{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9978947368421053,
  "eval_steps": 60,
  "global_step": 237,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004210526315789474,
      "grad_norm": 0.310546875,
      "learning_rate": 2e-05,
      "loss": 1.5605,
      "step": 1
    },
    {
      "epoch": 0.004210526315789474,
      "eval_loss": 1.5264556407928467,
      "eval_runtime": 26.3082,
      "eval_samples_per_second": 3.801,
      "eval_steps_per_second": 1.901,
      "step": 1
    },
    {
      "epoch": 0.008421052631578947,
      "grad_norm": 0.306640625,
      "learning_rate": 4e-05,
      "loss": 1.4702,
      "step": 2
    },
    {
      "epoch": 0.01263157894736842,
      "grad_norm": 0.2578125,
      "learning_rate": 6e-05,
      "loss": 1.4576,
      "step": 3
    },
    {
      "epoch": 0.016842105263157894,
      "grad_norm": 0.65234375,
      "learning_rate": 8e-05,
      "loss": 1.5868,
      "step": 4
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 0.56640625,
      "learning_rate": 0.0001,
      "loss": 1.5916,
      "step": 5
    },
    {
      "epoch": 0.02526315789473684,
      "grad_norm": 0.5703125,
      "learning_rate": 0.00012,
      "loss": 1.7851,
      "step": 6
    },
    {
      "epoch": 0.029473684210526315,
      "grad_norm": 0.3359375,
      "learning_rate": 0.00014,
      "loss": 1.5319,
      "step": 7
    },
    {
      "epoch": 0.03368421052631579,
      "grad_norm": 0.39453125,
      "learning_rate": 0.00016,
      "loss": 1.8462,
      "step": 8
    },
    {
      "epoch": 0.037894736842105266,
      "grad_norm": 0.484375,
      "learning_rate": 0.00018,
      "loss": 1.4219,
      "step": 9
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 0.30859375,
      "learning_rate": 0.0002,
      "loss": 1.6555,
      "step": 10
    },
    {
      "epoch": 0.04631578947368421,
      "grad_norm": 0.267578125,
      "learning_rate": 0.0001999994391281196,
      "loss": 1.1527,
      "step": 11
    },
    {
      "epoch": 0.05052631578947368,
      "grad_norm": 0.298828125,
      "learning_rate": 0.00019999775651876987,
      "loss": 1.4265,
      "step": 12
    },
    {
      "epoch": 0.05473684210526316,
      "grad_norm": 0.376953125,
      "learning_rate": 0.00019999495219082545,
      "loss": 1.5505,
      "step": 13
    },
    {
      "epoch": 0.05894736842105263,
      "grad_norm": 0.380859375,
      "learning_rate": 0.00019999102617574365,
      "loss": 1.0313,
      "step": 14
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 0.494140625,
      "learning_rate": 0.0001999859785175643,
      "loss": 1.439,
      "step": 15
    },
    {
      "epoch": 0.06736842105263158,
      "grad_norm": 0.40234375,
      "learning_rate": 0.00019997980927290927,
      "loss": 1.3511,
      "step": 16
    },
    {
      "epoch": 0.07157894736842105,
      "grad_norm": 0.390625,
      "learning_rate": 0.0001999725185109816,
      "loss": 1.2886,
      "step": 17
    },
    {
      "epoch": 0.07578947368421053,
      "grad_norm": 0.388671875,
      "learning_rate": 0.00019996410631356498,
      "loss": 1.3057,
      "step": 18
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.6328125,
      "learning_rate": 0.00019995457277502271,
      "loss": 1.7375,
      "step": 19
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 0.51953125,
      "learning_rate": 0.00019994391800229666,
      "loss": 1.3436,
      "step": 20
    },
    {
      "epoch": 0.08842105263157894,
      "grad_norm": 0.345703125,
      "learning_rate": 0.00019993214211490608,
      "loss": 1.14,
      "step": 21
    },
    {
      "epoch": 0.09263157894736843,
      "grad_norm": 0.357421875,
      "learning_rate": 0.00019991924524494627,
      "loss": 1.1322,
      "step": 22
    },
    {
      "epoch": 0.0968421052631579,
      "grad_norm": 0.431640625,
      "learning_rate": 0.00019990522753708705,
      "loss": 1.4512,
      "step": 23
    },
    {
      "epoch": 0.10105263157894737,
      "grad_norm": 0.2490234375,
      "learning_rate": 0.00019989008914857116,
      "loss": 1.3419,
      "step": 24
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.78515625,
      "learning_rate": 0.00019987383024921255,
      "loss": 1.382,
      "step": 25
    },
    {
      "epoch": 0.10947368421052632,
      "grad_norm": 0.56640625,
      "learning_rate": 0.0001998564510213944,
      "loss": 1.582,
      "step": 26
    },
    {
      "epoch": 0.11368421052631579,
      "grad_norm": 0.5703125,
      "learning_rate": 0.00019983795166006715,
      "loss": 1.188,
      "step": 27
    },
    {
      "epoch": 0.11789473684210526,
      "grad_norm": 0.46875,
      "learning_rate": 0.00019981833237274618,
      "loss": 1.4246,
      "step": 28
    },
    {
      "epoch": 0.12210526315789473,
      "grad_norm": 0.3984375,
      "learning_rate": 0.00019979759337950968,
      "loss": 1.2828,
      "step": 29
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 0.55078125,
