{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4,
  "eval_steps": 500,
  "global_step": 160,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "Batch Mean": -3.22894287109375,
      "accuracy": 0.5625,
      "epoch": 0,
      "step": 0
    },
    {
      "epoch": 0.0025,
      "grad_norm": 5.802114963531494,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 0.6948,
      "step": 1
    },
    {
      "Batch Mean": -3.20587158203125,
      "accuracy": 0.4921875,
      "epoch": 0.0025,
      "step": 1
    },
    {
      "epoch": 0.005,
      "grad_norm": 7.483729362487793,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.7075,
      "step": 2
    },
    {
      "Batch Mean": -3.23907470703125,
      "accuracy": 0.453125,
      "epoch": 0.005,
      "step": 2
    },
    {
      "epoch": 0.0075,
      "grad_norm": 6.9934587478637695,
      "learning_rate": 7.5e-07,
      "loss": 0.6985,
      "step": 3
    },
    {
      "Batch Mean": -3.25433349609375,
      "accuracy": 0.4609375,
      "epoch": 0.0075,
      "step": 3
    },
    {
      "epoch": 0.01,
      "grad_norm": 8.51505184173584,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.71,
      "step": 4
    },
    {
      "Batch Mean": -3.229034423828125,
      "accuracy": 0.546875,
      "epoch": 0.01,
      "step": 4
    },
    {
      "epoch": 0.0125,
      "grad_norm": 6.16685676574707,
      "learning_rate": 1.25e-06,
      "loss": 0.6887,
      "step": 5
    },
    {
      "Batch Mean": -3.19061279296875,
      "accuracy": 0.453125,
      "epoch": 0.0125,
      "step": 5
    },
    {
      "epoch": 0.015,
      "grad_norm": 9.016836166381836,
      "learning_rate": 1.5e-06,
      "loss": 0.7021,
      "step": 6
    },
    {
      "Batch Mean": -3.174072265625,
      "accuracy": 0.5859375,
      "epoch": 0.015,
      "step": 6
    },
    {
      "epoch": 0.0175,
      "grad_norm": 8.049066543579102,
      "learning_rate": 1.75e-06,
      "loss": 0.6692,
      "step": 7
    },
    {
      "Batch Mean": -3.18316650390625,
      "accuracy": 0.4296875,
      "epoch": 0.0175,
      "step": 7
    },
    {
      "epoch": 0.02,
      "grad_norm": 6.920315265655518,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.6972,
      "step": 8
    },
    {
      "Batch Mean": -3.1539306640625,
      "accuracy": 0.546875,
      "epoch": 0.02,
      "step": 8
    },
    {
      "epoch": 0.0225,
      "grad_norm": 11.55068302154541,
      "learning_rate": 2.25e-06,
      "loss": 0.6977,
      "step": 9
    },
    {
      "Batch Mean": -3.0648651123046875,
      "accuracy": 0.578125,
      "epoch": 0.0225,
      "step": 9
    },
    {
      "epoch": 0.025,
      "grad_norm": 8.16010570526123,
      "learning_rate": 2.5e-06,
      "loss": 0.6914,
      "step": 10
    },
    {
      "Batch Mean": -2.897817611694336,
      "accuracy": 0.5703125,
      "epoch": 0.025,
      "step": 10
    },
    {
      "epoch": 0.0275,
      "grad_norm": 11.839621543884277,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.7092,
      "step": 11
    },
    {
      "Batch Mean": -2.694028377532959,
      "accuracy": 0.5625,
      "epoch": 0.0275,
      "step": 11
    },
    {
      "epoch": 0.03,
      "grad_norm": 15.166038513183594,
      "learning_rate": 3e-06,
      "loss": 0.7144,
      "step": 12
    },
    {
      "Batch Mean": -2.681365966796875,
      "accuracy": 0.625,
      "epoch": 0.03,
      "step": 12
    },
    {
      "epoch": 0.0325,
      "grad_norm": 8.728507995605469,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.6493,
      "step": 13
    },
    {
      "Batch Mean": -2.1446685791015625,
      "accuracy": 0.6875,
      "epoch": 0.0325,
      "step": 13
    },
    {
      "epoch": 0.035,
      "grad_norm": 8.090866088867188,
      "learning_rate": 3.5e-06,
      "loss": 0.6339,
      "step": 14
    },
    {
      "Batch Mean": -1.779296875,
      "accuracy": 0.703125,
      "epoch": 0.035,
      "step": 14
    },
    {
      "epoch": 0.0375,
      "grad_norm": 6.903839588165283,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.5809,
      "step": 15
    },
    {
      "Batch Mean": -1.4260149002075195,
      "accuracy": 0.6953125,
      "epoch": 0.0375,
      "step": 15
    },
    {
      "epoch": 0.04,
      "grad_norm": 7.504371166229248,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.5785,
      "step": 16
    },
    {
      "Batch Mean": -1.3612947463989258,
      "accuracy": 0.734375,
      "epoch": 0.04,
      "step": 16
    },
    {
      "epoch": 0.0425,
      "grad_norm": 8.880864143371582,
      "learning_rate": 4.25e-06,
      "loss": 0.6355,
      "step": 17
    },
    {
      "Batch Mean": -1.0974332094192505,
      "accuracy": 0.671875,
      "epoch": 0.0425,
      "step": 17
    },
    {
      "epoch": 0.045,
      "grad_norm": 7.95067834854126,
      "learning_rate": 4.5e-06,
      "loss": 0.5865,
      "step": 18
    },
    {
      "Batch Mean": -1.0067845582962036,
      "accuracy": 0.6796875,
      "epoch": 0.045,
      "step": 18
    },
    {
      "epoch": 0.0475,
      "grad_norm": 11.53207778930664,
      "learning_rate": 4.75e-06,
      "loss": 0.6069,
      "step": 19
    },
    {
      "Batch Mean": -1.4595129489898682,
      "accuracy": 0.6640625,
      "epoch": 0.0475,
      "step": 19
    },
    {
      "epoch": 0.05,
      "grad_norm": 9.007086753845215,
      "learning_rate": 5e-06,
      "loss": 0.5642,
      "step": 20
    },
    {
      "Batch Mean": -2.0267333984375,
      "accuracy": 0.625,
      "epoch": 0.05,
      "step": 20
    },
    {
      "epoch": 0.0525,
