{
  "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": 1.9420166015625,
      "accuracy": 0.46875,
      "epoch": 0,
      "step": 0
    },
    {
      "epoch": 0.0025,
      "grad_norm": 9.666593551635742,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 0.7076,
      "step": 1
    },
    {
      "Batch Mean": 1.9312744140625,
      "accuracy": 0.4375,
      "epoch": 0.0025,
      "step": 1
    },
    {
      "epoch": 0.005,
      "grad_norm": 7.076696395874023,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.7073,
      "step": 2
    },
    {
      "Batch Mean": 1.9347686767578125,
      "accuracy": 0.5,
      "epoch": 0.005,
      "step": 2
    },
    {
      "epoch": 0.0075,
      "grad_norm": 6.997435092926025,
      "learning_rate": 7.5e-07,
      "loss": 0.6918,
      "step": 3
    },
    {
      "Batch Mean": 1.94329833984375,
      "accuracy": 0.53125,
      "epoch": 0.0075,
      "step": 3
    },
    {
      "epoch": 0.01,
      "grad_norm": 7.863523006439209,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.6877,
      "step": 4
    },
    {
      "Batch Mean": 1.94287109375,
      "accuracy": 0.5703125,
      "epoch": 0.01,
      "step": 4
    },
    {
      "epoch": 0.0125,
      "grad_norm": 6.760534286499023,
      "learning_rate": 1.25e-06,
      "loss": 0.6861,
      "step": 5
    },
    {
      "Batch Mean": 1.97332763671875,
      "accuracy": 0.53125,
      "epoch": 0.0125,
      "step": 5
    },
    {
      "epoch": 0.015,
      "grad_norm": 8.08924674987793,
      "learning_rate": 1.5e-06,
      "loss": 0.6869,
      "step": 6
    },
    {
      "Batch Mean": 2.018096923828125,
      "accuracy": 0.46875,
      "epoch": 0.015,
      "step": 6
    },
    {
      "epoch": 0.0175,
      "grad_norm": 6.236896991729736,
      "learning_rate": 1.75e-06,
      "loss": 0.7053,
      "step": 7
    },
    {
      "Batch Mean": 2.14398193359375,
      "accuracy": 0.5390625,
      "epoch": 0.0175,
      "step": 7
    },
    {
      "epoch": 0.02,
      "grad_norm": 6.7978620529174805,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.6925,
      "step": 8
    },
    {
      "Batch Mean": 2.214202880859375,
      "accuracy": 0.4453125,
      "epoch": 0.02,
      "step": 8
    },
    {
      "epoch": 0.0225,
      "grad_norm": 7.25023889541626,
      "learning_rate": 2.25e-06,
      "loss": 0.7048,
      "step": 9
    },
    {
      "Batch Mean": 2.3272705078125,
      "accuracy": 0.5859375,
      "epoch": 0.0225,
      "step": 9
    },
    {
      "epoch": 0.025,
      "grad_norm": 6.383249759674072,
      "learning_rate": 2.5e-06,
      "loss": 0.6815,
      "step": 10
    },
    {
      "Batch Mean": 2.49114990234375,
      "accuracy": 0.6640625,
      "epoch": 0.025,
      "step": 10
    },
    {
      "epoch": 0.0275,
      "grad_norm": 9.219279289245605,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.6547,
      "step": 11
    },
    {
      "Batch Mean": 2.550567626953125,
      "accuracy": 0.6328125,
      "epoch": 0.0275,
      "step": 11
    },
    {
      "epoch": 0.03,
      "grad_norm": 7.704563617706299,
      "learning_rate": 3e-06,
      "loss": 0.6432,
      "step": 12
    },
    {
      "Batch Mean": 2.645782470703125,
      "accuracy": 0.671875,
      "epoch": 0.03,
      "step": 12
    },
    {
      "epoch": 0.0325,
      "grad_norm": 7.639222145080566,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.6365,
      "step": 13
    },
    {
      "Batch Mean": 2.8451995849609375,
      "accuracy": 0.6171875,
      "epoch": 0.0325,
      "step": 13
    },
    {
      "epoch": 0.035,
      "grad_norm": 13.006075859069824,
      "learning_rate": 3.5e-06,
      "loss": 0.659,
      "step": 14
    },
    {
      "Batch Mean": 3.0160064697265625,
      "accuracy": 0.609375,
      "epoch": 0.035,
      "step": 14
    },
    {
      "epoch": 0.0375,
      "grad_norm": 11.644806861877441,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.6574,
      "step": 15
    },
    {
      "Batch Mean": 3.0444812774658203,
      "accuracy": 0.671875,
      "epoch": 0.0375,
      "step": 15
    },
    {
      "epoch": 0.04,
      "grad_norm": 12.809576034545898,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6138,
      "step": 16
    },
    {
      "Batch Mean": 3.1425399780273438,
      "accuracy": 0.6875,
      "epoch": 0.04,
      "step": 16
    },
    {
      "epoch": 0.0425,
      "grad_norm": 10.398422241210938,
      "learning_rate": 4.25e-06,
      "loss": 0.5373,
      "step": 17
    },
    {
      "Batch Mean": 2.997763156890869,
      "accuracy": 0.6015625,
      "epoch": 0.0425,
      "step": 17
    },
    {
      "epoch": 0.045,
      "grad_norm": 9.611076354980469,
      "learning_rate": 4.5e-06,
      "loss": 0.5884,
      "step": 18
    },
    {
      "Batch Mean": 2.822673797607422,
      "accuracy": 0.6953125,
      "epoch": 0.045,
      "step": 18
    },
    {
      "epoch": 0.0475,
      "grad_norm": 11.101300239562988,
      "learning_rate": 4.75e-06,
      "loss": 0.5819,
      "step": 19
    },
    {
      "Batch Mean": 2.9509963989257812,
      "accuracy": 0.6796875,
      "epoch": 0.0475,
      "step": 19
    },
    {
      "epoch": 0.05,
      "grad_norm": 11.16808032989502,
      "learning_rate": 5e-06,
      "loss": 0.5849,
      "step": 20
    },
    {
      "Batch Mean": 2.7339065074920654,
      "accuracy": 0.609375,
      "epoch": 0.05,
      "step": 20
    },
    {
      "epoch": 0.0525,
      "grad_norm": 13.900754928588867,
      "learning_rate": 4.986842105263158e-06,
