{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6493506493506493,
  "eval_steps": 10,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003246753246753247,
      "grad_norm": 16.375,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 1.4017,
      "step": 1
    },
    {
      "epoch": 0.006493506493506494,
      "grad_norm": 16.25,
      "learning_rate": 8.000000000000001e-07,
      "loss": 1.4229,
      "step": 2
    },
    {
      "epoch": 0.00974025974025974,
      "grad_norm": 16.75,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.4112,
      "step": 3
    },
    {
      "epoch": 0.012987012987012988,
      "grad_norm": 16.5,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 1.3959,
      "step": 4
    },
    {
      "epoch": 0.016233766233766232,
      "grad_norm": 16.125,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.3789,
      "step": 5
    },
    {
      "epoch": 0.01948051948051948,
      "grad_norm": 14.4375,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.3618,
      "step": 6
    },
    {
      "epoch": 0.022727272727272728,
      "grad_norm": 10.1875,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 1.3214,
      "step": 7
    },
    {
      "epoch": 0.025974025974025976,
      "grad_norm": 7.4375,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 1.2885,
      "step": 8
    },
    {
      "epoch": 0.02922077922077922,
      "grad_norm": 6.28125,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 1.2436,
      "step": 9
    },
    {
      "epoch": 0.032467532467532464,
      "grad_norm": 5.75,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.2269,
      "step": 10
    },
    {
      "epoch": 0.032467532467532464,
      "eval_loss": 1.1976113319396973,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 175.0273,
      "eval_samples_per_second": 11.878,
      "eval_steps_per_second": 1.485,
      "step": 10
    },
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 5.375,
      "learning_rate": 4.4e-06,
      "loss": 1.1925,
      "step": 11
    },
    {
      "epoch": 0.03896103896103896,
      "grad_norm": 5.125,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.1307,
      "step": 12
    },
    {
      "epoch": 0.04220779220779221,
      "grad_norm": 5.125,
      "learning_rate": 5.2e-06,
      "loss": 1.0778,
      "step": 13
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 5.0625,
      "learning_rate": 5.600000000000001e-06,
      "loss": 1.0067,
      "step": 14
    },
    {
      "epoch": 0.048701298701298704,
      "grad_norm": 5.75,
      "learning_rate": 6e-06,
      "loss": 0.9668,
      "step": 15
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 5.15625,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.875,
      "step": 16
    },
    {
      "epoch": 0.05519480519480519,
      "grad_norm": 4.875,
      "learning_rate": 6.800000000000001e-06,
      "loss": 0.8297,
      "step": 17
    },
    {
      "epoch": 0.05844155844155844,
      "grad_norm": 4.5625,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 0.7703,
      "step": 18
    },
    {
      "epoch": 0.06168831168831169,
      "grad_norm": 3.90625,
      "learning_rate": 7.600000000000001e-06,
      "loss": 0.7327,
      "step": 19
    },
    {
      "epoch": 0.06493506493506493,
      "grad_norm": 2.78125,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.6672,
      "step": 20
    },
    {
      "epoch": 0.06493506493506493,
      "eval_loss": 0.6521233320236206,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 174.999,
      "eval_samples_per_second": 11.88,
      "eval_steps_per_second": 1.486,
      "step": 20
    },
    {
      "epoch": 0.06818181818181818,
      "grad_norm": 2.140625,
      "learning_rate": 8.400000000000001e-06,
      "loss": 0.6507,
      "step": 21
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 1.828125,
      "learning_rate": 8.8e-06,
      "loss": 0.6215,
      "step": 22
    },
    {
      "epoch": 0.07467532467532467,
      "grad_norm": 1.5546875,
      "learning_rate": 9.200000000000002e-06,
      "loss": 0.5992,
      "step": 23
    },
    {
      "epoch": 0.07792207792207792,
      "grad_norm": 1.4453125,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.5748,
      "step": 24
    },
    {
      "epoch": 0.08116883116883117,
      "grad_norm": 1.328125,
      "learning_rate": 1e-05,
      "loss": 0.5572,
      "step": 25
    },
    {
      "epoch": 0.08441558441558442,
      "grad_norm": 1.4765625,
      "learning_rate": 1.04e-05,
      "loss": 0.542,
      "step": 26
    },
    {
      "epoch": 0.08766233766233766,
      "grad_norm": 1.1171875,
