{
  "best_metric": 1.3649392127990723,
  "best_model_checkpoint": "./output/checkpoints/2024-06-11_11-02-23/checkpoint-50",
  "epoch": 0.5154639175257731,
  "eval_steps": 1,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010309278350515464,
      "grad_norm": 2.784351348876953,
      "learning_rate": 4e-05,
      "loss": 5.0719,
      "step": 1
    },
    {
      "epoch": 0.010309278350515464,
      "eval_loss": 4.890735149383545,
      "eval_runtime": 11.998,
      "eval_samples_per_second": 11.252,
      "eval_steps_per_second": 0.75,
      "step": 1
    },
    {
      "epoch": 0.020618556701030927,
      "grad_norm": 2.8573310375213623,
      "learning_rate": 8e-05,
      "loss": 4.9508,
      "step": 2
    },
    {
      "epoch": 0.020618556701030927,
      "eval_loss": 4.775210857391357,
      "eval_runtime": 12.0698,
      "eval_samples_per_second": 11.185,
      "eval_steps_per_second": 0.746,
      "step": 2
    },
    {
      "epoch": 0.030927835051546393,
      "grad_norm": 2.920828104019165,
      "learning_rate": 0.00012,
      "loss": 4.973,
      "step": 3
    },
    {
      "epoch": 0.030927835051546393,
      "eval_loss": 4.2439093589782715,
      "eval_runtime": 12.1674,
      "eval_samples_per_second": 11.095,
      "eval_steps_per_second": 0.74,
      "step": 3
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 3.0682826042175293,
      "learning_rate": 0.00016,
      "loss": 4.3398,
      "step": 4
    },
    {
      "epoch": 0.041237113402061855,
      "eval_loss": 3.316483497619629,
      "eval_runtime": 12.1421,
      "eval_samples_per_second": 11.118,
      "eval_steps_per_second": 0.741,
      "step": 4
    },
    {
      "epoch": 0.05154639175257732,
      "grad_norm": 3.1937592029571533,
      "learning_rate": 0.0002,
      "loss": 3.253,
      "step": 5
    },
    {
      "epoch": 0.05154639175257732,
      "eval_loss": 2.4086239337921143,
      "eval_runtime": 12.0796,
      "eval_samples_per_second": 11.176,
      "eval_steps_per_second": 0.745,
      "step": 5
    },
    {
      "epoch": 0.061855670103092786,
      "grad_norm": 2.0619874000549316,
      "learning_rate": 0.00024,
      "loss": 2.3725,
      "step": 6
    },
    {
      "epoch": 0.061855670103092786,
      "eval_loss": 1.9427752494812012,
      "eval_runtime": 12.1816,
      "eval_samples_per_second": 11.082,
      "eval_steps_per_second": 0.739,
      "step": 6
    },
    {
      "epoch": 0.07216494845360824,
      "grad_norm": 1.4178358316421509,
      "learning_rate": 0.00028,
      "loss": 1.7391,
      "step": 7
    },
    {
      "epoch": 0.07216494845360824,
      "eval_loss": 1.6751385927200317,
      "eval_runtime": 12.2395,
      "eval_samples_per_second": 11.03,
      "eval_steps_per_second": 0.735,
      "step": 7
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 0.9345605373382568,
      "learning_rate": 0.00032,
      "loss": 1.4029,
      "step": 8
    },
    {
      "epoch": 0.08247422680412371,
      "eval_loss": 1.551221489906311,
      "eval_runtime": 12.2329,
      "eval_samples_per_second": 11.036,
      "eval_steps_per_second": 0.736,
      "step": 8
    },
    {
      "epoch": 0.09278350515463918,
      "grad_norm": 1.1335052251815796,
      "learning_rate": 0.00036,
      "loss": 1.4404,
      "step": 9
    },
    {
      "epoch": 0.09278350515463918,
      "eval_loss": 1.447738528251648,