      "learning_rate": 0.00019977573491299598,
      "loss": 1.6199,
      "step": 30
    },
    {
      "epoch": 0.13052631578947368,
      "grad_norm": 0.8359375,
      "learning_rate": 0.00019975275721840103,
      "loss": 1.2398,
      "step": 31
    },
    {
      "epoch": 0.13473684210526315,
      "grad_norm": 0.5,
      "learning_rate": 0.00019972866055347572,
      "loss": 1.4295,
      "step": 32
    },
    {
      "epoch": 0.13894736842105262,
      "grad_norm": 0.5390625,
      "learning_rate": 0.0001997034451885229,
      "loss": 1.2814,
      "step": 33
    },
    {
      "epoch": 0.1431578947368421,
      "grad_norm": 0.28515625,
      "learning_rate": 0.0001996771114063943,
      "loss": 1.532,
      "step": 34
    },
    {
      "epoch": 0.14736842105263157,
      "grad_norm": 0.40625,
      "learning_rate": 0.00019964965950248757,
      "loss": 1.3516,
      "step": 35
    },
    {
      "epoch": 0.15157894736842106,
      "grad_norm": 0.44921875,
      "learning_rate": 0.00019962108978474263,
      "loss": 1.1487,
      "step": 36
    },
    {
      "epoch": 0.15578947368421053,
      "grad_norm": 0.310546875,
      "learning_rate": 0.0001995914025736386,
      "loss": 1.3543,
      "step": 37
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.306640625,
      "learning_rate": 0.00019956059820218982,
      "loss": 1.2986,
      "step": 38
    },
    {
      "epoch": 0.16421052631578947,
      "grad_norm": 0.625,
      "learning_rate": 0.00019952867701594247,
      "loss": 1.0167,
      "step": 39
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 0.306640625,
      "learning_rate": 0.00019949563937297045,
      "loss": 1.2287,
      "step": 40
    },
    {
      "epoch": 0.1726315789473684,
      "grad_norm": 0.34765625,
      "learning_rate": 0.00019946148564387145,
      "loss": 1.0063,
      "step": 41
    },
    {
      "epoch": 0.17684210526315788,
      "grad_norm": 0.94921875,
      "learning_rate": 0.00019942621621176282,
      "loss": 1.2712,
      "step": 42
    },
    {
      "epoch": 0.18105263157894738,
      "grad_norm": 0.333984375,
      "learning_rate": 0.00019938983147227716,
      "loss": 1.2106,
      "step": 43
    },
    {
      "epoch": 0.18526315789473685,
      "grad_norm": 0.6328125,
      "learning_rate": 0.0001993523318335581,
      "loss": 1.4887,
      "step": 44
    },
    {
      "epoch": 0.18947368421052632,
      "grad_norm": 0.62890625,
      "learning_rate": 0.00019931371771625544,
      "loss": 1.2747,
      "step": 45
    },
    {
      "epoch": 0.1936842105263158,
      "grad_norm": 0.2216796875,
      "learning_rate": 0.00019927398955352061,
      "loss": 1.1946,
      "step": 46
    },
    {
      "epoch": 0.19789473684210526,
      "grad_norm": 0.54296875,
      "learning_rate": 0.00019923314779100184,
      "loss": 1.2467,
      "step": 47
    },
    {
      "epoch": 0.20210526315789473,
      "grad_norm": 0.25390625,
      "learning_rate": 0.00019919119288683908,
      "loss": 1.5067,
      "step": 48
    },
    {
      "epoch": 0.2063157894736842,
      "grad_norm": 0.404296875,
      "learning_rate": 0.00019914812531165877,
      "loss": 1.4291,
      "step": 49
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00019910394554856876,
      "loss": 1.0136,
      "step": 50
    },
    {
      "epoch": 0.21473684210526317,
      "grad_norm": 1.328125,
      "learning_rate": 0.00019905865409315288,
      "loss": 1.2874,
      "step": 51
    },
    {
      "epoch": 0.21894736842105264,
      "grad_norm": 0.244140625,
      "learning_rate": 0.0001990122514534651,
      "loss": 0.9588,
      "step": 52
    },
    {
      "epoch": 0.2231578947368421,
      "grad_norm": 0.376953125,
      "learning_rate": 0.0001989647381500242,
      "loss": 1.3036,
      "step": 53
    },
    {
      "epoch": 0.22736842105263158,
      "grad_norm": 0.5,
      "learning_rate": 0.00019891611471580764,
      "loss": 1.514,
      "step": 54
    },
    {
      "epoch": 0.23157894736842105,
      "grad_norm": 0.423828125,
      "learning_rate": 0.0001988663816962458,
      "loss": 1.2444,
      "step": 55
    },
    {
      "epoch": 0.23578947368421052,
      "grad_norm": 0.30078125,
      "learning_rate": 0.00019881553964921572,
      "loss": 1.2261,
      "step": 56
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.34765625,
      "learning_rate": 0.00019876358914503492,
      "loss": 1.2489,
      "step": 57
    },
    {
      "epoch": 0.24421052631578946,
      "grad_norm": 0.431640625,
      "learning_rate": 0.00019871053076645488,
      "loss": 1.2134,
      "step": 58
    },
    {
      "epoch": 0.24842105263157896,
      "grad_norm": 0.259765625,
      "learning_rate": 0.00019865636510865467,
      "loss": 1.1999,
      "step": 59
    },
    {
      "epoch": 0.25263157894736843,
      "grad_norm": 0.2421875,
      "learning_rate": 0.00019860109277923418,
      "loss": 1.1485,
      "step": 60
    },
    {
      "epoch": 0.25263157894736843,
