_rate": 3.93665055890212e-05,
"loss": 0.7177,
"step": 800
},
{
"epoch": 0.5819408406850026,
"grad_norm": 0.34375,
"learning_rate": 3.92514779894488e-05,
"loss": 0.732,
"step": 801
},
{
"epoch": 0.5826673585884795,
"grad_norm": 0.291015625,
"learning_rate": 3.913651000228035e-05,
"loss": 0.7491,
"step": 802
},
{
"epoch": 0.5833938764919564,
"grad_norm": 0.314453125,
"learning_rate": 3.902160226514007e-05,
"loss": 0.7483,
"step": 803
},
{
"epoch": 0.5841203943954333,
"grad_norm": 0.322265625,
"learning_rate": 3.8906755415318044e-05,
"loss": 0.7462,
"step": 804
},
{
"epoch": 0.5848469122989102,
"grad_norm": 0.31640625,
"learning_rate": 3.879197008976666e-05,
"loss": 0.7176,
"step": 805
},
{
"epoch": 0.5855734302023872,
"grad_norm": 0.30078125,
"learning_rate": 3.86772469250971e-05,
"loss": 0.7232,
"step": 806
},
{
"epoch": 0.586299948105864,
"grad_norm": 0.314453125,
"learning_rate": 3.856258655757578e-05,
"loss": 0.7285,
"step": 807
},
{
"epoch": 0.5870264660093409,
"grad_norm": 0.337890625,
"learning_rate": 3.844798962312085e-05,
"loss": 0.731,
"step": 808
},
{
"epoch": 0.5877529839128178,
"grad_norm": 0.314453125,
"learning_rate": 3.8333456757298624e-05,
"loss": 0.7125,
"step": 809
},
{
"epoch": 0.5884795018162947,
"grad_norm": 0.3125,
"learning_rate": 3.821898859532013e-05,
"loss": 0.7325,
"step": 810
},
{
"epoch": 0.5892060197197717,
"grad_norm": 0.318359375,
"learning_rate": 3.810458577203749e-05,
"loss": 0.7289,
"step": 811
},
{
"epoch": 0.5899325376232486,
"grad_norm": 0.3203125,
"learning_rate": 3.799024892194049e-05,
"loss": 0.7612,
"step": 812
},
{
"epoch": 0.5906590555267255,
"grad_norm": 0.328125,
"learning_rate": 3.787597867915303e-05,
"loss": 0.7679,
"step": 813
},
{
"epoch": 0.5913855734302024,
"grad_norm": 0.30859375,
"learning_rate": 3.776177567742957e-05,
"loss": 0.7277,
"step": 814
},
{
"epoch": 0.5921120913336793,
"grad_norm": 0.314453125,
"learning_rate": 3.7647640550151665e-05,
"loss": 0.7355,
"step": 815
},
{
"epoch": 0.5928386092371563,
"grad_norm": 0.310546875,
"learning_rate": 3.7533573930324396e-05,
"loss": 0.7345,
"step": 816
},
{
"epoch": 0.5935651271406331,
"grad_norm": 0.30078125,
"learning_rate": 3.7419576450572926e-05,
"loss": 0.7574,
"step": 817
},
{
"epoch": 0.59429164504411,
"grad_norm": 0.34375,
"learning_rate": 3.7305648743138964e-05,
"loss": 0.7571,
"step": 818
},
{
"epoch": 0.5950181629475869,
"grad_norm": 0.31640625,
"learning_rate": 3.7191791439877234e-05,
"loss": 0.7402,
"step": 819
},
{
"epoch": 0.5957446808510638,
"grad_norm": 0.302734375,
"learning_rate": 3.707800517225201e-05,
"loss": 0.723,
"step": 820
},
{
"epoch": 0.5964711987545407,
"grad_norm": 0.333984375,
"learning_rate": 3.696429057133358e-05,
"loss": 0.7109,
"step": 821
},
{
"epoch": 0.5971977166580177,
"grad_norm": 0.3203125,
"learning_rate": 3.685064826779477e-05,
"loss": 0.7079,
"step": 822
},
{
"epoch": 0.5979242345614946,
"grad_norm": 0.322265625,
"learning_rate": 3.673707889190744e-05,
"loss": 0.7287,
"step": 823
},
{
"epoch": 0.5986507524649715,
"grad_norm": 0.3203125,
"learning_rate": 3.6623583073538966e-05,
"loss": 0.7341,
"step": 824
},
{
"epoch": 0.5993772703684483,
"grad_norm": 0.318359375,
"learning_rate": 3.651016144214878e-05,
"loss": 0.7225,
"step": 825
},
{
"epoch": 0.6001037882719252,
"grad_norm": 0.3203125,
"learning_rate": 3.6396814626784894e-05,
"loss": 0.7269,
"step": 826
},
{
"epoch": 0.6008303061754022,
"grad_norm": 0.330078125,
"learning_rate": 3.628354325608033e-05,
"loss": 0.7393,
"step": 827
},
{
"epoch": 0.6015568240788791,
"grad_norm": 0.318359375,
"learning_rate": 3.6170347958249725e-05,
"loss": 0.7245,
"step": 828
},
{
"epoch": 0.602283341982356,
"grad_norm": 0.314453125,
"learning_rate": 3.6057229361085785e-05,
"loss": 0.7212,
"step": 829
},
{
"epoch": 0.6030098598858329,
"grad_norm": 0.306640625,
"learning_rate": 3.594418809195584e-05,
"loss": 0.751,
"step": 830
},
{
"epoch": 0.6037363777893098,
"grad_norm": 0.32421875,
"learning_rate": 3.583122477779835e-05,
"loss": 0.7447,
"step": 831
},
{
"epoch": 0.6044628956927867,
"grad_norm": 0.330078125,
"learning_rate": 3.5718340045119415e-05,
"loss": 0.738,
"step": 832
},
{
"epoch": 0.6051894135962637,
"grad_norm": 0.314453125,
"learning_rate": 3.560553451998933e-05,
"loss": 0.7204,
"step": 833
},
{
"epoch": 0.6059159314997405,
"grad_norm": 0.3359375,
"learning_rate": 3.549280882803908e-05,
"loss": 0.7415,
"step": 834
},
{
"epoch": 0.6066424494032174,
"grad_norm": 0.322265625,
"learning_rate": 3.5380163594456914e-05,
"loss": 0.7734,
"step": 835
},
{
"epoch": 0.6073689673066943,
"grad_norm": 0.306640625,
"learning_rate": 3.526759944398485e-05,
"loss": 0.7284,
"step": 836
},
{
"epoch": 0.6080954852101712,
"grad_norm": 0.3203125,
"learning_rate": 3.515511700091515e-05,
"loss": 0.7602,
"step": 837
},
{
"epoch": 0.6088220031136482,
"grad_norm": 0.296875,
"learning_rate": 3.5042716889086994e-05,
"loss": 0.7412,
"step": 838
},
{
"epoch": 0.6095485210171251,
"grad_norm": 0.30078125,
"learning_rate": 3.493039973188289e-05,
"loss": 0.7407,
"step": 839
},
{
"epoch": 0.610275038920602,
"grad_norm": 0.314453125,
"learning_rate": 3.481816615222533e-05,
"loss": 0.7032,
"step": 840
},
{
"epoch": 0.6110015568240789,
"grad_norm": 0.3125,
"learning_rate": 3.470601677257323e-05,
"loss": 0.7167,
"step": 841
},
{
"epoch": 0.6117280747275557,
"grad_norm": 0.3203125,
"learning_rate": 3.459395221491853e-05,
"loss": 0.7157,
"step": 842
},
{
"epoch": 0.6124545926310327,
"grad_norm": 0.326171875,
"learning_rate": 3.448197310078276e-05,
"loss": 0.7391,
"step": 843
},
{
"epoch": 0.6131811105345096,
"grad_norm": 0.328125,
"learning_rate": 3.4370080051213526e-05,
"loss": 0.7545,
"step": 844
},
{
"epoch": 0.6139076284379865,
"grad_norm": 0.314453125,
"learning_rate": 3.4258273686781154e-05,
"loss": 0.742,
"step": 845
},
{
"epoch": 0.6146341463414634,
"grad_norm": 0.326171875,
"learning_rate": 3.4146554627575205e-05,
"loss": 0.7466,
"step": 846
},
{
"epoch": 0.6153606642449403,
"grad_norm": 0.341796875,
"learning_rate": 3.403492349320101e-05,
"loss": 0.7548,
"step": 847
},
{
"epoch": 0.6160871821484172,
"grad_norm": 0.318359375,
"learning_rate": 3.392338090277628e-05,
"loss": 0.6977,
"step": 848
},
{
"epoch": 0.6168137000518942,
"grad_norm": 0.302734375,
"learning_rate": 3.381192747492764e-05,
"loss": 0.6957,
"step": 849
},
{
"epoch": 0.6175402179553711,
"grad_norm": 0.34765625,
"learning_rate": 3.3700563827787226e-05,
"loss": 0.7532,
"step": 850
},
{
"epoch": 0.618266735858848,
"grad_norm": 0.3203125,
"learning_rate": 3.358929057898922e-05,
"loss": 0.7099,
"step": 851
},
{
"epoch": 0.6189932537623248,
"grad_norm": 0.306640625,
"learning_rate": 3.347810834566645e-05,
"loss": 0.7294,
"step": 852
},
{
"epoch": 0.6197197716658017,
"grad_norm": 0.322265625,
"learning_rate": 3.336701774444699e-05,
"loss": 0.7237,
"step": 853
},
{
"epoch": 0.6204462895692787,
"grad_norm": 0.322265625,
"learning_rate": 3.325601939145069e-05,
"loss": 0.7183,
"step": 854
},
{
"epoch": 0.6211728074727556,
"grad_norm": 0.302734375,
"learning_rate": 3.314511390228578e-05,
"loss": 0.7121,
"step": 855
},
{
"epoch": 0.6218993253762325,
"grad_norm": 0.30859375,
"learning_rate": 3.303430189204545e-05,
"loss": 0.7106,
"step": 856
},
{
"epoch": 0.6226258432797094,
"grad_norm": 0.33203125,
"learning_rate": 3.292358397530447e-05,
"loss": 0.7482,
"step": 857
},
{
"epoch": 0.6233523611831863,
"grad_norm": 0.337890625,
"learning_rate": 3.2812960766115744e-05,
"loss": 0.7455,
"step": 858
},
{
"epoch": 0.6240788790866632,
"grad_norm": 0.31640625,
"learning_rate": 3.270243287800693e-05,
"loss": 0.7048,
"step": 859
},
{
"epoch": 0.6248053969901401,
"grad_norm": 0.28125,
"learning_rate": 3.2592000923976996e-05,
"loss": 0.7231,
"step": 860
},
{
"epoch": 0.625531914893617,
"grad_norm": 0.337890625,
"learning_rate": 3.248166551649288e-05,
"loss": 0.6935,
"step": 861
},
{
"epoch": 0.6262584327970939,
"grad_norm": 0.345703125,
"learning_rate": 3.2371427267486046e-05,
"loss": 0.7551,
"step": 862
},
{
"epoch": 0.6269849507005708,
"grad_norm": 0.314453125,
"learning_rate": 3.2261286788349126e-05,
"loss": 0.719,
"step": 863
},
{
"epoch": 0.6277114686040477,
"grad_norm": 0.314453125,
"learning_rate": 3.2151244689932505e-05,
"loss": 0.6961,
"step": 864
},
{
"epoch": 0.6284379865075247,
"grad_norm": 0.298828125,
"learning_rate": 3.20413015825409e-05,
"loss": 0.7051,
"step": 865
},
{
"epoch": 0.6291645044110016,
"grad_norm": 0.326171875,
"learning_rate": 3.193145807593004e-05,
"loss": 0.7683,
"step": 866
},
{
"epoch": 0.6298910223144785,
"grad_norm": 0.341796875,
"learning_rate": 3.182171477930332e-05,
"loss": 0.7217,
"step": 867
},
{
"epoch": 0.6306175402179554,
"grad_norm": 0.310546875,
"learning_rate": 3.171207230130826e-05,
"loss": 0.7245,
"step": 868
},
{
"epoch": 0.6313440581214322,
"grad_norm": 0.341796875,
"learning_rate": 3.160253125003328e-05,
"loss": 0.7626,
"step": 869
},
{
"epoch": 0.6320705760249092,
"grad_norm": 0.2890625,
"learning_rate": 3.149309223300428e-05,
"loss": 0.7165,
"step": 870
},
{
"epoch": 0.6327970939283861,
"grad_norm": 0.31640625,
"learning_rate": 3.138375585718125e-05,
"loss": 0.7256,
"step": 871
},
{
"epoch": 0.633523611831863,
"grad_norm": 0.3203125,
"learning_rate": 3.127452272895492e-05,
"loss": 0.7472,
"step": 872
},
{
"epoch": 0.6342501297353399,