      "grad_norm": 10.302614212036133,
      "learning_rate": 4.986842105263158e-06,
      "loss": 0.6487,
      "step": 21
    },
    {
      "Batch Mean": -2.4782352447509766,
      "accuracy": 0.765625,
      "epoch": 0.0525,
      "step": 21
    },
    {
      "epoch": 0.055,
      "grad_norm": 9.321782112121582,
      "learning_rate": 4.973684210526316e-06,
      "loss": 0.5038,
      "step": 22
    },
    {
      "Batch Mean": -2.5980658531188965,
      "accuracy": 0.6796875,
      "epoch": 0.055,
      "step": 22
    },
    {
      "epoch": 0.0575,
      "grad_norm": 8.676246643066406,
      "learning_rate": 4.960526315789474e-06,
      "loss": 0.5891,
      "step": 23
    },
    {
      "Batch Mean": -2.863405227661133,
      "accuracy": 0.59375,
      "epoch": 0.0575,
      "step": 23
    },
    {
      "epoch": 0.06,
      "grad_norm": 9.5335111618042,
      "learning_rate": 4.947368421052632e-06,
      "loss": 0.6704,
      "step": 24
    },
    {
      "Batch Mean": -2.9449462890625,
      "accuracy": 0.6796875,
      "epoch": 0.06,
      "step": 24
    },
    {
      "epoch": 0.0625,
      "grad_norm": 6.348640441894531,
      "learning_rate": 4.9342105263157895e-06,
      "loss": 0.5517,
      "step": 25
    },
    {
      "Batch Mean": -2.93194580078125,
      "accuracy": 0.6796875,
      "epoch": 0.0625,
      "step": 25
    },
    {
      "epoch": 0.065,
      "grad_norm": 7.16481876373291,
      "learning_rate": 4.921052631578948e-06,
      "loss": 0.554,
      "step": 26
    },
    {
      "Batch Mean": -2.9799575805664062,
      "accuracy": 0.78125,
      "epoch": 0.065,
      "step": 26
    },
    {
      "epoch": 0.0675,
      "grad_norm": 6.40033483505249,
      "learning_rate": 4.907894736842106e-06,
      "loss": 0.5142,
      "step": 27
    },
    {
      "Batch Mean": -3.10003662109375,
      "accuracy": 0.671875,
      "epoch": 0.0675,
      "step": 27
    },
    {
      "epoch": 0.07,
      "grad_norm": 6.684910774230957,
      "learning_rate": 4.894736842105264e-06,
      "loss": 0.5953,
      "step": 28
    },
    {
      "Batch Mean": -3.2201080322265625,
      "accuracy": 0.6796875,
      "epoch": 0.07,
      "step": 28
    },
    {
      "epoch": 0.0725,
      "grad_norm": 6.370337009429932,
      "learning_rate": 4.881578947368422e-06,
      "loss": 0.5572,
      "step": 29
    },
    {
      "Batch Mean": -3.1351852416992188,
      "accuracy": 0.7421875,
      "epoch": 0.0725,
      "step": 29
    },
    {
      "epoch": 0.075,
      "grad_norm": 6.65242338180542,
      "learning_rate": 4.8684210526315795e-06,
      "loss": 0.5418,
      "step": 30
    },
    {
      "Batch Mean": -3.2759580612182617,
      "accuracy": 0.7265625,
      "epoch": 0.075,
      "step": 30
    },
    {
      "epoch": 0.0775,
      "grad_norm": 7.722072124481201,
      "learning_rate": 4.855263157894737e-06,
      "loss": 0.5225,
      "step": 31
    },
    {
      "Batch Mean": -3.0810060501098633,
      "accuracy": 0.7109375,
      "epoch": 0.0775,
      "step": 31
    },
    {
      "epoch": 0.08,
      "grad_norm": 8.74831771850586,
      "learning_rate": 4.842105263157895e-06,
      "loss": 0.5407,
      "step": 32
    },
    {
      "Batch Mean": -2.9466419219970703,
      "accuracy": 0.71875,
      "epoch": 0.08,
      "step": 32
    },
    {
      "epoch": 0.0825,
      "grad_norm": 8.841214179992676,
      "learning_rate": 4.828947368421053e-06,
      "loss": 0.5603,
      "step": 33
    },
    {
      "Batch Mean": -3.164520263671875,
      "accuracy": 0.671875,
      "epoch": 0.0825,
      "step": 33
    },
    {
      "epoch": 0.085,
      "grad_norm": 8.782054901123047,
      "learning_rate": 4.815789473684211e-06,
      "loss": 0.5638,
      "step": 34
    },
    {
      "Batch Mean": -3.0882205963134766,
      "accuracy": 0.7421875,
      "epoch": 0.085,
      "step": 34
    },
    {
      "epoch": 0.0875,
      "grad_norm": 7.124765872955322,
      "learning_rate": 4.802631578947369e-06,
      "loss": 0.4709,
      "step": 35
    },
    {
      "Batch Mean": -3.3660800457000732,
      "accuracy": 0.7734375,
      "epoch": 0.0875,
      "step": 35
    },
    {
      "epoch": 0.09,
      "grad_norm": 8.432646751403809,
      "learning_rate": 4.789473684210527e-06,
      "loss": 0.5142,
      "step": 36
    },
    {
      "Batch Mean": -3.3540000915527344,
      "accuracy": 0.65625,
      "epoch": 0.09,
      "step": 36
    },
    {
      "epoch": 0.0925,
      "grad_norm": 8.90056037902832,
      "learning_rate": 4.7763157894736844e-06,
      "loss": 0.5726,
      "step": 37
    },
    {
      "Batch Mean": -3.630018949508667,
      "accuracy": 0.7578125,
      "epoch": 0.0925,
      "step": 37
    },
    {
      "epoch": 0.095,
      "grad_norm": 10.051451683044434,
      "learning_rate": 4.763157894736842e-06,
      "loss": 0.5455,
      "step": 38
    },
    {
      "Batch Mean": -3.8007164001464844,
      "accuracy": 0.671875,
      "epoch": 0.095,
      "step": 38
    },
    {
      "epoch": 0.0975,
      "grad_norm": 8.25788688659668,
      "learning_rate": 4.75e-06,
      "loss": 0.6009,
      "step": 39
    },
    {
      "Batch Mean": -3.8345565795898438,
      "accuracy": 0.7421875,
      "epoch": 0.0975,
      "step": 39
    },
    {
      "epoch": 0.1,
      "grad_norm": 6.112834453582764,
      "learning_rate": 4.736842105263158e-06,
      "loss": 0.4995,
      "step": 40
    },
    {
      "Batch Mean": -3.868865966796875,
      "accuracy": 0.765625,
      "epoch": 0.1,
      "step": 40
    },
    {
      "epoch": 0.1025,
      "grad_norm": 6.251713752746582,