      "learning_rate": 1.0800000000000002e-05,
      "loss": 0.5317,
      "step": 27
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 0.90625,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 0.5173,
      "step": 28
    },
    {
      "epoch": 0.09415584415584416,
      "grad_norm": 0.83984375,
      "learning_rate": 1.16e-05,
      "loss": 0.4892,
      "step": 29
    },
    {
      "epoch": 0.09740259740259741,
      "grad_norm": 0.828125,
      "learning_rate": 1.2e-05,
      "loss": 0.491,
      "step": 30
    },
    {
      "epoch": 0.09740259740259741,
      "eval_loss": 0.48583006858825684,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 174.9705,
      "eval_samples_per_second": 11.882,
      "eval_steps_per_second": 1.486,
      "step": 30
    },
    {
      "epoch": 0.10064935064935066,
      "grad_norm": 0.8359375,
      "learning_rate": 1.2400000000000002e-05,
      "loss": 0.4852,
      "step": 31
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 1.0078125,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 0.4749,
      "step": 32
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 0.99609375,
      "learning_rate": 1.3200000000000002e-05,
      "loss": 0.467,
      "step": 33
    },
    {
      "epoch": 0.11038961038961038,
      "grad_norm": 0.734375,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 0.4545,
      "step": 34
    },
    {
      "epoch": 0.11363636363636363,
      "grad_norm": 0.69140625,
      "learning_rate": 1.4e-05,
      "loss": 0.4609,
      "step": 35
    },
    {
      "epoch": 0.11688311688311688,
      "grad_norm": 0.69921875,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 0.4497,
      "step": 36
    },
    {
      "epoch": 0.12012987012987013,
      "grad_norm": 0.703125,
      "learning_rate": 1.48e-05,
      "loss": 0.4607,
      "step": 37
    },
    {
      "epoch": 0.12337662337662338,
      "grad_norm": 0.6328125,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 0.443,
      "step": 38
    },
    {
      "epoch": 0.1266233766233766,
      "grad_norm": 0.65234375,
      "learning_rate": 1.5600000000000003e-05,
      "loss": 0.4428,
      "step": 39
    },
    {
      "epoch": 0.12987012987012986,
      "grad_norm": 0.640625,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.435,
      "step": 40
    },
    {
      "epoch": 0.12987012987012986,
      "eval_loss": 0.4367639422416687,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 175.0177,
      "eval_samples_per_second": 11.879,
      "eval_steps_per_second": 1.486,
      "step": 40
    },
    {
      "epoch": 0.1331168831168831,
      "grad_norm": 0.671875,
      "learning_rate": 1.64e-05,
      "loss": 0.438,
      "step": 41
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 0.6484375,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 0.4392,
      "step": 42
    },
    {
      "epoch": 0.1396103896103896,
      "grad_norm": 0.65234375,
      "learning_rate": 1.72e-05,
      "loss": 0.435,
      "step": 43
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.62109375,
      "learning_rate": 1.76e-05,
      "loss": 0.4356,
      "step": 44
    },
    {
      "epoch": 0.1461038961038961,
      "grad_norm": 0.6171875,
      "learning_rate": 1.8e-05,
      "loss": 0.4172,
      "step": 45
    },
    {
      "epoch": 0.14935064935064934,
      "grad_norm": 0.6015625,
      "learning_rate": 1.8400000000000003e-05,
      "loss": 0.4162,
      "step": 46
    },
    {
      "epoch": 0.1525974025974026,
      "grad_norm": 0.609375,
      "learning_rate": 1.88e-05,
      "loss": 0.418,
      "step": 47
    },
    {
      "epoch": 0.15584415584415584,
      "grad_norm": 0.6328125,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.4177,
      "step": 48
    },
    {
      "epoch": 0.1590909090909091,
      "grad_norm": 0.6171875,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.4064,
      "step": 49
    },
    {
      "epoch": 0.16233766233766234,
      "grad_norm": 0.62890625,
      "learning_rate": 2e-05,
      "loss": 0.4078,
      "step": 50
    },
    {
      "epoch": 0.16233766233766234,
      "eval_loss": 0.4077843129634857,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 174.8482,
      "eval_samples_per_second": 11.89,
      "eval_steps_per_second": 1.487,
      "step": 50
    },
    {
      "epoch": 0.16558441558441558,
      "grad_norm": 0.61328125,
      "learning_rate": 1.9999258647132645e-05,
      "loss": 0.4057,
      "step": 51
    },
    {
      "epoch": 0.16883116883116883,
      "grad_norm": 0.62890625,
      "learning_rate": 1.9997034698451396e-05,
      "loss": 0.4172,
      "step": 52
