{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.7914691943127963,
  "eval_steps": 10,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 2.2e-05,
      "loss": 0.9856,
      "step": 1
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.1998557720321954e-05,
      "loss": 0.8657,
      "step": 2
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.1994231259500664e-05,
      "loss": 0.7599,
      "step": 3
    },
    {
      "epoch": 0.1,
      "learning_rate": 2.1987021752075498e-05,
      "loss": 0.6924,
      "step": 4
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.1976931088614826e-05,
      "loss": 0.818,
      "step": 5
    },
    {
      "epoch": 0.15,
      "learning_rate": 2.1963961915220263e-05,
      "loss": 1.2993,
      "step": 6
    },
    {
      "epoch": 0.18,
      "learning_rate": 2.1948117632832752e-05,
      "loss": 1.4107,
      "step": 7
    },
    {
      "epoch": 0.2,
      "learning_rate": 2.1929402396340756e-05,
      "loss": 0.8539,
      "step": 8
    },
    {
      "epoch": 0.23,
      "learning_rate": 2.1907821113490676e-05,
      "loss": 0.7822,
      "step": 9
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.1883379443599917e-05,
      "loss": 0.6498,
      "step": 10
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.777102530002594,
      "eval_runtime": 26.948,
      "eval_samples_per_second": 30.726,
      "eval_steps_per_second": 0.482,
      "step": 10
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.1856083796072795e-05,
      "loss": 0.7439,
      "step": 11
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.182594132871982e-05,
      "loss": 1.0097,
      "step": 12
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.179295994588063e-05,
      "loss": 1.3189,
      "step": 13
    },
    {
      "epoch": 0.35,
      "learning_rate": 2.175714829635128e-05,
      "loss": 0.7509,
      "step": 14
    },
    {
      "epoch": 0.38,
      "learning_rate": 2.1718515771116186e-05,
      "loss": 0.7273,
      "step": 15
    },
    {
      "epoch": 0.4,
      "learning_rate": 2.167707250088555e-05,
      "loss": 0.6242,
      "step": 16
    },
    {
      "epoch": 0.43,
      "learning_rate": 2.1632829353438724e-05,
      "loss": 0.6135,
      "step": 17
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.1585797930774335e-05,
      "loss": 0.9365,
      "step": 18
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.1535990566067858e-05,
      "loss": 1.4216,
      "step": 19
    },
    {
      "epoch": 0.51,
      "learning_rate": 2.148342032043747e-05,
      "loss": 0.7369,
      "step": 20
    },
    {
      "epoch": 0.51,
      "eval_loss": 0.7404242157936096,
      "eval_runtime": 26.98,
      "eval_samples_per_second": 30.689,
      "eval_steps_per_second": 0.482,
      "step": 20
    },
    {
      "epoch": 0.53,
      "learning_rate": 2.1428100979518976e-05,
      "loss": 0.7605,
      "step": 21
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.1370047049850775e-05,
      "loss": 0.6095,
      "step": 22
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.130927375506978e-05,
      "loss": 0.5955,
      "step": 23
    },
    {
      "epoch": 0.61,
      "learning_rate": 2.1245797031919265e-05,
      "loss": 0.851,
      "step": 24
    },
    {
      "epoch": 0.63,
      "learning_rate": 2.1179633526069748e-05,
      "loss": 1.324,
      "step": 25
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.1110800587753934e-05,
      "loss": 0.9368,
      "step": 26
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.103931626721694e-05,
      "loss": 0.7307,
      "step": 27
    },
    {
      "epoch": 0.71,
      "learning_rate": 2.0965199309982913e-05,
      "loss": 0.6489,
      "step": 28
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.0888469151939347e-05,
      "loss": 0.536,
      "step": 29
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.0809145914240356e-05,
      "loss": 0.732,
      "step": 30
    },
    {
      "epoch": 0.76,
      "eval_loss": 0.7266919612884521,
      "eval_runtime": 26.9346,
      "eval_samples_per_second": 30.741,
      "eval_steps_per_second": 0.483,
      "step": 30