      "learning_rate": 4.723684210526316e-06,
      "loss": 0.5117,
      "step": 41
    },
    {
      "Batch Mean": -4.0014801025390625,
      "accuracy": 0.7109375,
      "epoch": 0.1025,
      "step": 41
    },
    {
      "epoch": 0.105,
      "grad_norm": 6.486876487731934,
      "learning_rate": 4.710526315789474e-06,
      "loss": 0.5281,
      "step": 42
    },
    {
      "Batch Mean": -3.8963470458984375,
      "accuracy": 0.71875,
      "epoch": 0.105,
      "step": 42
    },
    {
      "epoch": 0.1075,
      "grad_norm": 7.075796604156494,
      "learning_rate": 4.697368421052632e-06,
      "loss": 0.5201,
      "step": 43
    },
    {
      "Batch Mean": -3.6251320838928223,
      "accuracy": 0.765625,
      "epoch": 0.1075,
      "step": 43
    },
    {
      "epoch": 0.11,
      "grad_norm": 6.587506294250488,
      "learning_rate": 4.68421052631579e-06,
      "loss": 0.453,
      "step": 44
    },
    {
      "Batch Mean": -3.119325637817383,
      "accuracy": 0.75,
      "epoch": 0.11,
      "step": 44
    },
    {
      "epoch": 0.1125,
      "grad_norm": 6.736975193023682,
      "learning_rate": 4.671052631578948e-06,
      "loss": 0.4731,
      "step": 45
    },
    {
      "Batch Mean": -2.6836140155792236,
      "accuracy": 0.7890625,
      "epoch": 0.1125,
      "step": 45
    },
    {
      "epoch": 0.115,
      "grad_norm": 7.933563709259033,
      "learning_rate": 4.657894736842106e-06,
      "loss": 0.4237,
      "step": 46
    },
    {
      "Batch Mean": -2.348551034927368,
      "accuracy": 0.7109375,
      "epoch": 0.115,
      "step": 46
    },
    {
      "epoch": 0.1175,
      "grad_norm": 12.173978805541992,
      "learning_rate": 4.6447368421052635e-06,
      "loss": 0.562,
      "step": 47
    },
    {
      "Batch Mean": -2.281805992126465,
      "accuracy": 0.8125,
      "epoch": 0.1175,
      "step": 47
    },
    {
      "epoch": 0.12,
      "grad_norm": 8.108612060546875,
      "learning_rate": 4.631578947368421e-06,
      "loss": 0.4135,
      "step": 48
    },
    {
      "Batch Mean": -1.5221551656723022,
      "accuracy": 0.7265625,
      "epoch": 0.12,
      "step": 48
    },
    {
      "epoch": 0.1225,
      "grad_norm": 9.601967811584473,
      "learning_rate": 4.618421052631579e-06,
      "loss": 0.5164,
      "step": 49
    },
    {
      "Batch Mean": -1.7016830444335938,
      "accuracy": 0.7109375,
      "epoch": 0.1225,
      "step": 49
    },
    {
      "epoch": 0.125,
      "grad_norm": 12.160585403442383,
      "learning_rate": 4.605263157894737e-06,
      "loss": 0.5847,
      "step": 50
    },
    {
      "Batch Mean": -1.818105697631836,
      "accuracy": 0.7265625,
      "epoch": 0.125,
      "step": 50
    },
    {
      "epoch": 0.1275,
      "grad_norm": 10.746450424194336,
      "learning_rate": 4.592105263157895e-06,
      "loss": 0.512,
      "step": 51
    },
    {
      "Batch Mean": -1.5451364517211914,
      "accuracy": 0.734375,
      "epoch": 0.1275,
      "step": 51
    },
    {
      "epoch": 0.13,
      "grad_norm": 8.993597984313965,
      "learning_rate": 4.578947368421053e-06,
      "loss": 0.4932,
      "step": 52
    },
    {
      "Batch Mean": -1.592740535736084,
      "accuracy": 0.734375,
      "epoch": 0.13,
      "step": 52
    },
    {
      "epoch": 0.1325,
      "grad_norm": 11.777365684509277,
      "learning_rate": 4.565789473684211e-06,
      "loss": 0.5973,
      "step": 53
    },
    {
      "Batch Mean": -1.7593857049942017,
      "accuracy": 0.75,
      "epoch": 0.1325,
      "step": 53
    },
    {
      "epoch": 0.135,
      "grad_norm": 8.874958992004395,
      "learning_rate": 4.552631578947369e-06,
      "loss": 0.4976,
      "step": 54
    },
    {
      "Batch Mean": -1.6973432302474976,
      "accuracy": 0.703125,
      "epoch": 0.135,
      "step": 54
    },
    {
      "epoch": 0.1375,
      "grad_norm": 7.982842922210693,
      "learning_rate": 4.539473684210527e-06,
      "loss": 0.523,
      "step": 55
    },
    {
      "Batch Mean": -1.5194091796875,
      "accuracy": 0.7578125,
      "epoch": 0.1375,
      "step": 55
    },
    {
      "epoch": 0.14,
      "grad_norm": 7.006033897399902,
      "learning_rate": 4.526315789473685e-06,
      "loss": 0.4739,
      "step": 56
    },
    {
      "Batch Mean": -1.8582556247711182,
      "accuracy": 0.6640625,
      "epoch": 0.14,
      "step": 56
    },
    {
      "epoch": 0.1425,
      "grad_norm": 10.20836067199707,
      "learning_rate": 4.513157894736843e-06,
      "loss": 0.5806,
      "step": 57
    },
    {
      "Batch Mean": -1.5920772552490234,
      "accuracy": 0.7265625,
      "epoch": 0.1425,
      "step": 57
    },
    {
      "epoch": 0.145,
      "grad_norm": 7.661640167236328,
      "learning_rate": 4.5e-06,
      "loss": 0.542,
      "step": 58
    },
    {
      "Batch Mean": -1.8221396207809448,
      "accuracy": 0.7265625,
      "epoch": 0.145,
      "step": 58
    },
    {
      "epoch": 0.1475,
      "grad_norm": 5.577967166900635,
      "learning_rate": 4.4868421052631584e-06,
      "loss": 0.484,
      "step": 59
    },
    {
      "Batch Mean": -1.7805979251861572,
      "accuracy": 0.734375,
      "epoch": 0.1475,
      "step": 59
    },
    {
      "epoch": 0.15,
      "grad_norm": 6.151084899902344,
      "learning_rate": 4.473684210526316e-06,
      "loss": 0.5184,
      "step": 60
    },
    {
      "Batch Mean": -1.9499595165252686,
      "accuracy": 0.78125,
      "epoch": 0.15,
      "step": 60
    },
    {
      "epoch": 0.1525,
      "grad_norm": 6.0847954750061035,
      "learning_rate": 4.460526315789474e-06,
