{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 2e-05,
      "loss": 1.8562,
      "step": 1
    },
    {
      "epoch": 0.04,
      "learning_rate": 4e-05,
      "loss": 1.8114,
      "step": 2
    },
    {
      "epoch": 0.06,
      "learning_rate": 6e-05,
      "loss": 1.816,
      "step": 3
    },
    {
      "epoch": 0.08,
      "learning_rate": 8e-05,
      "loss": 1.7654,
      "step": 4
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001,
      "loss": 1.7975,
      "step": 5
    },
    {
      "epoch": 0.1,
      "eval_loss": 1.751416563987732,
      "eval_runtime": 6.1216,
      "eval_samples_per_second": 0.327,
      "eval_steps_per_second": 0.163,
      "step": 5
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00012,
      "loss": 1.88,
      "step": 6
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00014,
      "loss": 1.7946,
      "step": 7
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00016,
      "loss": 1.9499,
      "step": 8
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018,
      "loss": 1.988,
      "step": 9
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.6376,
      "step": 10
    },
    {
      "epoch": 0.2,
      "eval_loss": 1.722676396369934,
      "eval_runtime": 6.1182,
      "eval_samples_per_second": 0.327,
      "eval_steps_per_second": 0.163,
      "step": 10
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019997482349425066,
      "loss": 1.2851,
      "step": 11
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019989930665413147,
      "loss": 1.3604,
      "step": 12
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001997734875046456,
      "loss": 1.7414,
      "step": 13
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019959742939952392,
      "loss": 1.7797,
      "step": 14
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019937122098932428,
      "loss": 1.7487,
      "step": 15
    },
    {
      "epoch": 0.3,
      "eval_loss": 1.7023706436157227,
      "eval_runtime": 6.1068,
      "eval_samples_per_second": 0.328,
      "eval_steps_per_second": 0.164,
      "step": 15
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019909497617679348,
      "loss": 1.8197,
      "step": 16
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019876883405951377,
      "loss": 1.7928,
      "step": 17
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019839295885986296,
      "loss": 1.7864,
      "step": 18
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019796753984232358,
      "loss": 1.8278,
      "step": 19
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019749279121818235,
      "loss": 1.7084,
      "step": 20
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.6931452751159668,
      "eval_runtime": 6.1126,
      "eval_samples_per_second": 0.327,
      "eval_steps_per_second": 0.164,
      "step": 20
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001969689520376687,
      "loss": 1.8612,
      "step": 21
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019639628606958533,
      "loss": 1.8796,
      "step": 22
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019577508166849304,
      "loss": 1.4313,
      "step": 23
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.3394,
      "step": 24
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019438833303083678,
      "loss": 1.8286,
      "step": 25
    },
    {
      "epoch": 0.5,
      "eval_loss": 1.6889530420303345,
      "eval_runtime": 6.1117,
      "eval_samples_per_second": 0.327,
      "eval_steps_per_second": 0.164,
      "step": 25
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019362348706397373,
      "loss": 1.6983,
      "step": 26
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001928114988519039,
      "loss": 1.8419,
      "step": 27
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001919527772551451,
      "loss": 1.7634,
      "step": 28
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019104775466588161,
      "loss": 1.6784,
      "step": 29
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001900968867902419,
      "loss": 1.8443,
      "step": 30
    },
    {
      "epoch": 0.6,
      "eval_loss": 1.6835517883300781,
      "eval_runtime": 6.113,
      "eval_samples_per_second": 0.327,
      "eval_steps_per_second": 0.164,
      "step": 30
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001891006524188368,
      "loss": 1.7155,
      "step": 31
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001880595531856738,
      "loss": 1.8511,
      "step": 32
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018697411331556956,
      "loss": 1.9756,
      "step": 33
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00018584487936018661,
      "loss": 1.7614,
      "step": 34
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00018467241992282843,
      "loss": 1.3127,
      "step": 35
    },
    {
      "epoch": 0.7,
      "eval_loss": 1.6799031496047974,
      "eval_runtime": 6.1132,