"grad_norm": 0.298828125,
"learning_rate": 3.116539345414342e-05,
"loss": 0.7263,
"step": 873
},
{
"epoch": 0.6349766476388168,
"grad_norm": 0.33203125,
"learning_rate": 3.105636863798888e-05,
"loss": 0.739,
"step": 874
},
{
"epoch": 0.6357031655422937,
"grad_norm": 0.314453125,
"learning_rate": 3.0947448885154084e-05,
"loss": 0.7548,
"step": 875
},
{
"epoch": 0.6364296834457707,
"grad_norm": 0.30859375,
"learning_rate": 3.083863479971916e-05,
"loss": 0.7428,
"step": 876
},
{
"epoch": 0.6371562013492476,
"grad_norm": 0.306640625,
"learning_rate": 3.072992698517815e-05,
"loss": 0.7339,
"step": 877
},
{
"epoch": 0.6378827192527244,
"grad_norm": 0.306640625,
"learning_rate": 3.062132604443574e-05,
"loss": 0.7296,
"step": 878
},
{
"epoch": 0.6386092371562013,
"grad_norm": 0.349609375,
"learning_rate": 3.0512832579803872e-05,
"loss": 0.791,
"step": 879
},
{
"epoch": 0.6393357550596782,
"grad_norm": 0.310546875,
"learning_rate": 3.0404447192998397e-05,
"loss": 0.7121,
"step": 880
},
{
"epoch": 0.6400622729631552,
"grad_norm": 0.310546875,
"learning_rate": 3.0296170485135787e-05,
"loss": 0.725,
"step": 881
},
{
"epoch": 0.6407887908666321,
"grad_norm": 0.310546875,
"learning_rate": 3.018800305672975e-05,
"loss": 0.7111,
"step": 882
},
{
"epoch": 0.641515308770109,
"grad_norm": 0.3046875,
"learning_rate": 3.007994550768793e-05,
"loss": 0.7268,
"step": 883
},
{
"epoch": 0.6422418266735859,
"grad_norm": 0.333984375,
"learning_rate": 2.9971998437308547e-05,
"loss": 0.7348,
"step": 884
},
{
"epoch": 0.6429683445770628,
"grad_norm": 0.30859375,
"learning_rate": 2.9864162444277116e-05,
"loss": 0.7313,
"step": 885
},
{
"epoch": 0.6436948624805398,
"grad_norm": 0.302734375,
"learning_rate": 2.97564381266631e-05,
"loss": 0.7111,
"step": 886
},
{
"epoch": 0.6444213803840166,
"grad_norm": 0.291015625,
"learning_rate": 2.964882608191659e-05,
"loss": 0.7054,
"step": 887
},
{
"epoch": 0.6451478982874935,
"grad_norm": 0.296875,
"learning_rate": 2.954132690686502e-05,
"loss": 0.7123,
"step": 888
},
{
"epoch": 0.6458744161909704,
"grad_norm": 0.3671875,
"learning_rate": 2.9433941197709814e-05,
"loss": 0.7509,
"step": 889
},
{
"epoch": 0.6466009340944473,
"grad_norm": 0.310546875,
"learning_rate": 2.932666955002312e-05,
"loss": 0.7098,
"step": 890
},
{
"epoch": 0.6473274519979242,
"grad_norm": 0.30078125,
"learning_rate": 2.9219512558744487e-05,
"loss": 0.7415,
"step": 891
},
{
"epoch": 0.6480539699014012,
"grad_norm": 0.34375,
"learning_rate": 2.911247081817756e-05,
"loss": 0.7191,
"step": 892
},
{
"epoch": 0.6487804878048781,
"grad_norm": 0.31640625,
"learning_rate": 2.900554492198677e-05,
"loss": 0.7245,
"step": 893
},
{
"epoch": 0.649507005708355,
"grad_norm": 0.326171875,
"learning_rate": 2.8898735463194127e-05,
"loss": 0.7731,
"step": 894
},
{
"epoch": 0.6502335236118318,
"grad_norm": 0.296875,
"learning_rate": 2.8792043034175813e-05,
"loss": 0.7349,
"step": 895
},
{
"epoch": 0.6509600415153087,
"grad_norm": 0.326171875,
"learning_rate": 2.8685468226658974e-05,
"loss": 0.7267,
"step": 896
},
{
"epoch": 0.6516865594187857,
"grad_norm": 0.3125,
"learning_rate": 2.85790116317184e-05,
"loss": 0.7175,
"step": 897
},
{
"epoch": 0.6524130773222626,
"grad_norm": 0.298828125,
"learning_rate": 2.8472673839773267e-05,
"loss": 0.7159,
"step": 898
},
{
"epoch": 0.6531395952257395,
"grad_norm": 0.3125,
"learning_rate": 2.8366455440583873e-05,
"loss": 0.7338,
"step": 899
},
{
"epoch": 0.6538661131292164,
"grad_norm": 0.314453125,
"learning_rate": 2.8260357023248324e-05,
"loss": 0.7108,
"step": 900
},
{
"epoch": 0.6545926310326933,
"grad_norm": 0.302734375,
"learning_rate": 2.8154379176199318e-05,
"loss": 0.7466,
"step": 901
},
{
"epoch": 0.6553191489361702,
"grad_norm": 0.3203125,
"learning_rate": 2.804852248720085e-05,
"loss": 0.7172,
"step": 902
},
{
"epoch": 0.6560456668396472,
"grad_norm": 0.330078125,
"learning_rate": 2.7942787543344955e-05,
"loss": 0.7806,
"step": 903
},
{
"epoch": 0.656772184743124,
"grad_norm": 0.302734375,
"learning_rate": 2.783717493104846e-05,
"loss": 0.7004,
"step": 904
},
{
"epoch": 0.6574987026466009,
"grad_norm": 0.328125,
"learning_rate": 2.7731685236049742e-05,
"loss": 0.7437,
"step": 905
},
{
"epoch": 0.6582252205500778,
"grad_norm": 0.314453125,
"learning_rate": 2.7626319043405457e-05,
"loss": 0.73,
"step": 906
},
{
"epoch": 0.6589517384535547,
"grad_norm": 0.365234375,
"learning_rate": 2.7521076937487244e-05,
"loss": 0.7448,
"step": 907
},
{
"epoch": 0.6596782563570317,
"grad_norm": 0.306640625,
"learning_rate": 2.741595950197867e-05,
"loss": 0.71,
"step": 908
},
{
"epoch": 0.6604047742605086,
"grad_norm": 0.33203125,
"learning_rate": 2.7310967319871774e-05,
"loss": 0.7704,
"step": 909
},
{
"epoch": 0.6611312921639855,
"grad_norm": 0.32421875,
"learning_rate": 2.7206100973463955e-05,
"loss": 0.7321,
"step": 910
},
{
"epoch": 0.6618578100674624,
"grad_norm": 0.306640625,
"learning_rate": 2.7101361044354702e-05,
"loss": 0.7369,
"step": 911
},
{
"epoch": 0.6625843279709392,
"grad_norm": 0.32421875,
"learning_rate": 2.6996748113442394e-05,
"loss": 0.7368,
"step": 912
},
{
"epoch": 0.6633108458744162,
"grad_norm": 0.32421875,
"learning_rate": 2.6892262760921067e-05,
"loss": 0.7008,
"step": 913
},
{
"epoch": 0.6640373637778931,
"grad_norm": 0.32421875,
"learning_rate": 2.6787905566277184e-05,
"loss": 0.7259,
"step": 914
},
{
"epoch": 0.66476388168137,
"grad_norm": 0.328125,
"learning_rate": 2.668367710828642e-05,
"loss": 0.7287,
"step": 915
},
{
"epoch": 0.6654903995848469,
"grad_norm": 0.3203125,
"learning_rate": 2.65795779650105e-05,
"loss": 0.7098,
"step": 916
},
{
"epoch": 0.6662169174883238,
"grad_norm": 0.33984375,
"learning_rate": 2.647560871379392e-05,
"loss": 0.716,
"step": 917
},
{
"epoch": 0.6669434353918007,
"grad_norm": 0.3125,
"learning_rate": 2.6371769931260805e-05,
"loss": 0.7018,
"step": 918
},
{
"epoch": 0.6676699532952777,
"grad_norm": 0.3203125,
"learning_rate": 2.626806219331167e-05,
"loss": 0.7044,
"step": 919
},
{
"epoch": 0.6683964711987546,
"grad_norm": 0.310546875,
"learning_rate": 2.6164486075120243e-05,
"loss": 0.7289,
"step": 920
},
{
"epoch": 0.6691229891022314,
"grad_norm": 0.30078125,
"learning_rate": 2.6061042151130327e-05,
"loss": 0.6935,
"step": 921
},
{
"epoch": 0.6698495070057083,
"grad_norm": 0.33984375,
"learning_rate": 2.5957730995052476e-05,
"loss": 0.755,
"step": 922
},
{
"epoch": 0.6705760249091852,
"grad_norm": 0.330078125,
"learning_rate": 2.585455317986095e-05,
"loss": 0.7401,
"step": 923
},
{
"epoch": 0.6713025428126622,
"grad_norm": 0.296875,
"learning_rate": 2.5751509277790486e-05,
"loss": 0.7217,
"step": 924
},
{
"epoch": 0.6720290607161391,
"grad_norm": 0.306640625,
"learning_rate": 2.5648599860333124e-05,
"loss": 0.7361,
"step": 925
},
{
"epoch": 0.672755578619616,
"grad_norm": 0.29296875,
"learning_rate": 2.5545825498235022e-05,
"loss": 0.7138,
"step": 926
},
{
"epoch": 0.6734820965230929,
"grad_norm": 0.3359375,
"learning_rate": 2.5443186761493325e-05,
"loss": 0.7396,
"step": 927
},
{
"epoch": 0.6742086144265698,
"grad_norm": 0.3125,
"learning_rate": 2.5340684219352977e-05,
"loss": 0.7102,
"step": 928
},
{
"epoch": 0.6749351323300466,
"grad_norm": 0.322265625,
"learning_rate": 2.5238318440303577e-05,
"loss": 0.7425,
"step": 929
},
{
"epoch": 0.6756616502335236,
"grad_norm": 0.359375,
"learning_rate": 2.5136089992076218e-05,
"loss": 0.7466,
"step": 930
},
{
"epoch": 0.6763881681370005,
"grad_norm": 0.3203125,
"learning_rate": 2.5033999441640348e-05,
"loss": 0.7399,
"step": 931
},
{
"epoch": 0.6771146860404774,
"grad_norm": 0.3046875,
"learning_rate": 2.493204735520061e-05,
"loss": 0.7258,
"step": 932
},
{
"epoch": 0.6778412039439543,
"grad_norm": 0.31640625,
"learning_rate": 2.4830234298193722e-05,
"loss": 0.713,
"step": 933
},
{
"epoch": 0.6785677218474312,
"grad_norm": 0.3125,
"learning_rate": 2.4728560835285308e-05,
"loss": 0.7294,
"step": 934
},
{
"epoch": 0.6792942397509082,
"grad_norm": 0.326171875,
"learning_rate": 2.4627027530366838e-05,
"loss": 0.7539,
"step": 935
},
{
"epoch": 0.6800207576543851,
"grad_norm": 0.3515625,
"learning_rate": 2.4525634946552408e-05,
"loss": 0.7643,
"step": 936
},
{
"epoch": 0.680747275557862,
"grad_norm": 0.310546875,
"learning_rate": 2.442438364617567e-05,
"loss": 0.7644,
"step": 937
},
{
"epoch": 0.6814737934613389,
"grad_norm": 0.31640625,
"learning_rate": 2.4323274190786704e-05,
"loss": 0.744,
"step": 938
},
{
"epoch": 0.6822003113648157,
"grad_norm": 0.326171875,
"learning_rate": 2.422230714114891e-05,
"loss": 0.7489,
"step": 939
},
{
"epoch": 0.6829268292682927,
"grad_norm": 0.337890625,
"learning_rate": 2.4121483057235883e-05,
"loss": 0.7216,
"step": 940
},
{
"epoch": 0.6836533471717696,
"grad_norm": 0.3125,
"learning_rate": 2.4020802498228335e-05,
"loss": 0.7211,
"step": 941
},
{
"epoch": 0.6843798650752465,
"grad_norm": 0.330078125,
"learning_rate": 2.392026602251093e-05,
"loss": 0.7428,
"step": 942
},
{
"epoch": 0.6851063829787234,
"grad_norm": 0.322265625,
"learning_rate": 2.3819874187669268e-05,
"loss": 0.7171,
"step": 943
},
{
"epoch": 0.6858329008822003,
"grad_norm": 0.298828125,
"learning_rate": 2.371962755048675e-05,
"loss": 0.725,
"step": 944
},
{
"epoch": 0.6865594187856772,
"grad_norm": 0.359375,
"learning_rate": 2.36195266669415e-05,
"loss": 0.787,
"step": 945
},
{
"epoch": 0.6872859366891542,