      "loss": 0.4684,
      "step": 61
    },
    {
      "Batch Mean": -1.6745810508728027,
      "accuracy": 0.71875,
      "epoch": 0.1525,
      "step": 61
    },
    {
      "epoch": 0.155,
      "grad_norm": 5.9063334465026855,
      "learning_rate": 4.447368421052632e-06,
      "loss": 0.4899,
      "step": 62
    },
    {
      "Batch Mean": -1.7260775566101074,
      "accuracy": 0.7734375,
      "epoch": 0.155,
      "step": 62
    },
    {
      "epoch": 0.1575,
      "grad_norm": 6.408818244934082,
      "learning_rate": 4.43421052631579e-06,
      "loss": 0.4802,
      "step": 63
    },
    {
      "Batch Mean": -1.6710443496704102,
      "accuracy": 0.7265625,
      "epoch": 0.1575,
      "step": 63
    },
    {
      "epoch": 0.16,
      "grad_norm": 6.913627624511719,
      "learning_rate": 4.4210526315789476e-06,
      "loss": 0.4864,
      "step": 64
    },
    {
      "Batch Mean": -1.5562989711761475,
      "accuracy": 0.7890625,
      "epoch": 0.16,
      "step": 64
    },
    {
      "epoch": 0.1625,
      "grad_norm": 6.550841808319092,
      "learning_rate": 4.407894736842105e-06,
      "loss": 0.5027,
      "step": 65
    },
    {
      "Batch Mean": -1.1634740829467773,
      "accuracy": 0.6875,
      "epoch": 0.1625,
      "step": 65
    },
    {
      "epoch": 0.165,
      "grad_norm": 8.442750930786133,
      "learning_rate": 4.394736842105263e-06,
      "loss": 0.5376,
      "step": 66
    },
    {
      "Batch Mean": -1.1364693641662598,
      "accuracy": 0.8046875,
      "epoch": 0.165,
      "step": 66
    },
    {
      "epoch": 0.1675,
      "grad_norm": 7.907973289489746,
      "learning_rate": 4.381578947368421e-06,
      "loss": 0.4159,
      "step": 67
    },
    {
      "Batch Mean": -0.5613183975219727,
      "accuracy": 0.7734375,
      "epoch": 0.1675,
      "step": 67
    },
    {
      "epoch": 0.17,
      "grad_norm": 8.844648361206055,
      "learning_rate": 4.368421052631579e-06,
      "loss": 0.4656,
      "step": 68
    },
    {
      "Batch Mean": -0.8619356155395508,
      "accuracy": 0.703125,
      "epoch": 0.17,
      "step": 68
    },
    {
      "epoch": 0.1725,
      "grad_norm": 9.813117027282715,
      "learning_rate": 4.3552631578947375e-06,
      "loss": 0.4931,
      "step": 69
    },
    {
      "Batch Mean": -0.7304730415344238,
      "accuracy": 0.7265625,
      "epoch": 0.1725,
      "step": 69
    },
    {
      "epoch": 0.175,
      "grad_norm": 9.341872215270996,
      "learning_rate": 4.342105263157895e-06,
      "loss": 0.5239,
      "step": 70
    },
    {
      "Batch Mean": -0.6615705490112305,
      "accuracy": 0.7109375,
      "epoch": 0.175,
      "step": 70
    },
    {
      "epoch": 0.1775,
      "grad_norm": 9.673095703125,
      "learning_rate": 4.328947368421053e-06,
      "loss": 0.5137,
      "step": 71
    },
    {
      "Batch Mean": -0.551055908203125,
      "accuracy": 0.765625,
      "epoch": 0.1775,
      "step": 71
    },
    {
      "epoch": 0.18,
      "grad_norm": 8.690629005432129,
      "learning_rate": 4.315789473684211e-06,
      "loss": 0.4509,
      "step": 72
    },
    {
      "Batch Mean": -0.6300144195556641,
      "accuracy": 0.8515625,
      "epoch": 0.18,
      "step": 72
    },
    {
      "epoch": 0.1825,
      "grad_norm": 6.654637336730957,
      "learning_rate": 4.302631578947369e-06,
      "loss": 0.3857,
      "step": 73
    },
    {
      "Batch Mean": -0.6115929484367371,
      "accuracy": 0.7734375,
      "epoch": 0.1825,
      "step": 73
    },
    {
      "epoch": 0.185,
      "grad_norm": 7.764965534210205,
      "learning_rate": 4.289473684210527e-06,
      "loss": 0.4766,
      "step": 74
    },
    {
      "Batch Mean": -0.9064078330993652,
      "accuracy": 0.7734375,
      "epoch": 0.185,
      "step": 74
    },
    {
      "epoch": 0.1875,
      "grad_norm": 7.712812423706055,
      "learning_rate": 4.276315789473684e-06,
      "loss": 0.4238,
      "step": 75
    },
    {
      "Batch Mean": -0.5394480228424072,
      "accuracy": 0.8203125,
      "epoch": 0.1875,
      "step": 75
    },
    {
      "epoch": 0.19,
      "grad_norm": 6.678032398223877,
      "learning_rate": 4.2631578947368425e-06,
      "loss": 0.3955,
      "step": 76
    },
    {
      "Batch Mean": -0.751708447933197,
      "accuracy": 0.7421875,
      "epoch": 0.19,
      "step": 76
    },
    {
      "epoch": 0.1925,
      "grad_norm": 7.722261428833008,
      "learning_rate": 4.25e-06,
      "loss": 0.4607,
      "step": 77
    },
    {
      "Batch Mean": -0.47676777839660645,
      "accuracy": 0.78125,
      "epoch": 0.1925,
      "step": 77
    },
    {
      "epoch": 0.195,
      "grad_norm": 7.482136249542236,
      "learning_rate": 4.236842105263158e-06,
      "loss": 0.4523,
      "step": 78
    },
    {
      "Batch Mean": -0.44623780250549316,
      "accuracy": 0.7109375,
      "epoch": 0.195,
      "step": 78
    },
    {
      "epoch": 0.1975,
      "grad_norm": 8.689245223999023,
      "learning_rate": 4.223684210526316e-06,
      "loss": 0.5507,
      "step": 79
    },
    {
      "Batch Mean": -0.44862329959869385,
      "accuracy": 0.7890625,
      "epoch": 0.1975,
      "step": 79
    },
    {
      "epoch": 0.2,
      "grad_norm": 8.543317794799805,
      "learning_rate": 4.210526315789474e-06,
      "loss": 0.481,
      "step": 80
    },
    {
      "Batch Mean": -0.8662099838256836,
      "accuracy": 0.7734375,
      "epoch": 0.2,
      "step": 80
    },
    {
      "epoch": 0.2025,
      "grad_norm": 8.948282241821289,
      "learning_rate": 4.197368421052632e-06,