      "eval_runtime": 12.2069,
      "eval_samples_per_second": 11.059,
      "eval_steps_per_second": 0.737,
      "step": 9
    },
    {
      "epoch": 0.10309278350515463,
      "grad_norm": 0.23779241740703583,
      "learning_rate": 0.0004,
      "loss": 1.3197,
      "step": 10
    },
    {
      "epoch": 0.10309278350515463,
      "eval_loss": 1.4138007164001465,
      "eval_runtime": 12.2609,
      "eval_samples_per_second": 11.011,
      "eval_steps_per_second": 0.734,
      "step": 10
    },
    {
      "epoch": 0.1134020618556701,
      "grad_norm": 0.19672752916812897,
      "learning_rate": 0.00039540229885057476,
      "loss": 1.2882,
      "step": 11
    },
    {
      "epoch": 0.1134020618556701,
      "eval_loss": 1.393249750137329,
      "eval_runtime": 12.1836,
      "eval_samples_per_second": 11.08,
      "eval_steps_per_second": 0.739,
      "step": 11
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 0.2525981366634369,
      "learning_rate": 0.00039080459770114945,
      "loss": 1.2831,
      "step": 12
    },
    {
      "epoch": 0.12371134020618557,
      "eval_loss": 1.4042422771453857,
      "eval_runtime": 12.232,
      "eval_samples_per_second": 11.037,
      "eval_steps_per_second": 0.736,
      "step": 12
    },
    {
      "epoch": 0.13402061855670103,
      "grad_norm": 0.23460708558559418,
      "learning_rate": 0.0003862068965517242,
      "loss": 1.1615,
      "step": 13
    },
    {
      "epoch": 0.13402061855670103,
      "eval_loss": 1.4705734252929688,
      "eval_runtime": 12.2648,
      "eval_samples_per_second": 11.007,
      "eval_steps_per_second": 0.734,
      "step": 13
    },
    {
      "epoch": 0.14432989690721648,
      "grad_norm": 0.21198733150959015,
      "learning_rate": 0.00038160919540229887,
      "loss": 1.0625,
      "step": 14
    },
    {
      "epoch": 0.14432989690721648,
      "eval_loss": 1.5055038928985596,
      "eval_runtime": 12.2044,
      "eval_samples_per_second": 11.062,
      "eval_steps_per_second": 0.737,
      "step": 14
    },
    {
      "epoch": 0.15463917525773196,
      "grad_norm": 0.3658374845981598,
      "learning_rate": 0.00037701149425287356,
      "loss": 1.1191,
      "step": 15
    },
    {
      "epoch": 0.15463917525773196,
      "eval_loss": 1.4498964548110962,
      "eval_runtime": 12.2004,
      "eval_samples_per_second": 11.065,
      "eval_steps_per_second": 0.738,
      "step": 15
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 0.222326397895813,
      "learning_rate": 0.0003724137931034483,
      "loss": 1.0887,
      "step": 16
    },
    {
      "epoch": 0.16494845360824742,
      "eval_loss": 1.3819501399993896,
      "eval_runtime": 12.1444,
      "eval_samples_per_second": 11.116,
      "eval_steps_per_second": 0.741,
      "step": 16
    },
    {
      "epoch": 0.17525773195876287,
      "grad_norm": 0.1682404726743698,
      "learning_rate": 0.000367816091954023,
      "loss": 1.0915,
      "step": 17
    },
    {
      "epoch": 0.17525773195876287,
      "eval_loss": 1.3552738428115845,
      "eval_runtime": 12.2121,
      "eval_samples_per_second": 11.055,
      "eval_steps_per_second": 0.737,
      "step": 17
    },
    {
      "epoch": 0.18556701030927836,
      "grad_norm": 0.15567483007907867,
      "learning_rate": 0.0003632183908045977,
      "loss": 1.0509,