"grad_norm": 0.345703125,
"learning_rate": 2.351957209220326e-05,
"loss": 0.7137,
"step": 946
},
{
"epoch": 0.688012454592631,
"grad_norm": 0.31640625,
"learning_rate": 2.341976438063035e-05,
"loss": 0.7238,
"step": 947
},
{
"epoch": 0.6887389724961079,
"grad_norm": 0.326171875,
"learning_rate": 2.332010408576653e-05,
"loss": 0.7638,
"step": 948
},
{
"epoch": 0.6894654903995848,
"grad_norm": 0.345703125,
"learning_rate": 2.3220591760338046e-05,
"loss": 0.72,
"step": 949
},
{
"epoch": 0.6901920083030617,
"grad_norm": 0.318359375,
"learning_rate": 2.3121227956250435e-05,
"loss": 0.7453,
"step": 950
},
{
"epoch": 0.6909185262065387,
"grad_norm": 0.353515625,
"learning_rate": 2.302201322458552e-05,
"loss": 0.7772,
"step": 951
},
{
"epoch": 0.6916450441100156,
"grad_norm": 0.314453125,
"learning_rate": 2.292294811559837e-05,
"loss": 0.7242,
"step": 952
},
{
"epoch": 0.6923715620134925,
"grad_norm": 0.310546875,
"learning_rate": 2.2824033178714222e-05,
"loss": 0.7559,
"step": 953
},
{
"epoch": 0.6930980799169694,
"grad_norm": 0.330078125,
"learning_rate": 2.2725268962525452e-05,
"loss": 0.7601,
"step": 954
},
{
"epoch": 0.6938245978204463,
"grad_norm": 0.326171875,
"learning_rate": 2.2626656014788515e-05,
"loss": 0.7292,
"step": 955
},
{
"epoch": 0.6945511157239233,
"grad_norm": 0.318359375,
"learning_rate": 2.252819488242093e-05,
"loss": 0.713,
"step": 956
},
{
"epoch": 0.6952776336274001,
"grad_norm": 0.306640625,
"learning_rate": 2.2429886111498198e-05,
"loss": 0.7184,
"step": 957
},
{
"epoch": 0.696004151530877,
"grad_norm": 0.328125,
"learning_rate": 2.2331730247250852e-05,
"loss": 0.7221,
"step": 958
},
{
"epoch": 0.6967306694343539,
"grad_norm": 0.3203125,
"learning_rate": 2.223372783406137e-05,
"loss": 0.7447,
"step": 959
},
{
"epoch": 0.6974571873378308,
"grad_norm": 0.3203125,
"learning_rate": 2.213587941546115e-05,
"loss": 0.7579,
"step": 960
},
{
"epoch": 0.6981837052413077,
"grad_norm": 0.337890625,
"learning_rate": 2.203818553412757e-05,
"loss": 0.758,
"step": 961
},
{
"epoch": 0.6989102231447847,
"grad_norm": 0.3359375,
"learning_rate": 2.194064673188089e-05,
"loss": 0.759,
"step": 962
},
{
"epoch": 0.6996367410482616,
"grad_norm": 0.328125,
"learning_rate": 2.1843263549681286e-05,
"loss": 0.7447,
"step": 963
},
{
"epoch": 0.7003632589517385,
"grad_norm": 0.3359375,
"learning_rate": 2.174603652762588e-05,
"loss": 0.7385,
"step": 964
},
{
"epoch": 0.7010897768552153,
"grad_norm": 0.314453125,
"learning_rate": 2.1648966204945686e-05,
"loss": 0.7295,
"step": 965
},
{
"epoch": 0.7018162947586922,
"grad_norm": 0.296875,
"learning_rate": 2.1552053120002652e-05,
"loss": 0.7036,
"step": 966
},
{
"epoch": 0.7025428126621692,
"grad_norm": 0.306640625,
"learning_rate": 2.145529781028668e-05,
"loss": 0.7046,
"step": 967
},
{
"epoch": 0.7032693305656461,
"grad_norm": 0.306640625,
"learning_rate": 2.1358700812412623e-05,
"loss": 0.743,
"step": 968
},
{
"epoch": 0.703995848469123,
"grad_norm": 0.328125,
"learning_rate": 2.1262262662117328e-05,
"loss": 0.7401,
"step": 969
},
{
"epoch": 0.7047223663725999,
"grad_norm": 0.3359375,
"learning_rate": 2.1165983894256647e-05,
"loss": 0.7284,
"step": 970
},
{
"epoch": 0.7054488842760768,
"grad_norm": 0.3203125,
"learning_rate": 2.10698650428025e-05,
"loss": 0.7131,
"step": 971
},
{
"epoch": 0.7061754021795537,
"grad_norm": 0.302734375,
"learning_rate": 2.097390664083987e-05,
"loss": 0.7576,
"step": 972
},
{
"epoch": 0.7069019200830307,
"grad_norm": 0.322265625,
"learning_rate": 2.0878109220563883e-05,
"loss": 0.7667,
"step": 973
},
{
"epoch": 0.7076284379865075,
"grad_norm": 0.3515625,
"learning_rate": 2.0782473313276852e-05,
"loss": 0.7311,
"step": 974
},
{
"epoch": 0.7083549558899844,
"grad_norm": 0.306640625,
"learning_rate": 2.0686999449385284e-05,
"loss": 0.7047,
"step": 975
},
{
"epoch": 0.7090814737934613,
"grad_norm": 0.30859375,
"learning_rate": 2.0591688158397054e-05,
"loss": 0.7102,
"step": 976
},
{
"epoch": 0.7098079916969382,
"grad_norm": 0.310546875,
"learning_rate": 2.0496539968918345e-05,
"loss": 0.7126,
"step": 977
},
{
"epoch": 0.7105345096004152,
"grad_norm": 0.33984375,
"learning_rate": 2.0401555408650715e-05,
"loss": 0.7863,
"step": 978
},
{
"epoch": 0.7112610275038921,
"grad_norm": 0.3203125,
"learning_rate": 2.0306735004388284e-05,
"loss": 0.7334,
"step": 979
},
{
"epoch": 0.711987545407369,
"grad_norm": 0.32421875,
"learning_rate": 2.0212079282014722e-05,
"loss": 0.7611,
"step": 980
},
{
"epoch": 0.7127140633108459,
"grad_norm": 0.330078125,
"learning_rate": 2.0117588766500374e-05,
"loss": 0.7141,
"step": 981
},
{
"epoch": 0.7134405812143227,
"grad_norm": 0.3359375,
"learning_rate": 2.002326398189931e-05,
"loss": 0.7515,
"step": 982
},
{
"epoch": 0.7141670991177997,
"grad_norm": 0.345703125,
"learning_rate": 1.9929105451346435e-05,
"loss": 0.7378,
"step": 983
},
{
"epoch": 0.7148936170212766,
"grad_norm": 0.294921875,
"learning_rate": 1.983511369705462e-05,
"loss": 0.7034,
"step": 984
},
{
"epoch": 0.7156201349247535,
"grad_norm": 0.322265625,
"learning_rate": 1.9741289240311755e-05,
"loss": 0.7425,
"step": 985
},
{
"epoch": 0.7163466528282304,
"grad_norm": 0.32421875,
"learning_rate": 1.9647632601477878e-05,
"loss": 0.7151,
"step": 986
},
{
"epoch": 0.7170731707317073,
"grad_norm": 0.31640625,
"learning_rate": 1.9554144299982312e-05,
"loss": 0.7316,
"step": 987
},
{
"epoch": 0.7177996886351842,
"grad_norm": 0.314453125,
"learning_rate": 1.9460824854320752e-05,
"loss": 0.7176,
"step": 988
},
{
"epoch": 0.7185262065386612,
"grad_norm": 0.314453125,
"learning_rate": 1.9367674782052374e-05,
"loss": 0.7245,
"step": 989
},
{
"epoch": 0.7192527244421381,
"grad_norm": 0.32421875,
"learning_rate": 1.9274694599797065e-05,
"loss": 0.6994,
"step": 990
},
{
"epoch": 0.719979242345615,
"grad_norm": 0.287109375,
"learning_rate": 1.9181884823232415e-05,
"loss": 0.7041,
"step": 991
},
{
"epoch": 0.7207057602490918,
"grad_norm": 0.310546875,
"learning_rate": 1.9089245967090953e-05,
"loss": 0.7628,
"step": 992
},
{
"epoch": 0.7214322781525687,
"grad_norm": 0.318359375,
"learning_rate": 1.8996778545157263e-05,
"loss": 0.7192,
"step": 993
},
{
"epoch": 0.7221587960560457,
"grad_norm": 0.3125,
"learning_rate": 1.8904483070265132e-05,
"loss": 0.7323,
"step": 994
},
{
"epoch": 0.7228853139595226,
"grad_norm": 0.306640625,
"learning_rate": 1.8812360054294724e-05,
"loss": 0.7534,
"step": 995
},
{
"epoch": 0.7236118318629995,
"grad_norm": 0.306640625,
"learning_rate": 1.8720410008169726e-05,
"loss": 0.7352,
"step": 996
},
{
"epoch": 0.7243383497664764,
"grad_norm": 0.365234375,
"learning_rate": 1.8628633441854513e-05,
"loss": 0.7612,
"step": 997
},
{
"epoch": 0.7250648676699533,
"grad_norm": 0.3046875,
"learning_rate": 1.8537030864351303e-05,
"loss": 0.7269,
"step": 998
},
{
"epoch": 0.7257913855734301,
"grad_norm": 0.330078125,
"learning_rate": 1.8445602783697374e-05,
"loss": 0.7404,
"step": 999
},
{
"epoch": 0.7265179034769071,
"grad_norm": 0.328125,
"learning_rate": 1.835434970696224e-05,
"loss": 0.7343,
"step": 1000
},
{
"epoch": 0.727244421380384,
"grad_norm": 0.318359375,
"learning_rate": 1.8263272140244802e-05,
"loss": 0.7163,
"step": 1001
},
{
"epoch": 0.7279709392838609,
"grad_norm": 0.31640625,
"learning_rate": 1.817237058867056e-05,
"loss": 0.7414,
"step": 1002
},
{
"epoch": 0.7286974571873378,
"grad_norm": 0.322265625,
"learning_rate": 1.8081645556388865e-05,
"loss": 0.7137,
"step": 1003
},
{
"epoch": 0.7294239750908147,
"grad_norm": 0.330078125,
"learning_rate": 1.7991097546570018e-05,
"loss": 0.729,
"step": 1004
},
{
"epoch": 0.7301504929942917,
"grad_norm": 0.302734375,
"learning_rate": 1.7900727061402557e-05,
"loss": 0.7281,
"step": 1005
},
{
"epoch": 0.7308770108977686,
"grad_norm": 0.30859375,
"learning_rate": 1.7810534602090444e-05,
"loss": 0.6918,
"step": 1006
},
{
"epoch": 0.7316035288012455,
"grad_norm": 0.32421875,
"learning_rate": 1.77205206688503e-05,
"loss": 0.7228,
"step": 1007
},
{
"epoch": 0.7323300467047223,
"grad_norm": 0.30078125,
"learning_rate": 1.7630685760908622e-05,
"loss": 0.6887,
"step": 1008
},
{
"epoch": 0.7330565646081992,
"grad_norm": 0.328125,
"learning_rate": 1.7541030376499002e-05,
"loss": 0.7307,
"step": 1009
},
{
"epoch": 0.7337830825116762,
"grad_norm": 0.28125,
"learning_rate": 1.7451555012859388e-05,
"loss": 0.7352,
"step": 1010
},
{
"epoch": 0.7345096004151531,
"grad_norm": 0.30859375,
"learning_rate": 1.736226016622931e-05,
"loss": 0.759,
"step": 1011
},
{
"epoch": 0.73523611831863,
"grad_norm": 0.3046875,
"learning_rate": 1.727314633184714e-05,
"loss": 0.7404,
"step": 1012
},
{
"epoch": 0.7359626362221069,
"grad_norm": 0.333984375,
"learning_rate": 1.7184214003947318e-05,
"loss": 0.7244,
"step": 1013
},
{
"epoch": 0.7366891541255838,
"grad_norm": 0.333984375,
"learning_rate": 1.7095463675757655e-05,
"loss": 0.7331,
"step": 1014
},
{
"epoch": 0.7374156720290607,
"grad_norm": 0.3359375,
"learning_rate": 1.7006895839496557e-05,
"loss": 0.7909,
"step": 1015
},
{
"epoch": 0.7381421899325377,
"grad_norm": 0.32421875,
"learning_rate": 1.6918510986370312e-05,
"loss": 0.7598,
"step": 1016
},
{
"epoch": 0.7388687078360145,
"grad_norm": 0.306640625,
"learning_rate": 1.683030960657037e-05,
"loss": 0.6913,
"step": 1017
},
{
"epoch": 0.7395952257394914,
"grad_norm": 0.310546875,
"learning_rate": 1.674229218927062e-05,