      "loss": 0.5276,
      "step": 81
    },
    {
      "Batch Mean": -1.0495636463165283,
      "accuracy": 0.7109375,
      "epoch": 0.2025,
      "step": 81
    },
    {
      "epoch": 0.205,
      "grad_norm": 7.718348026275635,
      "learning_rate": 4.18421052631579e-06,
      "loss": 0.4894,
      "step": 82
    },
    {
      "Batch Mean": -0.7387936115264893,
      "accuracy": 0.8046875,
      "epoch": 0.205,
      "step": 82
    },
    {
      "epoch": 0.2075,
      "grad_norm": 6.261586666107178,
      "learning_rate": 4.171052631578948e-06,
      "loss": 0.3884,
      "step": 83
    },
    {
      "Batch Mean": -1.0069444179534912,
      "accuracy": 0.7890625,
      "epoch": 0.2075,
      "step": 83
    },
    {
      "epoch": 0.21,
      "grad_norm": 7.533053874969482,
      "learning_rate": 4.157894736842106e-06,
      "loss": 0.5043,
      "step": 84
    },
    {
      "Batch Mean": -1.2979249954223633,
      "accuracy": 0.71875,
      "epoch": 0.21,
      "step": 84
    },
    {
      "epoch": 0.2125,
      "grad_norm": 8.032295227050781,
      "learning_rate": 4.144736842105263e-06,
      "loss": 0.5288,
      "step": 85
    },
    {
      "Batch Mean": -1.8461058139801025,
      "accuracy": 0.7421875,
      "epoch": 0.2125,
      "step": 85
    },
    {
      "epoch": 0.215,
      "grad_norm": 8.22770881652832,
      "learning_rate": 4.1315789473684216e-06,
      "loss": 0.5492,
      "step": 86
    },
    {
      "Batch Mean": -1.119255542755127,
      "accuracy": 0.734375,
      "epoch": 0.215,
      "step": 86
    },
    {
      "epoch": 0.2175,
      "grad_norm": 6.965932846069336,
      "learning_rate": 4.118421052631579e-06,
      "loss": 0.5123,
      "step": 87
    },
    {
      "Batch Mean": -1.3000688552856445,
      "accuracy": 0.7734375,
      "epoch": 0.2175,
      "step": 87
    },
    {
      "epoch": 0.22,
      "grad_norm": 6.322815418243408,
      "learning_rate": 4.105263157894737e-06,
      "loss": 0.5046,
      "step": 88
    },
    {
      "Batch Mean": -1.6452465057373047,
      "accuracy": 0.78125,
      "epoch": 0.22,
      "step": 88
    },
    {
      "epoch": 0.2225,
      "grad_norm": 5.874916076660156,
      "learning_rate": 4.092105263157895e-06,
      "loss": 0.4862,
      "step": 89
    },
    {
      "Batch Mean": -1.3325897455215454,
      "accuracy": 0.703125,
      "epoch": 0.2225,
      "step": 89
    },
    {
      "epoch": 0.225,
      "grad_norm": 6.671369552612305,
      "learning_rate": 4.078947368421053e-06,
      "loss": 0.4861,
      "step": 90
    },
    {
      "Batch Mean": -1.272374153137207,
      "accuracy": 0.7734375,
      "epoch": 0.225,
      "step": 90
    },
    {
      "epoch": 0.2275,
      "grad_norm": 6.803928375244141,
      "learning_rate": 4.065789473684211e-06,
      "loss": 0.5159,
      "step": 91
    },
    {
      "Batch Mean": -1.2404394149780273,
      "accuracy": 0.7265625,
      "epoch": 0.2275,
      "step": 91
    },
    {
      "epoch": 0.23,
      "grad_norm": 6.205514907836914,
      "learning_rate": 4.052631578947368e-06,
      "loss": 0.4998,
      "step": 92
    },
    {
      "Batch Mean": -0.8970499038696289,
      "accuracy": 0.7890625,
      "epoch": 0.23,
      "step": 92
    },
    {
      "epoch": 0.2325,
      "grad_norm": 6.928950309753418,
      "learning_rate": 4.0394736842105265e-06,
      "loss": 0.4457,
      "step": 93
    },
    {
      "Batch Mean": -1.1840200424194336,
      "accuracy": 0.7265625,
      "epoch": 0.2325,
      "step": 93
    },
    {
      "epoch": 0.235,
      "grad_norm": 6.628427028656006,
      "learning_rate": 4.026315789473684e-06,
      "loss": 0.4956,
      "step": 94
    },
    {
      "Batch Mean": -0.9916634559631348,
      "accuracy": 0.7421875,
      "epoch": 0.235,
      "step": 94
    },
    {
      "epoch": 0.2375,
      "grad_norm": 6.572470188140869,
      "learning_rate": 4.013157894736842e-06,
      "loss": 0.4784,
      "step": 95
    },
    {
      "Batch Mean": -1.0057942867279053,
      "accuracy": 0.6875,
      "epoch": 0.2375,
      "step": 95
    },
    {
      "epoch": 0.24,
      "grad_norm": 7.420350551605225,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.5301,
      "step": 96
    },
    {
      "Batch Mean": -1.141215205192566,
      "accuracy": 0.8125,
      "epoch": 0.24,
      "step": 96
    },
    {
      "epoch": 0.2425,
      "grad_norm": 6.693457126617432,
      "learning_rate": 3.986842105263158e-06,
      "loss": 0.4688,
      "step": 97
    },
    {
      "Batch Mean": -1.14703369140625,
      "accuracy": 0.796875,
      "epoch": 0.2425,
      "step": 97
    },
    {
      "epoch": 0.245,
      "grad_norm": 7.45700740814209,
      "learning_rate": 3.9736842105263165e-06,
      "loss": 0.4147,
      "step": 98
    },
    {
      "Batch Mean": -1.1375855207443237,
      "accuracy": 0.8359375,
      "epoch": 0.245,
      "step": 98
    },
    {
      "epoch": 0.2475,
      "grad_norm": 6.689132213592529,
      "learning_rate": 3.960526315789474e-06,
      "loss": 0.3805,
      "step": 99
    },
    {
      "Batch Mean": -0.9851565361022949,
      "accuracy": 0.75,
      "epoch": 0.2475,
      "step": 99
    },
    {
      "epoch": 0.25,
      "grad_norm": 9.684271812438965,
      "learning_rate": 3.947368421052632e-06,
      "loss": 0.4405,
      "step": 100
    },
    {
      "Batch Mean": -1.0915021896362305,
      "accuracy": 0.7734375,
      "epoch": 0.25,
      "step": 100
    },
    {
      "epoch": 0.2525,
      "grad_norm": 8.271260261535645,
      "learning_rate": 3.93421052631579e-06,