      "step": 18
    },
    {
      "epoch": 0.18556701030927836,
      "eval_loss": 1.3488575220108032,
      "eval_runtime": 12.2988,
      "eval_samples_per_second": 10.977,
      "eval_steps_per_second": 0.732,
      "step": 18
    },
    {
      "epoch": 0.1958762886597938,
      "grad_norm": 0.1600300371646881,
      "learning_rate": 0.0003586206896551724,
      "loss": 0.9982,
      "step": 19
    },
    {
      "epoch": 0.1958762886597938,
      "eval_loss": 1.3651177883148193,
      "eval_runtime": 12.1263,
      "eval_samples_per_second": 11.133,
      "eval_steps_per_second": 0.742,
      "step": 19
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 0.1044178307056427,
      "learning_rate": 0.00035402298850574715,
      "loss": 0.9809,
      "step": 20
    },
    {
      "epoch": 0.20618556701030927,
      "eval_loss": 1.401971697807312,
      "eval_runtime": 12.2092,
      "eval_samples_per_second": 11.057,
      "eval_steps_per_second": 0.737,
      "step": 20
    },
    {
      "epoch": 0.21649484536082475,
      "grad_norm": 0.12360141426324844,
      "learning_rate": 0.0003494252873563219,
      "loss": 1.0549,
      "step": 21
    },
    {
      "epoch": 0.21649484536082475,
      "eval_loss": 1.426545262336731,
      "eval_runtime": 12.1581,
      "eval_samples_per_second": 11.104,
      "eval_steps_per_second": 0.74,
      "step": 21
    },
    {
      "epoch": 0.2268041237113402,
      "grad_norm": 0.12509943544864655,
      "learning_rate": 0.0003448275862068965,
      "loss": 1.0323,
      "step": 22
    },
    {
      "epoch": 0.2268041237113402,
      "eval_loss": 1.4258630275726318,
      "eval_runtime": 12.201,
      "eval_samples_per_second": 11.065,
      "eval_steps_per_second": 0.738,
      "step": 22
    },
    {
      "epoch": 0.23711340206185566,
      "grad_norm": 0.13586747646331787,
      "learning_rate": 0.00034022988505747127,
      "loss": 1.0746,
      "step": 23
    },
    {
      "epoch": 0.23711340206185566,
      "eval_loss": 1.3952091932296753,
      "eval_runtime": 12.1932,
      "eval_samples_per_second": 11.072,
      "eval_steps_per_second": 0.738,
      "step": 23
    },
    {
      "epoch": 0.24742268041237114,
      "grad_norm": 0.08069202303886414,
      "learning_rate": 0.000335632183908046,
      "loss": 0.9645,
      "step": 24
    },
    {
      "epoch": 0.24742268041237114,
      "eval_loss": 1.376875638961792,
      "eval_runtime": 12.2172,
      "eval_samples_per_second": 11.05,
      "eval_steps_per_second": 0.737,
      "step": 24
    },
    {
      "epoch": 0.25773195876288657,
      "grad_norm": 0.09109444171190262,
      "learning_rate": 0.0003310344827586207,
      "loss": 0.9345,
      "step": 25
    },
    {
      "epoch": 0.25773195876288657,
      "eval_loss": 1.373625636100769,
      "eval_runtime": 12.2642,
      "eval_samples_per_second": 11.008,
      "eval_steps_per_second": 0.734,
      "step": 25
    },
    {
      "epoch": 0.26804123711340205,
      "grad_norm": 0.0649966150522232,
      "learning_rate": 0.00032643678160919543,
      "loss": 1.0266,
      "step": 26
    },
    {
      "epoch": 0.26804123711340205,
      "eval_loss": 1.3720897436141968,
      "eval_runtime": 12.1576,
      "eval_samples_per_second": 11.104,
      "eval_steps_per_second": 0.74,
      "step": 26
    },
    {
      "epoch": 0.27835051546391754,