"loss": 0.7444,
"step": 1018
},
{
"epoch": 0.7403217436429683,
"grad_norm": 0.314453125,
"learning_rate": 1.665445922262467e-05,
"loss": 0.7384,
"step": 1019
},
{
"epoch": 0.7410482615464452,
"grad_norm": 0.310546875,
"learning_rate": 1.656681119376315e-05,
"loss": 0.7497,
"step": 1020
},
{
"epoch": 0.7417747794499222,
"grad_norm": 0.283203125,
"learning_rate": 1.6479348588791e-05,
"loss": 0.7102,
"step": 1021
},
{
"epoch": 0.7425012973533991,
"grad_norm": 0.314453125,
"learning_rate": 1.6392071892784787e-05,
"loss": 0.7023,
"step": 1022
},
{
"epoch": 0.743227815256876,
"grad_norm": 0.322265625,
"learning_rate": 1.6304981589790012e-05,
"loss": 0.756,
"step": 1023
},
{
"epoch": 0.7439543331603529,
"grad_norm": 0.310546875,
"learning_rate": 1.6218078162818418e-05,
"loss": 0.7294,
"step": 1024
},
{
"epoch": 0.7446808510638298,
"grad_norm": 0.3203125,
"learning_rate": 1.6131362093845296e-05,
"loss": 0.7419,
"step": 1025
},
{
"epoch": 0.7454073689673067,
"grad_norm": 0.31640625,
"learning_rate": 1.6044833863806862e-05,
"loss": 0.7202,
"step": 1026
},
{
"epoch": 0.7461338868707836,
"grad_norm": 0.296875,
"learning_rate": 1.5958493952597536e-05,
"loss": 0.7197,
"step": 1027
},
{
"epoch": 0.7468604047742605,
"grad_norm": 0.318359375,
"learning_rate": 1.5872342839067306e-05,
"loss": 0.7478,
"step": 1028
},
{
"epoch": 0.7475869226777374,
"grad_norm": 0.32421875,
"learning_rate": 1.578638100101905e-05,
"loss": 0.7458,
"step": 1029
},
{
"epoch": 0.7483134405812143,
"grad_norm": 0.3125,
"learning_rate": 1.570060891520598e-05,
"loss": 0.7131,
"step": 1030
},
{
"epoch": 0.7490399584846912,
"grad_norm": 0.322265625,
"learning_rate": 1.561502705732883e-05,
"loss": 0.6989,
"step": 1031
},
{
"epoch": 0.7497664763881682,
"grad_norm": 0.32421875,
"learning_rate": 1.5529635902033358e-05,
"loss": 0.7103,
"step": 1032
},
{
"epoch": 0.7504929942916451,
"grad_norm": 0.314453125,
"learning_rate": 1.5444435922907668e-05,
"loss": 0.7047,
"step": 1033
},
{
"epoch": 0.751219512195122,
"grad_norm": 0.333984375,
"learning_rate": 1.535942759247955e-05,
"loss": 0.7355,
"step": 1034
},
{
"epoch": 0.7519460300985988,
"grad_norm": 0.314453125,
"learning_rate": 1.5274611382213922e-05,
"loss": 0.7169,
"step": 1035
},
{
"epoch": 0.7526725480020757,
"grad_norm": 0.30859375,
"learning_rate": 1.5189987762510167e-05,
"loss": 0.7117,
"step": 1036
},
{
"epoch": 0.7533990659055527,
"grad_norm": 0.31640625,
"learning_rate": 1.510555720269955e-05,
"loss": 0.7205,
"step": 1037
},
{
"epoch": 0.7541255838090296,
"grad_norm": 0.333984375,
"learning_rate": 1.5021320171042608e-05,
"loss": 0.7395,
"step": 1038
},
{
"epoch": 0.7548521017125065,
"grad_norm": 0.390625,
"learning_rate": 1.493727713472654e-05,
"loss": 0.6943,
"step": 1039
},
{
"epoch": 0.7555786196159834,
"grad_norm": 0.314453125,
"learning_rate": 1.4853428559862636e-05,
"loss": 0.6992,
"step": 1040
},
{
"epoch": 0.7563051375194603,
"grad_norm": 0.31640625,
"learning_rate": 1.4769774911483685e-05,
"loss": 0.7296,
"step": 1041
},
{
"epoch": 0.7570316554229372,
"grad_norm": 0.3203125,
"learning_rate": 1.4686316653541377e-05,
"loss": 0.71,
"step": 1042
},
{
"epoch": 0.7577581733264142,
"grad_norm": 0.32421875,
"learning_rate": 1.4603054248903752e-05,
"loss": 0.74,
"step": 1043
},
{
"epoch": 0.758484691229891,
"grad_norm": 0.318359375,
"learning_rate": 1.4519988159352666e-05,
"loss": 0.7457,
"step": 1044
},
{
"epoch": 0.7592112091333679,
"grad_norm": 0.314453125,
"learning_rate": 1.4437118845581138e-05,
"loss": 0.726,
"step": 1045
},
{
"epoch": 0.7599377270368448,
"grad_norm": 0.328125,
"learning_rate": 1.4354446767190871e-05,
"loss": 0.7261,
"step": 1046
},
{
"epoch": 0.7606642449403217,
"grad_norm": 0.3203125,
"learning_rate": 1.4271972382689685e-05,
"loss": 0.7144,
"step": 1047
},
{
"epoch": 0.7613907628437987,
"grad_norm": 0.30859375,
"learning_rate": 1.4189696149488957e-05,
"loss": 0.7331,
"step": 1048
},
{
"epoch": 0.7621172807472756,
"grad_norm": 0.310546875,
"learning_rate": 1.41076185239011e-05,
"loss": 0.745,
"step": 1049
},
{
"epoch": 0.7628437986507525,
"grad_norm": 0.3203125,
"learning_rate": 1.402573996113704e-05,
"loss": 0.7249,
"step": 1050
},
{
"epoch": 0.7635703165542294,
"grad_norm": 0.357421875,
"learning_rate": 1.3944060915303669e-05,
"loss": 0.7555,
"step": 1051
},
{
"epoch": 0.7642968344577062,
"grad_norm": 0.34765625,
"learning_rate": 1.3862581839401344e-05,
"loss": 0.7404,
"step": 1052
},
{
"epoch": 0.7650233523611832,
"grad_norm": 0.3125,
"learning_rate": 1.3781303185321376e-05,
"loss": 0.7305,
"step": 1053
},
{
"epoch": 0.7657498702646601,
"grad_norm": 0.31640625,
"learning_rate": 1.3700225403843469e-05,
"loss": 0.7065,
"step": 1054
},
{
"epoch": 0.766476388168137,
"grad_norm": 0.326171875,
"learning_rate": 1.3619348944633331e-05,
"loss": 0.7467,
"step": 1055
},
{
"epoch": 0.7672029060716139,
"grad_norm": 0.326171875,
"learning_rate": 1.3538674256240086e-05,
"loss": 0.7669,
"step": 1056
},
{
"epoch": 0.7679294239750908,
"grad_norm": 0.287109375,
"learning_rate": 1.3458201786093794e-05,
"loss": 0.7234,
"step": 1057
},
{
"epoch": 0.7686559418785677,
"grad_norm": 0.318359375,
"learning_rate": 1.3377931980503055e-05,
"loss": 0.7239,
"step": 1058
},
{
"epoch": 0.7693824597820447,
"grad_norm": 0.29296875,
"learning_rate": 1.3297865284652416e-05,
"loss": 0.7106,
"step": 1059
},
{
"epoch": 0.7701089776855216,
"grad_norm": 0.322265625,
"learning_rate": 1.3218002142599972e-05,
"loss": 0.702,
"step": 1060
},
{
"epoch": 0.7708354955889984,
"grad_norm": 0.310546875,
"learning_rate": 1.3138342997274883e-05,
"loss": 0.7141,
"step": 1061
},
{
"epoch": 0.7715620134924753,
"grad_norm": 0.330078125,
"learning_rate": 1.3058888290474935e-05,
"loss": 0.7474,
"step": 1062
},
{
"epoch": 0.7722885313959522,
"grad_norm": 0.328125,
"learning_rate": 1.2979638462864069e-05,
"loss": 0.7179,
"step": 1063
},
{
"epoch": 0.7730150492994292,
"grad_norm": 0.32421875,
"learning_rate": 1.2900593953969948e-05,
"loss": 0.7304,
"step": 1064
},
{
"epoch": 0.7737415672029061,
"grad_norm": 0.3203125,
"learning_rate": 1.2821755202181501e-05,
"loss": 0.732,
"step": 1065
},
{
"epoch": 0.774468085106383,
"grad_norm": 0.30859375,
"learning_rate": 1.2743122644746536e-05,
"loss": 0.7031,
"step": 1066
},
{
"epoch": 0.7751946030098599,
"grad_norm": 0.30078125,
"learning_rate": 1.2664696717769258e-05,
"loss": 0.7187,
"step": 1067
},
{
"epoch": 0.7759211209133368,
"grad_norm": 0.30859375,
"learning_rate": 1.25864778562079e-05,
"loss": 0.7155,
"step": 1068
},
{
"epoch": 0.7766476388168136,
"grad_norm": 0.318359375,
"learning_rate": 1.2508466493872273e-05,
"loss": 0.7083,
"step": 1069
},
{
"epoch": 0.7773741567202906,
"grad_norm": 0.3125,
"learning_rate": 1.2430663063421389e-05,
"loss": 0.7202,
"step": 1070
},
{
"epoch": 0.7781006746237675,
"grad_norm": 0.310546875,
"learning_rate": 1.2353067996361034e-05,
"loss": 0.7086,
"step": 1071
},
{
"epoch": 0.7788271925272444,
"grad_norm": 0.33203125,
"learning_rate": 1.2275681723041405e-05,
"loss": 0.7738,
"step": 1072
},
{
"epoch": 0.7795537104307213,
"grad_norm": 0.310546875,
"learning_rate": 1.2198504672654692e-05,
"loss": 0.7269,
"step": 1073
},
{
"epoch": 0.7802802283341982,
"grad_norm": 0.314453125,
"learning_rate": 1.212153727323273e-05,
"loss": 0.7157,
"step": 1074
},
{
"epoch": 0.7810067462376752,
"grad_norm": 0.30859375,
"learning_rate": 1.2044779951644585e-05,
"loss": 0.7055,
"step": 1075
},
{
"epoch": 0.7817332641411521,
"grad_norm": 0.314453125,
"learning_rate": 1.1968233133594242e-05,
"loss": 0.7276,
"step": 1076
},
{
"epoch": 0.782459782044629,
"grad_norm": 0.322265625,
"learning_rate": 1.1891897243618182e-05,
"loss": 0.7335,
"step": 1077
},
{
"epoch": 0.7831862999481058,
"grad_norm": 0.31640625,
"learning_rate": 1.1815772705083073e-05,
"loss": 0.7147,
"step": 1078
},
{
"epoch": 0.7839128178515827,
"grad_norm": 0.3671875,
"learning_rate": 1.17398599401834e-05,
"loss": 0.7505,
"step": 1079
},
{
"epoch": 0.7846393357550597,
"grad_norm": 0.328125,
"learning_rate": 1.1664159369939138e-05,
"loss": 0.7296,
"step": 1080
},
{
"epoch": 0.7853658536585366,
"grad_norm": 0.322265625,
"learning_rate": 1.1588671414193397e-05,
"loss": 0.7385,
"step": 1081
},
{
"epoch": 0.7860923715620135,
"grad_norm": 0.31640625,
"learning_rate": 1.1513396491610113e-05,
"loss": 0.7457,
"step": 1082
},
{
"epoch": 0.7868188894654904,
"grad_norm": 0.322265625,
"learning_rate": 1.1438335019671714e-05,
"loss": 0.7422,
"step": 1083
},
{
"epoch": 0.7875454073689673,
"grad_norm": 0.318359375,
"learning_rate": 1.1363487414676804e-05,
"loss": 0.7647,
"step": 1084
},
{
"epoch": 0.7882719252724442,
"grad_norm": 0.3359375,
"learning_rate": 1.1288854091737889e-05,
"loss": 0.7306,
"step": 1085
},
{
"epoch": 0.7889984431759212,
"grad_norm": 0.337890625,
"learning_rate": 1.1214435464779006e-05,
"loss": 0.7337,
"step": 1086
},
{
"epoch": 0.789724961079398,
"grad_norm": 0.326171875,
"learning_rate": 1.1140231946533486e-05,
"loss": 0.7171,
"step": 1087
},
{
"epoch": 0.7904514789828749,
"grad_norm": 0.3125,
"learning_rate": 1.1066243948541638e-05,
"loss": 0.7112,
"step": 1088
},
{
"epoch": 0.7911779968863518,
"grad_norm": 0.298828125,
"learning_rate": 1.0992471881148498e-05,
"loss": 0.7175,
"step": 1089
},
{
"epoch": 0.7919045147898287,
"grad_norm": 0.326171875,
"learning_rate": 1.0918916153501469e-05,
