{
  "best_metric": 1.0710123777389526,
  "best_model_checkpoint": "data/Llama-31-8B_task-2_60-samples_config-3_full/checkpoint-276",
  "epoch": 54.95652173913044,
  "eval_steps": 500,
  "global_step": 316,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.5168920755386353,
      "learning_rate": 1.3333333333333336e-07,
      "loss": 1.5956,
      "step": 1
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.5719501376152039,
      "learning_rate": 2.666666666666667e-07,
      "loss": 1.6046,
      "step": 2
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.4981832504272461,
      "learning_rate": 5.333333333333335e-07,
      "loss": 1.5659,
      "step": 4
    },
    {
      "epoch": 0.8695652173913043,
      "eval_loss": 1.5845621824264526,
      "eval_runtime": 12.9809,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 5
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 0.4701167941093445,
      "learning_rate": 8.000000000000001e-07,
      "loss": 1.5639,
      "step": 6
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 0.5071099996566772,
      "learning_rate": 1.066666666666667e-06,
      "loss": 1.5807,
      "step": 8
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.5001740455627441,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 1.5947,
      "step": 10
    },
    {
      "epoch": 1.9130434782608696,
      "eval_loss": 1.581119179725647,
      "eval_runtime": 12.9812,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 11
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 0.5267815589904785,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 1.589,
      "step": 12
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 0.49407559633255005,
      "learning_rate": 1.8666666666666669e-06,
      "loss": 1.5287,
      "step": 14
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 0.45030105113983154,
      "learning_rate": 2.133333333333334e-06,
      "loss": 1.6305,
      "step": 16
    },
    {
      "epoch": 2.9565217391304346,
      "eval_loss": 1.5758260488510132,
      "eval_runtime": 12.9766,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 17
    },
    {
      "epoch": 3.130434782608696,
      "grad_norm": 0.4595053493976593,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.5404,
      "step": 18
    },
    {
      "epoch": 3.4782608695652173,
      "grad_norm": 0.519245982170105,
      "learning_rate": 2.666666666666667e-06,
      "loss": 1.5737,
      "step": 20
    },
    {
      "epoch": 3.8260869565217392,
      "grad_norm": 0.4773900508880615,
      "learning_rate": 2.9333333333333338e-06,
      "loss": 1.5682,
      "step": 22
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.5672565698623657,
      "eval_runtime": 12.9785,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 23
    },
    {
      "epoch": 4.173913043478261,
      "grad_norm": 0.4907453954219818,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 1.5736,
      "step": 24
    },
    {
      "epoch": 4.521739130434782,
      "grad_norm": 0.4995110332965851,
      "learning_rate": 3.4666666666666672e-06,
      "loss": 1.548,
      "step": 26
    },
    {
      "epoch": 4.869565217391305,
      "grad_norm": 0.48306918144226074,
      "learning_rate": 3.7333333333333337e-06,
      "loss": 1.5687,
      "step": 28
    },
    {
      "epoch": 4.869565217391305,
      "eval_loss": 1.5570815801620483,
      "eval_runtime": 12.977,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 28
    },
    {
      "epoch": 5.217391304347826,
      "grad_norm": 0.5053550601005554,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.5427,
      "step": 30
    },
    {
      "epoch": 5.565217391304348,
      "grad_norm": 0.5055222511291504,
      "learning_rate": 4.266666666666668e-06,
      "loss": 1.5277,
      "step": 32
    },
    {
      "epoch": 5.913043478260869,
      "grad_norm": 0.45084983110427856,
      "learning_rate": 4.533333333333334e-06,
      "loss": 1.5556,
      "step": 34
    },
    {
      "epoch": 5.913043478260869,
      "eval_loss": 1.5406227111816406,
      "eval_runtime": 12.9754,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 34
    },
    {
      "epoch": 6.260869565217392,
      "grad_norm": 0.5172422528266907,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.5111,
      "step": 36
    },
    {
      "epoch": 6.608695652173913,
      "grad_norm": 0.571245551109314,
      "learning_rate": 5.0666666666666676e-06,
      "loss": 1.5721,
      "step": 38
    },
    {
      "epoch": 6.956521739130435,
      "grad_norm": 0.46223798394203186,
      "learning_rate": 5.333333333333334e-06,
      "loss": 1.4699,
      "step": 40