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.072725039803026e-05,
      "loss": 1.1248,
      "step": 31
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.0642804078988827e-05,
      "loss": 1.0917,
      "step": 32
    },
    {
      "epoch": 0.83,
      "learning_rate": 2.055582910169966e-05,
      "loss": 0.735,
      "step": 33
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.0466348273843176e-05,
      "loss": 0.6749,
      "step": 34
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.0374385060215662e-05,
      "loss": 0.5519,
      "step": 35
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.027996357657605e-05,
      "loss": 0.6593,
      "step": 36
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.018310858332198e-05,
      "loss": 0.959,
      "step": 37
    },
    {
      "epoch": 0.96,
      "learning_rate": 2.008384547899682e-05,
      "loss": 1.168,
      "step": 38
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.9982200293629318e-05,
      "loss": 0.6186,
      "step": 39
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.9878199681907702e-05,
      "loss": 1.1207,
      "step": 40
    },
    {
      "epoch": 1.01,
      "eval_loss": 0.7203702926635742,
      "eval_runtime": 26.9926,
      "eval_samples_per_second": 30.675,
      "eval_steps_per_second": 0.482,
      "step": 40
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.977187091618993e-05,
      "loss": 0.7095,
      "step": 41
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.9663241879351998e-05,
      "loss": 0.6781,
      "step": 42
    },
    {
      "epoch": 1.09,
      "learning_rate": 1.9552341057476144e-05,
      "loss": 0.5649,
      "step": 43
    },
    {
      "epoch": 1.11,
      "learning_rate": 1.9439197532380845e-05,
      "loss": 0.5466,
      "step": 44
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.9323840973994647e-05,
      "loss": 0.8721,
      "step": 45
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.9206301632575707e-05,
      "loss": 1.2152,
      "step": 46
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.9086610330779205e-05,
      "loss": 0.6863,
      "step": 47
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.8964798455574637e-05,
      "loss": 0.6792,
      "step": 48
    },
    {
      "epoch": 1.24,
      "learning_rate": 1.884089795001512e-05,
      "loss": 0.5667,
      "step": 49
    },
    {
      "epoch": 1.26,
      "learning_rate": 1.871494130486089e-05,
      "loss": 0.5256,
      "step": 50
    },
    {
      "epoch": 1.26,
      "eval_loss": 0.6949857473373413,
      "eval_runtime": 26.8774,
      "eval_samples_per_second": 30.807,
      "eval_steps_per_second": 0.484,
      "step": 50
    },
    {
      "epoch": 1.29,
      "learning_rate": 1.8586961550059147e-05,
      "loss": 0.7481,
      "step": 51
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.8456992246082534e-05,
      "loss": 1.2028,
      "step": 52
    },
    {
      "epoch": 1.34,
      "learning_rate": 1.8325067475128493e-05,
      "loss": 0.8791,
      "step": 53
    },
    {
      "epoch": 1.36,
      "learning_rate": 1.8191221832181777e-05,
      "loss": 0.6651,
      "step": 54
    },
    {
      "epoch": 1.39,
      "learning_rate": 1.8055490415942538e-05,
      "loss": 0.5875,
      "step": 55
    },
    {
      "epoch": 1.42,
      "learning_rate": 1.791790881962229e-05,
      "loss": 0.5143,
      "step": 56
    },
    {
      "epoch": 1.44,
      "learning_rate": 1.77785131216102e-05,
      "loss": 0.6447,
      "step": 57
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.7637339876012172e-05,
      "loss": 1.0286,
      "step": 58
    },
    {
      "epoch": 1.49,
      "learning_rate": 1.749442610306515e-05,
      "loss": 1.1227,
      "step": 59
    },
    {
      "epoch": 1.52,
      "learning_rate": 1.7349809279429216e-05,
      "loss": 0.6634,
      "step": 60
    },
    {
      "epoch": 1.52,
      "eval_loss": 0.6882586479187012,
      "eval_runtime": 26.9816,
      "eval_samples_per_second": 30.688,
      "eval_steps_per_second": 0.482,
      "step": 60
    },
    {
      "epoch": 1.54,
      "learning_rate": 1.7203527328359972e-05,
      "loss": 0.6145,
      "step": 61