      "loss": 0.6193,
      "step": 21
    },
    {
      "Batch Mean": 2.5777530670166016,
      "accuracy": 0.71875,
      "epoch": 0.0525,
      "step": 21
    },
    {
      "epoch": 0.055,
      "grad_norm": 9.619379997253418,
      "learning_rate": 4.973684210526316e-06,
      "loss": 0.599,
      "step": 22
    },
    {
      "Batch Mean": 2.6994237899780273,
      "accuracy": 0.65625,
      "epoch": 0.055,
      "step": 22
    },
    {
      "epoch": 0.0575,
      "grad_norm": 9.464532852172852,
      "learning_rate": 4.960526315789474e-06,
      "loss": 0.6118,
      "step": 23
    },
    {
      "Batch Mean": 2.70928955078125,
      "accuracy": 0.6484375,
      "epoch": 0.0575,
      "step": 23
    },
    {
      "epoch": 0.06,
      "grad_norm": 8.05068588256836,
      "learning_rate": 4.947368421052632e-06,
      "loss": 0.6214,
      "step": 24
    },
    {
      "Batch Mean": 2.8170089721679688,
      "accuracy": 0.6796875,
      "epoch": 0.06,
      "step": 24
    },
    {
      "epoch": 0.0625,
      "grad_norm": 9.21177864074707,
      "learning_rate": 4.9342105263157895e-06,
      "loss": 0.6165,
      "step": 25
    },
    {
      "Batch Mean": 2.7590713500976562,
      "accuracy": 0.6171875,
      "epoch": 0.0625,
      "step": 25
    },
    {
      "epoch": 0.065,
      "grad_norm": 6.078210353851318,
      "learning_rate": 4.921052631578948e-06,
      "loss": 0.6027,
      "step": 26
    },
    {
      "Batch Mean": 2.8484420776367188,
      "accuracy": 0.6796875,
      "epoch": 0.065,
      "step": 26
    },
    {
      "epoch": 0.0675,
      "grad_norm": 5.933135032653809,
      "learning_rate": 4.907894736842106e-06,
      "loss": 0.5721,
      "step": 27
    },
    {
      "Batch Mean": 2.9572601318359375,
      "accuracy": 0.6796875,
      "epoch": 0.0675,
      "step": 27
    },
    {
      "epoch": 0.07,
      "grad_norm": 6.4003143310546875,
      "learning_rate": 4.894736842105264e-06,
      "loss": 0.5626,
      "step": 28
    },
    {
      "Batch Mean": 2.9868011474609375,
      "accuracy": 0.6796875,
      "epoch": 0.07,
      "step": 28
    },
    {
      "epoch": 0.0725,
      "grad_norm": 4.7936859130859375,
      "learning_rate": 4.881578947368422e-06,
      "loss": 0.5809,
      "step": 29
    },
    {
      "Batch Mean": 3.106109619140625,
      "accuracy": 0.65625,
      "epoch": 0.0725,
      "step": 29
    },
    {
      "epoch": 0.075,
      "grad_norm": 5.339725017547607,
      "learning_rate": 4.8684210526315795e-06,
      "loss": 0.6132,
      "step": 30
    },
    {
      "Batch Mean": 3.29296875,
      "accuracy": 0.734375,
      "epoch": 0.075,
      "step": 30
    },
    {
      "epoch": 0.0775,
      "grad_norm": 5.850327491760254,
      "learning_rate": 4.855263157894737e-06,
      "loss": 0.584,
      "step": 31
    },
    {
      "Batch Mean": 3.51275634765625,
      "accuracy": 0.65625,
      "epoch": 0.0775,
      "step": 31
    },
    {
      "epoch": 0.08,
      "grad_norm": 6.158403396606445,
      "learning_rate": 4.842105263157895e-06,
      "loss": 0.5911,
      "step": 32
    },
    {
      "Batch Mean": 3.4871044158935547,
      "accuracy": 0.71875,
      "epoch": 0.08,
      "step": 32
    },
    {
      "epoch": 0.0825,
      "grad_norm": 5.687869071960449,
      "learning_rate": 4.828947368421053e-06,
      "loss": 0.5243,
      "step": 33
    },
    {
      "Batch Mean": 3.6311264038085938,
      "accuracy": 0.8203125,
      "epoch": 0.0825,
      "step": 33
    },
    {
      "epoch": 0.085,
      "grad_norm": 6.883860111236572,
      "learning_rate": 4.815789473684211e-06,
      "loss": 0.4525,
      "step": 34
    },
    {
      "Batch Mean": 3.747730255126953,
      "accuracy": 0.6875,
      "epoch": 0.085,
      "step": 34
    },
    {
      "epoch": 0.0875,
      "grad_norm": 8.108345031738281,
      "learning_rate": 4.802631578947369e-06,
      "loss": 0.5392,
      "step": 35
    },
    {
      "Batch Mean": 4.052231788635254,
      "accuracy": 0.671875,
      "epoch": 0.0875,
      "step": 35
    },
    {
      "epoch": 0.09,
      "grad_norm": 8.877079963684082,
      "learning_rate": 4.789473684210527e-06,
      "loss": 0.5759,
      "step": 36
    },
    {
      "Batch Mean": 4.003006458282471,
      "accuracy": 0.7421875,
      "epoch": 0.09,
      "step": 36
    },
    {
      "epoch": 0.0925,
      "grad_norm": 9.152173042297363,
      "learning_rate": 4.7763157894736844e-06,
      "loss": 0.5118,
      "step": 37
    },
    {
      "Batch Mean": 4.063720703125,
      "accuracy": 0.6171875,
      "epoch": 0.0925,
      "step": 37
    },
    {
      "epoch": 0.095,
      "grad_norm": 10.134416580200195,
      "learning_rate": 4.763157894736842e-06,
      "loss": 0.6653,
      "step": 38
    },
    {
      "Batch Mean": 4.406402587890625,
      "accuracy": 0.703125,
      "epoch": 0.095,
      "step": 38
    },
    {
      "epoch": 0.0975,
      "grad_norm": 7.997857570648193,
      "learning_rate": 4.75e-06,
      "loss": 0.525,
      "step": 39
    },
    {
      "Batch Mean": 4.049163818359375,
      "accuracy": 0.7578125,
      "epoch": 0.0975,
      "step": 39
    },
    {
      "epoch": 0.1,
      "grad_norm": 8.24782657623291,
      "learning_rate": 4.736842105263158e-06,
      "loss": 0.4568,
      "step": 40
    },
    {
      "Batch Mean": 4.293998718261719,
      "accuracy": 0.7890625,
      "epoch": 0.1,
      "step": 40
    },
    {
      "epoch": 0.1025,
      "grad_norm": 7.328802108764648,
      "learning_rate": 4.723684210526316e-06,