    },
    {
      "epoch": 6.956521739130435,
      "eval_loss": 1.5189919471740723,
      "eval_runtime": 12.9806,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 40
    },
    {
      "epoch": 7.304347826086957,
      "grad_norm": 0.44059333205223083,
      "learning_rate": 5.600000000000001e-06,
      "loss": 1.5389,
      "step": 42
    },
    {
      "epoch": 7.6521739130434785,
      "grad_norm": 0.39538195729255676,
      "learning_rate": 5.8666666666666675e-06,
      "loss": 1.4685,
      "step": 44
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.44168609380722046,
      "learning_rate": 6.133333333333334e-06,
      "loss": 1.5027,
      "step": 46
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.4957526922225952,
      "eval_runtime": 12.982,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 46
    },
    {
      "epoch": 8.347826086956522,
      "grad_norm": 0.4372757375240326,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 1.4465,
      "step": 48
    },
    {
      "epoch": 8.695652173913043,
      "grad_norm": 0.4501511752605438,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.5203,
      "step": 50
    },
    {
      "epoch": 8.869565217391305,
      "eval_loss": 1.4718750715255737,
      "eval_runtime": 12.9768,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 51
    },
    {
      "epoch": 9.043478260869565,
      "grad_norm": 0.38575872778892517,
      "learning_rate": 6.9333333333333344e-06,
      "loss": 1.4364,
      "step": 52
    },
    {
      "epoch": 9.391304347826088,
      "grad_norm": 0.3618987798690796,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 1.4197,
      "step": 54
    },
    {
      "epoch": 9.73913043478261,
      "grad_norm": 0.3317548930644989,
      "learning_rate": 7.4666666666666675e-06,
      "loss": 1.4872,
      "step": 56
    },
    {
      "epoch": 9.91304347826087,
      "eval_loss": 1.4444891214370728,
      "eval_runtime": 12.9775,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 57
    },
    {
      "epoch": 10.08695652173913,
      "grad_norm": 0.3010832369327545,
      "learning_rate": 7.733333333333334e-06,
      "loss": 1.4324,
      "step": 58
    },
    {
      "epoch": 10.434782608695652,
      "grad_norm": 0.32329097390174866,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.4333,
      "step": 60
    },
    {
      "epoch": 10.782608695652174,
      "grad_norm": 0.3354980945587158,
      "learning_rate": 8.266666666666667e-06,
      "loss": 1.4184,
      "step": 62
    },
    {
      "epoch": 10.956521739130435,
      "eval_loss": 1.4150630235671997,
      "eval_runtime": 12.9754,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 63
    },
    {
      "epoch": 11.130434782608695,
      "grad_norm": 0.33713477849960327,
      "learning_rate": 8.533333333333335e-06,
      "loss": 1.3763,
      "step": 64
    },
    {
      "epoch": 11.478260869565217,
      "grad_norm": 0.23276787996292114,
      "learning_rate": 8.8e-06,
      "loss": 1.3969,
      "step": 66
    },
    {
      "epoch": 11.826086956521738,
      "grad_norm": 0.2602153718471527,
      "learning_rate": 9.066666666666667e-06,
      "loss": 1.3817,
      "step": 68
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.386828064918518,
      "eval_runtime": 12.979,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 69
    },
    {
      "epoch": 12.173913043478262,
      "grad_norm": 0.2566069960594177,
      "learning_rate": 9.333333333333334e-06,
      "loss": 1.3523,
      "step": 70
    },
    {
      "epoch": 12.521739130434783,
      "grad_norm": 0.2781592607498169,
      "learning_rate": 9.600000000000001e-06,
      "loss": 1.3737,
      "step": 72
    },
    {
      "epoch": 12.869565217391305,
      "grad_norm": 0.2503822147846222,
      "learning_rate": 9.866666666666668e-06,
      "loss": 1.3397,
      "step": 74
    },
    {
      "epoch": 12.869565217391305,
      "eval_loss": 1.3647750616073608,
      "eval_runtime": 12.9767,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 74
    },
    {
      "epoch": 13.217391304347826,
      "grad_norm": 0.269147664308548,
      "learning_rate": 9.999945845889795e-06,
      "loss": 1.3282,
      "step": 76
    },
    {
      "epoch": 13.565217391304348,
      "grad_norm": 0.25336846709251404,
      "learning_rate": 9.999512620046523e-06,
      "loss": 1.3328,
      "step": 78
    },
    {
      "epoch": 13.91304347826087,
      "grad_norm": 0.24610716104507446,
      "learning_rate": 9.99864620589731e-06,
      "loss": 1.3234,
      "step": 80
    },
    {
      "epoch": 13.91304347826087,
      "eval_loss": 1.3389836549758911,