    },
    {
      "epoch": 0.17207792207792208,
      "grad_norm": 0.61328125,
      "learning_rate": 1.9993328483702393e-05,
      "loss": 0.4082,
      "step": 53
    },
    {
      "epoch": 0.17532467532467533,
      "grad_norm": 0.59375,
      "learning_rate": 1.998814055240823e-05,
      "loss": 0.3973,
      "step": 54
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 0.59375,
      "learning_rate": 1.998147167378645e-05,
      "loss": 0.3969,
      "step": 55
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.609375,
      "learning_rate": 1.9973322836635517e-05,
      "loss": 0.4032,
      "step": 56
    },
    {
      "epoch": 0.18506493506493507,
      "grad_norm": 0.5859375,
      "learning_rate": 1.9963695249188185e-05,
      "loss": 0.3956,
      "step": 57
    },
    {
      "epoch": 0.18831168831168832,
      "grad_norm": 0.57421875,
      "learning_rate": 1.995259033893236e-05,
      "loss": 0.3952,
      "step": 58
    },
    {
      "epoch": 0.19155844155844157,
      "grad_norm": 0.59765625,
      "learning_rate": 1.9940009752399462e-05,
      "loss": 0.3905,
      "step": 59
    },
    {
      "epoch": 0.19480519480519481,
      "grad_norm": 0.60546875,
      "learning_rate": 1.9925955354920265e-05,
      "loss": 0.3822,
      "step": 60
    },
    {
      "epoch": 0.19480519480519481,
      "eval_loss": 0.38575297594070435,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 174.9122,
      "eval_samples_per_second": 11.886,
      "eval_steps_per_second": 1.486,
      "step": 60
    },
    {
      "epoch": 0.19805194805194806,
      "grad_norm": 0.5859375,
      "learning_rate": 1.9910429230348348e-05,
      "loss": 0.3976,
      "step": 61
    },
    {
      "epoch": 0.2012987012987013,
      "grad_norm": 0.578125,
      "learning_rate": 1.9893433680751105e-05,
      "loss": 0.3714,
      "step": 62
    },
    {
      "epoch": 0.20454545454545456,
      "grad_norm": 0.5859375,
      "learning_rate": 1.9874971226068417e-05,
      "loss": 0.3739,
      "step": 63
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 0.5859375,
      "learning_rate": 1.985504460373903e-05,
      "loss": 0.3907,
      "step": 64
    },
    {
      "epoch": 0.21103896103896103,
      "grad_norm": 0.609375,
      "learning_rate": 1.983365676829466e-05,
      "loss": 0.3803,
      "step": 65
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.59765625,
      "learning_rate": 1.9810810890921943e-05,
      "loss": 0.3902,
      "step": 66
    },
    {
      "epoch": 0.21753246753246752,
      "grad_norm": 0.578125,
      "learning_rate": 1.9786510358992213e-05,
      "loss": 0.3744,
      "step": 67
    },
    {
      "epoch": 0.22077922077922077,
      "grad_norm": 0.56640625,
      "learning_rate": 1.9760758775559275e-05,
      "loss": 0.3668,
      "step": 68
    },
    {
      "epoch": 0.22402597402597402,
      "grad_norm": 0.625,
      "learning_rate": 1.9733559958825167e-05,
      "loss": 0.3755,
      "step": 69
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 0.60546875,
      "learning_rate": 1.9704917941574053e-05,
      "loss": 0.3733,
      "step": 70
    },
    {
      "epoch": 0.22727272727272727,
      "eval_loss": 0.3694484233856201,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 174.9363,
      "eval_samples_per_second": 11.884,
      "eval_steps_per_second": 1.486,
      "step": 70
    },
    {
      "epoch": 0.2305194805194805,
      "grad_norm": 0.6015625,
      "learning_rate": 1.9674836970574253e-05,
      "loss": 0.3676,
      "step": 71
    },
    {
      "epoch": 0.23376623376623376,
      "grad_norm": 0.60546875,
      "learning_rate": 1.9643321505948588e-05,
      "loss": 0.3721,
      "step": 72
    },
    {
      "epoch": 0.237012987012987,
      "grad_norm": 0.60546875,
      "learning_rate": 1.9610376220513067e-05,
      "loss": 0.3558,
      "step": 73
    },
    {
      "epoch": 0.24025974025974026,
      "grad_norm": 0.625,
      "learning_rate": 1.957600599908406e-05,
      "loss": 0.357,
      "step": 74
    },
    {
      "epoch": 0.2435064935064935,
      "grad_norm": 0.66015625,
      "learning_rate": 1.954021593775401e-05,
      "loss": 0.3608,
      "step": 75
    },
    {
      "epoch": 0.24675324675324675,
      "grad_norm": 0.59375,
      "learning_rate": 1.9503011343135828e-05,
      "loss": 0.3513,
      "step": 76
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.609375,
      "learning_rate": 1.9464397731576093e-05,
      "loss": 0.3693,
      "step": 77
    },
    {
      "epoch": 0.2532467532467532,
      "grad_norm": 0.59375,
      "learning_rate": 1.9424380828337146e-05,