      "loss": 0.4442,
      "step": 101
    },
    {
      "Batch Mean": -0.7684752941131592,
      "accuracy": 0.7890625,
      "epoch": 0.2525,
      "step": 101
    },
    {
      "epoch": 0.255,
      "grad_norm": 8.824223518371582,
      "learning_rate": 3.921052631578947e-06,
      "loss": 0.4561,
      "step": 102
    },
    {
      "Batch Mean": -0.8534479141235352,
      "accuracy": 0.734375,
      "epoch": 0.255,
      "step": 102
    },
    {
      "epoch": 0.2575,
      "grad_norm": 10.552571296691895,
      "learning_rate": 3.907894736842106e-06,
      "loss": 0.4812,
      "step": 103
    },
    {
      "Batch Mean": -0.4684869349002838,
      "accuracy": 0.7421875,
      "epoch": 0.2575,
      "step": 103
    },
    {
      "epoch": 0.26,
      "grad_norm": 9.715003967285156,
      "learning_rate": 3.894736842105263e-06,
      "loss": 0.468,
      "step": 104
    },
    {
      "Batch Mean": -0.3979635238647461,
      "accuracy": 0.7734375,
      "epoch": 0.26,
      "step": 104
    },
    {
      "epoch": 0.2625,
      "grad_norm": 10.01593017578125,
      "learning_rate": 3.8815789473684214e-06,
      "loss": 0.4727,
      "step": 105
    },
    {
      "Batch Mean": -0.1986093521118164,
      "accuracy": 0.796875,
      "epoch": 0.2625,
      "step": 105
    },
    {
      "epoch": 0.265,
      "grad_norm": 10.657917022705078,
      "learning_rate": 3.868421052631579e-06,
      "loss": 0.455,
      "step": 106
    },
    {
      "Batch Mean": -0.09849877655506134,
      "accuracy": 0.7734375,
      "epoch": 0.265,
      "step": 106
    },
    {
      "epoch": 0.2675,
      "grad_norm": 11.969587326049805,
      "learning_rate": 3.855263157894737e-06,
      "loss": 0.4715,
      "step": 107
    },
    {
      "Batch Mean": -0.21042925119400024,
      "accuracy": 0.8046875,
      "epoch": 0.2675,
      "step": 107
    },
    {
      "epoch": 0.27,
      "grad_norm": 10.609965324401855,
      "learning_rate": 3.842105263157895e-06,
      "loss": 0.4328,
      "step": 108
    },
    {
      "Batch Mean": -0.5359489917755127,
      "accuracy": 0.8046875,
      "epoch": 0.27,
      "step": 108
    },
    {
      "epoch": 0.2725,
      "grad_norm": 9.500229835510254,
      "learning_rate": 3.828947368421053e-06,
      "loss": 0.4106,
      "step": 109
    },
    {
      "Batch Mean": 0.3338432312011719,
      "accuracy": 0.796875,
      "epoch": 0.2725,
      "step": 109
    },
    {
      "epoch": 0.275,
      "grad_norm": 11.425292015075684,
      "learning_rate": 3.815789473684211e-06,
      "loss": 0.483,
      "step": 110
    },
    {
      "Batch Mean": -0.30494236946105957,
      "accuracy": 0.796875,
      "epoch": 0.275,
      "step": 110
    },
    {
      "epoch": 0.2775,
      "grad_norm": 9.747135162353516,
      "learning_rate": 3.802631578947369e-06,
      "loss": 0.457,
      "step": 111
    },
    {
      "Batch Mean": -0.5019316673278809,
      "accuracy": 0.75,
      "epoch": 0.2775,
      "step": 111
    },
    {
      "epoch": 0.28,
      "grad_norm": 10.03312873840332,
      "learning_rate": 3.789473684210527e-06,
      "loss": 0.489,
      "step": 112
    },
    {
      "Batch Mean": -0.3197094202041626,
      "accuracy": 0.7734375,
      "epoch": 0.28,
      "step": 112
    },
    {
      "epoch": 0.2825,
      "grad_norm": 7.567203044891357,
      "learning_rate": 3.7763157894736847e-06,
      "loss": 0.4097,
      "step": 113
    },
    {
      "Batch Mean": -0.6099193096160889,
      "accuracy": 0.7890625,
      "epoch": 0.2825,
      "step": 113
    },
    {
      "epoch": 0.285,
      "grad_norm": 9.13629150390625,
      "learning_rate": 3.7631578947368426e-06,
      "loss": 0.5063,
      "step": 114
    },
    {
      "Batch Mean": -0.5079336166381836,
      "accuracy": 0.78125,
      "epoch": 0.285,
      "step": 114
    },
    {
      "epoch": 0.2875,
      "grad_norm": 7.463940143585205,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.4452,
      "step": 115
    },
    {
      "Batch Mean": -0.982884407043457,
      "accuracy": 0.8125,
      "epoch": 0.2875,
      "step": 115
    },
    {
      "epoch": 0.29,
      "grad_norm": 6.665597438812256,
      "learning_rate": 3.736842105263158e-06,
      "loss": 0.4275,
      "step": 116
    },
    {
      "Batch Mean": -1.1093603372573853,
      "accuracy": 0.7265625,
      "epoch": 0.29,
      "step": 116
    },
    {
      "epoch": 0.2925,
      "grad_norm": 7.881545066833496,
      "learning_rate": 3.723684210526316e-06,
      "loss": 0.5385,
      "step": 117
    },
    {
      "Batch Mean": -1.0912278890609741,
      "accuracy": 0.7421875,
      "epoch": 0.2925,
      "step": 117
    },
    {
      "epoch": 0.295,
      "grad_norm": 7.39991569519043,
      "learning_rate": 3.710526315789474e-06,
      "loss": 0.5116,
      "step": 118
    },
    {
      "Batch Mean": -1.1224448680877686,
      "accuracy": 0.7265625,
      "epoch": 0.295,
      "step": 118
    },
    {
      "epoch": 0.2975,
      "grad_norm": 6.270720481872559,
      "learning_rate": 3.6973684210526317e-06,
      "loss": 0.4805,
      "step": 119
    },
    {
      "Batch Mean": -0.8693461418151855,
      "accuracy": 0.7578125,
      "epoch": 0.2975,
      "step": 119
    },
    {
      "epoch": 0.3,
      "grad_norm": 5.773062705993652,
      "learning_rate": 3.6842105263157896e-06,
      "loss": 0.4403,
      "step": 120
    },
    {
      "Batch Mean": -1.0121287107467651,
      "accuracy": 0.7734375,
      "epoch": 0.3,
      "step": 120
    },
    {
      "epoch": 0.3025,
      "grad_norm": 6.426705837249756,