"loss": 0.7344,
"step": 1090
},
{
"epoch": 0.7926310326933057,
"grad_norm": 0.318359375,
"learning_rate": 1.0845577173548171e-05,
"loss": 0.7479,
"step": 1091
},
{
"epoch": 0.7933575505967826,
"grad_norm": 0.318359375,
"learning_rate": 1.0772455348034099e-05,
"loss": 0.7345,
"step": 1092
},
{
"epoch": 0.7940840685002595,
"grad_norm": 0.34765625,
"learning_rate": 1.0699551082500387e-05,
"loss": 0.7273,
"step": 1093
},
{
"epoch": 0.7948105864037364,
"grad_norm": 0.330078125,
"learning_rate": 1.0626864781281554e-05,
"loss": 0.7571,
"step": 1094
},
{
"epoch": 0.7955371043072132,
"grad_norm": 0.353515625,
"learning_rate": 1.0554396847503273e-05,
"loss": 0.7469,
"step": 1095
},
{
"epoch": 0.7962636222106902,
"grad_norm": 0.30859375,
"learning_rate": 1.0482147683080123e-05,
"loss": 0.72,
"step": 1096
},
{
"epoch": 0.7969901401141671,
"grad_norm": 0.326171875,
"learning_rate": 1.0410117688713367e-05,
"loss": 0.76,
"step": 1097
},
{
"epoch": 0.797716658017644,
"grad_norm": 0.314453125,
"learning_rate": 1.0338307263888747e-05,
"loss": 0.7353,
"step": 1098
},
{
"epoch": 0.7984431759211209,
"grad_norm": 0.30859375,
"learning_rate": 1.0266716806874227e-05,
"loss": 0.7124,
"step": 1099
},
{
"epoch": 0.7991696938245978,
"grad_norm": 0.341796875,
"learning_rate": 1.0195346714717813e-05,
"loss": 0.7431,
"step": 1100
},
{
"epoch": 0.7998962117280747,
"grad_norm": 0.326171875,
"learning_rate": 1.0124197383245343e-05,
"loss": 0.7158,
"step": 1101
},
{
"epoch": 0.8006227296315517,
"grad_norm": 0.314453125,
"learning_rate": 1.0053269207058296e-05,
"loss": 0.7346,
"step": 1102
},
{
"epoch": 0.8013492475350286,
"grad_norm": 0.318359375,
"learning_rate": 9.982562579531607e-06,
"loss": 0.7101,
"step": 1103
},
{
"epoch": 0.8020757654385055,
"grad_norm": 0.318359375,
"learning_rate": 9.912077892811471e-06,
"loss": 0.7365,
"step": 1104
},
{
"epoch": 0.8028022833419823,
"grad_norm": 0.314453125,
"learning_rate": 9.841815537813176e-06,
"loss": 0.7069,
"step": 1105
},
{
"epoch": 0.8035288012454592,
"grad_norm": 0.3125,
"learning_rate": 9.771775904218949e-06,
"loss": 0.7113,
"step": 1106
},
{
"epoch": 0.8042553191489362,
"grad_norm": 0.328125,
"learning_rate": 9.70195938047576e-06,
"loss": 0.708,
"step": 1107
},
{
"epoch": 0.8049818370524131,
"grad_norm": 0.318359375,
"learning_rate": 9.632366353793209e-06,
"loss": 0.7231,
"step": 1108
},
{
"epoch": 0.80570835495589,
"grad_norm": 0.3515625,
"learning_rate": 9.562997210141356e-06,
"loss": 0.7228,
"step": 1109
},
{
"epoch": 0.8064348728593669,
"grad_norm": 0.3359375,
"learning_rate": 9.49385233424856e-06,
"loss": 0.7477,
"step": 1110
},
{
"epoch": 0.8071613907628438,
"grad_norm": 0.314453125,
"learning_rate": 9.424932109599371e-06,
"loss": 0.7084,
"step": 1111
},
{
"epoch": 0.8078879086663207,
"grad_norm": 0.330078125,
"learning_rate": 9.356236918432453e-06,
"loss": 0.7565,
"step": 1112
},
{
"epoch": 0.8086144265697977,
"grad_norm": 0.314453125,
"learning_rate": 9.287767141738352e-06,
"loss": 0.7428,
"step": 1113
},
{
"epoch": 0.8093409444732745,
"grad_norm": 0.328125,
"learning_rate": 9.21952315925746e-06,
"loss": 0.7424,
"step": 1114
},
{
"epoch": 0.8100674623767514,
"grad_norm": 0.337890625,
"learning_rate": 9.151505349477902e-06,
"loss": 0.7159,
"step": 1115
},
{
"epoch": 0.8107939802802283,
"grad_norm": 0.291015625,
"learning_rate": 9.08371408963341e-06,
"loss": 0.7173,
"step": 1116
},
{
"epoch": 0.8115204981837052,
"grad_norm": 0.341796875,
"learning_rate": 9.016149755701258e-06,
"loss": 0.7062,
"step": 1117
},
{
"epoch": 0.8122470160871822,
"grad_norm": 0.3125,
"learning_rate": 8.948812722400158e-06,
"loss": 0.7098,
"step": 1118
},
{
"epoch": 0.8129735339906591,
"grad_norm": 0.314453125,
"learning_rate": 8.881703363188198e-06,
"loss": 0.7434,
"step": 1119
},
{
"epoch": 0.813700051894136,
"grad_norm": 0.328125,
"learning_rate": 8.814822050260757e-06,
"loss": 0.7392,
"step": 1120
},
{
"epoch": 0.8144265697976129,
"grad_norm": 0.34375,
"learning_rate": 8.748169154548446e-06,
"loss": 0.7506,
"step": 1121
},
{
"epoch": 0.8151530877010897,
"grad_norm": 0.3125,
"learning_rate": 8.681745045715046e-06,
"loss": 0.7231,
"step": 1122
},
{
"epoch": 0.8158796056045667,
"grad_norm": 0.3203125,
"learning_rate": 8.615550092155478e-06,
"loss": 0.7286,
"step": 1123
},
{
"epoch": 0.8166061235080436,
"grad_norm": 0.31640625,
"learning_rate": 8.549584660993726e-06,
"loss": 0.7368,
"step": 1124
},
{
"epoch": 0.8173326414115205,
"grad_norm": 0.314453125,
"learning_rate": 8.483849118080827e-06,
"loss": 0.7295,
"step": 1125
},
{
"epoch": 0.8180591593149974,
"grad_norm": 0.34765625,
"learning_rate": 8.418343827992842e-06,
"loss": 0.7641,
"step": 1126
},
{
"epoch": 0.8187856772184743,
"grad_norm": 0.3359375,
"learning_rate": 8.353069154028815e-06,
"loss": 0.7274,
"step": 1127
},
{
"epoch": 0.8195121951219512,
"grad_norm": 0.302734375,
"learning_rate": 8.28802545820877e-06,
"loss": 0.7295,
"step": 1128
},
{
"epoch": 0.8202387130254282,
"grad_norm": 0.306640625,
"learning_rate": 8.22321310127171e-06,
"loss": 0.7611,
"step": 1129
},
{
"epoch": 0.820965230928905,
"grad_norm": 0.3046875,
"learning_rate": 8.158632442673602e-06,
"loss": 0.7111,
"step": 1130
},
{
"epoch": 0.8216917488323819,
"grad_norm": 0.3125,
"learning_rate": 8.094283840585398e-06,
"loss": 0.7099,
"step": 1131
},
{
"epoch": 0.8224182667358588,
"grad_norm": 0.310546875,
"learning_rate": 8.03016765189103e-06,
"loss": 0.7327,
"step": 1132
},
{
"epoch": 0.8231447846393357,
"grad_norm": 0.3359375,
"learning_rate": 7.966284232185451e-06,
"loss": 0.7305,
"step": 1133
},
{
"epoch": 0.8238713025428127,
"grad_norm": 0.326171875,
"learning_rate": 7.902633935772647e-06,
"loss": 0.7349,
"step": 1134
},
{
"epoch": 0.8245978204462896,
"grad_norm": 0.322265625,
"learning_rate": 7.839217115663683e-06,
"loss": 0.739,
"step": 1135
},
{
"epoch": 0.8253243383497665,
"grad_norm": 0.306640625,
"learning_rate": 7.776034123574737e-06,
"loss": 0.7441,
"step": 1136
},
{
"epoch": 0.8260508562532434,
"grad_norm": 0.369140625,
"learning_rate": 7.713085309925156e-06,
"loss": 0.7881,
"step": 1137
},
{
"epoch": 0.8267773741567203,
"grad_norm": 0.353515625,
"learning_rate": 7.650371023835495e-06,
"loss": 0.7609,
"step": 1138
},
{
"epoch": 0.8275038920601971,
"grad_norm": 0.298828125,
"learning_rate": 7.587891613125631e-06,
"loss": 0.7206,
"step": 1139
},
{
"epoch": 0.8282304099636741,
"grad_norm": 0.3125,
"learning_rate": 7.525647424312765e-06,
"loss": 0.7359,
"step": 1140
},
{
"epoch": 0.828956927867151,
"grad_norm": 0.314453125,
"learning_rate": 7.463638802609541e-06,
"loss": 0.7158,
"step": 1141
},
{
"epoch": 0.8296834457706279,
"grad_norm": 0.31640625,
"learning_rate": 7.401866091922133e-06,
"loss": 0.7325,
"step": 1142
},
{
"epoch": 0.8304099636741048,
"grad_norm": 0.287109375,
"learning_rate": 7.340329634848309e-06,
"loss": 0.7173,
"step": 1143
},
{
"epoch": 0.8311364815775817,
"grad_norm": 0.322265625,
"learning_rate": 7.2790297726755716e-06,
"loss": 0.7622,
"step": 1144
},
{
"epoch": 0.8318629994810587,
"grad_norm": 0.287109375,
"learning_rate": 7.217966845379243e-06,
"loss": 0.6867,
"step": 1145
},
{
"epoch": 0.8325895173845356,
"grad_norm": 0.318359375,
"learning_rate": 7.157141191620548e-06,
"loss": 0.7192,
"step": 1146
},
{
"epoch": 0.8333160352880125,
"grad_norm": 0.306640625,
"learning_rate": 7.096553148744805e-06,
"loss": 0.7363,
"step": 1147
},
{
"epoch": 0.8340425531914893,
"grad_norm": 0.31640625,
"learning_rate": 7.036203052779505e-06,
"loss": 0.718,
"step": 1148
},
{
"epoch": 0.8347690710949662,
"grad_norm": 0.3046875,
"learning_rate": 6.976091238432469e-06,
"loss": 0.7662,
"step": 1149
},
{
"epoch": 0.8354955889984432,
"grad_norm": 0.314453125,
"learning_rate": 6.9162180390899615e-06,
"loss": 0.7426,
"step": 1150
},
{
"epoch": 0.8362221069019201,
"grad_norm": 0.322265625,
"learning_rate": 6.8565837868148906e-06,
"loss": 0.723,
"step": 1151
},
{
"epoch": 0.836948624805397,
"grad_norm": 0.31640625,
"learning_rate": 6.797188812344907e-06,
"loss": 0.7523,
"step": 1152
},
{
"epoch": 0.8376751427088739,
"grad_norm": 0.326171875,
"learning_rate": 6.738033445090653e-06,
"loss": 0.7289,
"step": 1153
},
{
"epoch": 0.8384016606123508,
"grad_norm": 0.3203125,
"learning_rate": 6.679118013133839e-06,
"loss": 0.7055,
"step": 1154
},
{
"epoch": 0.8391281785158277,
"grad_norm": 0.32421875,
"learning_rate": 6.6204428432254826e-06,
"loss": 0.7354,
"step": 1155
},
{
"epoch": 0.8398546964193047,
"grad_norm": 0.30078125,
"learning_rate": 6.5620082607840915e-06,
"loss": 0.7124,
"step": 1156
},
{
"epoch": 0.8405812143227815,
"grad_norm": 0.32421875,
"learning_rate": 6.503814589893836e-06,
"loss": 0.7586,
"step": 1157
},
{
"epoch": 0.8413077322262584,
"grad_norm": 0.3125,
"learning_rate": 6.4458621533027844e-06,
"loss": 0.7337,
"step": 1158
},
{
"epoch": 0.8420342501297353,
"grad_norm": 0.318359375,
"learning_rate": 6.388151272421078e-06,
"loss": 0.7187,
"step": 1159
},
{
"epoch": 0.8427607680332122,
"grad_norm": 0.3203125,
"learning_rate": 6.330682267319177e-06,
"loss": 0.7311,
"step": 1160
},
{
"epoch": 0.8434872859366892,
"grad_norm": 0.32421875,
"learning_rate": 6.273455456726074e-06,
"loss": 0.7352,
"step": 1161
},
{
"epoch": 0.8442138038401661,
"grad_norm": 0.328125,
"learning_rate": 6.2164711580275145e-06,
"loss": 0.7512,
"step": 1162
},
{