      "eval_runtime": 12.9781,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 80
    },
    {
      "epoch": 14.26086956521739,
      "grad_norm": 0.23158159852027893,
      "learning_rate": 9.99734667851357e-06,
      "loss": 1.2771,
      "step": 82
    },
    {
      "epoch": 14.608695652173914,
      "grad_norm": 0.2516274154186249,
      "learning_rate": 9.995614150494293e-06,
      "loss": 1.3073,
      "step": 84
    },
    {
      "epoch": 14.956521739130435,
      "grad_norm": 0.28719547390937805,
      "learning_rate": 9.993448771956285e-06,
      "loss": 1.2893,
      "step": 86
    },
    {
      "epoch": 14.956521739130435,
      "eval_loss": 1.3121906518936157,
      "eval_runtime": 12.9801,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 86
    },
    {
      "epoch": 15.304347826086957,
      "grad_norm": 0.2287660539150238,
      "learning_rate": 9.99085073052117e-06,
      "loss": 1.2679,
      "step": 88
    },
    {
      "epoch": 15.652173913043478,
      "grad_norm": 0.29683366417884827,
      "learning_rate": 9.987820251299121e-06,
      "loss": 1.2504,
      "step": 90
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.20408132672309875,
      "learning_rate": 9.984357596869369e-06,
      "loss": 1.2999,
      "step": 92
    },
    {
      "epoch": 16.0,
      "eval_loss": 1.2852083444595337,
      "eval_runtime": 12.9826,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 92
    },
    {
      "epoch": 16.347826086956523,
      "grad_norm": 0.2704583406448364,
      "learning_rate": 9.980463067257437e-06,
      "loss": 1.2504,
      "step": 94
    },
    {
      "epoch": 16.695652173913043,
      "grad_norm": 0.2368343323469162,
      "learning_rate": 9.976136999909156e-06,
      "loss": 1.2212,
      "step": 96
    },
    {
      "epoch": 16.869565217391305,
      "eval_loss": 1.2628425359725952,
      "eval_runtime": 12.9802,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 97
    },
    {
      "epoch": 17.043478260869566,
      "grad_norm": 0.22224029898643494,
      "learning_rate": 9.971379769661422e-06,
      "loss": 1.2242,
      "step": 98
    },
    {
      "epoch": 17.391304347826086,
      "grad_norm": 0.2928115725517273,
      "learning_rate": 9.966191788709716e-06,
      "loss": 1.2211,
      "step": 100
    },
    {
      "epoch": 17.73913043478261,
      "grad_norm": 0.22390316426753998,
      "learning_rate": 9.960573506572391e-06,
      "loss": 1.234,
      "step": 102
    },
    {
      "epoch": 17.91304347826087,
      "eval_loss": 1.2357784509658813,
      "eval_runtime": 12.9749,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 103
    },
    {
      "epoch": 18.08695652173913,
      "grad_norm": 0.25287434458732605,
      "learning_rate": 9.95452541005172e-06,
      "loss": 1.1594,
      "step": 104
    },
    {
      "epoch": 18.434782608695652,
      "grad_norm": 0.22554974257946014,
      "learning_rate": 9.948048023191728e-06,
      "loss": 1.1941,
      "step": 106
    },
    {
      "epoch": 18.782608695652176,
      "grad_norm": 0.28337913751602173,
      "learning_rate": 9.941141907232766e-06,
      "loss": 1.1704,
      "step": 108
    },
    {
      "epoch": 18.956521739130434,
      "eval_loss": 1.2077757120132446,
      "eval_runtime": 12.9864,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 109
    },
    {
      "epoch": 19.130434782608695,
      "grad_norm": 0.2129991501569748,
      "learning_rate": 9.933807660562898e-06,
      "loss": 1.1575,
      "step": 110
    },
    {
      "epoch": 19.47826086956522,
      "grad_norm": 0.3318869471549988,
      "learning_rate": 9.926045918666045e-06,
      "loss": 1.1555,
      "step": 112
    },
    {
      "epoch": 19.82608695652174,
      "grad_norm": 0.3031323552131653,
      "learning_rate": 9.91785735406693e-06,
      "loss": 1.1499,
      "step": 114
    },
    {
      "epoch": 20.0,
      "eval_loss": 1.1795598268508911,
      "eval_runtime": 12.9743,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 115
    },
    {
      "epoch": 20.17391304347826,
      "grad_norm": 0.2700609862804413,
      "learning_rate": 9.909242676272797e-06,
      "loss": 1.1176,
      "step": 116
    },
    {
      "epoch": 20.52173913043478,
      "grad_norm": 0.24468179047107697,
      "learning_rate": 9.90020263171194e-06,
      "loss": 1.1005,
      "step": 118
    },
    {
      "epoch": 20.869565217391305,
      "grad_norm": 0.2991030216217041,
      "learning_rate": 9.890738003669029e-06,
      "loss": 1.1265,
      "step": 120
    },
    {
      "epoch": 20.869565217391305,
      "eval_loss": 1.1569637060165405,