      "loss": 0.4618,
      "step": 41
    },
    {
      "Batch Mean": 4.420158386230469,
      "accuracy": 0.75,
      "epoch": 0.1025,
      "step": 41
    },
    {
      "epoch": 0.105,
      "grad_norm": 7.795598030090332,
      "learning_rate": 4.710526315789474e-06,
      "loss": 0.5121,
      "step": 42
    },
    {
      "Batch Mean": 4.374538421630859,
      "accuracy": 0.6953125,
      "epoch": 0.105,
      "step": 42
    },
    {
      "epoch": 0.1075,
      "grad_norm": 9.923321723937988,
      "learning_rate": 4.697368421052632e-06,
      "loss": 0.5919,
      "step": 43
    },
    {
      "Batch Mean": 4.3918304443359375,
      "accuracy": 0.78125,
      "epoch": 0.1075,
      "step": 43
    },
    {
      "epoch": 0.11,
      "grad_norm": 6.950074672698975,
      "learning_rate": 4.68421052631579e-06,
      "loss": 0.499,
      "step": 44
    },
    {
      "Batch Mean": 4.343505859375,
      "accuracy": 0.7578125,
      "epoch": 0.11,
      "step": 44
    },
    {
      "epoch": 0.1125,
      "grad_norm": 7.051249980926514,
      "learning_rate": 4.671052631578948e-06,
      "loss": 0.5362,
      "step": 45
    },
    {
      "Batch Mean": 4.268529891967773,
      "accuracy": 0.7265625,
      "epoch": 0.1125,
      "step": 45
    },
    {
      "epoch": 0.115,
      "grad_norm": 7.27433443069458,
      "learning_rate": 4.657894736842106e-06,
      "loss": 0.527,
      "step": 46
    },
    {
      "Batch Mean": 4.0211334228515625,
      "accuracy": 0.796875,
      "epoch": 0.115,
      "step": 46
    },
    {
      "epoch": 0.1175,
      "grad_norm": 7.680591106414795,
      "learning_rate": 4.6447368421052635e-06,
      "loss": 0.5004,
      "step": 47
    },
    {
      "Batch Mean": 4.125762939453125,
      "accuracy": 0.7578125,
      "epoch": 0.1175,
      "step": 47
    },
    {
      "epoch": 0.12,
      "grad_norm": 6.570550441741943,
      "learning_rate": 4.631578947368421e-06,
      "loss": 0.4887,
      "step": 48
    },
    {
      "Batch Mean": 3.82733154296875,
      "accuracy": 0.6953125,
      "epoch": 0.12,
      "step": 48
    },
    {
      "epoch": 0.1225,
      "grad_norm": 6.966435432434082,
      "learning_rate": 4.618421052631579e-06,
      "loss": 0.5351,
      "step": 49
    },
    {
      "Batch Mean": 3.548530101776123,
      "accuracy": 0.6796875,
      "epoch": 0.1225,
      "step": 49
    },
    {
      "epoch": 0.125,
      "grad_norm": 9.178398132324219,
      "learning_rate": 4.605263157894737e-06,
      "loss": 0.6348,
      "step": 50
    },
    {
      "Batch Mean": 3.5271453857421875,
      "accuracy": 0.7421875,
      "epoch": 0.125,
      "step": 50
    },
    {
      "epoch": 0.1275,
      "grad_norm": 7.21920108795166,
      "learning_rate": 4.592105263157895e-06,
      "loss": 0.5138,
      "step": 51
    },
    {
      "Batch Mean": 3.3803443908691406,
      "accuracy": 0.75,
      "epoch": 0.1275,
      "step": 51
    },
    {
      "epoch": 0.13,
      "grad_norm": 6.866484642028809,
      "learning_rate": 4.578947368421053e-06,
      "loss": 0.5163,
      "step": 52
    },
    {
      "Batch Mean": 3.42218017578125,
      "accuracy": 0.734375,
      "epoch": 0.13,
      "step": 52
    },
    {
      "epoch": 0.1325,
      "grad_norm": 5.488794803619385,
      "learning_rate": 4.565789473684211e-06,
      "loss": 0.5135,
      "step": 53
    },
    {
      "Batch Mean": 3.271286964416504,
      "accuracy": 0.6484375,
      "epoch": 0.1325,
      "step": 53
    },
    {
      "epoch": 0.135,
      "grad_norm": 6.306389808654785,
      "learning_rate": 4.552631578947369e-06,
      "loss": 0.5649,
      "step": 54
    },
    {
      "Batch Mean": 3.0698814392089844,
      "accuracy": 0.7578125,
      "epoch": 0.135,
      "step": 54
    },
    {
      "epoch": 0.1375,
      "grad_norm": 6.536716461181641,
      "learning_rate": 4.539473684210527e-06,
      "loss": 0.5415,
      "step": 55
    },
    {
      "Batch Mean": 3.088502883911133,
      "accuracy": 0.75,
      "epoch": 0.1375,
      "step": 55
    },
    {
      "epoch": 0.14,
      "grad_norm": 7.343382358551025,
      "learning_rate": 4.526315789473685e-06,
      "loss": 0.5206,
      "step": 56
    },
    {
      "Batch Mean": 3.2023324966430664,
      "accuracy": 0.6796875,
      "epoch": 0.14,
      "step": 56
    },
    {
      "epoch": 0.1425,
      "grad_norm": 7.171923637390137,
      "learning_rate": 4.513157894736843e-06,
      "loss": 0.5765,
      "step": 57
    },
    {
      "Batch Mean": 2.9620323181152344,
      "accuracy": 0.75,
      "epoch": 0.1425,
      "step": 57
    },
    {
      "epoch": 0.145,
      "grad_norm": 7.703383922576904,
      "learning_rate": 4.5e-06,
      "loss": 0.5144,
      "step": 58
    },
    {
      "Batch Mean": 2.995695114135742,
      "accuracy": 0.734375,
      "epoch": 0.145,
      "step": 58
    },
    {
      "epoch": 0.1475,
      "grad_norm": 8.559469223022461,
      "learning_rate": 4.4868421052631584e-06,
      "loss": 0.4926,
      "step": 59
    },
    {
      "Batch Mean": 3.2689762115478516,
      "accuracy": 0.7421875,
      "epoch": 0.1475,
      "step": 59
    },
    {
      "epoch": 0.15,
      "grad_norm": 6.663382530212402,
      "learning_rate": 4.473684210526316e-06,
      "loss": 0.4705,
      "step": 60
    },
    {
      "Batch Mean": 2.9887285232543945,
      "accuracy": 0.7265625,
      "epoch": 0.15,
      "step": 60
    },
    {
      "epoch": 0.1525,
      "grad_norm": 7.883590221405029,
      "learning_rate": 4.460526315789474e-06,