"epoch": 0.844940321743643,
"grad_norm": 0.3046875,
"learning_rate": 6.159729687264254e-06,
"loss": 0.7228,
"step": 1163
},
{
"epoch": 0.8456668396471199,
"grad_norm": 0.328125,
"learning_rate": 6.103231359130307e-06,
"loss": 0.7394,
"step": 1164
},
{
"epoch": 0.8463933575505967,
"grad_norm": 0.330078125,
"learning_rate": 6.046976486971201e-06,
"loss": 0.7335,
"step": 1165
},
{
"epoch": 0.8471198754540736,
"grad_norm": 0.302734375,
"learning_rate": 5.990965382782176e-06,
"loss": 0.7536,
"step": 1166
},
{
"epoch": 0.8478463933575506,
"grad_norm": 0.318359375,
"learning_rate": 5.935198357206595e-06,
"loss": 0.7273,
"step": 1167
},
{
"epoch": 0.8485729112610275,
"grad_norm": 0.33984375,
"learning_rate": 5.879675719534078e-06,
"loss": 0.7012,
"step": 1168
},
{
"epoch": 0.8492994291645044,
"grad_norm": 0.328125,
"learning_rate": 5.824397777698859e-06,
"loss": 0.7415,
"step": 1169
},
{
"epoch": 0.8500259470679813,
"grad_norm": 0.314453125,
"learning_rate": 5.769364838278063e-06,
"loss": 0.7249,
"step": 1170
},
{
"epoch": 0.8507524649714582,
"grad_norm": 0.341796875,
"learning_rate": 5.714577206490018e-06,
"loss": 0.7123,
"step": 1171
},
{
"epoch": 0.8514789828749352,
"grad_norm": 0.306640625,
"learning_rate": 5.66003518619253e-06,
"loss": 0.7115,
"step": 1172
},
{
"epoch": 0.8522055007784121,
"grad_norm": 0.33203125,
"learning_rate": 5.605739079881239e-06,
"loss": 0.7143,
"step": 1173
},
{
"epoch": 0.852932018681889,
"grad_norm": 0.3203125,
"learning_rate": 5.551689188687908e-06,
"loss": 0.6933,
"step": 1174
},
{
"epoch": 0.8536585365853658,
"grad_norm": 0.314453125,
"learning_rate": 5.497885812378772e-06,
"loss": 0.6963,
"step": 1175
},
{
"epoch": 0.8543850544888427,
"grad_norm": 0.30078125,
"learning_rate": 5.444329249352859e-06,
"loss": 0.7281,
"step": 1176
},
{
"epoch": 0.8551115723923197,
"grad_norm": 0.3203125,
"learning_rate": 5.391019796640362e-06,
"loss": 0.7338,
"step": 1177
},
{
"epoch": 0.8558380902957966,
"grad_norm": 0.31640625,
"learning_rate": 5.337957749900957e-06,
"loss": 0.7431,
"step": 1178
},
{
"epoch": 0.8565646081992735,
"grad_norm": 0.3125,
"learning_rate": 5.285143403422188e-06,
"loss": 0.7051,
"step": 1179
},
{
"epoch": 0.8572911261027504,
"grad_norm": 0.32421875,
"learning_rate": 5.23257705011786e-06,
"loss": 0.7369,
"step": 1180
},
{
"epoch": 0.8580176440062273,
"grad_norm": 0.322265625,
"learning_rate": 5.180258981526309e-06,
"loss": 0.7213,
"step": 1181
},
{
"epoch": 0.8587441619097042,
"grad_norm": 0.333984375,
"learning_rate": 5.128189487808927e-06,
"loss": 0.7534,
"step": 1182
},
{
"epoch": 0.8594706798131811,
"grad_norm": 0.3359375,
"learning_rate": 5.076368857748454e-06,
"loss": 0.7312,
"step": 1183
},
{
"epoch": 0.860197197716658,
"grad_norm": 0.32421875,
"learning_rate": 5.024797378747414e-06,
"loss": 0.7195,
"step": 1184
},
{
"epoch": 0.8609237156201349,
"grad_norm": 0.3203125,
"learning_rate": 4.973475336826505e-06,
"loss": 0.7191,
"step": 1185
},
{
"epoch": 0.8616502335236118,
"grad_norm": 0.3046875,
"learning_rate": 4.922403016623034e-06,
"loss": 0.7147,
"step": 1186
},
{
"epoch": 0.8623767514270887,
"grad_norm": 0.302734375,
"learning_rate": 4.871580701389317e-06,
"loss": 0.7074,
"step": 1187
},
{
"epoch": 0.8631032693305657,
"grad_norm": 0.318359375,
"learning_rate": 4.821008672991118e-06,
"loss": 0.7417,
"step": 1188
},
{
"epoch": 0.8638297872340426,
"grad_norm": 0.30859375,
"learning_rate": 4.770687211906088e-06,
"loss": 0.6977,
"step": 1189
},
{
"epoch": 0.8645563051375195,
"grad_norm": 0.3046875,
"learning_rate": 4.720616597222205e-06,
"loss": 0.7337,
"step": 1190
},
{
"epoch": 0.8652828230409964,
"grad_norm": 0.3125,
"learning_rate": 4.670797106636232e-06,
"loss": 0.7066,
"step": 1191
},
{
"epoch": 0.8660093409444732,
"grad_norm": 0.330078125,
"learning_rate": 4.621229016452156e-06,
"loss": 0.7162,
"step": 1192
},
{
"epoch": 0.8667358588479502,
"grad_norm": 0.31640625,
"learning_rate": 4.571912601579675e-06,
"loss": 0.736,
"step": 1193
},
{
"epoch": 0.8674623767514271,
"grad_norm": 0.326171875,
"learning_rate": 4.522848135532698e-06,
"loss": 0.748,
"step": 1194
},
{
"epoch": 0.868188894654904,
"grad_norm": 0.3203125,
"learning_rate": 4.474035890427769e-06,
"loss": 0.7347,
"step": 1195
},
{
"epoch": 0.8689154125583809,
"grad_norm": 0.31640625,
"learning_rate": 4.425476136982598e-06,
"loss": 0.7129,
"step": 1196
},
{
"epoch": 0.8696419304618578,
"grad_norm": 0.322265625,
"learning_rate": 4.377169144514553e-06,
"loss": 0.742,
"step": 1197
},
{
"epoch": 0.8703684483653347,
"grad_norm": 0.34375,
"learning_rate": 4.329115180939164e-06,
"loss": 0.769,
"step": 1198
},
{
"epoch": 0.8710949662688117,
"grad_norm": 0.36328125,
"learning_rate": 4.281314512768625e-06,
"loss": 0.7293,
"step": 1199
},
{
"epoch": 0.8718214841722886,
"grad_norm": 0.30859375,
"learning_rate": 4.23376740511035e-06,
"loss": 0.7219,
"step": 1200
},
{
"epoch": 0.8725480020757654,
"grad_norm": 0.3125,
"learning_rate": 4.186474121665468e-06,
"loss": 0.7038,
"step": 1201
},
{
"epoch": 0.8732745199792423,
"grad_norm": 0.32421875,
"learning_rate": 4.139434924727359e-06,
"loss": 0.7391,
"step": 1202
},
{
"epoch": 0.8740010378827192,
"grad_norm": 0.326171875,
"learning_rate": 4.092650075180232e-06,
"loss": 0.7653,
"step": 1203
},
{
"epoch": 0.8747275557861962,
"grad_norm": 0.314453125,
"learning_rate": 4.046119832497658e-06,
"loss": 0.7443,
"step": 1204
},
{
"epoch": 0.8754540736896731,
"grad_norm": 0.318359375,
"learning_rate": 3.999844454741125e-06,
"loss": 0.7172,
"step": 1205
},
{
"epoch": 0.87618059159315,
"grad_norm": 0.298828125,
"learning_rate": 3.953824198558614e-06,
"loss": 0.7103,
"step": 1206
},
{
"epoch": 0.8769071094966269,
"grad_norm": 0.306640625,
"learning_rate": 3.908059319183194e-06,
"loss": 0.7129,
"step": 1207
},
{
"epoch": 0.8776336274001038,
"grad_norm": 0.318359375,
"learning_rate": 3.8625500704315646e-06,
"loss": 0.7102,
"step": 1208
},
{
"epoch": 0.8783601453035806,
"grad_norm": 0.33203125,
"learning_rate": 3.817296704702683e-06,
"loss": 0.7458,
"step": 1209
},
{
"epoch": 0.8790866632070576,
"grad_norm": 0.328125,
"learning_rate": 3.7722994729763428e-06,
"loss": 0.7241,
"step": 1210
},
{
"epoch": 0.8798131811105345,
"grad_norm": 0.3125,
"learning_rate": 3.727558624811811e-06,
"loss": 0.7503,
"step": 1211
},
{
"epoch": 0.8805396990140114,
"grad_norm": 0.35546875,
"learning_rate": 3.683074408346404e-06,
"loss": 0.7368,
"step": 1212
},
{
"epoch": 0.8812662169174883,
"grad_norm": 0.30078125,
"learning_rate": 3.6388470702941437e-06,
"loss": 0.7214,
"step": 1213
},
{
"epoch": 0.8819927348209652,
"grad_norm": 0.306640625,
"learning_rate": 3.5948768559443847e-06,
"loss": 0.7252,
"step": 1214
},
{
"epoch": 0.8827192527244422,
"grad_norm": 0.310546875,
"learning_rate": 3.551164009160429e-06,
"loss": 0.7155,
"step": 1215
},
{
"epoch": 0.8834457706279191,
"grad_norm": 0.337890625,
"learning_rate": 3.50770877237821e-06,
"loss": 0.7592,
"step": 1216
},
{
"epoch": 0.884172288531396,
"grad_norm": 0.310546875,
"learning_rate": 3.4645113866049184e-06,
"loss": 0.7336,
"step": 1217
},
{
"epoch": 0.8848988064348728,
"grad_norm": 0.28515625,
"learning_rate": 3.4215720914176796e-06,
"loss": 0.7073,
"step": 1218
},
{
"epoch": 0.8856253243383497,
"grad_norm": 0.328125,
"learning_rate": 3.378891124962219e-06,
"loss": 0.7317,
"step": 1219
},
{
"epoch": 0.8863518422418267,
"grad_norm": 0.314453125,
"learning_rate": 3.336468723951558e-06,
"loss": 0.7349,
"step": 1220
},
{
"epoch": 0.8870783601453036,
"grad_norm": 0.318359375,
"learning_rate": 3.294305123664665e-06,
"loss": 0.7114,
"step": 1221
},
{
"epoch": 0.8878048780487805,
"grad_norm": 0.31640625,
"learning_rate": 3.252400557945201e-06,
"loss": 0.7419,
"step": 1222
},
{
"epoch": 0.8885313959522574,
"grad_norm": 0.349609375,
"learning_rate": 3.2107552592001656e-06,
"loss": 0.738,
"step": 1223
},
{
"epoch": 0.8892579138557343,
"grad_norm": 0.302734375,
"learning_rate": 3.1693694583986523e-06,
"loss": 0.7161,
"step": 1224
},
{
"epoch": 0.8899844317592112,
"grad_norm": 0.3125,
"learning_rate": 3.1282433850705618e-06,
"loss": 0.7226,
"step": 1225
},
{
"epoch": 0.8907109496626882,
"grad_norm": 0.330078125,
"learning_rate": 3.087377267305297e-06,
"loss": 0.7437,
"step": 1226
},
{
"epoch": 0.891437467566165,
"grad_norm": 0.322265625,
"learning_rate": 3.0467713317505365e-06,
"loss": 0.7642,
"step": 1227
},
{
"epoch": 0.8921639854696419,
"grad_norm": 0.337890625,
"learning_rate": 3.0064258036109626e-06,
"loss": 0.7748,
"step": 1228
},
{
"epoch": 0.8928905033731188,
"grad_norm": 0.30859375,
"learning_rate": 2.9663409066470025e-06,
"loss": 0.7118,
"step": 1229
},
{
"epoch": 0.8936170212765957,
"grad_norm": 0.328125,
"learning_rate": 2.926516863173601e-06,
"loss": 0.7333,
"step": 1230
},
{
"epoch": 0.8943435391800727,
"grad_norm": 0.30078125,
"learning_rate": 2.88695389405898e-06,
"loss": 0.7431,
"step": 1231
},
{
"epoch": 0.8950700570835496,
"grad_norm": 0.32421875,
"learning_rate": 2.8476522187234178e-06,
"loss": 0.7063,
"step": 1232
},
{
"epoch": 0.8957965749870265,
"grad_norm": 0.314453125,
"learning_rate": 2.808612055138038e-06,
"loss": 0.7379,
"step": 1233
},
{
"epoch": 0.8965230928905034,
"grad_norm": 0.318359375,
"learning_rate": 2.7698336198235695e-06,
"loss": 0.7009,
"step": 1234
},
{
"epoch": 0.8972496107939802,
"grad_norm": 0.337890625,