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.705561860976384e-05,
      "loss": 0.5139,
      "step": 62
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.6906121910138824e-05,
      "loss": 0.5819,
      "step": 63
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.675507643240343e-05,
      "loss": 0.8716,
      "step": 64
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.6602521785616394e-05,
      "loss": 1.2125,
      "step": 65
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.6448497974589863e-05,
      "loss": 0.6803,
      "step": 66
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.6293045389398855e-05,
      "loss": 0.6762,
      "step": 67
    },
    {
      "epoch": 1.72,
      "learning_rate": 1.6136204794789646e-05,
      "loss": 0.5324,
      "step": 68
    },
    {
      "epoch": 1.74,
      "learning_rate": 1.597801731948993e-05,
      "loss": 0.541,
      "step": 69
    },
    {
      "epoch": 1.77,
      "learning_rate": 1.5818524445423504e-05,
      "loss": 0.8724,
      "step": 70
    },
    {
      "epoch": 1.77,
      "eval_loss": 0.6789196729660034,
      "eval_runtime": 26.8064,
      "eval_samples_per_second": 30.888,
      "eval_steps_per_second": 0.485,
      "step": 70
    },
    {
      "epoch": 1.79,
      "learning_rate": 1.5657767996832395e-05,
      "loss": 1.204,
      "step": 71
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.549579012930912e-05,
      "loss": 0.6885,
      "step": 72
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.5332633318742157e-05,
      "loss": 0.6975,
      "step": 73
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.5168340350177374e-05,
      "loss": 0.5451,
      "step": 74
    },
    {
      "epoch": 1.9,
      "learning_rate": 1.5002954306598364e-05,
      "loss": 0.4803,
      "step": 75
    },
    {
      "epoch": 1.92,
      "learning_rate": 1.4836518557628703e-05,
      "loss": 0.6776,
      "step": 76
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.4669076748159028e-05,
      "loss": 1.0698,
      "step": 77
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.4500672786901884e-05,
      "loss": 0.7064,
      "step": 78
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.4331350834877457e-05,
      "loss": 0.7407,
      "step": 79
    },
    {
      "epoch": 2.02,
      "learning_rate": 1.4161155293833112e-05,
      "loss": 0.9098,
      "step": 80
    },
    {
      "epoch": 2.02,
      "eval_loss": 0.6750211715698242,
      "eval_runtime": 27.1108,
      "eval_samples_per_second": 30.541,
      "eval_steps_per_second": 0.48,
      "step": 80
    },
    {
      "epoch": 2.05,
      "learning_rate": 1.3990130794599772e-05,
      "loss": 0.6304,
      "step": 81
    },
    {
      "epoch": 2.07,
      "learning_rate": 1.3818322185388293e-05,
      "loss": 0.5601,
      "step": 82
    },
    {
      "epoch": 2.1,
      "learning_rate": 1.3645774520028791e-05,
      "loss": 0.4661,
      "step": 83
    },
    {
      "epoch": 2.12,
      "learning_rate": 1.3472533046156025e-05,
      "loss": 0.5971,
      "step": 84
    },
    {
      "epoch": 2.15,
      "learning_rate": 1.3298643193344028e-05,
      "loss": 0.8505,
      "step": 85
    },
    {
      "epoch": 2.17,
      "learning_rate": 1.3124150561192969e-05,
      "loss": 1.1119,
      "step": 86
    },
    {
      "epoch": 2.2,
      "learning_rate": 1.2949100907371452e-05,
      "loss": 0.6298,
      "step": 87
    },
    {
      "epoch": 2.22,
      "learning_rate": 1.2773540135617358e-05,
      "loss": 0.5901,
      "step": 88
    },
    {
      "epoch": 2.25,
      "learning_rate": 1.2597514283700393e-05,
      "loss": 0.483,
      "step": 89
    },
    {
      "epoch": 2.27,
      "learning_rate": 1.2421069511349471e-05,
      "loss": 0.522,
      "step": 90
    },
    {
      "epoch": 2.27,
      "eval_loss": 0.6687783002853394,
      "eval_runtime": 26.924,
      "eval_samples_per_second": 30.753,
      "eval_steps_per_second": 0.483,
      "step": 90
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.2244252088148128e-05,
      "loss": 0.8623,
      "step": 91
    },
    {
      "epoch": 2.33,
      "learning_rate": 1.2067108381401128e-05,