      "loss": 0.5447,
      "step": 61
    },
    {
      "Batch Mean": 2.901198387145996,
      "accuracy": 0.78125,
      "epoch": 0.1525,
      "step": 61
    },
    {
      "epoch": 0.155,
      "grad_norm": 7.087621688842773,
      "learning_rate": 4.447368421052632e-06,
      "loss": 0.4382,
      "step": 62
    },
    {
      "Batch Mean": 2.978053569793701,
      "accuracy": 0.7265625,
      "epoch": 0.155,
      "step": 62
    },
    {
      "epoch": 0.1575,
      "grad_norm": 8.361074447631836,
      "learning_rate": 4.43421052631579e-06,
      "loss": 0.5379,
      "step": 63
    },
    {
      "Batch Mean": 2.9929721355438232,
      "accuracy": 0.765625,
      "epoch": 0.1575,
      "step": 63
    },
    {
      "epoch": 0.16,
      "grad_norm": 10.397054672241211,
      "learning_rate": 4.4210526315789476e-06,
      "loss": 0.489,
      "step": 64
    },
    {
      "Batch Mean": 2.9623823165893555,
      "accuracy": 0.734375,
      "epoch": 0.16,
      "step": 64
    },
    {
      "epoch": 0.1625,
      "grad_norm": 11.552237510681152,
      "learning_rate": 4.407894736842105e-06,
      "loss": 0.5394,
      "step": 65
    },
    {
      "Batch Mean": 2.897951602935791,
      "accuracy": 0.734375,
      "epoch": 0.1625,
      "step": 65
    },
    {
      "epoch": 0.165,
      "grad_norm": 9.772311210632324,
      "learning_rate": 4.394736842105263e-06,
      "loss": 0.5274,
      "step": 66
    },
    {
      "Batch Mean": 2.8228421211242676,
      "accuracy": 0.75,
      "epoch": 0.165,
      "step": 66
    },
    {
      "epoch": 0.1675,
      "grad_norm": 8.786587715148926,
      "learning_rate": 4.381578947368421e-06,
      "loss": 0.5151,
      "step": 67
    },
    {
      "Batch Mean": 2.93172550201416,
      "accuracy": 0.8125,
      "epoch": 0.1675,
      "step": 67
    },
    {
      "epoch": 0.17,
      "grad_norm": 7.272209167480469,
      "learning_rate": 4.368421052631579e-06,
      "loss": 0.4259,
      "step": 68
    },
    {
      "Batch Mean": 3.0047380924224854,
      "accuracy": 0.6953125,
      "epoch": 0.17,
      "step": 68
    },
    {
      "epoch": 0.1725,
      "grad_norm": 10.469968795776367,
      "learning_rate": 4.3552631578947375e-06,
      "loss": 0.5409,
      "step": 69
    },
    {
      "Batch Mean": 3.2963790893554688,
      "accuracy": 0.75,
      "epoch": 0.1725,
      "step": 69
    },
    {
      "epoch": 0.175,
      "grad_norm": 8.683908462524414,
      "learning_rate": 4.342105263157895e-06,
      "loss": 0.4782,
      "step": 70
    },
    {
      "Batch Mean": 3.195692300796509,
      "accuracy": 0.7734375,
      "epoch": 0.175,
      "step": 70
    },
    {
      "epoch": 0.1775,
      "grad_norm": 7.932145118713379,
      "learning_rate": 4.328947368421053e-06,
      "loss": 0.4693,
      "step": 71
    },
    {
      "Batch Mean": 3.188863754272461,
      "accuracy": 0.8125,
      "epoch": 0.1775,
      "step": 71
    },
    {
      "epoch": 0.18,
      "grad_norm": 6.82938814163208,
      "learning_rate": 4.315789473684211e-06,
      "loss": 0.3917,
      "step": 72
    },
    {
      "Batch Mean": 3.1435837745666504,
      "accuracy": 0.7421875,
      "epoch": 0.18,
      "step": 72
    },
    {
      "epoch": 0.1825,
      "grad_norm": 6.974360942840576,
      "learning_rate": 4.302631578947369e-06,
      "loss": 0.49,
      "step": 73
    },
    {
      "Batch Mean": 3.5599288940429688,
      "accuracy": 0.78125,
      "epoch": 0.1825,
      "step": 73
    },
    {
      "epoch": 0.185,
      "grad_norm": 7.391234397888184,
      "learning_rate": 4.289473684210527e-06,
      "loss": 0.507,
      "step": 74
    },
    {
      "Batch Mean": 3.1217479705810547,
      "accuracy": 0.7421875,
      "epoch": 0.185,
      "step": 74
    },
    {
      "epoch": 0.1875,
      "grad_norm": 6.925199508666992,
      "learning_rate": 4.276315789473684e-06,
      "loss": 0.5203,
      "step": 75
    },
    {
      "Batch Mean": 3.3439712524414062,
      "accuracy": 0.7109375,
      "epoch": 0.1875,
      "step": 75
    },
    {
      "epoch": 0.19,
      "grad_norm": 8.055448532104492,
      "learning_rate": 4.2631578947368425e-06,
      "loss": 0.5173,
      "step": 76
    },
    {
      "Batch Mean": 3.372138023376465,
      "accuracy": 0.7734375,
      "epoch": 0.19,
      "step": 76
    },
    {
      "epoch": 0.1925,
      "grad_norm": 7.226714611053467,
      "learning_rate": 4.25e-06,
      "loss": 0.487,
      "step": 77
    },
    {
      "Batch Mean": 3.52044677734375,
      "accuracy": 0.8359375,
      "epoch": 0.1925,
      "step": 77
    },
    {
      "epoch": 0.195,
      "grad_norm": 7.280280113220215,
      "learning_rate": 4.236842105263158e-06,
      "loss": 0.4553,
      "step": 78
    },
    {
      "Batch Mean": 3.2147364616394043,
      "accuracy": 0.8359375,
      "epoch": 0.195,
      "step": 78
    },
    {
      "epoch": 0.1975,
      "grad_norm": 6.3655781745910645,
      "learning_rate": 4.223684210526316e-06,
      "loss": 0.4328,
      "step": 79
    },
    {
      "Batch Mean": 3.4875216484069824,
      "accuracy": 0.8203125,
      "epoch": 0.1975,
      "step": 79
    },
    {
      "epoch": 0.2,
      "grad_norm": 6.6272759437561035,
      "learning_rate": 4.210526315789474e-06,
      "loss": 0.4119,
      "step": 80
    },
    {
      "Batch Mean": 3.427578926086426,
      "accuracy": 0.78125,
      "epoch": 0.2,
      "step": 80
    },
    {
      "epoch": 0.2025,
      "grad_norm": 8.57567024230957,
      "learning_rate": 4.197368421052632e-06,