      "loss": 0.3605,
      "step": 78
    },
    {
      "epoch": 0.2564935064935065,
      "grad_norm": 0.6171875,
      "learning_rate": 1.938296656674817e-05,
      "loss": 0.3553,
      "step": 79
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 0.671875,
      "learning_rate": 1.9340161087325483e-05,
      "loss": 0.3721,
      "step": 80
    },
    {
      "epoch": 0.2597402597402597,
      "eval_loss": 0.3553767800331116,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 175.0277,
      "eval_samples_per_second": 11.878,
      "eval_steps_per_second": 1.485,
      "step": 80
    },
    {
      "epoch": 0.262987012987013,
      "grad_norm": 0.609375,
      "learning_rate": 1.9295970736862063e-05,
      "loss": 0.3597,
      "step": 81
    },
    {
      "epoch": 0.2662337662337662,
      "grad_norm": 0.65625,
      "learning_rate": 1.9250402067486523e-05,
      "loss": 0.3527,
      "step": 82
    },
    {
      "epoch": 0.2694805194805195,
      "grad_norm": 0.61328125,
      "learning_rate": 1.9203461835691596e-05,
      "loss": 0.3528,
      "step": 83
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.6640625,
      "learning_rate": 1.9155157001332374e-05,
      "loss": 0.356,
      "step": 84
    },
    {
      "epoch": 0.275974025974026,
      "grad_norm": 0.6171875,
      "learning_rate": 1.9105494726594344e-05,
      "loss": 0.3556,
      "step": 85
    },
    {
      "epoch": 0.2792207792207792,
      "grad_norm": 0.6171875,
      "learning_rate": 1.905448237493147e-05,
      "loss": 0.3473,
      "step": 86
    },
    {
      "epoch": 0.2824675324675325,
      "grad_norm": 0.5859375,
      "learning_rate": 1.9002127509974376e-05,
      "loss": 0.3441,
      "step": 87
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.6171875,
      "learning_rate": 1.894843789440892e-05,
      "loss": 0.3492,
      "step": 88
    },
    {
      "epoch": 0.288961038961039,
      "grad_norm": 0.6328125,
      "learning_rate": 1.889342148882519e-05,
      "loss": 0.3338,
      "step": 89
    },
    {
      "epoch": 0.2922077922077922,
      "grad_norm": 0.67578125,
      "learning_rate": 1.8837086450537195e-05,
      "loss": 0.3347,
      "step": 90
    },
    {
      "epoch": 0.2922077922077922,
      "eval_loss": 0.34332525730133057,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 174.9257,
      "eval_samples_per_second": 11.885,
      "eval_steps_per_second": 1.486,
      "step": 90
    },
    {
      "epoch": 0.29545454545454547,
      "grad_norm": 0.6328125,
      "learning_rate": 1.877944113237336e-05,
      "loss": 0.3438,
      "step": 91
    },
    {
      "epoch": 0.2987012987012987,
      "grad_norm": 0.6328125,
      "learning_rate": 1.872049408143808e-05,
      "loss": 0.3505,
      "step": 92
    },
    {
      "epoch": 0.30194805194805197,
      "grad_norm": 0.6328125,
      "learning_rate": 1.866025403784439e-05,
      "loss": 0.3362,
      "step": 93
    },
    {
      "epoch": 0.3051948051948052,
      "grad_norm": 0.640625,
      "learning_rate": 1.8598729933418102e-05,
      "loss": 0.337,
      "step": 94
    },
    {
      "epoch": 0.30844155844155846,
      "grad_norm": 0.64453125,
      "learning_rate": 1.8535930890373467e-05,
      "loss": 0.3324,
      "step": 95
    },
    {
      "epoch": 0.3116883116883117,
      "grad_norm": 0.6875,
      "learning_rate": 1.8471866219960604e-05,
      "loss": 0.3461,
      "step": 96
    },
    {
      "epoch": 0.31493506493506496,
      "grad_norm": 0.6328125,
      "learning_rate": 1.840654542108494e-05,
      "loss": 0.3318,
      "step": 97
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 0.62109375,
      "learning_rate": 1.833997817889878e-05,
      "loss": 0.3335,
      "step": 98
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 0.61328125,
      "learning_rate": 1.82721743633653e-05,
      "loss": 0.3291,
      "step": 99
    },
    {
      "epoch": 0.3246753246753247,
      "grad_norm": 0.6171875,
      "learning_rate": 1.820314402779511e-05,
      "loss": 0.3324,
      "step": 100
    },
    {
      "epoch": 0.3246753246753247,
      "eval_loss": 0.33332687616348267,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 174.9506,
      "eval_samples_per_second": 11.883,
      "eval_steps_per_second": 1.486,
      "step": 100
    },
    {
      "epoch": 0.32792207792207795,
      "grad_norm": 0.6328125,
      "learning_rate": 1.8132897407355657e-05,
      "loss": 0.3288,
      "step": 101
    },
    {
      "epoch": 0.33116883116883117,
      "grad_norm": 0.6484375,
      "learning_rate": 1.806144491755363e-05,
      "loss": 0.3384,
      "step": 102
    },
    {