      "learning_rate": 3.6710526315789476e-06,
      "loss": 0.4496,
      "step": 121
    },
    {
      "Batch Mean": -1.0755189657211304,
      "accuracy": 0.765625,
      "epoch": 0.3025,
      "step": 121
    },
    {
      "epoch": 0.305,
      "grad_norm": 6.251639366149902,
      "learning_rate": 3.657894736842106e-06,
      "loss": 0.4839,
      "step": 122
    },
    {
      "Batch Mean": -0.6420345306396484,
      "accuracy": 0.8359375,
      "epoch": 0.305,
      "step": 122
    },
    {
      "epoch": 0.3075,
      "grad_norm": 6.248297691345215,
      "learning_rate": 3.644736842105264e-06,
      "loss": 0.4346,
      "step": 123
    },
    {
      "Batch Mean": -0.5942535400390625,
      "accuracy": 0.75,
      "epoch": 0.3075,
      "step": 123
    },
    {
      "epoch": 0.31,
      "grad_norm": 6.997790813446045,
      "learning_rate": 3.6315789473684217e-06,
      "loss": 0.4997,
      "step": 124
    },
    {
      "Batch Mean": -0.3599095344543457,
      "accuracy": 0.765625,
      "epoch": 0.31,
      "step": 124
    },
    {
      "epoch": 0.3125,
      "grad_norm": 6.403144836425781,
      "learning_rate": 3.618421052631579e-06,
      "loss": 0.4857,
      "step": 125
    },
    {
      "Batch Mean": -0.12914514541625977,
      "accuracy": 0.8046875,
      "epoch": 0.3125,
      "step": 125
    },
    {
      "epoch": 0.315,
      "grad_norm": 6.186731338500977,
      "learning_rate": 3.605263157894737e-06,
      "loss": 0.4258,
      "step": 126
    },
    {
      "Batch Mean": -0.026085376739501953,
      "accuracy": 0.8203125,
      "epoch": 0.315,
      "step": 126
    },
    {
      "epoch": 0.3175,
      "grad_norm": 6.993777275085449,
      "learning_rate": 3.592105263157895e-06,
      "loss": 0.4127,
      "step": 127
    },
    {
      "Batch Mean": -0.19666238129138947,
      "accuracy": 0.75,
      "epoch": 0.3175,
      "step": 127
    },
    {
      "epoch": 0.32,
      "grad_norm": 6.9689483642578125,
      "learning_rate": 3.578947368421053e-06,
      "loss": 0.4782,
      "step": 128
    },
    {
      "Batch Mean": -0.2396249771118164,
      "accuracy": 0.75,
      "epoch": 0.32,
      "step": 128
    },
    {
      "epoch": 0.3225,
      "grad_norm": 8.292496681213379,
      "learning_rate": 3.565789473684211e-06,
      "loss": 0.5033,
      "step": 129
    },
    {
      "Batch Mean": -0.08678841590881348,
      "accuracy": 0.828125,
      "epoch": 0.3225,
      "step": 129
    },
    {
      "epoch": 0.325,
      "grad_norm": 8.41964054107666,
      "learning_rate": 3.5526315789473687e-06,
      "loss": 0.4106,
      "step": 130
    },
    {
      "Batch Mean": -0.2747459411621094,
      "accuracy": 0.7578125,
      "epoch": 0.325,
      "step": 130
    },
    {
      "epoch": 0.3275,
      "grad_norm": 9.222663879394531,
      "learning_rate": 3.5394736842105266e-06,
      "loss": 0.4377,
      "step": 131
    },
    {
      "Batch Mean": 0.3878480792045593,
      "accuracy": 0.7421875,
      "epoch": 0.3275,
      "step": 131
    },
    {
      "epoch": 0.33,
      "grad_norm": 10.44568920135498,
      "learning_rate": 3.5263157894736846e-06,
      "loss": 0.507,
      "step": 132
    },
    {
      "Batch Mean": 0.42960524559020996,
      "accuracy": 0.7734375,
      "epoch": 0.33,
      "step": 132
    },
    {
      "epoch": 0.3325,
      "grad_norm": 8.473082542419434,
      "learning_rate": 3.513157894736842e-06,
      "loss": 0.468,
      "step": 133
    },
    {
      "Batch Mean": 0.5482549667358398,
      "accuracy": 0.75,
      "epoch": 0.3325,
      "step": 133
    },
    {
      "epoch": 0.335,
      "grad_norm": 9.393155097961426,
      "learning_rate": 3.5e-06,
      "loss": 0.5064,
      "step": 134
    },
    {
      "Batch Mean": 0.21044254302978516,
      "accuracy": 0.8125,
      "epoch": 0.335,
      "step": 134
    },
    {
      "epoch": 0.3375,
      "grad_norm": 7.462342739105225,
      "learning_rate": 3.486842105263158e-06,
      "loss": 0.4034,
      "step": 135
    },
    {
      "Batch Mean": 0.511605978012085,
      "accuracy": 0.765625,
      "epoch": 0.3375,
      "step": 135
    },
    {
      "epoch": 0.34,
      "grad_norm": 7.791304588317871,
      "learning_rate": 3.473684210526316e-06,
      "loss": 0.4827,
      "step": 136
    },
    {
      "Batch Mean": -0.08954060077667236,
      "accuracy": 0.7421875,
      "epoch": 0.34,
      "step": 136
    },
    {
      "epoch": 0.3425,
      "grad_norm": 9.468352317810059,
      "learning_rate": 3.460526315789474e-06,
      "loss": 0.5404,
      "step": 137
    },
    {
      "Batch Mean": -0.3172520399093628,
      "accuracy": 0.7578125,
      "epoch": 0.3425,
      "step": 137
    },
    {
      "epoch": 0.345,
      "grad_norm": 7.7005720138549805,
      "learning_rate": 3.447368421052632e-06,
      "loss": 0.4348,
      "step": 138
    },
    {
      "Batch Mean": -0.38188767433166504,
      "accuracy": 0.8046875,
      "epoch": 0.345,
      "step": 138
    },
    {
      "epoch": 0.3475,
      "grad_norm": 7.671250820159912,
      "learning_rate": 3.43421052631579e-06,
      "loss": 0.4548,
      "step": 139
    },
    {
      "Batch Mean": -0.5834815502166748,
      "accuracy": 0.7890625,
      "epoch": 0.3475,
      "step": 139
    },
    {
      "epoch": 0.35,
      "grad_norm": 6.371372699737549,
      "learning_rate": 3.421052631578948e-06,
      "loss": 0.4407,
      "step": 140
    },
    {
      "Batch Mean": -0.794266939163208,
      "accuracy": 0.78125,
      "epoch": 0.35,
      "step": 140
    },
    {
      "epoch": 0.3525,
      "grad_norm": 6.418947696685791,