      "loss": 0.4891,
      "step": 81
    },
    {
      "Batch Mean": 3.7187185287475586,
      "accuracy": 0.7578125,
      "epoch": 0.2025,
      "step": 81
    },
    {
      "epoch": 0.205,
      "grad_norm": 7.171870708465576,
      "learning_rate": 4.18421052631579e-06,
      "loss": 0.439,
      "step": 82
    },
    {
      "Batch Mean": 3.990264892578125,
      "accuracy": 0.7734375,
      "epoch": 0.205,
      "step": 82
    },
    {
      "epoch": 0.2075,
      "grad_norm": 8.19045639038086,
      "learning_rate": 4.171052631578948e-06,
      "loss": 0.4541,
      "step": 83
    },
    {
      "Batch Mean": 4.509843826293945,
      "accuracy": 0.7265625,
      "epoch": 0.2075,
      "step": 83
    },
    {
      "epoch": 0.21,
      "grad_norm": 9.934694290161133,
      "learning_rate": 4.157894736842106e-06,
      "loss": 0.5258,
      "step": 84
    },
    {
      "Batch Mean": 4.694008827209473,
      "accuracy": 0.8125,
      "epoch": 0.21,
      "step": 84
    },
    {
      "epoch": 0.2125,
      "grad_norm": 7.037469863891602,
      "learning_rate": 4.144736842105263e-06,
      "loss": 0.4123,
      "step": 85
    },
    {
      "Batch Mean": 4.4774580001831055,
      "accuracy": 0.71875,
      "epoch": 0.2125,
      "step": 85
    },
    {
      "epoch": 0.215,
      "grad_norm": 9.059208869934082,
      "learning_rate": 4.1315789473684216e-06,
      "loss": 0.541,
      "step": 86
    },
    {
      "Batch Mean": 4.323337078094482,
      "accuracy": 0.7734375,
      "epoch": 0.215,
      "step": 86
    },
    {
      "epoch": 0.2175,
      "grad_norm": 7.794407367706299,
      "learning_rate": 4.118421052631579e-06,
      "loss": 0.4797,
      "step": 87
    },
    {
      "Batch Mean": 4.874683380126953,
      "accuracy": 0.7578125,
      "epoch": 0.2175,
      "step": 87
    },
    {
      "epoch": 0.22,
      "grad_norm": 9.554245948791504,
      "learning_rate": 4.105263157894737e-06,
      "loss": 0.5024,
      "step": 88
    },
    {
      "Batch Mean": 4.5128173828125,
      "accuracy": 0.8046875,
      "epoch": 0.22,
      "step": 88
    },
    {
      "epoch": 0.2225,
      "grad_norm": 7.580309867858887,
      "learning_rate": 4.092105263157895e-06,
      "loss": 0.4127,
      "step": 89
    },
    {
      "Batch Mean": 4.122764587402344,
      "accuracy": 0.7890625,
      "epoch": 0.2225,
      "step": 89
    },
    {
      "epoch": 0.225,
      "grad_norm": 7.205588340759277,
      "learning_rate": 4.078947368421053e-06,
      "loss": 0.4207,
      "step": 90
    },
    {
      "Batch Mean": 4.157896041870117,
      "accuracy": 0.765625,
      "epoch": 0.225,
      "step": 90
    },
    {
      "epoch": 0.2275,
      "grad_norm": 9.179079055786133,
      "learning_rate": 4.065789473684211e-06,
      "loss": 0.505,
      "step": 91
    },
    {
      "Batch Mean": 4.137635231018066,
      "accuracy": 0.7890625,
      "epoch": 0.2275,
      "step": 91
    },
    {
      "epoch": 0.23,
      "grad_norm": 6.633444309234619,
      "learning_rate": 4.052631578947368e-06,
      "loss": 0.3927,
      "step": 92
    },
    {
      "Batch Mean": 3.7938804626464844,
      "accuracy": 0.828125,
      "epoch": 0.23,
      "step": 92
    },
    {
      "epoch": 0.2325,
      "grad_norm": 6.795446395874023,
      "learning_rate": 4.0394736842105265e-06,
      "loss": 0.4159,
      "step": 93
    },
    {
      "Batch Mean": 3.357052803039551,
      "accuracy": 0.8046875,
      "epoch": 0.2325,
      "step": 93
    },
    {
      "epoch": 0.235,
      "grad_norm": 7.158699989318848,
      "learning_rate": 4.026315789473684e-06,
      "loss": 0.4018,
      "step": 94
    },
    {
      "Batch Mean": 3.3779516220092773,
      "accuracy": 0.75,
      "epoch": 0.235,
      "step": 94
    },
    {
      "epoch": 0.2375,
      "grad_norm": 7.249587059020996,
      "learning_rate": 4.013157894736842e-06,
      "loss": 0.4374,
      "step": 95
    },
    {
      "Batch Mean": 3.2399396896362305,
      "accuracy": 0.8046875,
      "epoch": 0.2375,
      "step": 95
    },
    {
      "epoch": 0.24,
      "grad_norm": 7.230793476104736,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.4345,
      "step": 96
    },
    {
      "Batch Mean": 3.1136474609375,
      "accuracy": 0.8046875,
      "epoch": 0.24,
      "step": 96
    },
    {
      "epoch": 0.2425,
      "grad_norm": 8.101882934570312,
      "learning_rate": 3.986842105263158e-06,
      "loss": 0.4576,
      "step": 97
    },
    {
      "Batch Mean": 3.214869260787964,
      "accuracy": 0.8125,
      "epoch": 0.2425,
      "step": 97
    },
    {
      "epoch": 0.245,
      "grad_norm": 8.142618179321289,
      "learning_rate": 3.9736842105263165e-06,
      "loss": 0.4481,
      "step": 98
    },
    {
      "Batch Mean": 3.2699995040893555,
      "accuracy": 0.8046875,
      "epoch": 0.245,
      "step": 98
    },
    {
      "epoch": 0.2475,
      "grad_norm": 8.672248840332031,
      "learning_rate": 3.960526315789474e-06,
      "loss": 0.4518,
      "step": 99
    },
    {
      "Batch Mean": 3.287128448486328,
      "accuracy": 0.7578125,
      "epoch": 0.2475,
      "step": 99
    },
    {
      "epoch": 0.25,
      "grad_norm": 9.054008483886719,
      "learning_rate": 3.947368421052632e-06,
      "loss": 0.4934,
      "step": 100
    },
    {
      "Batch Mean": 2.6553401947021484,
      "accuracy": 0.7734375,
      "epoch": 0.25,
      "step": 100
    },
    {
      "epoch": 0.2525,
      "grad_norm": 9.374197006225586,
      "learning_rate": 3.93421052631579e-06,