      "eval_runtime": 12.9777,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 120
    },
    {
      "epoch": 21.217391304347824,
      "grad_norm": 0.2351488173007965,
      "learning_rate": 9.880849612217238e-06,
      "loss": 1.1073,
      "step": 122
    },
    {
      "epoch": 21.565217391304348,
      "grad_norm": 0.26138749718666077,
      "learning_rate": 9.870538314147194e-06,
      "loss": 1.0675,
      "step": 124
    },
    {
      "epoch": 21.91304347826087,
      "grad_norm": 0.2605469226837158,
      "learning_rate": 9.859805002892733e-06,
      "loss": 1.0716,
      "step": 126
    },
    {
      "epoch": 21.91304347826087,
      "eval_loss": 1.1357496976852417,
      "eval_runtime": 12.9785,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 126
    },
    {
      "epoch": 22.26086956521739,
      "grad_norm": 0.2572947144508362,
      "learning_rate": 9.84865060845349e-06,
      "loss": 1.0791,
      "step": 128
    },
    {
      "epoch": 22.608695652173914,
      "grad_norm": 0.2186698317527771,
      "learning_rate": 9.83707609731432e-06,
      "loss": 1.0729,
      "step": 130
    },
    {
      "epoch": 22.956521739130434,
      "grad_norm": 0.3026718199253082,
      "learning_rate": 9.825082472361558e-06,
      "loss": 1.0332,
      "step": 132
    },
    {
      "epoch": 22.956521739130434,
      "eval_loss": 1.122292160987854,
      "eval_runtime": 12.9802,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 132
    },
    {
      "epoch": 23.304347826086957,
      "grad_norm": 0.21330009400844574,
      "learning_rate": 9.812670772796113e-06,
      "loss": 1.0612,
      "step": 134
    },
    {
      "epoch": 23.652173913043477,
      "grad_norm": 0.17287513613700867,
      "learning_rate": 9.799842074043438e-06,
      "loss": 1.05,
      "step": 136
    },
    {
      "epoch": 24.0,
      "grad_norm": 0.17213226854801178,
      "learning_rate": 9.786597487660336e-06,
      "loss": 1.0631,
      "step": 138
    },
    {
      "epoch": 24.0,
      "eval_loss": 1.1154590845108032,
      "eval_runtime": 12.9794,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 138
    },
    {
      "epoch": 24.347826086956523,
      "grad_norm": 0.17510361969470978,
      "learning_rate": 9.77293816123866e-06,
      "loss": 1.0322,
      "step": 140
    },
    {
      "epoch": 24.695652173913043,
      "grad_norm": 0.16553597152233124,
      "learning_rate": 9.75886527830587e-06,
      "loss": 1.0659,
      "step": 142
    },
    {
      "epoch": 24.869565217391305,
      "eval_loss": 1.1110743284225464,
      "eval_runtime": 12.9742,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 143
    },
    {
      "epoch": 25.043478260869566,
      "grad_norm": 0.17666411399841309,
      "learning_rate": 9.744380058222483e-06,
      "loss": 1.0226,
      "step": 144
    },
    {
      "epoch": 25.391304347826086,
      "grad_norm": 0.1684177666902542,
      "learning_rate": 9.729483756076436e-06,
      "loss": 1.0355,
      "step": 146
    },
    {
      "epoch": 25.73913043478261,
      "grad_norm": 0.18400514125823975,
      "learning_rate": 9.714177662574316e-06,
      "loss": 1.0637,
      "step": 148
    },
    {
      "epoch": 25.91304347826087,
      "eval_loss": 1.1067678928375244,
      "eval_runtime": 12.9821,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 149
    },
    {
      "epoch": 26.08695652173913,
      "grad_norm": 0.16044579446315765,
      "learning_rate": 9.698463103929542e-06,
      "loss": 1.0691,
      "step": 150
    },
    {
      "epoch": 26.434782608695652,
      "grad_norm": 0.17162466049194336,
      "learning_rate": 9.682341441747446e-06,
      "loss": 1.0148,
      "step": 152
    },
    {
      "epoch": 26.782608695652176,
      "grad_norm": 0.16096869111061096,
      "learning_rate": 9.665814072907293e-06,
      "loss": 0.9979,
      "step": 154
    },
    {
      "epoch": 26.956521739130434,
      "eval_loss": 1.1030863523483276,
      "eval_runtime": 12.9795,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 155
    },
    {
      "epoch": 27.130434782608695,
      "grad_norm": 0.15515439212322235,
      "learning_rate": 9.648882429441258e-06,
      "loss": 1.0792,
      "step": 156
    },
    {
      "epoch": 27.47826086956522,
      "grad_norm": 0.21910764276981354,
      "learning_rate": 9.63154797841033e-06,
      "loss": 0.9741,
      "step": 158
    },
    {
      "epoch": 27.82608695652174,
      "grad_norm": 0.15719705820083618,
      "learning_rate": 9.613812221777212e-06,
      "loss": 1.0495,
      "step": 160
    },
    {
      "epoch": 28.0,
      "eval_loss": 1.0992634296417236,
      "eval_runtime": 12.9823,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 161