      "eval_samples_per_second": 0.327,
      "eval_steps_per_second": 0.164,
      "step": 35
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00018345732537213027,
      "loss": 0.8749,
      "step": 36
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00018220020754479102,
      "loss": 1.7892,
      "step": 37
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.8039,
      "step": 38
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017956245488817812,
      "loss": 1.673,
      "step": 39
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000178183148246803,
      "loss": 1.786,
      "step": 40
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.6771162748336792,
      "eval_runtime": 6.1006,
      "eval_samples_per_second": 0.328,
      "eval_steps_per_second": 0.164,
      "step": 40
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001767644740358011,
      "loss": 1.7318,
      "step": 41
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00017530714660036112,
      "loss": 1.8771,
      "step": 42
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00017381189974873407,
      "loss": 1.8525,
      "step": 43
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00017227948638273916,
      "loss": 1.8761,
      "step": 44
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.8343,
      "step": 45
    },
    {
      "epoch": 0.9,
      "eval_loss": 1.6742032766342163,
      "eval_runtime": 6.1111,
      "eval_samples_per_second": 0.327,
      "eval_steps_per_second": 0.164,
      "step": 45
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00016910626489868649,
      "loss": 1.6979,
      "step": 46
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00016746705459320745,
      "loss": 1.2549,
      "step": 47
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00016579387259397127,
      "loss": 1.0941,
      "step": 48
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001640875613985024,
      "loss": 1.7805,
      "step": 49
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00016234898018587337,
      "loss": 1.5179,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.672481656074524,
      "eval_runtime": 6.1089,
      "eval_samples_per_second": 0.327,
      "eval_steps_per_second": 0.164,
      "step": 50
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.000160579004384082,
      "loss": 1.7744,
      "step": 51
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00015877852522924732,
      "loss": 1.7504,
      "step": 52
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001569484493168452,
      "loss": 1.7334,
      "step": 53
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00015508969814521025,
      "loss": 1.7141,
      "step": 54
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00015320320765153367,
      "loss": 1.8183,
      "step": 55
    },
    {
      "epoch": 1.1,
      "eval_loss": 1.6722060441970825,
      "eval_runtime": 6.1182,
      "eval_samples_per_second": 0.327,
      "eval_steps_per_second": 0.163,
      "step": 55
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00015128992774059063,
      "loss": 1.8504,
      "step": 56
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001493508218064347,
      "loss": 1.7066,
      "step": 57
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00014738686624729986,
      "loss": 1.7424,
      "step": 58
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00014539904997395468,
      "loss": 1.8836,
      "step": 59
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00014338837391175582,
      "loss": 1.5515,
      "step": 60
    },
    {
      "epoch": 1.2,
      "eval_loss": 1.667909860610962,
      "eval_runtime": 6.1058,
      "eval_samples_per_second": 0.328,
      "eval_steps_per_second": 0.164,
      "step": 60
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00014135585049665207,
      "loss": 1.069,
      "step": 61
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00013930250316539238,
      "loss": 1.2383,
      "step": 62
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00013722936584019453,
      "loss": 1.7975,
      "step": 63
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001351374824081343,
      "loss": 1.7685,
      "step": 64
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00013302790619551674,
      "loss": 1.831,
      "step": 65
    },
    {
      "epoch": 1.3,
      "eval_loss": 1.6692527532577515,
      "eval_runtime": 6.1077,
      "eval_samples_per_second": 0.327,
      "eval_steps_per_second": 0.164,
      "step": 65
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.6875,
      "step": 66
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00012875993274320173,
      "loss": 1.7344,
      "step": 67
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00012660368455666752,
      "loss": 1.6883,
      "step": 68
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0001244340406137894,
      "loss": 1.7168,
      "step": 69