      "epoch": 0.3344155844155844,
      "grad_norm": 0.6328125,
      "learning_rate": 1.798879715269067e-05,
      "loss": 0.3329,
      "step": 103
    },
    {
      "epoch": 0.33766233766233766,
      "grad_norm": 0.6171875,
      "learning_rate": 1.7914964884292543e-05,
      "loss": 0.3329,
      "step": 104
    },
    {
      "epoch": 0.3409090909090909,
      "grad_norm": 0.671875,
      "learning_rate": 1.7839959059512016e-05,
      "loss": 0.3335,
      "step": 105
    },
    {
      "epoch": 0.34415584415584416,
      "grad_norm": 0.609375,
      "learning_rate": 1.7763790799505746e-05,
      "loss": 0.3201,
      "step": 106
    },
    {
      "epoch": 0.3474025974025974,
      "grad_norm": 0.6171875,
      "learning_rate": 1.7686471397785322e-05,
      "loss": 0.3327,
      "step": 107
    },
    {
      "epoch": 0.35064935064935066,
      "grad_norm": 0.640625,
      "learning_rate": 1.760801231854278e-05,
      "loss": 0.3205,
      "step": 108
    },
    {
      "epoch": 0.3538961038961039,
      "grad_norm": 0.6328125,
      "learning_rate": 1.7528425194950794e-05,
      "loss": 0.334,
      "step": 109
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.6015625,
      "learning_rate": 1.744772182743782e-05,
      "loss": 0.3165,
      "step": 110
    },
    {
      "epoch": 0.35714285714285715,
      "eval_loss": 0.32505103945732117,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 175.0106,
      "eval_samples_per_second": 11.879,
      "eval_steps_per_second": 1.486,
      "step": 110
    },
    {
      "epoch": 0.36038961038961037,
      "grad_norm": 0.62890625,
      "learning_rate": 1.736591418193844e-05,
      "loss": 0.3236,
      "step": 111
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.63671875,
      "learning_rate": 1.728301438811916e-05,
      "loss": 0.3192,
      "step": 112
    },
    {
      "epoch": 0.36688311688311687,
      "grad_norm": 0.6484375,
      "learning_rate": 1.7199034737579962e-05,
      "loss": 0.327,
      "step": 113
    },
    {
      "epoch": 0.37012987012987014,
      "grad_norm": 0.62109375,
      "learning_rate": 1.711398768203178e-05,
      "loss": 0.3169,
      "step": 114
    },
    {
      "epoch": 0.37337662337662336,
      "grad_norm": 0.625,
      "learning_rate": 1.7027885831450318e-05,
      "loss": 0.3186,
      "step": 115
    },
    {
      "epoch": 0.37662337662337664,
      "grad_norm": 0.60546875,
      "learning_rate": 1.6940741952206342e-05,
      "loss": 0.3136,
      "step": 116
    },
    {
      "epoch": 0.37987012987012986,
      "grad_norm": 0.62109375,
      "learning_rate": 1.6852568965172794e-05,
      "loss": 0.3184,
      "step": 117
    },
    {
      "epoch": 0.38311688311688313,
      "grad_norm": 0.60546875,
      "learning_rate": 1.676337994380903e-05,
      "loss": 0.3114,
      "step": 118
    },
    {
      "epoch": 0.38636363636363635,
      "grad_norm": 0.6640625,
      "learning_rate": 1.6673188112222394e-05,
      "loss": 0.3329,
      "step": 119
    },
    {
      "epoch": 0.38961038961038963,
      "grad_norm": 0.60546875,
      "learning_rate": 1.658200684320748e-05,
      "loss": 0.3105,
      "step": 120
    },
    {
      "epoch": 0.38961038961038963,
      "eval_loss": 0.31796982884407043,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 174.9896,
      "eval_samples_per_second": 11.881,
      "eval_steps_per_second": 1.486,
      "step": 120
    },
    {
      "epoch": 0.39285714285714285,
      "grad_norm": 0.58203125,
      "learning_rate": 1.6489849656263336e-05,
      "loss": 0.3084,
      "step": 121
    },
    {
      "epoch": 0.3961038961038961,
      "grad_norm": 0.57421875,
      "learning_rate": 1.6396730215588913e-05,
      "loss": 0.3124,
      "step": 122
    },
    {
      "epoch": 0.39935064935064934,
      "grad_norm": 0.609375,
      "learning_rate": 1.630266232805709e-05,
      "loss": 0.3167,
      "step": 123
    },
    {
      "epoch": 0.4025974025974026,
      "grad_norm": 0.6171875,
      "learning_rate": 1.6207659941167485e-05,
      "loss": 0.3084,
      "step": 124
    },
    {
      "epoch": 0.40584415584415584,
      "grad_norm": 0.62890625,
      "learning_rate": 1.6111737140978495e-05,
      "loss": 0.3143,
      "step": 125
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 0.6171875,
      "learning_rate": 1.6014908150018703e-05,
      "loss": 0.3173,
      "step": 126
    },
    {
      "epoch": 0.41233766233766234,
      "grad_norm": 0.609375,
      "learning_rate": 1.591718732517814e-05,
      "loss": 0.3199,
      "step": 127
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 0.609375,