      "eval_loss": 1.2386109828948975,
      "eval_runtime": 25.8708,
      "eval_samples_per_second": 3.865,
      "eval_steps_per_second": 1.933,
      "step": 60
    },
    {
      "epoch": 0.25684210526315787,
      "grad_norm": 0.5390625,
      "learning_rate": 0.00019854471439820733,
      "loss": 1.2963,
      "step": 61
    },
    {
      "epoch": 0.26105263157894737,
      "grad_norm": 0.345703125,
      "learning_rate": 0.00019848723059799506,
      "loss": 1.097,
      "step": 62
    },
    {
      "epoch": 0.26526315789473687,
      "grad_norm": 0.49609375,
      "learning_rate": 0.00019842864202341835,
      "loss": 1.1463,
      "step": 63
    },
    {
      "epoch": 0.2694736842105263,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00019836894933169088,
      "loss": 1.1921,
      "step": 64
    },
    {
      "epoch": 0.2736842105263158,
      "grad_norm": 0.349609375,
      "learning_rate": 0.00019830815319241168,
      "loss": 1.1835,
      "step": 65
    },
    {
      "epoch": 0.27789473684210525,
      "grad_norm": 0.333984375,
      "learning_rate": 0.0001982462542875576,
      "loss": 1.1998,
      "step": 66
    },
    {
      "epoch": 0.28210526315789475,
      "grad_norm": 0.244140625,
      "learning_rate": 0.00019818325331147585,
      "loss": 1.1047,
      "step": 67
    },
    {
      "epoch": 0.2863157894736842,
      "grad_norm": 0.244140625,
      "learning_rate": 0.00019811915097087587,
      "loss": 1.2452,
      "step": 68
    },
    {
      "epoch": 0.2905263157894737,
      "grad_norm": 0.259765625,
      "learning_rate": 0.00019805394798482167,
      "loss": 1.1633,
      "step": 69
    },
    {
      "epoch": 0.29473684210526313,
      "grad_norm": 0.44140625,
      "learning_rate": 0.00019798764508472373,
      "loss": 1.0081,
      "step": 70
    },
    {
      "epoch": 0.29894736842105263,
      "grad_norm": 0.5703125,
      "learning_rate": 0.00019792024301433064,
      "loss": 0.9194,
      "step": 71
    },
    {
      "epoch": 0.3031578947368421,
      "grad_norm": 0.357421875,
      "learning_rate": 0.00019785174252972092,
      "loss": 0.8091,
      "step": 72
    },
    {
      "epoch": 0.30736842105263157,
      "grad_norm": 0.33984375,
      "learning_rate": 0.00019778214439929452,
      "loss": 1.1248,
      "step": 73
    },
    {
      "epoch": 0.31157894736842107,
      "grad_norm": 0.23046875,
      "learning_rate": 0.0001977114494037641,
      "loss": 1.1204,
      "step": 74
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 0.51171875,
      "learning_rate": 0.0001976396583361464,
      "loss": 1.1662,
      "step": 75
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.2578125,
      "learning_rate": 0.00019756677200175315,
      "loss": 1.1222,
      "step": 76
    },
    {
      "epoch": 0.32421052631578945,
      "grad_norm": 0.796875,
      "learning_rate": 0.00019749279121818235,
      "loss": 1.0329,
      "step": 77
    },
    {
      "epoch": 0.32842105263157895,
      "grad_norm": 0.2490234375,
      "learning_rate": 0.0001974177168153088,
      "loss": 1.1199,
      "step": 78
    },
    {
      "epoch": 0.33263157894736844,
      "grad_norm": 0.26171875,
      "learning_rate": 0.00019734154963527495,
      "loss": 1.4391,
      "step": 79
    },
    {
      "epoch": 0.3368421052631579,
      "grad_norm": 0.30078125,
      "learning_rate": 0.0001972642905324813,
      "loss": 1.3924,
      "step": 80
    },
    {
      "epoch": 0.3410526315789474,
      "grad_norm": 0.208984375,
      "learning_rate": 0.00019718594037357713,
      "loss": 1.1518,
      "step": 81
    },
    {
      "epoch": 0.3452631578947368,
      "grad_norm": 0.953125,
      "learning_rate": 0.0001971065000374504,
      "loss": 1.2606,
      "step": 82
    },
    {
      "epoch": 0.3494736842105263,
      "grad_norm": 0.306640625,
      "learning_rate": 0.0001970259704152181,
      "loss": 1.2293,
      "step": 83
    },
    {
      "epoch": 0.35368421052631577,
      "grad_norm": 0.6328125,
      "learning_rate": 0.0001969443524102163,
      "loss": 0.9564,
      "step": 84
    },
    {
      "epoch": 0.35789473684210527,
      "grad_norm": 0.279296875,
      "learning_rate": 0.00019686164693798986,
      "loss": 1.2023,
      "step": 85
    },
    {
      "epoch": 0.36210526315789476,
      "grad_norm": 0.263671875,
      "learning_rate": 0.0001967778549262822,
      "loss": 0.9322,
      "step": 86
    },
    {
      "epoch": 0.3663157894736842,
      "grad_norm": 0.51171875,
      "learning_rate": 0.00019669297731502507,
      "loss": 1.2589,
      "step": 87
    },
    {
      "epoch": 0.3705263157894737,
      "grad_norm": 0.392578125,
      "learning_rate": 0.00019660701505632772,
      "loss": 1.3188,
      "step": 88
    },
    {
      "epoch": 0.37473684210526315,
      "grad_norm": 0.51953125,
      "learning_rate": 0.00019651996911446647,
      "loss": 1.0415,
      "step": 89
    },
    {
      "epoch": 0.37894736842105264,