"learning_rate": 2.731317127849209e-06,
"loss": 0.7308,
"step": 1235
},
{
"epoch": 0.8979761286974571,
"grad_norm": 0.3203125,
"learning_rate": 2.693062792831358e-06,
"loss": 0.7386,
"step": 1236
},
{
"epoch": 0.8987026466009341,
"grad_norm": 0.33984375,
"learning_rate": 2.655070826932471e-06,
"loss": 0.7407,
"step": 1237
},
{
"epoch": 0.899429164504411,
"grad_norm": 0.333984375,
"learning_rate": 2.6173414408598827e-06,
"loss": 0.7362,
"step": 1238
},
{
"epoch": 0.9001556824078879,
"grad_norm": 0.314453125,
"learning_rate": 2.5798748438646326e-06,
"loss": 0.701,
"step": 1239
},
{
"epoch": 0.9008822003113648,
"grad_norm": 0.296875,
"learning_rate": 2.5426712437403134e-06,
"loss": 0.7462,
"step": 1240
},
{
"epoch": 0.9016087182148417,
"grad_norm": 0.3359375,
"learning_rate": 2.5057308468218908e-06,
"loss": 0.7483,
"step": 1241
},
{
"epoch": 0.9023352361183187,
"grad_norm": 0.3046875,
"learning_rate": 2.4690538579845932e-06,
"loss": 0.7249,
"step": 1242
},
{
"epoch": 0.9030617540217956,
"grad_norm": 0.330078125,
"learning_rate": 2.4326404806427562e-06,
"loss": 0.7434,
"step": 1243
},
{
"epoch": 0.9037882719252724,
"grad_norm": 0.296875,
"learning_rate": 2.396490916748706e-06,
"loss": 0.7132,
"step": 1244
},
{
"epoch": 0.9045147898287493,
"grad_norm": 0.29296875,
"learning_rate": 2.360605366791624e-06,
"loss": 0.7222,
"step": 1245
},
{
"epoch": 0.9052413077322262,
"grad_norm": 0.330078125,
"learning_rate": 2.32498402979644e-06,
"loss": 0.7344,
"step": 1246
},
{
"epoch": 0.9059678256357032,
"grad_norm": 0.310546875,
"learning_rate": 2.289627103322739e-06,
"loss": 0.7085,
"step": 1247
},
{
"epoch": 0.9066943435391801,
"grad_norm": 0.3203125,
"learning_rate": 2.254534783463663e-06,
"loss": 0.7336,
"step": 1248
},
{
"epoch": 0.907420861442657,
"grad_norm": 0.30859375,
"learning_rate": 2.219707264844806e-06,
"loss": 0.7013,
"step": 1249
},
{
"epoch": 0.9081473793461339,
"grad_norm": 0.326171875,
"learning_rate": 2.185144740623157e-06,
"loss": 0.7105,
"step": 1250
},
{
"epoch": 0.9088738972496108,
"grad_norm": 0.322265625,
"learning_rate": 2.150847402486017e-06,
"loss": 0.759,
"step": 1251
},
{
"epoch": 0.9096004151530876,
"grad_norm": 0.318359375,
"learning_rate": 2.1168154406499274e-06,
"loss": 0.7083,
"step": 1252
},
{
"epoch": 0.9103269330565646,
"grad_norm": 0.34765625,
"learning_rate": 2.083049043859642e-06,
"loss": 0.7646,
"step": 1253
},
{
"epoch": 0.9110534509600415,
"grad_norm": 0.302734375,
"learning_rate": 2.049548399387058e-06,
"loss": 0.7262,
"step": 1254
},
{
"epoch": 0.9117799688635184,
"grad_norm": 0.298828125,
"learning_rate": 2.0163136930301697e-06,
"loss": 0.6995,
"step": 1255
},
{
"epoch": 0.9125064867669953,
"grad_norm": 0.328125,
"learning_rate": 1.9833451091120724e-06,
"loss": 0.7373,
"step": 1256
},
{
"epoch": 0.9132330046704722,
"grad_norm": 0.310546875,
"learning_rate": 1.9506428304799095e-06,
"loss": 0.702,
"step": 1257
},
{
"epoch": 0.9139595225739492,
"grad_norm": 0.328125,
"learning_rate": 1.9182070385038555e-06,
"loss": 0.7358,
"step": 1258
},
{
"epoch": 0.9146860404774261,
"grad_norm": 0.34375,
"learning_rate": 1.886037913076144e-06,
"loss": 0.7701,
"step": 1259
},
{
"epoch": 0.915412558380903,
"grad_norm": 0.314453125,
"learning_rate": 1.8541356326100433e-06,
"loss": 0.7053,
"step": 1260
},
{
"epoch": 0.9161390762843798,
"grad_norm": 0.314453125,
"learning_rate": 1.8225003740388547e-06,
"loss": 0.7492,
"step": 1261
},
{
"epoch": 0.9168655941878567,
"grad_norm": 0.345703125,
"learning_rate": 1.7911323128149749e-06,
"loss": 0.7624,
"step": 1262
},
{
"epoch": 0.9175921120913337,
"grad_norm": 0.32421875,
"learning_rate": 1.760031622908881e-06,
"loss": 0.7519,
"step": 1263
},
{
"epoch": 0.9183186299948106,
"grad_norm": 0.314453125,
"learning_rate": 1.729198476808186e-06,
"loss": 0.7196,
"step": 1264
},
{
"epoch": 0.9190451478982875,
"grad_norm": 0.3359375,
"learning_rate": 1.6986330455166732e-06,
"loss": 0.7353,
"step": 1265
},
{
"epoch": 0.9197716658017644,
"grad_norm": 0.3203125,
"learning_rate": 1.6683354985533584e-06,
"loss": 0.7271,
"step": 1266
},
{
"epoch": 0.9204981837052413,
"grad_norm": 0.3125,
"learning_rate": 1.638306003951534e-06,
"loss": 0.6993,
"step": 1267
},
{
"epoch": 0.9212247016087182,
"grad_norm": 0.29296875,
"learning_rate": 1.6085447282578548e-06,
"loss": 0.7007,
"step": 1268
},
{
"epoch": 0.9219512195121952,
"grad_norm": 0.33203125,
"learning_rate": 1.5790518365314088e-06,
"loss": 0.7163,
"step": 1269
},
{
"epoch": 0.922677737415672,
"grad_norm": 0.3359375,
"learning_rate": 1.5498274923427925e-06,
"loss": 0.7084,
"step": 1270
},
{
"epoch": 0.9234042553191489,
"grad_norm": 0.3046875,
"learning_rate": 1.5208718577732096e-06,
"loss": 0.7247,
"step": 1271
},
{
"epoch": 0.9241307732226258,
"grad_norm": 0.314453125,
"learning_rate": 1.4921850934135784e-06,
"loss": 0.7322,
"step": 1272
},
{
"epoch": 0.9248572911261027,
"grad_norm": 0.328125,
"learning_rate": 1.4637673583636268e-06,
"loss": 0.7462,
"step": 1273
},
{
"epoch": 0.9255838090295797,
"grad_norm": 0.32421875,
"learning_rate": 1.4356188102310264e-06,
"loss": 0.7323,
"step": 1274
},
{
"epoch": 0.9263103269330566,
"grad_norm": 0.314453125,
"learning_rate": 1.4077396051305092e-06,
"loss": 0.7263,
"step": 1275
},
{
"epoch": 0.9270368448365335,
"grad_norm": 0.298828125,
"learning_rate": 1.3801298976830023e-06,
"loss": 0.7346,
"step": 1276
},
{
"epoch": 0.9277633627400104,
"grad_norm": 0.333984375,
"learning_rate": 1.3527898410147677e-06,
"loss": 0.7468,
"step": 1277
},
{
"epoch": 0.9284898806434873,
"grad_norm": 0.345703125,
"learning_rate": 1.325719586756563e-06,
"loss": 0.7428,
"step": 1278
},
{
"epoch": 0.9292163985469641,
"grad_norm": 0.294921875,
"learning_rate": 1.2989192850427933e-06,
"loss": 0.6796,
"step": 1279
},
{
"epoch": 0.9299429164504411,
"grad_norm": 0.322265625,
"learning_rate": 1.2723890845106722e-06,
"loss": 0.7259,
"step": 1280
},
{
"epoch": 0.930669434353918,
"grad_norm": 0.302734375,
"learning_rate": 1.2461291322994118e-06,
"loss": 0.7379,
"step": 1281
},
{
"epoch": 0.9313959522573949,
"grad_norm": 0.306640625,
"learning_rate": 1.2201395740493949e-06,
"loss": 0.7384,
"step": 1282
},
{
"epoch": 0.9321224701608718,
"grad_norm": 0.310546875,
"learning_rate": 1.1944205539013708e-06,
"loss": 0.7513,
"step": 1283
},
{
"epoch": 0.9328489880643487,
"grad_norm": 0.32421875,
"learning_rate": 1.1689722144956671e-06,
"loss": 0.7001,
"step": 1284
},
{
"epoch": 0.9335755059678257,
"grad_norm": 0.30078125,
"learning_rate": 1.1437946969713731e-06,
"loss": 0.7136,
"step": 1285
},
{
"epoch": 0.9343020238713026,
"grad_norm": 0.34375,
"learning_rate": 1.118888140965585e-06,
"loss": 0.7576,
"step": 1286
},
{
"epoch": 0.9350285417747795,
"grad_norm": 0.322265625,
"learning_rate": 1.0942526846126123e-06,
"loss": 0.7427,
"step": 1287
},
{
"epoch": 0.9357550596782563,
"grad_norm": 0.3125,
"learning_rate": 1.0698884645432118e-06,
"loss": 0.7344,
"step": 1288
},
{
"epoch": 0.9364815775817332,
"grad_norm": 0.322265625,
"learning_rate": 1.0457956158838544e-06,
"loss": 0.7208,
"step": 1289
},
{
"epoch": 0.9372080954852102,
"grad_norm": 0.291015625,
"learning_rate": 1.0219742722559433e-06,
"loss": 0.7013,
"step": 1290
},
{
"epoch": 0.9379346133886871,
"grad_norm": 0.30078125,
"learning_rate": 9.984245657750857e-07,
"loss": 0.7336,
"step": 1291
},
{
"epoch": 0.938661131292164,
"grad_norm": 0.314453125,
"learning_rate": 9.751466270503718e-07,
"loss": 0.7332,
"step": 1292
},
{
"epoch": 0.9393876491956409,
"grad_norm": 0.3046875,
"learning_rate": 9.521405851836251e-07,
"loss": 0.728,
"step": 1293
},
{
"epoch": 0.9401141670991178,
"grad_norm": 0.30859375,
"learning_rate": 9.294065677687202e-07,
"loss": 0.7302,
"step": 1294
},
{
"epoch": 0.9408406850025947,
"grad_norm": 0.298828125,
"learning_rate": 9.069447008908383e-07,
"loss": 0.7102,
"step": 1295
},
{
"epoch": 0.9415672029060717,
"grad_norm": 0.287109375,
"learning_rate": 8.847551091257955e-07,
"loss": 0.6986,
"step": 1296
},
{
"epoch": 0.9422937208095485,
"grad_norm": 0.328125,
"learning_rate": 8.62837915539344e-07,
"loss": 0.757,
"step": 1297
},
{
"epoch": 0.9430202387130254,
"grad_norm": 0.3125,
"learning_rate": 8.411932416864832e-07,
"loss": 0.7289,
"step": 1298
},
{
"epoch": 0.9437467566165023,
"grad_norm": 0.322265625,
"learning_rate": 8.198212076107881e-07,
"loss": 0.73,
"step": 1299
},
{
"epoch": 0.9444732745199792,
"grad_norm": 0.34375,
"learning_rate": 7.987219318437489e-07,
"loss": 0.753,
"step": 1300
},
{
"epoch": 0.9451997924234562,
"grad_norm": 0.306640625,
"learning_rate": 7.778955314041103e-07,
"loss": 0.7292,
"step": 1301
},
{
"epoch": 0.9459263103269331,
"grad_norm": 0.31640625,
"learning_rate": 7.573421217972221e-07,
"loss": 0.7396,
"step": 1302
},
{
"epoch": 0.94665282823041,
"grad_norm": 0.369140625,
"learning_rate": 7.370618170144061e-07,
"loss": 0.7631,
"step": 1303
},
{
"epoch": 0.9473793461338869,
"grad_norm": 0.2890625,
"learning_rate": 7.170547295323015e-07,
"loss": 0.6927,
"step": 1304
},
{
"epoch": 0.9481058640373637,
"grad_norm": 0.3125,
"learning_rate": 6.973209703122652e-07,
"loss": 0.7091,
"step": 1305
},
{
"epoch": 0.9488323819408406,
"grad_norm": 0.33203125,
"learning_rate": 6.778606487997496e-07,
"loss": 0.7336,
"step": 1306
},
{
"epoch": 0.9495588998443176,
"grad_norm": 0.298828125,
"learning_rate": 6.58673872923693e-07,