      "learning_rate": 3.4078947368421057e-06,
      "loss": 0.4297,
      "step": 141
    },
    {
      "Batch Mean": -1.031827449798584,
      "accuracy": 0.78125,
      "epoch": 0.3525,
      "step": 141
    },
    {
      "epoch": 0.355,
      "grad_norm": 7.1692023277282715,
      "learning_rate": 3.3947368421052636e-06,
      "loss": 0.4884,
      "step": 142
    },
    {
      "Batch Mean": -1.0245031118392944,
      "accuracy": 0.8125,
      "epoch": 0.355,
      "step": 142
    },
    {
      "epoch": 0.3575,
      "grad_norm": 6.299808025360107,
      "learning_rate": 3.381578947368421e-06,
      "loss": 0.4165,
      "step": 143
    },
    {
      "Batch Mean": -1.6456010341644287,
      "accuracy": 0.78125,
      "epoch": 0.3575,
      "step": 143
    },
    {
      "epoch": 0.36,
      "grad_norm": 7.132191181182861,
      "learning_rate": 3.368421052631579e-06,
      "loss": 0.496,
      "step": 144
    },
    {
      "Batch Mean": -1.4577171802520752,
      "accuracy": 0.8046875,
      "epoch": 0.36,
      "step": 144
    },
    {
      "epoch": 0.3625,
      "grad_norm": 7.309590816497803,
      "learning_rate": 3.355263157894737e-06,
      "loss": 0.4046,
      "step": 145
    },
    {
      "Batch Mean": -1.2381335496902466,
      "accuracy": 0.7890625,
      "epoch": 0.3625,
      "step": 145
    },
    {
      "epoch": 0.365,
      "grad_norm": 7.03560209274292,
      "learning_rate": 3.342105263157895e-06,
      "loss": 0.4463,
      "step": 146
    },
    {
      "Batch Mean": -1.3830366134643555,
      "accuracy": 0.7890625,
      "epoch": 0.365,
      "step": 146
    },
    {
      "epoch": 0.3675,
      "grad_norm": 7.277976036071777,
      "learning_rate": 3.3289473684210528e-06,
      "loss": 0.4238,
      "step": 147
    },
    {
      "Batch Mean": -1.2444829940795898,
      "accuracy": 0.84375,
      "epoch": 0.3675,
      "step": 147
    },
    {
      "epoch": 0.37,
      "grad_norm": 6.460512638092041,
      "learning_rate": 3.3157894736842107e-06,
      "loss": 0.3967,
      "step": 148
    },
    {
      "Batch Mean": -0.9982385039329529,
      "accuracy": 0.7734375,
      "epoch": 0.37,
      "step": 148
    },
    {
      "epoch": 0.3725,
      "grad_norm": 7.685225486755371,
      "learning_rate": 3.302631578947369e-06,
      "loss": 0.4706,
      "step": 149
    },
    {
      "Batch Mean": -0.9622928500175476,
      "accuracy": 0.78125,
      "epoch": 0.3725,
      "step": 149
    },
    {
      "epoch": 0.375,
      "grad_norm": 7.0924153327941895,
      "learning_rate": 3.289473684210527e-06,
      "loss": 0.425,
      "step": 150
    },
    {
      "Batch Mean": -0.6390509605407715,
      "accuracy": 0.7421875,
      "epoch": 0.375,
      "step": 150
    },
    {
      "epoch": 0.3775,
      "grad_norm": 8.69453239440918,
      "learning_rate": 3.276315789473685e-06,
      "loss": 0.5108,
      "step": 151
    },
    {
      "Batch Mean": -0.0986168384552002,
      "accuracy": 0.7578125,
      "epoch": 0.3775,
      "step": 151
    },
    {
      "epoch": 0.38,
      "grad_norm": 10.331669807434082,
      "learning_rate": 3.2631578947368423e-06,
      "loss": 0.5265,
      "step": 152
    },
    {
      "Batch Mean": -0.36638665199279785,
      "accuracy": 0.8203125,
      "epoch": 0.38,
      "step": 152
    },
    {
      "epoch": 0.3825,
      "grad_norm": 6.3816704750061035,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.3436,
      "step": 153
    },
    {
      "Batch Mean": -0.700871467590332,
      "accuracy": 0.828125,
      "epoch": 0.3825,
      "step": 153
    },
    {
      "epoch": 0.385,
      "grad_norm": 7.452230453491211,
      "learning_rate": 3.236842105263158e-06,
      "loss": 0.3744,
      "step": 154
    },
    {
      "Batch Mean": -0.22220516204833984,
      "accuracy": 0.7734375,
      "epoch": 0.385,
      "step": 154
    },
    {
      "epoch": 0.3875,
      "grad_norm": 9.25493049621582,
      "learning_rate": 3.223684210526316e-06,
      "loss": 0.473,
      "step": 155
    },
    {
      "Batch Mean": -0.5362415313720703,
      "accuracy": 0.8203125,
      "epoch": 0.3875,
      "step": 155
    },
    {
      "epoch": 0.39,
      "grad_norm": 8.848881721496582,
      "learning_rate": 3.210526315789474e-06,
      "loss": 0.4727,
      "step": 156
    },
    {
      "Batch Mean": -0.39302539825439453,
      "accuracy": 0.7890625,
      "epoch": 0.39,
      "step": 156
    },
    {
      "epoch": 0.3925,
      "grad_norm": 8.796403884887695,
      "learning_rate": 3.197368421052632e-06,
      "loss": 0.4675,
      "step": 157
    },
    {
      "Batch Mean": -0.24126970767974854,
      "accuracy": 0.7734375,
      "epoch": 0.3925,
      "step": 157
    },
    {
      "epoch": 0.395,
      "grad_norm": 9.450688362121582,
      "learning_rate": 3.1842105263157898e-06,
      "loss": 0.4724,
      "step": 158
    },
    {
      "Batch Mean": -0.40082311630249023,
      "accuracy": 0.8046875,
      "epoch": 0.395,
      "step": 158
    },
    {
      "epoch": 0.3975,
      "grad_norm": 8.867382049560547,
      "learning_rate": 3.1710526315789477e-06,
      "loss": 0.4516,
      "step": 159
    },
    {
      "Batch Mean": -0.40192973613739014,
      "accuracy": 0.7421875,
      "epoch": 0.3975,
      "step": 159
    },
    {
      "epoch": 0.4,
      "grad_norm": 11.669089317321777,
      "learning_rate": 3.157894736842105e-06,
      "loss": 0.5932,
      "step": 160
    }
  ],
  "logging_steps": 1,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 80,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}