      "learning_rate": 1.581858915557953e-05,
      "loss": 0.312,
      "step": 128
    },
    {
      "epoch": 0.41883116883116883,
      "grad_norm": 0.61328125,
      "learning_rate": 1.571912826043003e-05,
      "loss": 0.3217,
      "step": 129
    },
    {
      "epoch": 0.42207792207792205,
      "grad_norm": 0.59765625,
      "learning_rate": 1.5618819386853607e-05,
      "loss": 0.3123,
      "step": 130
    },
    {
      "epoch": 0.42207792207792205,
      "eval_loss": 0.3119741976261139,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 174.9669,
      "eval_samples_per_second": 11.882,
      "eval_steps_per_second": 1.486,
      "step": 130
    },
    {
      "epoch": 0.4253246753246753,
      "grad_norm": 0.61328125,
      "learning_rate": 1.551767740770446e-05,
      "loss": 0.3088,
      "step": 131
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.578125,
      "learning_rate": 1.541571731936185e-05,
      "loss": 0.3084,
      "step": 132
    },
    {
      "epoch": 0.4318181818181818,
      "grad_norm": 0.6328125,
      "learning_rate": 1.5312954239506536e-05,
      "loss": 0.3179,
      "step": 133
    },
    {
      "epoch": 0.43506493506493504,
      "grad_norm": 0.60546875,
      "learning_rate": 1.5209403404879305e-05,
      "loss": 0.3145,
      "step": 134
    },
    {
      "epoch": 0.4383116883116883,
      "grad_norm": 0.59765625,
      "learning_rate": 1.5105080169021792e-05,
      "loss": 0.3045,
      "step": 135
    },
    {
      "epoch": 0.44155844155844154,
      "grad_norm": 0.5859375,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.314,
      "step": 136
    },
    {
      "epoch": 0.4448051948051948,
      "grad_norm": 0.6484375,
      "learning_rate": 1.4894178478110856e-05,
      "loss": 0.2985,
      "step": 137
    },
    {
      "epoch": 0.44805194805194803,
      "grad_norm": 0.58984375,
      "learning_rate": 1.4787631293572094e-05,
      "loss": 0.3114,
      "step": 138
    },
    {
      "epoch": 0.4512987012987013,
      "grad_norm": 0.60546875,
      "learning_rate": 1.4680374244195861e-05,
      "loss": 0.3129,
      "step": 139
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.58984375,
      "learning_rate": 1.4572423233046386e-05,
      "loss": 0.3007,
      "step": 140
    },
    {
      "epoch": 0.45454545454545453,
      "eval_loss": 0.30710509419441223,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 174.9622,
      "eval_samples_per_second": 11.883,
      "eval_steps_per_second": 1.486,
      "step": 140
    },
    {
      "epoch": 0.4577922077922078,
      "grad_norm": 0.58203125,
      "learning_rate": 1.4463794266081994e-05,
      "loss": 0.2981,
      "step": 141
    },
    {
      "epoch": 0.461038961038961,
      "grad_norm": 0.5703125,
      "learning_rate": 1.4354503449781914e-05,
      "loss": 0.2974,
      "step": 142
    },
    {
      "epoch": 0.4642857142857143,
      "grad_norm": 0.5859375,
      "learning_rate": 1.4244566988758152e-05,
      "loss": 0.3064,
      "step": 143
    },
    {
      "epoch": 0.4675324675324675,
      "grad_norm": 0.56640625,
      "learning_rate": 1.4134001183352833e-05,
      "loss": 0.298,
      "step": 144
    },
    {
      "epoch": 0.4707792207792208,
      "grad_norm": 0.5703125,
      "learning_rate": 1.4022822427221325e-05,
      "loss": 0.3037,
      "step": 145
    },
    {
      "epoch": 0.474025974025974,
      "grad_norm": 0.58203125,
      "learning_rate": 1.391104720490156e-05,
      "loss": 0.3062,
      "step": 146
    },
    {
      "epoch": 0.4772727272727273,
      "grad_norm": 0.609375,
      "learning_rate": 1.3798692089369855e-05,
      "loss": 0.3019,
      "step": 147
    },
    {
      "epoch": 0.4805194805194805,
      "grad_norm": 0.61328125,
      "learning_rate": 1.368577373958362e-05,
      "loss": 0.3008,
      "step": 148
    },
    {
      "epoch": 0.4837662337662338,
      "grad_norm": 0.56640625,
      "learning_rate": 1.3572308898011328e-05,
      "loss": 0.3055,
      "step": 149
    },
    {
      "epoch": 0.487012987012987,
      "grad_norm": 0.5859375,
      "learning_rate": 1.3458314388150115e-05,
      "loss": 0.2942,
      "step": 150
    },
    {
      "epoch": 0.487012987012987,
      "eval_loss": 0.30315953493118286,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 174.9566,
      "eval_samples_per_second": 11.883,
      "eval_steps_per_second": 1.486,
      "step": 150
    },
    {
      "epoch": 0.4902597402597403,
      "grad_norm": 0.578125,
      "learning_rate": 1.3343807112031329e-05,
      "loss": 0.3097,
      "step": 151
    },
    {
      "epoch": 0.4935064935064935,