"loss": 0.7262,
"step": 1307
},
{
"epoch": 0.9502854177477945,
"grad_norm": 0.34375,
"learning_rate": 6.397607490959135e-07,
"loss": 0.7284,
"step": 1308
},
{
"epoch": 0.9510119356512714,
"grad_norm": 0.322265625,
"learning_rate": 6.211213822105377e-07,
"loss": 0.7243,
"step": 1309
},
{
"epoch": 0.9517384535547483,
"grad_norm": 0.326171875,
"learning_rate": 6.027558756434016e-07,
"loss": 0.7221,
"step": 1310
},
{
"epoch": 0.9524649714582252,
"grad_norm": 0.322265625,
"learning_rate": 5.846643312514888e-07,
"loss": 0.7146,
"step": 1311
},
{
"epoch": 0.9531914893617022,
"grad_norm": 0.33203125,
"learning_rate": 5.668468493723489e-07,
"loss": 0.7441,
"step": 1312
},
{
"epoch": 0.9539180072651791,
"grad_norm": 0.310546875,
"learning_rate": 5.493035288235749e-07,
"loss": 0.7402,
"step": 1313
},
{
"epoch": 0.9546445251686559,
"grad_norm": 0.345703125,
"learning_rate": 5.320344669022037e-07,
"loss": 0.738,
"step": 1314
},
{
"epoch": 0.9553710430721328,
"grad_norm": 0.349609375,
"learning_rate": 5.150397593842282e-07,
"loss": 0.731,
"step": 1315
},
{
"epoch": 0.9560975609756097,
"grad_norm": 0.291015625,
"learning_rate": 4.983195005240416e-07,
"loss": 0.7473,
"step": 1316
},
{
"epoch": 0.9568240788790867,
"grad_norm": 0.32421875,
"learning_rate": 4.818737830539099e-07,
"loss": 0.7436,
"step": 1317
},
{
"epoch": 0.9575505967825636,
"grad_norm": 0.3359375,
"learning_rate": 4.6570269818346224e-07,
"loss": 0.742,
"step": 1318
},
{
"epoch": 0.9582771146860405,
"grad_norm": 0.330078125,
"learning_rate": 4.4980633559919547e-07,
"loss": 0.7646,
"step": 1319
},
{
"epoch": 0.9590036325895174,
"grad_norm": 0.318359375,
"learning_rate": 4.341847834639645e-07,
"loss": 0.7624,
"step": 1320
},
{
"epoch": 0.9597301504929943,
"grad_norm": 0.294921875,
"learning_rate": 4.188381284164933e-07,
"loss": 0.703,
"step": 1321
},
{
"epoch": 0.9604566683964711,
"grad_norm": 0.3125,
"learning_rate": 4.0376645557090865e-07,
"loss": 0.7107,
"step": 1322
},
{
"epoch": 0.9611831862999481,
"grad_norm": 0.322265625,
"learning_rate": 3.889698485162463e-07,
"loss": 0.744,
"step": 1323
},
{
"epoch": 0.961909704203425,
"grad_norm": 0.33984375,
"learning_rate": 3.7444838931600666e-07,
"loss": 0.7413,
"step": 1324
},
{
"epoch": 0.9626362221069019,
"grad_norm": 0.3125,
"learning_rate": 3.6020215850769424e-07,
"loss": 0.7332,
"step": 1325
},
{
"epoch": 0.9633627400103788,
"grad_norm": 0.31640625,
"learning_rate": 3.4623123510235666e-07,
"loss": 0.7735,
"step": 1326
},
{
"epoch": 0.9640892579138557,
"grad_norm": 0.296875,
"learning_rate": 3.325356965841686e-07,
"loss": 0.7114,
"step": 1327
},
{
"epoch": 0.9648157758173327,
"grad_norm": 0.337890625,
"learning_rate": 3.1911561890999307e-07,
"loss": 0.726,
"step": 1328
},
{
"epoch": 0.9655422937208096,
"grad_norm": 0.3125,
"learning_rate": 3.059710765089485e-07,
"loss": 0.6981,
"step": 1329
},
{
"epoch": 0.9662688116242865,
"grad_norm": 0.310546875,
"learning_rate": 2.9310214228202013e-07,
"loss": 0.7325,
"step": 1330
},
{
"epoch": 0.9669953295277633,
"grad_norm": 0.3046875,
"learning_rate": 2.8050888760163263e-07,
"loss": 0.7512,
"step": 1331
},
{
"epoch": 0.9677218474312402,
"grad_norm": 0.34765625,
"learning_rate": 2.6819138231126693e-07,
"loss": 0.7215,
"step": 1332
},
{
"epoch": 0.9684483653347172,
"grad_norm": 0.314453125,
"learning_rate": 2.561496947250663e-07,
"loss": 0.7459,
"step": 1333
},
{
"epoch": 0.9691748832381941,
"grad_norm": 0.318359375,
"learning_rate": 2.4438389162746433e-07,
"loss": 0.7182,
"step": 1334
},
{
"epoch": 0.969901401141671,
"grad_norm": 0.302734375,
"learning_rate": 2.3289403827281287e-07,
"loss": 0.7246,
"step": 1335
},
{
"epoch": 0.9706279190451479,
"grad_norm": 0.318359375,
"learning_rate": 2.2168019838501032e-07,
"loss": 0.7387,
"step": 1336
},
{
"epoch": 0.9713544369486248,
"grad_norm": 0.30078125,
"learning_rate": 2.107424341571629e-07,
"loss": 0.7811,
"step": 1337
},
{
"epoch": 0.9720809548521017,
"grad_norm": 0.345703125,
"learning_rate": 2.000808062512405e-07,
"loss": 0.757,
"step": 1338
},
{
"epoch": 0.9728074727555787,
"grad_norm": 0.31640625,
"learning_rate": 1.896953737977103e-07,
"loss": 0.7123,
"step": 1339
},
{
"epoch": 0.9735339906590555,
"grad_norm": 0.314453125,
"learning_rate": 1.7958619439524815e-07,
"loss": 0.7381,
"step": 1340
},
{
"epoch": 0.9742605085625324,
"grad_norm": 0.30859375,
"learning_rate": 1.6975332411040546e-07,
"loss": 0.7015,
"step": 1341
},
{
"epoch": 0.9749870264660093,
"grad_norm": 0.322265625,
"learning_rate": 1.601968174772761e-07,
"loss": 0.7174,
"step": 1342
},
{
"epoch": 0.9757135443694862,
"grad_norm": 0.3203125,
"learning_rate": 1.5091672749723562e-07,
"loss": 0.7337,
"step": 1343
},
{
"epoch": 0.9764400622729632,
"grad_norm": 0.3125,
"learning_rate": 1.4191310563860804e-07,
"loss": 0.749,
"step": 1344
},
{
"epoch": 0.9771665801764401,
"grad_norm": 0.30078125,
"learning_rate": 1.331860018363995e-07,
"loss": 0.717,
"step": 1345
},
{
"epoch": 0.977893098079917,
"grad_norm": 0.3359375,
"learning_rate": 1.2473546449203178e-07,
"loss": 0.75,
"step": 1346
},
{
"epoch": 0.9786196159833939,
"grad_norm": 0.318359375,
"learning_rate": 1.1656154047303691e-07,
"loss": 0.7331,
"step": 1347
},
{
"epoch": 0.9793461338868708,
"grad_norm": 0.322265625,
"learning_rate": 1.0866427511285194e-07,
"loss": 0.7277,
"step": 1348
},
{
"epoch": 0.9800726517903476,
"grad_norm": 0.326171875,
"learning_rate": 1.0104371221050235e-07,
"loss": 0.7082,
"step": 1349
},
{
"epoch": 0.9807991696938246,
"grad_norm": 0.306640625,
"learning_rate": 9.369989403041346e-08,
"loss": 0.7114,
"step": 1350
},
{
"epoch": 0.9815256875973015,
"grad_norm": 0.302734375,
"learning_rate": 8.663286130216608e-08,
"loss": 0.7011,
"step": 1351
},
{
"epoch": 0.9822522055007784,
"grad_norm": 0.287109375,
"learning_rate": 7.98426532202301e-08,
"loss": 0.732,
"step": 1352
},
{
"epoch": 0.9829787234042553,
"grad_norm": 0.3359375,
"learning_rate": 7.332930744380906e-08,
"loss": 0.7575,
"step": 1353
},
{
"epoch": 0.9837052413077322,
"grad_norm": 0.30078125,
"learning_rate": 6.709286009657368e-08,
"loss": 0.7442,
"step": 1354
},
{
"epoch": 0.9844317592112092,
"grad_norm": 0.30859375,
"learning_rate": 6.113334576651197e-08,
"loss": 0.7179,
"step": 1355
},
{
"epoch": 0.9851582771146861,
"grad_norm": 0.3203125,
"learning_rate": 5.54507975056906e-08,
"loss": 0.7088,
"step": 1356
},
{
"epoch": 0.985884795018163,
"grad_norm": 0.3203125,
"learning_rate": 5.004524683011047e-08,
"loss": 0.7393,
"step": 1357
},
{
"epoch": 0.9866113129216398,
"grad_norm": 0.32421875,
"learning_rate": 4.491672371950695e-08,
"loss": 0.7058,
"step": 1358
},
{
"epoch": 0.9873378308251167,
"grad_norm": 0.328125,
"learning_rate": 4.006525661719995e-08,
"loss": 0.7644,
"step": 1359
},
{
"epoch": 0.9880643487285937,
"grad_norm": 0.31640625,
"learning_rate": 3.549087242991078e-08,
"loss": 0.7453,
"step": 1360
},
{
"epoch": 0.9887908666320706,
"grad_norm": 0.326171875,
"learning_rate": 3.119359652765108e-08,
"loss": 0.7208,
"step": 1361
},
{
"epoch": 0.9895173845355475,
"grad_norm": 0.33984375,
"learning_rate": 2.7173452743550763e-08,
"loss": 0.7418,
"step": 1362
},
{
"epoch": 0.9902439024390244,
"grad_norm": 0.30859375,
"learning_rate": 2.343046337374144e-08,
"loss": 0.7377,
"step": 1363
},
{
"epoch": 0.9909704203425013,
"grad_norm": 0.318359375,
"learning_rate": 1.9964649177223183e-08,
"loss": 0.7427,
"step": 1364
},
{
"epoch": 0.9916969382459782,
"grad_norm": 0.33203125,
"learning_rate": 1.6776029375759062e-08,
"loss": 0.7377,
"step": 1365
},
{
"epoch": 0.9924234561494552,
"grad_norm": 0.333984375,
"learning_rate": 1.386462165375857e-08,
"loss": 0.7162,
"step": 1366
},
{
"epoch": 0.993149974052932,
"grad_norm": 0.302734375,
"learning_rate": 1.1230442158188803e-08,
"loss": 0.7022,
"step": 1367
},
{
"epoch": 0.9938764919564089,
"grad_norm": 0.349609375,
"learning_rate": 8.873505498474543e-09,
"loss": 0.7479,
"step": 1368
},
{
"epoch": 0.9946030098598858,
"grad_norm": 0.330078125,
"learning_rate": 6.793824746437194e-09,
"loss": 0.754,
"step": 1369
},
{
"epoch": 0.9953295277633627,
"grad_norm": 0.330078125,
"learning_rate": 4.991411436189308e-09,
"loss": 0.7238,
"step": 1370
},
{
"epoch": 0.9960560456668397,
"grad_norm": 0.32421875,
"learning_rate": 3.4662755641012845e-09,
"loss": 0.7215,
"step": 1371
},
{
"epoch": 0.9967825635703166,
"grad_norm": 0.306640625,
"learning_rate": 2.2184255887403025e-09,
"loss": 0.7249,
"step": 1372
},
{
"epoch": 0.9975090814737935,
"grad_norm": 0.318359375,
"learning_rate": 1.2478684308037114e-09,
"loss": 0.7044,
"step": 1373
},
{
"epoch": 0.9982355993772704,
"grad_norm": 0.31640625,
"learning_rate": 5.546094731023743e-10,
"loss": 0.7163,
"step": 1374
},
{
"epoch": 0.9989621172807472,
"grad_norm": 0.298828125,
"learning_rate": 1.3865256052181253e-10,
"loss": 0.72,
"step": 1375
},
{
"epoch": 0.9996886351842241,
"grad_norm": 0.30859375,
"learning_rate": 0.0,
"loss": 0.7134,
"step": 1376
},
{
"epoch": 0.9996886351842241,
"step": 1376,
"total_flos": 4.220978486489815e+23,
"train_loss": 0.7485993359844352,
"train_runtime": 44088.8096,
"train_samples_per_second": 31.467,
"train_steps_per_second": 0.031
}
],
"logging_steps": 1.0,
"max_steps": 1376,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 200,
"total_flos": 4.220978486489815e+23,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}