    },
    {
      "epoch": 28.17391304347826,
      "grad_norm": 0.17963844537734985,
      "learning_rate": 9.595676696276173e-06,
      "loss": 0.956,
      "step": 162
    },
    {
      "epoch": 28.52173913043478,
      "grad_norm": 0.1683446168899536,
      "learning_rate": 9.577142973279896e-06,
      "loss": 1.0629,
      "step": 164
    },
    {
      "epoch": 28.869565217391305,
      "grad_norm": 0.18944136798381805,
      "learning_rate": 9.55821265866333e-06,
      "loss": 1.0126,
      "step": 166
    },
    {
      "epoch": 28.869565217391305,
      "eval_loss": 1.096557378768921,
      "eval_runtime": 12.9756,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 166
    },
    {
      "epoch": 29.217391304347824,
      "grad_norm": 0.17034175992012024,
      "learning_rate": 9.538887392664544e-06,
      "loss": 1.0652,
      "step": 168
    },
    {
      "epoch": 29.565217391304348,
      "grad_norm": 0.17872415482997894,
      "learning_rate": 9.519168849742603e-06,
      "loss": 0.9865,
      "step": 170
    },
    {
      "epoch": 29.91304347826087,
      "grad_norm": 0.17247214913368225,
      "learning_rate": 9.499058738432492e-06,
      "loss": 0.9884,
      "step": 172
    },
    {
      "epoch": 29.91304347826087,
      "eval_loss": 1.0938386917114258,
      "eval_runtime": 12.9748,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 172
    },
    {
      "epoch": 30.26086956521739,
      "grad_norm": 0.18095757067203522,
      "learning_rate": 9.478558801197065e-06,
      "loss": 1.026,
      "step": 174
    },
    {
      "epoch": 30.608695652173914,
      "grad_norm": 0.17440937459468842,
      "learning_rate": 9.457670814276083e-06,
      "loss": 1.007,
      "step": 176
    },
    {
      "epoch": 30.956521739130434,
      "grad_norm": 0.17576059699058533,
      "learning_rate": 9.436396587532297e-06,
      "loss": 1.0366,
      "step": 178
    },
    {
      "epoch": 30.956521739130434,
      "eval_loss": 1.0909334421157837,
      "eval_runtime": 12.9767,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 178
    },
    {
      "epoch": 31.304347826086957,
      "grad_norm": 0.18143777549266815,
      "learning_rate": 9.414737964294636e-06,
      "loss": 0.9512,
      "step": 180
    },
    {
      "epoch": 31.652173913043477,
      "grad_norm": 0.1847611963748932,
      "learning_rate": 9.392696821198488e-06,
      "loss": 1.0277,
      "step": 182
    },
    {
      "epoch": 32.0,
      "grad_norm": 0.18112817406654358,
      "learning_rate": 9.370275068023097e-06,
      "loss": 1.0434,
      "step": 184
    },
    {
      "epoch": 32.0,
      "eval_loss": 1.0885893106460571,
      "eval_runtime": 12.9743,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 184
    },
    {
      "epoch": 32.34782608695652,
      "grad_norm": 0.2060151845216751,
      "learning_rate": 9.347474647526095e-06,
      "loss": 1.0112,
      "step": 186
    },
    {
      "epoch": 32.69565217391305,
      "grad_norm": 0.18784299492835999,
      "learning_rate": 9.324297535275156e-06,
      "loss": 1.0222,
      "step": 188
    },
    {
      "epoch": 32.869565217391305,
      "eval_loss": 1.086158037185669,
      "eval_runtime": 12.9781,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 189
    },
    {
      "epoch": 33.04347826086956,
      "grad_norm": 0.20884543657302856,
      "learning_rate": 9.30074573947683e-06,
      "loss": 0.9734,
      "step": 190
    },
    {
      "epoch": 33.391304347826086,
      "grad_norm": 0.19983573257923126,
      "learning_rate": 9.276821300802535e-06,
      "loss": 0.9753,
      "step": 192
    },
    {
      "epoch": 33.73913043478261,
      "grad_norm": 0.1889132559299469,
      "learning_rate": 9.25252629221175e-06,
      "loss": 0.9978,
      "step": 194
    },
    {
      "epoch": 33.91304347826087,
      "eval_loss": 1.0842341184616089,
      "eval_runtime": 12.9762,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 195
    },
    {
      "epoch": 34.08695652173913,
      "grad_norm": 0.1903546005487442,
      "learning_rate": 9.227862818772392e-06,
      "loss": 0.993,
      "step": 196
    },
    {
      "epoch": 34.43478260869565,
      "grad_norm": 0.1973000466823578,
      "learning_rate": 9.202833017478421e-06,
      "loss": 0.9973,
      "step": 198
    },
    {
      "epoch": 34.78260869565217,
      "grad_norm": 0.23764756321907043,
      "learning_rate": 9.177439057064684e-06,
      "loss": 0.9593,
      "step": 200
    },
    {
      "epoch": 34.95652173913044,
      "eval_loss": 1.0823968648910522,
      "eval_runtime": 12.9773,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 201