      "loss": 1.1752,
      "step": 92
    },
    {
      "epoch": 2.35,
      "learning_rate": 1.1889684843975447e-05,
      "loss": 0.6268,
      "step": 93
    },
    {
      "epoch": 2.38,
      "learning_rate": 1.1712028002118794e-05,
      "loss": 0.6146,
      "step": 94
    },
    {
      "epoch": 2.4,
      "learning_rate": 1.1534184443258931e-05,
      "loss": 0.4776,
      "step": 95
    },
    {
      "epoch": 2.43,
      "learning_rate": 1.1356200803786916e-05,
      "loss": 0.4863,
      "step": 96
    },
    {
      "epoch": 2.45,
      "learning_rate": 1.1178123756827518e-05,
      "loss": 0.7674,
      "step": 97
    },
    {
      "epoch": 2.48,
      "learning_rate": 1.1e-05,
      "loss": 1.1923,
      "step": 98
    },
    {
      "epoch": 2.5,
      "learning_rate": 1.0821876243172483e-05,
      "loss": 0.6922,
      "step": 99
    },
    {
      "epoch": 2.53,
      "learning_rate": 1.0643799196213087e-05,
      "loss": 0.6416,
      "step": 100
    },
    {
      "epoch": 2.53,
      "eval_loss": 0.6664387583732605,
      "eval_runtime": 27.0713,
      "eval_samples_per_second": 30.586,
      "eval_steps_per_second": 0.48,
      "step": 100
    },
    {
      "epoch": 2.55,
      "learning_rate": 1.0465815556741072e-05,
      "loss": 0.5438,
      "step": 101
    },
    {
      "epoch": 2.58,
      "learning_rate": 1.0287971997881207e-05,
      "loss": 0.4733,
      "step": 102
    },
    {
      "epoch": 2.6,
      "learning_rate": 1.0110315156024555e-05,
      "loss": 0.6894,
      "step": 103
    },
    {
      "epoch": 2.63,
      "learning_rate": 9.932891618598871e-06,
      "loss": 1.0594,
      "step": 104
    },
    {
      "epoch": 2.65,
      "learning_rate": 9.755747911851873e-06,
      "loss": 0.8682,
      "step": 105
    },
    {
      "epoch": 2.68,
      "learning_rate": 9.578930488650532e-06,
      "loss": 0.6275,
      "step": 106
    },
    {
      "epoch": 2.7,
      "learning_rate": 9.40248571629961e-06,
      "loss": 0.5676,
      "step": 107
    },
    {
      "epoch": 2.73,
      "learning_rate": 9.226459864382642e-06,
      "loss": 0.4443,
      "step": 108
    },
    {
      "epoch": 2.76,
      "learning_rate": 9.05089909262855e-06,
      "loss": 0.5907,
      "step": 109
    },
    {
      "epoch": 2.78,
      "learning_rate": 8.875849438807032e-06,
      "loss": 0.9166,
      "step": 110
    },
    {
      "epoch": 2.78,
      "eval_loss": 0.6656625270843506,
      "eval_runtime": 26.8682,
      "eval_samples_per_second": 30.817,
      "eval_steps_per_second": 0.484,
      "step": 110
    },
    {
      "epoch": 2.81,
      "learning_rate": 8.701356806655973e-06,
      "loss": 1.0669,
      "step": 111
    },
    {
      "epoch": 2.83,
      "learning_rate": 8.52746695384398e-06,
      "loss": 0.6286,
      "step": 112
    },
    {
      "epoch": 2.86,
      "learning_rate": 8.354225479971213e-06,
      "loss": 0.5951,
      "step": 113
    },
    {
      "epoch": 2.88,
      "learning_rate": 8.181677814611703e-06,
      "loss": 0.4757,
      "step": 114
    },
    {
      "epoch": 2.91,
      "learning_rate": 8.009869205400227e-06,
      "loss": 0.5694,
      "step": 115
    },
    {
      "epoch": 2.93,
      "learning_rate": 7.83884470616689e-06,
      "loss": 0.8569,
      "step": 116
    },
    {
      "epoch": 2.96,
      "learning_rate": 7.668649165122545e-06,
      "loss": 1.0254,
      "step": 117
    },
    {
      "epoch": 2.98,
      "learning_rate": 7.49932721309812e-06,
      "loss": 0.5457,
      "step": 118
    },
    {
      "epoch": 3.01,
      "learning_rate": 7.330923251840976e-06,
      "loss": 0.9681,
      "step": 119
    },
    {
      "epoch": 3.03,
      "learning_rate": 7.163481442371295e-06,
      "loss": 0.5708,
      "step": 120
    },
    {
      "epoch": 3.03,
      "eval_loss": 0.6612405776977539,
      "eval_runtime": 27.1115,
      "eval_samples_per_second": 30.541,
      "eval_steps_per_second": 0.48,
      "step": 120
    },
    {
      "epoch": 3.06,
      "learning_rate": 6.997045693401637e-06,
      "loss": 0.5819,
      "step": 121
    },
    {
      "epoch": 3.08,
      "learning_rate": 6.831659649822625e-06,