      "grad_norm": 0.56640625,
      "learning_rate": 1.3228804047714462e-05,
      "loss": 0.3004,
      "step": 152
    },
    {
      "epoch": 0.4967532467532468,
      "grad_norm": 0.58203125,
      "learning_rate": 1.3113322246769817e-05,
      "loss": 0.3046,
      "step": 153
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.57421875,
      "learning_rate": 1.2997378831750242e-05,
      "loss": 0.2966,
      "step": 154
    },
    {
      "epoch": 0.5032467532467533,
      "grad_norm": 0.5703125,
      "learning_rate": 1.2880990993652379e-05,
      "loss": 0.2989,
      "step": 155
    },
    {
      "epoch": 0.5064935064935064,
      "grad_norm": 0.609375,
      "learning_rate": 1.2764175989367717e-05,
      "loss": 0.3015,
      "step": 156
    },
    {
      "epoch": 0.5097402597402597,
      "grad_norm": 0.5703125,
      "learning_rate": 1.2646951139123935e-05,
      "loss": 0.2976,
      "step": 157
    },
    {
      "epoch": 0.512987012987013,
      "grad_norm": 0.59765625,
      "learning_rate": 1.2529333823916807e-05,
      "loss": 0.2919,
      "step": 158
    },
    {
      "epoch": 0.5162337662337663,
      "grad_norm": 0.6328125,
      "learning_rate": 1.241134148293311e-05,
      "loss": 0.3041,
      "step": 159
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 0.58984375,
      "learning_rate": 1.2292991610964902e-05,
      "loss": 0.3053,
      "step": 160
    },
    {
      "epoch": 0.5194805194805194,
      "eval_loss": 0.3000594675540924,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 174.9643,
      "eval_samples_per_second": 11.882,
      "eval_steps_per_second": 1.486,
      "step": 160
    },
    {
      "epoch": 0.5227272727272727,
      "grad_norm": 0.5859375,
      "learning_rate": 1.2174301755815572e-05,
      "loss": 0.3043,
      "step": 161
    },
    {
      "epoch": 0.525974025974026,
      "grad_norm": 0.55859375,
      "learning_rate": 1.2055289515698008e-05,
      "loss": 0.2988,
      "step": 162
    },
    {
      "epoch": 0.5292207792207793,
      "grad_norm": 0.5703125,
      "learning_rate": 1.1935972536625302e-05,
      "loss": 0.2871,
      "step": 163
    },
    {
      "epoch": 0.5324675324675324,
      "grad_norm": 0.578125,
      "learning_rate": 1.1816368509794365e-05,
      "loss": 0.2985,
      "step": 164
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 0.609375,
      "learning_rate": 1.1696495168962848e-05,
      "loss": 0.3066,
      "step": 165
    },
    {
      "epoch": 0.538961038961039,
      "grad_norm": 0.57421875,
      "learning_rate": 1.1576370287819737e-05,
      "loss": 0.296,
      "step": 166
    },
    {
      "epoch": 0.5422077922077922,
      "grad_norm": 0.59375,
      "learning_rate": 1.1456011677350052e-05,
      "loss": 0.2997,
      "step": 167
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.58984375,
      "learning_rate": 1.133543718319398e-05,
      "loss": 0.3011,
      "step": 168
    },
    {
      "epoch": 0.5487012987012987,
      "grad_norm": 0.5703125,
      "learning_rate": 1.1214664683000927e-05,
      "loss": 0.2898,
      "step": 169
    },
    {
      "epoch": 0.551948051948052,
      "grad_norm": 0.58203125,
      "learning_rate": 1.1093712083778748e-05,
      "loss": 0.292,
      "step": 170
    },
    {
      "epoch": 0.551948051948052,
      "eval_loss": 0.29717138409614563,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 174.9869,
      "eval_samples_per_second": 11.881,
      "eval_steps_per_second": 1.486,
      "step": 170
    },
    {
      "epoch": 0.5551948051948052,
      "grad_norm": 0.578125,
      "learning_rate": 1.0972597319238692e-05,
      "loss": 0.2995,
      "step": 171
    },
    {
      "epoch": 0.5584415584415584,
      "grad_norm": 0.58984375,
      "learning_rate": 1.0851338347136358e-05,
      "loss": 0.3015,
      "step": 172
    },
    {
      "epoch": 0.5616883116883117,
      "grad_norm": 0.5625,
      "learning_rate": 1.0729953146609076e-05,
      "loss": 0.2953,
      "step": 173
    },
    {
      "epoch": 0.564935064935065,
      "grad_norm": 0.55859375,
      "learning_rate": 1.060845971551014e-05,
      "loss": 0.3011,
      "step": 174
    },
    {
      "epoch": 0.5681818181818182,
      "grad_norm": 0.58984375,
      "learning_rate": 1.0486876067740253e-05,
      "loss": 0.3016,
      "step": 175
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.5859375,
      "learning_rate": 1.0365220230576592e-05,
      "loss": 0.2953,
      "step": 176
    },
    {
      "epoch": 0.5746753246753247,
      "grad_norm": 0.5625,
      "learning_rate": 1.0243510241999898e-05,
      "loss": 0.2948,