    },
    {
      "epoch": 35.130434782608695,
      "grad_norm": 0.1871621310710907,
      "learning_rate": 9.151683137818989e-06,
      "loss": 1.066,
      "step": 202
    },
    {
      "epoch": 35.47826086956522,
      "grad_norm": 0.20576035976409912,
      "learning_rate": 9.125567491391476e-06,
      "loss": 0.9734,
      "step": 204
    },
    {
      "epoch": 35.82608695652174,
      "grad_norm": 0.1983082890510559,
      "learning_rate": 9.099094380601244e-06,
      "loss": 1.0383,
      "step": 206
    },
    {
      "epoch": 36.0,
      "eval_loss": 1.0803947448730469,
      "eval_runtime": 12.9755,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 207
    },
    {
      "epoch": 36.17391304347826,
      "grad_norm": 0.18446066975593567,
      "learning_rate": 9.072266099240286e-06,
      "loss": 0.9198,
      "step": 208
    },
    {
      "epoch": 36.52173913043478,
      "grad_norm": 0.20637229084968567,
      "learning_rate": 9.045084971874738e-06,
      "loss": 1.0071,
      "step": 210
    },
    {
      "epoch": 36.869565217391305,
      "grad_norm": 0.21963337063789368,
      "learning_rate": 9.017553353643479e-06,
      "loss": 0.9958,
      "step": 212
    },
    {
      "epoch": 36.869565217391305,
      "eval_loss": 1.0792189836502075,
      "eval_runtime": 12.9787,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 212
    },
    {
      "epoch": 37.21739130434783,
      "grad_norm": 0.2046482264995575,
      "learning_rate": 8.989673630054044e-06,
      "loss": 0.9336,
      "step": 214
    },
    {
      "epoch": 37.56521739130435,
      "grad_norm": 0.21577562391757965,
      "learning_rate": 8.961448216775955e-06,
      "loss": 1.01,
      "step": 216
    },
    {
      "epoch": 37.91304347826087,
      "grad_norm": 0.21256496012210846,
      "learning_rate": 8.932879559431392e-06,
      "loss": 0.9774,
      "step": 218
    },
    {
      "epoch": 37.91304347826087,
      "eval_loss": 1.0778032541275024,
      "eval_runtime": 12.9805,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 218
    },
    {
      "epoch": 38.26086956521739,
      "grad_norm": 0.2028392106294632,
      "learning_rate": 8.903970133383297e-06,
      "loss": 0.9966,
      "step": 220
    },
    {
      "epoch": 38.608695652173914,
      "grad_norm": 0.22231891751289368,
      "learning_rate": 8.874722443520898e-06,
      "loss": 0.936,
      "step": 222
    },
    {
      "epoch": 38.95652173913044,
      "grad_norm": 0.23805910348892212,
      "learning_rate": 8.845139024042664e-06,
      "loss": 0.9853,
      "step": 224
    },
    {
      "epoch": 38.95652173913044,
      "eval_loss": 1.0763030052185059,
      "eval_runtime": 12.9799,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 224
    },
    {
      "epoch": 39.30434782608695,
      "grad_norm": 0.21919763088226318,
      "learning_rate": 8.815222438236726e-06,
      "loss": 1.0162,
      "step": 226
    },
    {
      "epoch": 39.65217391304348,
      "grad_norm": 0.24376323819160461,
      "learning_rate": 8.784975278258783e-06,
      "loss": 0.9777,
      "step": 228
    },
    {
      "epoch": 40.0,
      "grad_norm": 0.2683652639389038,
      "learning_rate": 8.754400164907496e-06,
      "loss": 0.9241,
      "step": 230
    },
    {
      "epoch": 40.0,
      "eval_loss": 1.07473886013031,
      "eval_runtime": 12.9776,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 230
    },
    {
      "epoch": 40.34782608695652,
      "grad_norm": 0.23253561556339264,
      "learning_rate": 8.723499747397415e-06,
      "loss": 0.9221,
      "step": 232
    },
    {
      "epoch": 40.69565217391305,
      "grad_norm": 0.2230878323316574,
      "learning_rate": 8.692276703129421e-06,
      "loss": 1.0387,
      "step": 234
    },
    {
      "epoch": 40.869565217391305,
      "eval_loss": 1.0742899179458618,
      "eval_runtime": 12.9772,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 235
    },
    {
      "epoch": 41.04347826086956,
      "grad_norm": 0.23267078399658203,
      "learning_rate": 8.660733737458751e-06,
      "loss": 0.9551,
      "step": 236
    },
    {
      "epoch": 41.391304347826086,
      "grad_norm": 0.25790396332740784,
      "learning_rate": 8.628873583460593e-06,
      "loss": 0.9623,
      "step": 238
    },
    {
      "epoch": 41.73913043478261,
      "grad_norm": 0.23886793851852417,
      "learning_rate": 8.596699001693257e-06,
      "loss": 0.9616,
      "step": 240
    },
    {
      "epoch": 41.91304347826087,
      "eval_loss": 1.073310375213623,
      "eval_runtime": 12.9821,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 241