      "grad_norm": 0.427734375,
      "learning_rate": 0.0001964318404658737,
      "loss": 1.467,
      "step": 90
    },
    {
      "epoch": 0.3831578947368421,
      "grad_norm": 0.4453125,
      "learning_rate": 0.00019634263009912705,
      "loss": 1.5527,
      "step": 91
    },
    {
      "epoch": 0.3873684210526316,
      "grad_norm": 0.30859375,
      "learning_rate": 0.00019625233901493822,
      "loss": 1.2043,
      "step": 92
    },
    {
      "epoch": 0.391578947368421,
      "grad_norm": 0.279296875,
      "learning_rate": 0.00019616096822614186,
      "loss": 0.9677,
      "step": 93
    },
    {
      "epoch": 0.3957894736842105,
      "grad_norm": 0.46484375,
      "learning_rate": 0.000196068518757684,
      "loss": 1.1942,
      "step": 94
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.435546875,
      "learning_rate": 0.00019597499164661093,
      "loss": 1.3481,
      "step": 95
    },
    {
      "epoch": 0.40421052631578946,
      "grad_norm": 0.291015625,
      "learning_rate": 0.00019588038794205703,
      "loss": 1.2776,
      "step": 96
    },
    {
      "epoch": 0.40842105263157896,
      "grad_norm": 0.3828125,
      "learning_rate": 0.00019578470870523359,
      "loss": 1.4808,
      "step": 97
    },
    {
      "epoch": 0.4126315789473684,
      "grad_norm": 0.28125,
      "learning_rate": 0.00019568795500941635,
      "loss": 1.3385,
      "step": 98
    },
    {
      "epoch": 0.4168421052631579,
      "grad_norm": 0.484375,
      "learning_rate": 0.00019559012793993392,
      "loss": 1.5787,
      "step": 99
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.298828125,
      "learning_rate": 0.00019549122859415538,
      "loss": 1.2151,
      "step": 100
    },
    {
      "epoch": 0.42526315789473684,
      "grad_norm": 0.65234375,
      "learning_rate": 0.0001953912580814779,
      "loss": 1.0332,
      "step": 101
    },
    {
      "epoch": 0.42947368421052634,
      "grad_norm": 0.37890625,
      "learning_rate": 0.00019529021752331453,
      "loss": 1.2677,
      "step": 102
    },
    {
      "epoch": 0.4336842105263158,
      "grad_norm": 0.265625,
      "learning_rate": 0.0001951881080530814,
      "loss": 1.0672,
      "step": 103
    },
    {
      "epoch": 0.4378947368421053,
      "grad_norm": 0.498046875,
      "learning_rate": 0.00019508493081618513,
      "loss": 1.1736,
      "step": 104
    },
    {
      "epoch": 0.4421052631578947,
      "grad_norm": 0.298828125,
      "learning_rate": 0.00019498068697000994,
      "loss": 1.1174,
      "step": 105
    },
    {
      "epoch": 0.4463157894736842,
      "grad_norm": 0.169921875,
      "learning_rate": 0.00019487537768390464,
      "loss": 1.0712,
      "step": 106
    },
    {
      "epoch": 0.45052631578947366,
      "grad_norm": 0.55078125,
      "learning_rate": 0.0001947690041391696,
      "loss": 1.4496,
      "step": 107
    },
    {
      "epoch": 0.45473684210526316,
      "grad_norm": 0.47265625,
      "learning_rate": 0.00019466156752904343,
      "loss": 1.2413,
      "step": 108
    },
    {
      "epoch": 0.4589473684210526,
      "grad_norm": 0.6015625,
      "learning_rate": 0.0001945530690586896,
      "loss": 1.0208,
      "step": 109
    },
    {
      "epoch": 0.4631578947368421,
      "grad_norm": 0.35546875,
      "learning_rate": 0.0001944435099451829,
      "loss": 1.3997,
      "step": 110
    },
    {
      "epoch": 0.4673684210526316,
      "grad_norm": 0.330078125,
      "learning_rate": 0.00019433289141749586,
      "loss": 1.2914,
      "step": 111
    },
    {
      "epoch": 0.47157894736842104,
      "grad_norm": 0.63671875,
      "learning_rate": 0.00019422121471648497,
      "loss": 0.8134,
      "step": 112
    },
    {
      "epoch": 0.47578947368421054,
      "grad_norm": 0.30859375,
      "learning_rate": 0.00019410848109487658,
      "loss": 1.1282,
      "step": 113
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.5625,
      "learning_rate": 0.0001939946918172531,
      "loss": 1.3254,
      "step": 114
    },
    {
      "epoch": 0.4842105263157895,
      "grad_norm": 0.30859375,
      "learning_rate": 0.00019387984816003867,
      "loss": 1.6428,
      "step": 115
    },
    {
      "epoch": 0.4884210526315789,
      "grad_norm": 0.33203125,
      "learning_rate": 0.00019376395141148476,
      "loss": 1.0688,
      "step": 116
    },
    {
      "epoch": 0.4926315789473684,
      "grad_norm": 0.6953125,
      "learning_rate": 0.00019364700287165604,
      "loss": 1.0969,
      "step": 117
    },
    {
      "epoch": 0.4968421052631579,
      "grad_norm": 1.296875,
      "learning_rate": 0.00019352900385241536,
      "loss": 1.5249,
      "step": 118
    },
    {
      "epoch": 0.5010526315789474,
      "grad_norm": 0.2001953125,
      "learning_rate": 0.00019340995567740938,
      "loss": 1.2095,
      "step": 119
    },
    {
      "epoch": 0.5052631578947369,
      "grad_norm": 0.53515625,