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00012225209339563145,
      "loss": 1.7975,
      "step": 70
    },
    {
      "epoch": 1.4,
      "eval_loss": 1.6680976152420044,
      "eval_runtime": 6.1243,
      "eval_samples_per_second": 0.327,
      "eval_steps_per_second": 0.163,
      "step": 70
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00012005894157832729,
      "loss": 1.869,
      "step": 71
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00011785568947986367,
      "loss": 1.6853,
      "step": 72
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0001156434465040231,
      "loss": 1.2465,
      "step": 73
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00011342332658176555,
      "loss": 0.8489,
      "step": 74
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00011119644761033078,
      "loss": 1.7818,
      "step": 75
    },
    {
      "epoch": 1.5,
      "eval_loss": 1.669010043144226,
      "eval_runtime": 6.1095,
      "eval_samples_per_second": 0.327,
      "eval_steps_per_second": 0.164,
      "step": 75
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00010896393089034336,
      "loss": 1.7696,
      "step": 76
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00010672690056120399,
      "loss": 1.7764,
      "step": 77
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00010448648303505151,
      "loss": 1.7498,
      "step": 78
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00010224380642958052,
      "loss": 1.8195,
      "step": 79
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001,
      "loss": 1.7768,
      "step": 80
    },
    {
      "epoch": 1.6,
      "eval_loss": 1.667705774307251,
      "eval_runtime": 6.1125,
      "eval_samples_per_second": 0.327,
      "eval_steps_per_second": 0.164,
      "step": 80
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.775619357041952e-05,
      "loss": 1.9044,
      "step": 81
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.551351696494854e-05,
      "loss": 1.8899,
      "step": 82
    },
    {
      "epoch": 1.66,
      "learning_rate": 9.327309943879604e-05,
      "loss": 1.9218,
      "step": 83
    },
    {
      "epoch": 1.68,
      "learning_rate": 9.103606910965666e-05,
      "loss": 1.7831,
      "step": 84
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.880355238966923e-05,
      "loss": 1.3084,
      "step": 85
    },
    {
      "epoch": 1.7,
      "eval_loss": 1.667492389678955,
      "eval_runtime": 6.107,
      "eval_samples_per_second": 0.327,
      "eval_steps_per_second": 0.164,
      "step": 85
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.657667341823448e-05,
      "loss": 0.9686,
      "step": 86
    },
    {
      "epoch": 1.74,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.788,
      "step": 87
    },
    {
      "epoch": 1.76,
      "learning_rate": 8.214431052013634e-05,
      "loss": 1.6448,
      "step": 88
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.994105842167273e-05,
      "loss": 1.6639,
      "step": 89
    },
    {
      "epoch": 1.8,
      "learning_rate": 7.774790660436858e-05,
      "loss": 1.7402,
      "step": 90
    },
    {
      "epoch": 1.8,
      "eval_loss": 1.6677496433258057,
      "eval_runtime": 6.0974,
      "eval_samples_per_second": 0.328,
      "eval_steps_per_second": 0.164,
      "step": 90
    },
    {
      "epoch": 1.82,
      "learning_rate": 7.556595938621058e-05,
      "loss": 1.7281,
      "step": 91
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.339631544333249e-05,
      "loss": 1.7017,
      "step": 92
    },
    {
      "epoch": 1.86,
      "learning_rate": 7.124006725679828e-05,
      "loss": 1.758,
      "step": 93
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.7958,
      "step": 94
    },
    {
      "epoch": 1.9,
      "learning_rate": 6.697209380448333e-05,
      "loss": 1.8462,
      "step": 95
    },
    {
      "epoch": 1.9,
      "eval_loss": 1.6652313470840454,
      "eval_runtime": 6.1048,
      "eval_samples_per_second": 0.328,
      "eval_steps_per_second": 0.164,
      "step": 95
    },
    {
      "epoch": 1.92,
      "learning_rate": 6.486251759186572e-05,
      "loss": 1.8275,
      "step": 96
    },
    {
      "epoch": 1.94,
      "learning_rate": 6.277063415980549e-05,
      "loss": 1.4802,
      "step": 97
    },
    {
      "epoch": 1.96,
      "learning_rate": 6.069749683460765e-05,
      "loss": 1.1441,
      "step": 98
    },
    {
      "epoch": 1.98,
      "learning_rate": 5.864414950334796e-05,
      "loss": 1.7344,
      "step": 99
    },
    {
      "epoch": 2.0,
      "learning_rate": 5.6611626088244194e-05,
      "loss": 1.6543,
      "step": 100
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.6656206846237183,
      "eval_runtime": 6.1082,
      "eval_samples_per_second": 0.327,
      "eval_steps_per_second": 0.164,
      "step": 100
    }
  ],
  "max_steps": 150,
  "num_train_epochs": 3,
  "total_flos": 2.8763598340286054e+17,
  "trial_name": null,
  "trial_params": null
}