      "loss": 0.4961,
      "step": 122
    },
    {
      "epoch": 3.11,
      "learning_rate": 6.667366681257843e-06,
      "loss": 0.4893,
      "step": 123
    },
    {
      "epoch": 3.13,
      "learning_rate": 6.504209870690885e-06,
      "loss": 0.7579,
      "step": 124
    },
    {
      "epoch": 3.16,
      "learning_rate": 6.342232003167612e-06,
      "loss": 1.0994,
      "step": 125
    },
    {
      "epoch": 3.18,
      "learning_rate": 6.181475554576494e-06,
      "loss": 0.7208,
      "step": 126
    },
    {
      "epoch": 3.21,
      "learning_rate": 6.021982680510073e-06,
      "loss": 0.6245,
      "step": 127
    },
    {
      "epoch": 3.24,
      "learning_rate": 5.863795205210353e-06,
      "loss": 0.4971,
      "step": 128
    },
    {
      "epoch": 3.26,
      "learning_rate": 5.7069546106011436e-06,
      "loss": 0.4555,
      "step": 129
    },
    {
      "epoch": 3.29,
      "learning_rate": 5.551502025410141e-06,
      "loss": 0.6616,
      "step": 130
    },
    {
      "epoch": 3.29,
      "eval_loss": 0.6605544686317444,
      "eval_runtime": 26.9513,
      "eval_samples_per_second": 30.722,
      "eval_steps_per_second": 0.482,
      "step": 130
    },
    {
      "epoch": 3.31,
      "learning_rate": 5.397478214383611e-06,
      "loss": 0.9955,
      "step": 131
    },
    {
      "epoch": 3.34,
      "learning_rate": 5.244923567596569e-06,
      "loss": 0.9027,
      "step": 132
    },
    {
      "epoch": 3.36,
      "learning_rate": 5.093878089861178e-06,
      "loss": 0.5898,
      "step": 133
    },
    {
      "epoch": 3.39,
      "learning_rate": 4.9443813902361605e-06,
      "loss": 0.5661,
      "step": 134
    },
    {
      "epoch": 3.41,
      "learning_rate": 4.796472671640028e-06,
      "loss": 0.4364,
      "step": 135
    },
    {
      "epoch": 3.44,
      "learning_rate": 4.650190720570789e-06,
      "loss": 0.5682,
      "step": 136
    },
    {
      "epoch": 3.46,
      "learning_rate": 4.505573896934854e-06,
      "loss": 0.8235,
      "step": 137
    },
    {
      "epoch": 3.49,
      "learning_rate": 4.3626601239878285e-06,
      "loss": 1.1127,
      "step": 138
    },
    {
      "epoch": 3.51,
      "learning_rate": 4.221486878389799e-06,
      "loss": 0.6107,
      "step": 139
    },
    {
      "epoch": 3.54,
      "learning_rate": 4.08209118037771e-06,
      "loss": 0.5709,
      "step": 140
    },
    {
      "epoch": 3.54,
      "eval_loss": 0.6593899726867676,
      "eval_runtime": 27.0907,
      "eval_samples_per_second": 30.564,
      "eval_steps_per_second": 0.48,
      "step": 140
    },
    {
      "epoch": 3.56,
      "learning_rate": 3.944509584057463e-06,
      "loss": 0.4484,
      "step": 141
    },
    {
      "epoch": 3.59,
      "learning_rate": 3.808778167818225e-06,
      "loss": 0.4906,
      "step": 142
    },
    {
      "epoch": 3.61,
      "learning_rate": 3.67493252487151e-06,
      "loss": 0.8204,
      "step": 143
    },
    {
      "epoch": 3.64,
      "learning_rate": 3.543007753917464e-06,
      "loss": 1.1114,
      "step": 144
    },
    {
      "epoch": 3.67,
      "learning_rate": 3.4130384499408527e-06,
      "loss": 0.6144,
      "step": 145
    },
    {
      "epoch": 3.69,
      "learning_rate": 3.285058695139109e-06,
      "loss": 0.6036,
      "step": 146
    },
    {
      "epoch": 3.72,
      "learning_rate": 3.159102049984881e-06,
      "loss": 0.4777,
      "step": 147
    },
    {
      "epoch": 3.74,
      "learning_rate": 3.0352015444253654e-06,
      "loss": 0.4602,
      "step": 148
    },
    {
      "epoch": 3.77,
      "learning_rate": 2.9133896692207982e-06,
      "loss": 0.6665,
      "step": 149
    },
    {
      "epoch": 3.79,
      "learning_rate": 2.7936983674242933e-06,
      "loss": 1.1254,
      "step": 150
    },
    {
      "epoch": 3.79,
      "eval_loss": 0.6585595607757568,
      "eval_runtime": 26.9155,
      "eval_samples_per_second": 30.763,
      "eval_steps_per_second": 0.483,
      "step": 150
    }
  ],
  "logging_steps": 1,
  "max_steps": 195,
  "num_train_epochs": 5,
  "save_steps": 25,
  "total_flos": 3.7484357972760986e+18,
  "trial_name": null,
  "trial_params": null
}