    },
    {
      "epoch": 42.08695652173913,
      "grad_norm": 0.24948331713676453,
      "learning_rate": 8.564212779959003e-06,
      "loss": 0.9294,
      "step": 242
    },
    {
      "epoch": 42.43478260869565,
      "grad_norm": 0.24044832587242126,
      "learning_rate": 8.531417733062476e-06,
      "loss": 0.9579,
      "step": 244
    },
    {
      "epoch": 42.78260869565217,
      "grad_norm": 0.2429089993238449,
      "learning_rate": 8.498316702566828e-06,
      "loss": 0.9909,
      "step": 246
    },
    {
      "epoch": 42.95652173913044,
      "eval_loss": 1.0724002122879028,
      "eval_runtime": 12.9815,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 247
    },
    {
      "epoch": 43.130434782608695,
      "grad_norm": 0.25010445713996887,
      "learning_rate": 8.464912556547486e-06,
      "loss": 0.9609,
      "step": 248
    },
    {
      "epoch": 43.47826086956522,
      "grad_norm": 0.25847363471984863,
      "learning_rate": 8.43120818934367e-06,
      "loss": 0.9271,
      "step": 250
    },
    {
      "epoch": 43.82608695652174,
      "grad_norm": 0.25236183404922485,
      "learning_rate": 8.397206521307584e-06,
      "loss": 0.9055,
      "step": 252
    },
    {
      "epoch": 44.0,
      "eval_loss": 1.0719984769821167,
      "eval_runtime": 12.9768,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 253
    },
    {
      "epoch": 44.17391304347826,
      "grad_norm": 0.2587444484233856,
      "learning_rate": 8.362910498551402e-06,
      "loss": 0.9453,
      "step": 254
    },
    {
      "epoch": 44.52173913043478,
      "grad_norm": 0.2820061147212982,
      "learning_rate": 8.328323092691985e-06,
      "loss": 0.952,
      "step": 256
    },
    {
      "epoch": 44.869565217391305,
      "grad_norm": 0.2769736349582672,
      "learning_rate": 8.293447300593402e-06,
      "loss": 1.0025,
      "step": 258
    },
    {
      "epoch": 44.869565217391305,
      "eval_loss": 1.0721515417099,
      "eval_runtime": 12.979,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 258
    },
    {
      "epoch": 45.21739130434783,
      "grad_norm": 0.2502345144748688,
      "learning_rate": 8.258286144107277e-06,
      "loss": 0.9481,
      "step": 260
    },
    {
      "epoch": 45.56521739130435,
      "grad_norm": 0.2711241841316223,
      "learning_rate": 8.222842669810936e-06,
      "loss": 0.9477,
      "step": 262
    },
    {
      "epoch": 45.91304347826087,
      "grad_norm": 0.25015076994895935,
      "learning_rate": 8.18711994874345e-06,
      "loss": 0.9325,
      "step": 264
    },
    {
      "epoch": 45.91304347826087,
      "eval_loss": 1.0710887908935547,
      "eval_runtime": 12.9806,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 264
    },
    {
      "epoch": 46.26086956521739,
      "grad_norm": 0.3114207088947296,
      "learning_rate": 8.151121076139534e-06,
      "loss": 0.8994,
      "step": 266
    },
    {
      "epoch": 46.608695652173914,
      "grad_norm": 0.2907244861125946,
      "learning_rate": 8.11484917116136e-06,
      "loss": 1.0092,
      "step": 268
    },
    {
      "epoch": 46.95652173913044,
      "grad_norm": 0.3372167646884918,
      "learning_rate": 8.078307376628292e-06,
      "loss": 0.8921,
      "step": 270
    },
    {
      "epoch": 46.95652173913044,
      "eval_loss": 1.0723286867141724,
      "eval_runtime": 12.9797,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 270
    },
    {
      "epoch": 47.30434782608695,
      "grad_norm": 0.32444846630096436,
      "learning_rate": 8.041498858744572e-06,
      "loss": 0.954,
      "step": 272
    },
    {
      "epoch": 47.65217391304348,
      "grad_norm": 0.2917410731315613,
      "learning_rate": 8.004426806824985e-06,
      "loss": 0.9444,
      "step": 274
    },
    {
      "epoch": 48.0,
      "grad_norm": 0.3161114454269409,
      "learning_rate": 7.967094433018508e-06,
      "loss": 0.9079,
      "step": 276
    },
    {
      "epoch": 48.0,
      "eval_loss": 1.0710123777389526,
      "eval_runtime": 12.9764,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 276
    },
    {
      "epoch": 48.34782608695652,
      "grad_norm": 0.27982279658317566,
      "learning_rate": 7.929504972030003e-06,
      "loss": 0.8982,
      "step": 278
    },
    {
      "epoch": 48.69565217391305,
      "grad_norm": 0.29784122109413147,
      "learning_rate": 7.891661680839932e-06,
      "loss": 0.9615,
      "step": 280
    },
    {
      "epoch": 48.869565217391305,
      "eval_loss": 1.07285475730896,
      "eval_runtime": 12.9818,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 281
    },
    {