      "learning_rate": 0.0001932898596820536,
      "loss": 1.1249,
      "step": 120
    },
    {
      "epoch": 0.5052631578947369,
      "eval_loss": 1.2166697978973389,
      "eval_runtime": 25.8713,
      "eval_samples_per_second": 3.865,
      "eval_steps_per_second": 1.933,
      "step": 120
    },
    {
      "epoch": 0.5094736842105263,
      "grad_norm": 0.423828125,
      "learning_rate": 0.00019316871721351733,
      "loss": 1.5017,
      "step": 121
    },
    {
      "epoch": 0.5136842105263157,
      "grad_norm": 0.7421875,
      "learning_rate": 0.0001930465296307087,
      "loss": 1.0994,
      "step": 122
    },
    {
      "epoch": 0.5178947368421053,
      "grad_norm": 0.21875,
      "learning_rate": 0.0001929232983042592,
      "loss": 1.0339,
      "step": 123
    },
    {
      "epoch": 0.5221052631578947,
      "grad_norm": 0.6328125,
      "learning_rate": 0.00019279902461650866,
      "loss": 1.1317,
      "step": 124
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.3984375,
      "learning_rate": 0.00019267370996148934,
      "loss": 0.9421,
      "step": 125
    },
    {
      "epoch": 0.5305263157894737,
      "grad_norm": 0.396484375,
      "learning_rate": 0.00019254735574491058,
      "loss": 1.3029,
      "step": 126
    },
    {
      "epoch": 0.5347368421052632,
      "grad_norm": 0.8359375,
      "learning_rate": 0.00019241996338414296,
      "loss": 1.3548,
      "step": 127
    },
    {
      "epoch": 0.5389473684210526,
      "grad_norm": 0.84765625,
      "learning_rate": 0.00019229153430820232,
      "loss": 1.0865,
      "step": 128
    },
    {
      "epoch": 0.5431578947368421,
      "grad_norm": 0.453125,
      "learning_rate": 0.00019216206995773373,
      "loss": 0.8151,
      "step": 129
    },
    {
      "epoch": 0.5473684210526316,
      "grad_norm": 0.8046875,
      "learning_rate": 0.0001920315717849956,
      "loss": 1.3576,
      "step": 130
    },
    {
      "epoch": 0.5515789473684211,
      "grad_norm": 0.82421875,
      "learning_rate": 0.00019190004125384293,
      "loss": 1.2439,
      "step": 131
    },
    {
      "epoch": 0.5557894736842105,
      "grad_norm": 0.56640625,
      "learning_rate": 0.0001917674798397113,
      "loss": 0.9743,
      "step": 132
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0001916338890296001,
      "loss": 1.3315,
      "step": 133
    },
    {
      "epoch": 0.5642105263157895,
      "grad_norm": 0.333984375,
      "learning_rate": 0.00019149927032205587,
      "loss": 1.3268,
      "step": 134
    },
    {
      "epoch": 0.5684210526315789,
      "grad_norm": 0.388671875,
      "learning_rate": 0.00019136362522715562,
      "loss": 1.4751,
      "step": 135
    },
    {
      "epoch": 0.5726315789473684,
      "grad_norm": 0.2734375,
      "learning_rate": 0.00019122695526648968,
      "loss": 1.1219,
      "step": 136
    },
    {
      "epoch": 0.5768421052631579,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00019108926197314486,
      "loss": 1.4059,
      "step": 137
    },
    {
      "epoch": 0.5810526315789474,
      "grad_norm": 0.33203125,
      "learning_rate": 0.00019095054689168705,
      "loss": 1.3282,
      "step": 138
    },
    {
      "epoch": 0.5852631578947368,
      "grad_norm": 0.6171875,
      "learning_rate": 0.00019081081157814404,
      "loss": 1.6334,
      "step": 139
    },
    {
      "epoch": 0.5894736842105263,
      "grad_norm": 0.359375,
      "learning_rate": 0.00019067005759998797,
      "loss": 1.159,
      "step": 140
    },
    {
      "epoch": 0.5936842105263158,
      "grad_norm": 0.470703125,
      "learning_rate": 0.00019052828653611786,
      "loss": 1.3261,
      "step": 141
    },
    {
      "epoch": 0.5978947368421053,
      "grad_norm": 0.26171875,
      "learning_rate": 0.0001903854999768417,
      "loss": 1.2041,
      "step": 142
    },
    {
      "epoch": 0.6021052631578947,
      "grad_norm": 0.27734375,
      "learning_rate": 0.00019024169952385885,
      "loss": 1.1998,
      "step": 143
    },
    {
      "epoch": 0.6063157894736843,
      "grad_norm": 0.56640625,
      "learning_rate": 0.0001900968867902419,
      "loss": 1.6427,
      "step": 144
    },
    {
      "epoch": 0.6105263157894737,
      "grad_norm": 0.419921875,
      "learning_rate": 0.00018995106340041873,
      "loss": 1.1968,
      "step": 145
    },
    {
      "epoch": 0.6147368421052631,
      "grad_norm": 0.671875,
      "learning_rate": 0.00018980423099015402,
      "loss": 0.8641,
      "step": 146
    },
    {
      "epoch": 0.6189473684210526,
      "grad_norm": 0.333984375,
      "learning_rate": 0.00018965639120653121,
      "loss": 1.4518,
      "step": 147
    },
    {
      "epoch": 0.6231578947368421,
      "grad_norm": 0.423828125,
      "learning_rate": 0.00018950754570793384,
      "loss": 1.3077,
      "step": 148
    },
    {
      "epoch": 0.6273684210526316,
      "grad_norm": 0.85546875,
      "learning_rate": 0.00018935769616402703,