      "loss": 0.5046,
      "step": 101
    },
    {
      "Batch Mean": 2.436018943786621,
      "accuracy": 0.78125,
      "epoch": 0.2525,
      "step": 101
    },
    {
      "epoch": 0.255,
      "grad_norm": 9.066594123840332,
      "learning_rate": 3.921052631578947e-06,
      "loss": 0.5216,
      "step": 102
    },
    {
      "Batch Mean": 2.2069954872131348,
      "accuracy": 0.7734375,
      "epoch": 0.255,
      "step": 102
    },
    {
      "epoch": 0.2575,
      "grad_norm": 6.94660758972168,
      "learning_rate": 3.907894736842106e-06,
      "loss": 0.4278,
      "step": 103
    },
    {
      "Batch Mean": 2.225872755050659,
      "accuracy": 0.7734375,
      "epoch": 0.2575,
      "step": 103
    },
    {
      "epoch": 0.26,
      "grad_norm": 6.518649101257324,
      "learning_rate": 3.894736842105263e-06,
      "loss": 0.4473,
      "step": 104
    },
    {
      "Batch Mean": 2.217318058013916,
      "accuracy": 0.796875,
      "epoch": 0.26,
      "step": 104
    },
    {
      "epoch": 0.2625,
      "grad_norm": 6.582048416137695,
      "learning_rate": 3.8815789473684214e-06,
      "loss": 0.4356,
      "step": 105
    },
    {
      "Batch Mean": 1.917119026184082,
      "accuracy": 0.828125,
      "epoch": 0.2625,
      "step": 105
    },
    {
      "epoch": 0.265,
      "grad_norm": 7.497337818145752,
      "learning_rate": 3.868421052631579e-06,
      "loss": 0.3825,
      "step": 106
    },
    {
      "Batch Mean": 1.5780539512634277,
      "accuracy": 0.7578125,
      "epoch": 0.265,
      "step": 106
    },
    {
      "epoch": 0.2675,
      "grad_norm": 8.559232711791992,
      "learning_rate": 3.855263157894737e-06,
      "loss": 0.4984,
      "step": 107
    },
    {
      "Batch Mean": 1.9931042194366455,
      "accuracy": 0.8203125,
      "epoch": 0.2675,
      "step": 107
    },
    {
      "epoch": 0.27,
      "grad_norm": 6.91691780090332,
      "learning_rate": 3.842105263157895e-06,
      "loss": 0.401,
      "step": 108
    },
    {
      "Batch Mean": 2.131106376647949,
      "accuracy": 0.8046875,
      "epoch": 0.27,
      "step": 108
    },
    {
      "epoch": 0.2725,
      "grad_norm": 6.739565849304199,
      "learning_rate": 3.828947368421053e-06,
      "loss": 0.3582,
      "step": 109
    },
    {
      "Batch Mean": 2.5897467136383057,
      "accuracy": 0.8671875,
      "epoch": 0.2725,
      "step": 109
    },
    {
      "epoch": 0.275,
      "grad_norm": 8.209200859069824,
      "learning_rate": 3.815789473684211e-06,
      "loss": 0.3216,
      "step": 110
    },
    {
      "Batch Mean": 2.6740541458129883,
      "accuracy": 0.75,
      "epoch": 0.275,
      "step": 110
    },
    {
      "epoch": 0.2775,
      "grad_norm": 10.885510444641113,
      "learning_rate": 3.802631578947369e-06,
      "loss": 0.5196,
      "step": 111
    },
    {
      "Batch Mean": 2.9480109214782715,
      "accuracy": 0.703125,
      "epoch": 0.2775,
      "step": 111
    },
    {
      "epoch": 0.28,
      "grad_norm": 13.55850887298584,
      "learning_rate": 3.789473684210527e-06,
      "loss": 0.5931,
      "step": 112
    },
    {
      "Batch Mean": 3.3308558464050293,
      "accuracy": 0.8515625,
      "epoch": 0.28,
      "step": 112
    },
    {
      "epoch": 0.2825,
      "grad_norm": 9.246851921081543,
      "learning_rate": 3.7763157894736847e-06,
      "loss": 0.3901,
      "step": 113
    },
    {
      "Batch Mean": 2.8297948837280273,
      "accuracy": 0.7890625,
      "epoch": 0.2825,
      "step": 113
    },
    {
      "epoch": 0.285,
      "grad_norm": 9.644515037536621,
      "learning_rate": 3.7631578947368426e-06,
      "loss": 0.4573,
      "step": 114
    },
    {
      "Batch Mean": 3.7451376914978027,
      "accuracy": 0.7265625,
      "epoch": 0.285,
      "step": 114
    },
    {
      "epoch": 0.2875,
      "grad_norm": 12.58398151397705,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.5545,
      "step": 115
    },
    {
      "Batch Mean": 3.6171021461486816,
      "accuracy": 0.7890625,
      "epoch": 0.2875,
      "step": 115
    },
    {
      "epoch": 0.29,
      "grad_norm": 9.254029273986816,
      "learning_rate": 3.736842105263158e-06,
      "loss": 0.4333,
      "step": 116
    },
    {
      "Batch Mean": 2.7716548442840576,
      "accuracy": 0.8046875,
      "epoch": 0.29,
      "step": 116
    },
    {
      "epoch": 0.2925,
      "grad_norm": 10.669205665588379,
      "learning_rate": 3.723684210526316e-06,
      "loss": 0.4602,
      "step": 117
    },
    {
      "Batch Mean": 2.781661033630371,
      "accuracy": 0.7734375,
      "epoch": 0.2925,
      "step": 117
    },
    {
      "epoch": 0.295,
      "grad_norm": 10.094223976135254,
      "learning_rate": 3.710526315789474e-06,
      "loss": 0.528,
      "step": 118
    },
    {
      "Batch Mean": 2.198807716369629,
      "accuracy": 0.7578125,
      "epoch": 0.295,
      "step": 118
    },
    {
      "epoch": 0.2975,
      "grad_norm": 7.635989189147949,
      "learning_rate": 3.6973684210526317e-06,
      "loss": 0.4268,
      "step": 119
    },
    {
      "Batch Mean": 2.0033488273620605,
      "accuracy": 0.7734375,
      "epoch": 0.2975,
      "step": 119
    },
    {
      "epoch": 0.3,
      "grad_norm": 7.30623197555542,
      "learning_rate": 3.6842105263157896e-06,
      "loss": 0.4528,
      "step": 120
    },
    {
      "Batch Mean": 1.8473689556121826,
      "accuracy": 0.859375,
      "epoch": 0.3,
      "step": 120
    },
    {
      "epoch": 0.3025,