      "epoch": 49.04347826086956,
      "grad_norm": 0.3300091326236725,
      "learning_rate": 7.85356783842216e-06,
      "loss": 0.8969,
      "step": 282
    },
    {
      "epoch": 49.391304347826086,
      "grad_norm": 0.3034118413925171,
      "learning_rate": 7.815226745459831e-06,
      "loss": 0.9267,
      "step": 284
    },
    {
      "epoch": 49.73913043478261,
      "grad_norm": 0.28807440400123596,
      "learning_rate": 7.776641724059398e-06,
      "loss": 0.9517,
      "step": 286
    },
    {
      "epoch": 49.91304347826087,
      "eval_loss": 1.0717887878417969,
      "eval_runtime": 12.9755,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 287
    },
    {
      "epoch": 50.08695652173913,
      "grad_norm": 0.34060779213905334,
      "learning_rate": 7.737816117462752e-06,
      "loss": 0.9092,
      "step": 288
    },
    {
      "epoch": 50.43478260869565,
      "grad_norm": 0.28578662872314453,
      "learning_rate": 7.698753289757565e-06,
      "loss": 0.9824,
      "step": 290
    },
    {
      "epoch": 50.78260869565217,
      "grad_norm": 0.316270112991333,
      "learning_rate": 7.65945662558579e-06,
      "loss": 0.8619,
      "step": 292
    },
    {
      "epoch": 50.95652173913044,
      "eval_loss": 1.0729678869247437,
      "eval_runtime": 12.9784,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 293
    },
    {
      "epoch": 51.130434782608695,
      "grad_norm": 0.2928197681903839,
      "learning_rate": 7.619929529850397e-06,
      "loss": 0.946,
      "step": 294
    },
    {
      "epoch": 51.47826086956522,
      "grad_norm": 0.30175477266311646,
      "learning_rate": 7.580175427420358e-06,
      "loss": 0.9319,
      "step": 296
    },
    {
      "epoch": 51.82608695652174,
      "grad_norm": 0.3955518305301666,
      "learning_rate": 7.54019776283389e-06,
      "loss": 0.8894,
      "step": 298
    },
    {
      "epoch": 52.0,
      "eval_loss": 1.0739282369613647,
      "eval_runtime": 12.9857,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 299
    },
    {
      "epoch": 52.17391304347826,
      "grad_norm": 0.33545202016830444,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.8967,
      "step": 300
    },
    {
      "epoch": 52.52173913043478,
      "grad_norm": 0.3249565362930298,
      "learning_rate": 7.459585621898353e-06,
      "loss": 0.9514,
      "step": 302
    },
    {
      "epoch": 52.869565217391305,
      "grad_norm": 0.3969457745552063,
      "learning_rate": 7.418958130277483e-06,
      "loss": 0.8389,
      "step": 304
    },
    {
      "epoch": 52.869565217391305,
      "eval_loss": 1.0741795301437378,
      "eval_runtime": 12.9752,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 304
    },
    {
      "epoch": 53.21739130434783,
      "grad_norm": 0.3565354347229004,
      "learning_rate": 7.378121045351378e-06,
      "loss": 0.882,
      "step": 306
    },
    {
      "epoch": 53.56521739130435,
      "grad_norm": 0.41273507475852966,
      "learning_rate": 7.337077905494472e-06,
      "loss": 0.8992,
      "step": 308
    },
    {
      "epoch": 53.91304347826087,
      "grad_norm": 0.3917119801044464,
      "learning_rate": 7.295832266935059e-06,
      "loss": 0.9032,
      "step": 310
    },
    {
      "epoch": 53.91304347826087,
      "eval_loss": 1.0749919414520264,
      "eval_runtime": 12.9751,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 310
    },
    {
      "epoch": 54.26086956521739,
      "grad_norm": 0.34160563349723816,
      "learning_rate": 7.254387703447154e-06,
      "loss": 0.9499,
      "step": 312
    },
    {
      "epoch": 54.608695652173914,
      "grad_norm": 0.4153737723827362,
      "learning_rate": 7.212747806040845e-06,
      "loss": 0.9246,
      "step": 314
    },
    {
      "epoch": 54.95652173913044,
      "grad_norm": 0.3735916316509247,
      "learning_rate": 7.170916182651141e-06,
      "loss": 0.9015,
      "step": 316
    },
    {
      "epoch": 54.95652173913044,
      "eval_loss": 1.0760287046432495,
      "eval_runtime": 12.9763,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 316
    },
    {
      "epoch": 54.95652173913044,
      "step": 316,
      "total_flos": 2.4451647665917133e+17,
      "train_loss": 1.137867835975146,
      "train_runtime": 8799.2233,
      "train_samples_per_second": 0.784,
      "train_steps_per_second": 0.085
    }
  ],
  "logging_steps": 2,
  "max_steps": 750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 150,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 7,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4451647665917133e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}