      "loss": 1.2077,
      "step": 149
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.224609375,
      "learning_rate": 0.00018920684425573865,
      "loss": 1.0868,
      "step": 150
    },
    {
      "epoch": 0.6357894736842106,
      "grad_norm": 0.25390625,
      "learning_rate": 0.00018905499167524062,
      "loss": 1.2018,
      "step": 151
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.498046875,
      "learning_rate": 0.00018890214012592975,
      "loss": 1.1675,
      "step": 152
    },
    {
      "epoch": 0.6442105263157895,
      "grad_norm": 0.2451171875,
      "learning_rate": 0.00018874829132240874,
      "loss": 1.2348,
      "step": 153
    },
    {
      "epoch": 0.6484210526315789,
      "grad_norm": 0.33984375,
      "learning_rate": 0.000188593446990467,
      "loss": 1.3202,
      "step": 154
    },
    {
      "epoch": 0.6526315789473685,
      "grad_norm": 1.0078125,
      "learning_rate": 0.0001884376088670611,
      "loss": 1.0171,
      "step": 155
    },
    {
      "epoch": 0.6568421052631579,
      "grad_norm": 0.318359375,
      "learning_rate": 0.00018828077870029552,
      "loss": 1.219,
      "step": 156
    },
    {
      "epoch": 0.6610526315789473,
      "grad_norm": 0.369140625,
      "learning_rate": 0.00018812295824940285,
      "loss": 0.8956,
      "step": 157
    },
    {
      "epoch": 0.6652631578947369,
      "grad_norm": 0.328125,
      "learning_rate": 0.00018796414928472417,
      "loss": 0.9322,
      "step": 158
    },
    {
      "epoch": 0.6694736842105263,
      "grad_norm": 0.2890625,
      "learning_rate": 0.0001878043535876891,
      "loss": 1.2062,
      "step": 159
    },
    {
      "epoch": 0.6736842105263158,
      "grad_norm": 0.41015625,
      "learning_rate": 0.0001876435729507959,
      "loss": 1.3113,
      "step": 160
    },
    {
      "epoch": 0.6778947368421052,
      "grad_norm": 0.53515625,
      "learning_rate": 0.00018748180917759136,
      "loss": 1.1539,
      "step": 161
    },
    {
      "epoch": 0.6821052631578948,
      "grad_norm": 0.279296875,
      "learning_rate": 0.0001873190640826505,
      "loss": 1.3287,
      "step": 162
    },
    {
      "epoch": 0.6863157894736842,
      "grad_norm": 0.298828125,
      "learning_rate": 0.00018715533949155625,
      "loss": 1.0616,
      "step": 163
    },
    {
      "epoch": 0.6905263157894737,
      "grad_norm": 0.388671875,
      "learning_rate": 0.00018699063724087904,
      "loss": 1.0171,
      "step": 164
    },
    {
      "epoch": 0.6947368421052632,
      "grad_norm": 0.32421875,
      "learning_rate": 0.00018682495917815608,
      "loss": 1.1113,
      "step": 165
    },
    {
      "epoch": 0.6989473684210527,
      "grad_norm": 0.46875,
      "learning_rate": 0.00018665830716187065,
      "loss": 0.8351,
      "step": 166
    },
    {
      "epoch": 0.7031578947368421,
      "grad_norm": 0.6015625,
      "learning_rate": 0.0001864906830614314,
      "loss": 1.2181,
      "step": 167
    },
    {
      "epoch": 0.7073684210526315,
      "grad_norm": 0.71875,
      "learning_rate": 0.0001863220887571512,
      "loss": 1.1843,
      "step": 168
    },
    {
      "epoch": 0.7115789473684211,
      "grad_norm": 0.51953125,
      "learning_rate": 0.00018615252614022617,
      "loss": 1.3809,
      "step": 169
    },
    {
      "epoch": 0.7157894736842105,
      "grad_norm": 0.34375,
      "learning_rate": 0.0001859819971127143,
      "loss": 1.4288,
      "step": 170
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.41796875,
      "learning_rate": 0.00018581050358751445,
      "loss": 1.1449,
      "step": 171
    },
    {
      "epoch": 0.7242105263157895,
      "grad_norm": 0.578125,
      "learning_rate": 0.00018563804748834438,
      "loss": 1.0703,
      "step": 172
    },
    {
      "epoch": 0.728421052631579,
      "grad_norm": 0.43359375,
      "learning_rate": 0.00018546463074971977,
      "loss": 1.2093,
      "step": 173
    },
    {
      "epoch": 0.7326315789473684,
      "grad_norm": 0.26171875,
      "learning_rate": 0.000185290255316932,
      "loss": 0.7346,
      "step": 174
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.369140625,
      "learning_rate": 0.00018511492314602656,
      "loss": 1.2782,
      "step": 175
    },
    {
      "epoch": 0.7410526315789474,
      "grad_norm": 0.56640625,
      "learning_rate": 0.00018493863620378122,
      "loss": 1.0844,
      "step": 176
    },
    {
      "epoch": 0.7452631578947368,
      "grad_norm": 0.2470703125,
      "learning_rate": 0.00018476139646768372,
      "loss": 1.1771,
      "step": 177
    },
    {
      "epoch": 0.7494736842105263,
      "grad_norm": 0.228515625,
      "learning_rate": 0.00018458320592590975,
      "loss": 1.2,
      "step": 178
    },
    {
      "epoch": 0.7536842105263157,
      "grad_norm": 0.310546875,
      "learning_rate": 0.00018440406657730058,
      "loss": 1.2248,
      "step": 179
    },
    {