      "grad_norm": 6.51129674911499,
      "learning_rate": 3.6710526315789476e-06,
      "loss": 0.4022,
      "step": 121
    },
    {
      "Batch Mean": 1.650212287902832,
      "accuracy": 0.78125,
      "epoch": 0.3025,
      "step": 121
    },
    {
      "epoch": 0.305,
      "grad_norm": 7.191035270690918,
      "learning_rate": 3.657894736842106e-06,
      "loss": 0.4487,
      "step": 122
    },
    {
      "Batch Mean": 1.7975679636001587,
      "accuracy": 0.7890625,
      "epoch": 0.305,
      "step": 122
    },
    {
      "epoch": 0.3075,
      "grad_norm": 6.7035651206970215,
      "learning_rate": 3.644736842105264e-06,
      "loss": 0.4338,
      "step": 123
    },
    {
      "Batch Mean": 1.5073213577270508,
      "accuracy": 0.8125,
      "epoch": 0.3075,
      "step": 123
    },
    {
      "epoch": 0.31,
      "grad_norm": 6.955989837646484,
      "learning_rate": 3.6315789473684217e-06,
      "loss": 0.4144,
      "step": 124
    },
    {
      "Batch Mean": 1.7353585958480835,
      "accuracy": 0.75,
      "epoch": 0.31,
      "step": 124
    },
    {
      "epoch": 0.3125,
      "grad_norm": 8.312121391296387,
      "learning_rate": 3.618421052631579e-06,
      "loss": 0.5017,
      "step": 125
    },
    {
      "Batch Mean": 1.718948245048523,
      "accuracy": 0.734375,
      "epoch": 0.3125,
      "step": 125
    },
    {
      "epoch": 0.315,
      "grad_norm": 8.334877967834473,
      "learning_rate": 3.605263157894737e-06,
      "loss": 0.4731,
      "step": 126
    },
    {
      "Batch Mean": 1.7114816904067993,
      "accuracy": 0.8359375,
      "epoch": 0.315,
      "step": 126
    },
    {
      "epoch": 0.3175,
      "grad_norm": 7.221029281616211,
      "learning_rate": 3.592105263157895e-06,
      "loss": 0.3843,
      "step": 127
    },
    {
      "Batch Mean": 1.466775894165039,
      "accuracy": 0.7578125,
      "epoch": 0.3175,
      "step": 127
    },
    {
      "epoch": 0.32,
      "grad_norm": 9.671870231628418,
      "learning_rate": 3.578947368421053e-06,
      "loss": 0.517,
      "step": 128
    },
    {
      "Batch Mean": 2.0674805641174316,
      "accuracy": 0.8125,
      "epoch": 0.32,
      "step": 128
    },
    {
      "epoch": 0.3225,
      "grad_norm": 7.535254955291748,
      "learning_rate": 3.565789473684211e-06,
      "loss": 0.4002,
      "step": 129
    },
    {
      "Batch Mean": 1.9499692916870117,
      "accuracy": 0.8046875,
      "epoch": 0.3225,
      "step": 129
    },
    {
      "epoch": 0.325,
      "grad_norm": 8.19841480255127,
      "learning_rate": 3.5526315789473687e-06,
      "loss": 0.4101,
      "step": 130
    },
    {
      "Batch Mean": 1.8141679763793945,
      "accuracy": 0.7890625,
      "epoch": 0.325,
      "step": 130
    },
    {
      "epoch": 0.3275,
      "grad_norm": 8.877778053283691,
      "learning_rate": 3.5394736842105266e-06,
      "loss": 0.458,
      "step": 131
    },
    {
      "Batch Mean": 2.349834680557251,
      "accuracy": 0.8046875,
      "epoch": 0.3275,
      "step": 131
    },
    {
      "epoch": 0.33,
      "grad_norm": 7.818430423736572,
      "learning_rate": 3.5263157894736846e-06,
      "loss": 0.3948,
      "step": 132
    },
    {
      "Batch Mean": 2.4295411109924316,
      "accuracy": 0.765625,
      "epoch": 0.33,
      "step": 132
    },
    {
      "epoch": 0.3325,
      "grad_norm": 10.082527160644531,
      "learning_rate": 3.513157894736842e-06,
      "loss": 0.4616,
      "step": 133
    },
    {
      "Batch Mean": 2.609513282775879,
      "accuracy": 0.8359375,
      "epoch": 0.3325,
      "step": 133
    },
    {
      "epoch": 0.335,
      "grad_norm": 8.784564971923828,
      "learning_rate": 3.5e-06,
      "loss": 0.3703,
      "step": 134
    },
    {
      "Batch Mean": 2.7128183841705322,
      "accuracy": 0.7890625,
      "epoch": 0.335,
      "step": 134
    },
    {
      "epoch": 0.3375,
      "grad_norm": 9.766796112060547,
      "learning_rate": 3.486842105263158e-06,
      "loss": 0.3847,
      "step": 135
    },
    {
      "Batch Mean": 3.1417746543884277,
      "accuracy": 0.7265625,
      "epoch": 0.3375,
      "step": 135
    },
    {
      "epoch": 0.34,
      "grad_norm": 11.59825325012207,
      "learning_rate": 3.473684210526316e-06,
      "loss": 0.5143,
      "step": 136
    },
    {
      "Batch Mean": 2.894944190979004,
      "accuracy": 0.7421875,
      "epoch": 0.34,
      "step": 136
    },
    {
      "epoch": 0.3425,
      "grad_norm": 12.137927055358887,
      "learning_rate": 3.460526315789474e-06,
      "loss": 0.5355,
      "step": 137
    },
    {
      "Batch Mean": 2.7786073684692383,
      "accuracy": 0.7890625,
      "epoch": 0.3425,
      "step": 137
    },
    {
      "epoch": 0.345,
      "grad_norm": 9.075066566467285,
      "learning_rate": 3.447368421052632e-06,
      "loss": 0.4115,
      "step": 138
    },
    {
      "Batch Mean": 3.0002739429473877,
      "accuracy": 0.734375,
      "epoch": 0.345,
      "step": 138
    },
    {
      "epoch": 0.3475,
      "grad_norm": 10.028230667114258,
      "learning_rate": 3.43421052631579e-06,
      "loss": 0.4722,
      "step": 139
    },
    {
      "Batch Mean": 2.4786624908447266,
      "accuracy": 0.765625,
      "epoch": 0.3475,
      "step": 139
    },
    {
      "epoch": 0.35,
      "grad_norm": 9.266149520874023,
      "learning_rate": 3.421052631578948e-06,
      "loss": 0.4656,
      "step": 140
    },
    {
      "Batch Mean": 2.1704983711242676,
      "accuracy": 0.8125,
      "epoch": 0.35,
      "step": 140