      "step": 177
    },
    {
      "epoch": 0.577922077922078,
      "grad_norm": 0.5703125,
      "learning_rate": 1.0121764148019977e-05,
      "loss": 0.2958,
      "step": 178
    },
    {
      "epoch": 0.5811688311688312,
      "grad_norm": 0.5546875,
      "learning_rate": 1e-05,
      "loss": 0.2829,
      "step": 179
    },
    {
      "epoch": 0.5844155844155844,
      "grad_norm": 0.58203125,
      "learning_rate": 9.878235851980027e-06,
      "loss": 0.2917,
      "step": 180
    },
    {
      "epoch": 0.5844155844155844,
      "eval_loss": 0.29469791054725647,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 174.9839,
      "eval_samples_per_second": 11.881,
      "eval_steps_per_second": 1.486,
      "step": 180
    },
    {
      "epoch": 0.5876623376623377,
      "grad_norm": 0.59375,
      "learning_rate": 9.756489758000105e-06,
      "loss": 0.2994,
      "step": 181
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 0.57421875,
      "learning_rate": 9.634779769423412e-06,
      "loss": 0.3054,
      "step": 182
    },
    {
      "epoch": 0.5941558441558441,
      "grad_norm": 0.59375,
      "learning_rate": 9.51312393225975e-06,
      "loss": 0.2925,
      "step": 183
    },
    {
      "epoch": 0.5974025974025974,
      "grad_norm": 0.5703125,
      "learning_rate": 9.391540284489862e-06,
      "loss": 0.2816,
      "step": 184
    },
    {
      "epoch": 0.6006493506493507,
      "grad_norm": 0.5390625,
      "learning_rate": 9.270046853390924e-06,
      "loss": 0.2856,
      "step": 185
    },
    {
      "epoch": 0.6038961038961039,
      "grad_norm": 0.5703125,
      "learning_rate": 9.148661652863644e-06,
      "loss": 0.2936,
      "step": 186
    },
    {
      "epoch": 0.6071428571428571,
      "grad_norm": 0.55078125,
      "learning_rate": 9.02740268076131e-06,
      "loss": 0.2938,
      "step": 187
    },
    {
      "epoch": 0.6103896103896104,
      "grad_norm": 0.5859375,
      "learning_rate": 8.906287916221259e-06,
      "loss": 0.3017,
      "step": 188
    },
    {
      "epoch": 0.6136363636363636,
      "grad_norm": 0.578125,
      "learning_rate": 8.785335316999078e-06,
      "loss": 0.2957,
      "step": 189
    },
    {
      "epoch": 0.6168831168831169,
      "grad_norm": 0.58203125,
      "learning_rate": 8.664562816806022e-06,
      "loss": 0.2961,
      "step": 190
    },
    {
      "epoch": 0.6168831168831169,
      "eval_loss": 0.2927069365978241,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 174.9405,
      "eval_samples_per_second": 11.884,
      "eval_steps_per_second": 1.486,
      "step": 190
    },
    {
      "epoch": 0.6201298701298701,
      "grad_norm": 0.58203125,
      "learning_rate": 8.543988322649954e-06,
      "loss": 0.2915,
      "step": 191
    },
    {
      "epoch": 0.6233766233766234,
      "grad_norm": 0.57421875,
      "learning_rate": 8.423629712180265e-06,
      "loss": 0.2875,
      "step": 192
    },
    {
      "epoch": 0.6266233766233766,
      "grad_norm": 0.5703125,
      "learning_rate": 8.303504831037154e-06,
      "loss": 0.2979,
      "step": 193
    },
    {
      "epoch": 0.6298701298701299,
      "grad_norm": 0.5703125,
      "learning_rate": 8.183631490205636e-06,
      "loss": 0.2891,
      "step": 194
    },
    {
      "epoch": 0.6331168831168831,
      "grad_norm": 0.5703125,
      "learning_rate": 8.064027463374702e-06,
      "loss": 0.2796,
      "step": 195
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.57421875,
      "learning_rate": 7.944710484301995e-06,
      "loss": 0.285,
      "step": 196
    },
    {
      "epoch": 0.6396103896103896,
      "grad_norm": 0.58203125,
      "learning_rate": 7.825698244184432e-06,
      "loss": 0.295,
      "step": 197
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 0.57421875,
      "learning_rate": 7.707008389035102e-06,
      "loss": 0.2962,
      "step": 198
    },
    {
      "epoch": 0.6461038961038961,
      "grad_norm": 0.57421875,
      "learning_rate": 7.588658517066893e-06,
      "loss": 0.2912,
      "step": 199
    },
    {
      "epoch": 0.6493506493506493,
      "grad_norm": 0.57421875,
      "learning_rate": 7.470666176083193e-06,
      "loss": 0.2917,
      "step": 200
    },
    {
      "epoch": 0.6493506493506493,
      "eval_loss": 0.2912693917751312,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 174.9875,
      "eval_samples_per_second": 11.881,
      "eval_steps_per_second": 1.486,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 308,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1804225839300608e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}