      "epoch": 0.7578947368421053,
      "grad_norm": 0.263671875,
      "learning_rate": 0.00018422398043134067,
      "loss": 1.3675,
      "step": 180
    },
    {
      "epoch": 0.7578947368421053,
      "eval_loss": 1.2129631042480469,
      "eval_runtime": 25.9253,
      "eval_samples_per_second": 3.857,
      "eval_steps_per_second": 1.929,
      "step": 180
    },
    {
      "epoch": 0.7621052631578947,
      "grad_norm": 0.2412109375,
      "learning_rate": 0.0001840429495081352,
      "loss": 1.2456,
      "step": 181
    },
    {
      "epoch": 0.7663157894736842,
      "grad_norm": 0.25390625,
      "learning_rate": 0.00018386097583838714,
      "loss": 1.2617,
      "step": 182
    },
    {
      "epoch": 0.7705263157894737,
      "grad_norm": 0.283203125,
      "learning_rate": 0.00018367806146337483,
      "loss": 1.2708,
      "step": 183
    },
    {
      "epoch": 0.7747368421052632,
      "grad_norm": 0.318359375,
      "learning_rate": 0.00018349420843492888,
      "loss": 1.3771,
      "step": 184
    },
    {
      "epoch": 0.7789473684210526,
      "grad_norm": 0.73046875,
      "learning_rate": 0.00018330941881540915,
      "loss": 1.3123,
      "step": 185
    },
    {
      "epoch": 0.783157894736842,
      "grad_norm": 0.46875,
      "learning_rate": 0.00018312369467768166,
      "loss": 1.1952,
      "step": 186
    },
    {
      "epoch": 0.7873684210526316,
      "grad_norm": 0.7578125,
      "learning_rate": 0.00018293703810509537,
      "loss": 1.426,
      "step": 187
    },
    {
      "epoch": 0.791578947368421,
      "grad_norm": 0.33203125,
      "learning_rate": 0.0001827494511914587,
      "loss": 1.3205,
      "step": 188
    },
    {
      "epoch": 0.7957894736842105,
      "grad_norm": 0.365234375,
      "learning_rate": 0.00018256093604101617,
      "loss": 1.2221,
      "step": 189
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.36328125,
      "learning_rate": 0.0001823714947684247,
      "loss": 1.4212,
      "step": 190
    },
    {
      "epoch": 0.8042105263157895,
      "grad_norm": 0.349609375,
      "learning_rate": 0.00018218112949872995,
      "loss": 1.2183,
      "step": 191
    },
    {
      "epoch": 0.8084210526315789,
      "grad_norm": 0.392578125,
      "learning_rate": 0.00018198984236734246,
      "loss": 0.9922,
      "step": 192
    },
    {
      "epoch": 0.8126315789473684,
      "grad_norm": 0.373046875,
      "learning_rate": 0.0001817976355200137,
      "loss": 1.334,
      "step": 193
    },
    {
      "epoch": 0.8168421052631579,
      "grad_norm": 0.30859375,
      "learning_rate": 0.000181604511112812,
      "loss": 1.1052,
      "step": 194
    },
    {
      "epoch": 0.8210526315789474,
      "grad_norm": 0.349609375,
      "learning_rate": 0.0001814104713120983,
      "loss": 0.8112,
      "step": 195
    },
    {
      "epoch": 0.8252631578947368,
      "grad_norm": 0.35546875,
      "learning_rate": 0.000181215518294502,
      "loss": 1.2507,
      "step": 196
    },
    {
      "epoch": 0.8294736842105264,
      "grad_norm": 0.671875,
      "learning_rate": 0.0001810196542468964,
      "loss": 1.1228,
      "step": 197
    },
    {
      "epoch": 0.8336842105263158,
      "grad_norm": 0.41015625,
      "learning_rate": 0.00018082288136637422,
      "loss": 1.3562,
      "step": 198
    },
    {
      "epoch": 0.8378947368421052,
      "grad_norm": 0.302734375,
      "learning_rate": 0.000180625201860223,
      "loss": 0.7766,
      "step": 199
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.322265625,
      "learning_rate": 0.00018042661794590023,
      "loss": 1.2885,
      "step": 200
    },
    {
      "epoch": 0.8463157894736842,
      "grad_norm": 0.609375,
      "learning_rate": 0.0001802271318510086,
      "loss": 1.271,
      "step": 201
    },
    {
      "epoch": 0.8505263157894737,
      "grad_norm": 0.341796875,
      "learning_rate": 0.00018002674581327094,
      "loss": 1.3777,
      "step": 202
    },
    {
      "epoch": 0.8547368421052631,
      "grad_norm": 0.3828125,
      "learning_rate": 0.00017982546208050515,
      "loss": 1.32,
      "step": 203
    },
    {
      "epoch": 0.8589473684210527,
      "grad_norm": 0.392578125,
      "learning_rate": 0.00017962328291059888,
      "loss": 1.1265,
      "step": 204
    },
    {
      "epoch": 0.8631578947368421,
      "grad_norm": 0.73046875,
      "learning_rate": 0.00017942021057148436,
      "loss": 1.523,
      "step": 205
    },
    {
      "epoch": 0.8673684210526316,
      "grad_norm": 1.046875,
      "learning_rate": 0.00017921624734111292,
      "loss": 1.0251,
      "step": 206
    },
    {
      "epoch": 0.871578947368421,
      "grad_norm": 0.490234375,
      "learning_rate": 0.0001790113955074294,
      "loss": 1.2665,
      "step": 207
    },
    {
      "epoch": 0.8757894736842106,
      "grad_norm": 0.6875,
      "learning_rate": 0.0001788056573683464,
      "loss": 1.2244,
      "step": 208