    },
    {
      "epoch": 0.3525,
      "grad_norm": 6.836582660675049,
      "learning_rate": 3.4078947368421057e-06,
      "loss": 0.3686,
      "step": 141
    },
    {
      "Batch Mean": 2.178023338317871,
      "accuracy": 0.828125,
      "epoch": 0.3525,
      "step": 141
    },
    {
      "epoch": 0.355,
      "grad_norm": 7.482564449310303,
      "learning_rate": 3.3947368421052636e-06,
      "loss": 0.4434,
      "step": 142
    },
    {
      "Batch Mean": 2.207672595977783,
      "accuracy": 0.8359375,
      "epoch": 0.355,
      "step": 142
    },
    {
      "epoch": 0.3575,
      "grad_norm": 9.649080276489258,
      "learning_rate": 3.381578947368421e-06,
      "loss": 0.4042,
      "step": 143
    },
    {
      "Batch Mean": 2.477532386779785,
      "accuracy": 0.8046875,
      "epoch": 0.3575,
      "step": 143
    },
    {
      "epoch": 0.36,
      "grad_norm": 6.769596576690674,
      "learning_rate": 3.368421052631579e-06,
      "loss": 0.3742,
      "step": 144
    },
    {
      "Batch Mean": 2.3647336959838867,
      "accuracy": 0.7578125,
      "epoch": 0.36,
      "step": 144
    },
    {
      "epoch": 0.3625,
      "grad_norm": 9.769651412963867,
      "learning_rate": 3.355263157894737e-06,
      "loss": 0.4972,
      "step": 145
    },
    {
      "Batch Mean": 2.282806396484375,
      "accuracy": 0.765625,
      "epoch": 0.3625,
      "step": 145
    },
    {
      "epoch": 0.365,
      "grad_norm": 9.153217315673828,
      "learning_rate": 3.342105263157895e-06,
      "loss": 0.4581,
      "step": 146
    },
    {
      "Batch Mean": 2.2191848754882812,
      "accuracy": 0.7421875,
      "epoch": 0.365,
      "step": 146
    },
    {
      "epoch": 0.3675,
      "grad_norm": 7.448163032531738,
      "learning_rate": 3.3289473684210528e-06,
      "loss": 0.4751,
      "step": 147
    },
    {
      "Batch Mean": 2.034508228302002,
      "accuracy": 0.7109375,
      "epoch": 0.3675,
      "step": 147
    },
    {
      "epoch": 0.37,
      "grad_norm": 8.64769458770752,
      "learning_rate": 3.3157894736842107e-06,
      "loss": 0.55,
      "step": 148
    },
    {
      "Batch Mean": 1.7862319946289062,
      "accuracy": 0.859375,
      "epoch": 0.37,
      "step": 148
    },
    {
      "epoch": 0.3725,
      "grad_norm": 6.058819770812988,
      "learning_rate": 3.302631578947369e-06,
      "loss": 0.3536,
      "step": 149
    },
    {
      "Batch Mean": 1.8278677463531494,
      "accuracy": 0.8046875,
      "epoch": 0.3725,
      "step": 149
    },
    {
      "epoch": 0.375,
      "grad_norm": 7.812012672424316,
      "learning_rate": 3.289473684210527e-06,
      "loss": 0.4398,
      "step": 150
    },
    {
      "Batch Mean": 1.9891557693481445,
      "accuracy": 0.8203125,
      "epoch": 0.375,
      "step": 150
    },
    {
      "epoch": 0.3775,
      "grad_norm": 7.331231117248535,
      "learning_rate": 3.276315789473685e-06,
      "loss": 0.4227,
      "step": 151
    },
    {
      "Batch Mean": 1.683842658996582,
      "accuracy": 0.7578125,
      "epoch": 0.3775,
      "step": 151
    },
    {
      "epoch": 0.38,
      "grad_norm": 6.605899333953857,
      "learning_rate": 3.2631578947368423e-06,
      "loss": 0.4956,
      "step": 152
    },
    {
      "Batch Mean": 1.8491768836975098,
      "accuracy": 0.8203125,
      "epoch": 0.38,
      "step": 152
    },
    {
      "epoch": 0.3825,
      "grad_norm": 6.61679744720459,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.3815,
      "step": 153
    },
    {
      "Batch Mean": 1.5500710010528564,
      "accuracy": 0.8203125,
      "epoch": 0.3825,
      "step": 153
    },
    {
      "epoch": 0.385,
      "grad_norm": 7.707108497619629,
      "learning_rate": 3.236842105263158e-06,
      "loss": 0.4151,
      "step": 154
    },
    {
      "Batch Mean": 1.4066014289855957,
      "accuracy": 0.7890625,
      "epoch": 0.385,
      "step": 154
    },
    {
      "epoch": 0.3875,
      "grad_norm": 7.169893741607666,
      "learning_rate": 3.223684210526316e-06,
      "loss": 0.4474,
      "step": 155
    },
    {
      "Batch Mean": 1.7346997261047363,
      "accuracy": 0.7734375,
      "epoch": 0.3875,
      "step": 155
    },
    {
      "epoch": 0.39,
      "grad_norm": 10.779695510864258,
      "learning_rate": 3.210526315789474e-06,
      "loss": 0.4299,
      "step": 156
    },
    {
      "Batch Mean": 1.810314655303955,
      "accuracy": 0.796875,
      "epoch": 0.39,
      "step": 156
    },
    {
      "epoch": 0.3925,
      "grad_norm": 7.573057174682617,
      "learning_rate": 3.197368421052632e-06,
      "loss": 0.4399,
      "step": 157
    },
    {
      "Batch Mean": 1.7872644662857056,
      "accuracy": 0.7734375,
      "epoch": 0.3925,
      "step": 157
    },
    {
      "epoch": 0.395,
      "grad_norm": 7.816164493560791,
      "learning_rate": 3.1842105263157898e-06,
      "loss": 0.4131,
      "step": 158
    },
    {
      "Batch Mean": 1.804029941558838,
      "accuracy": 0.765625,
      "epoch": 0.395,
      "step": 158
    },
    {
      "epoch": 0.3975,
      "grad_norm": 8.655269622802734,
      "learning_rate": 3.1710526315789477e-06,
      "loss": 0.4737,
      "step": 159
    },
    {
      "Batch Mean": 1.565956711769104,
      "accuracy": 0.796875,
      "epoch": 0.3975,
      "step": 159
    },
    {
      "epoch": 0.4,
      "grad_norm": 7.699905872344971,
      "learning_rate": 3.157894736842105e-06,
      "loss": 0.4022,
      "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
}