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.2177734375,
      "learning_rate": 0.0001785990352317187,
      "loss": 1.1621,
      "step": 209
    },
    {
      "epoch": 0.8842105263157894,
      "grad_norm": 0.4921875,
      "learning_rate": 0.00017839153141531718,
      "loss": 1.3182,
      "step": 210
    },
    {
      "epoch": 0.888421052631579,
      "grad_norm": 0.388671875,
      "learning_rate": 0.000178183148246803,
      "loss": 1.4508,
      "step": 211
    },
    {
      "epoch": 0.8926315789473684,
      "grad_norm": 0.388671875,
      "learning_rate": 0.00017797388806370132,
      "loss": 1.1155,
      "step": 212
    },
    {
      "epoch": 0.8968421052631579,
      "grad_norm": 0.416015625,
      "learning_rate": 0.00017776375321337521,
      "loss": 0.9191,
      "step": 213
    },
    {
      "epoch": 0.9010526315789473,
      "grad_norm": 0.2431640625,
      "learning_rate": 0.00017755274605299923,
      "loss": 1.1577,
      "step": 214
    },
    {
      "epoch": 0.9052631578947369,
      "grad_norm": 0.412109375,
      "learning_rate": 0.00017734086894953305,
      "loss": 1.372,
      "step": 215
    },
    {
      "epoch": 0.9094736842105263,
      "grad_norm": 0.353515625,
      "learning_rate": 0.00017712812427969485,
      "loss": 1.1932,
      "step": 216
    },
    {
      "epoch": 0.9136842105263158,
      "grad_norm": 0.291015625,
      "learning_rate": 0.0001769145144299347,
      "loss": 1.3167,
      "step": 217
    },
    {
      "epoch": 0.9178947368421052,
      "grad_norm": 0.255859375,
      "learning_rate": 0.00017670004179640774,
      "loss": 1.2357,
      "step": 218
    },
    {
      "epoch": 0.9221052631578948,
      "grad_norm": 0.5703125,
      "learning_rate": 0.00017648470878494737,
      "loss": 0.9556,
      "step": 219
    },
    {
      "epoch": 0.9263157894736842,
      "grad_norm": 0.36328125,
      "learning_rate": 0.0001762685178110382,
      "loss": 1.2047,
      "step": 220
    },
    {
      "epoch": 0.9305263157894736,
      "grad_norm": 0.271484375,
      "learning_rate": 0.00017605147129978903,
      "loss": 1.1935,
      "step": 221
    },
    {
      "epoch": 0.9347368421052632,
      "grad_norm": 0.400390625,
      "learning_rate": 0.0001758335716859055,
      "loss": 1.3426,
      "step": 222
    },
    {
      "epoch": 0.9389473684210526,
      "grad_norm": 0.73046875,
      "learning_rate": 0.000175614821413663,
      "loss": 1.5181,
      "step": 223
    },
    {
      "epoch": 0.9431578947368421,
      "grad_norm": 0.3203125,
      "learning_rate": 0.00017539522293687898,
      "loss": 1.0962,
      "step": 224
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.232421875,
      "learning_rate": 0.00017517477871888568,
      "loss": 1.3922,
      "step": 225
    },
    {
      "epoch": 0.9515789473684211,
      "grad_norm": 0.5546875,
      "learning_rate": 0.00017495349123250242,
      "loss": 1.2535,
      "step": 226
    },
    {
      "epoch": 0.9557894736842105,
      "grad_norm": 0.296875,
      "learning_rate": 0.00017473136296000772,
      "loss": 1.1987,
      "step": 227
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.77734375,
      "learning_rate": 0.00017450839639311162,
      "loss": 1.4301,
      "step": 228
    },
    {
      "epoch": 0.9642105263157895,
      "grad_norm": 0.35546875,
      "learning_rate": 0.00017428459403292767,
      "loss": 1.3164,
      "step": 229
    },
    {
      "epoch": 0.968421052631579,
      "grad_norm": 0.419921875,
      "learning_rate": 0.00017405995838994494,
      "loss": 1.1554,
      "step": 230
    },
    {
      "epoch": 0.9726315789473684,
      "grad_norm": 0.3125,
      "learning_rate": 0.00017383449198399964,
      "loss": 1.3036,
      "step": 231
    },
    {
      "epoch": 0.9768421052631578,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00017360819734424715,
      "loss": 1.2797,
      "step": 232
    },
    {
      "epoch": 0.9810526315789474,
      "grad_norm": 0.412109375,
      "learning_rate": 0.00017338107700913354,
      "loss": 1.1202,
      "step": 233
    },
    {
      "epoch": 0.9852631578947368,
      "grad_norm": 0.365234375,
      "learning_rate": 0.0001731531335263669,
      "loss": 0.8187,
      "step": 234
    },
    {
      "epoch": 0.9894736842105263,
      "grad_norm": 0.5546875,
      "learning_rate": 0.0001729243694528891,
      "loss": 1.1702,
      "step": 235
    },
    {
      "epoch": 0.9936842105263158,
      "grad_norm": 0.5546875,
      "learning_rate": 0.00017269478735484683,
      "loss": 1.1406,
      "step": 236
    },
    {
      "epoch": 0.9978947368421053,
      "grad_norm": 0.3359375,
      "learning_rate": 0.00017246438980756293,
      "loss": 0.9633,
      "step": 237
    }
  ],
  "logging_steps": 1,
  "max_steps": 948,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 237,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3952216796823552.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}