      "grad_norm": 0.09308775514364243,
      "learning_rate": 0.0003218390804597701,
      "loss": 0.9797,
      "step": 27
    },
    {
      "epoch": 0.27835051546391754,
      "eval_loss": 1.3858685493469238,
      "eval_runtime": 12.1546,
      "eval_samples_per_second": 11.107,
      "eval_steps_per_second": 0.74,
      "step": 27
    },
    {
      "epoch": 0.28865979381443296,
      "grad_norm": 0.06654678285121918,
      "learning_rate": 0.00031724137931034486,
      "loss": 1.0072,
      "step": 28
    },
    {
      "epoch": 0.28865979381443296,
      "eval_loss": 1.4031970500946045,
      "eval_runtime": 12.1666,
      "eval_samples_per_second": 11.096,
      "eval_steps_per_second": 0.74,
      "step": 28
    },
    {
      "epoch": 0.29896907216494845,
      "grad_norm": 0.07720344513654709,
      "learning_rate": 0.0003126436781609196,
      "loss": 0.923,
      "step": 29
    },
    {
      "epoch": 0.29896907216494845,
      "eval_loss": 1.4118249416351318,
      "eval_runtime": 12.1572,
      "eval_samples_per_second": 11.105,
      "eval_steps_per_second": 0.74,
      "step": 29
    },
    {
      "epoch": 0.30927835051546393,
      "grad_norm": 0.10230278223752975,
      "learning_rate": 0.00030804597701149423,
      "loss": 0.9821,
      "step": 30
    },
    {
      "epoch": 0.30927835051546393,
      "eval_loss": 1.4045817852020264,
      "eval_runtime": 12.1974,
      "eval_samples_per_second": 11.068,
      "eval_steps_per_second": 0.738,
      "step": 30
    },
    {
      "epoch": 0.31958762886597936,
      "grad_norm": 0.07451125234365463,
      "learning_rate": 0.00030344827586206897,
      "loss": 1.0021,
      "step": 31
    },
    {
      "epoch": 0.31958762886597936,
      "eval_loss": 1.391209363937378,
      "eval_runtime": 12.2389,
      "eval_samples_per_second": 11.03,
      "eval_steps_per_second": 0.735,
      "step": 31
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 0.0714351087808609,
      "learning_rate": 0.00029885057471264366,
      "loss": 1.0071,
      "step": 32
    },
    {
      "epoch": 0.32989690721649484,
      "eval_loss": 1.3730576038360596,
      "eval_runtime": 12.2102,
      "eval_samples_per_second": 11.056,
      "eval_steps_per_second": 0.737,
      "step": 32
    },
    {
      "epoch": 0.3402061855670103,
      "grad_norm": 0.06839103996753693,
      "learning_rate": 0.0002942528735632184,
      "loss": 0.973,
      "step": 33
    },
    {
      "epoch": 0.3402061855670103,
      "eval_loss": 1.3659778833389282,
      "eval_runtime": 12.2323,
      "eval_samples_per_second": 11.036,
      "eval_steps_per_second": 0.736,
      "step": 33
    },
    {
      "epoch": 0.35051546391752575,
      "grad_norm": 0.08078178018331528,
      "learning_rate": 0.00028965517241379314,
      "loss": 0.964,
      "step": 34
    },
    {
      "epoch": 0.35051546391752575,
      "eval_loss": 1.3762452602386475,
      "eval_runtime": 12.2027,
      "eval_samples_per_second": 11.063,
      "eval_steps_per_second": 0.738,
      "step": 34
    },
    {
      "epoch": 0.36082474226804123,
      "grad_norm": 0.06870069354772568,
      "learning_rate": 0.0002850574712643678,
      "loss": 0.9148,
      "step": 35
    },
    {
      "epoch": 0.36082474226804123,
      "eval_loss": 1.3925738334655762,
      "eval_runtime": 12.2644,
      "eval_samples_per_second": 11.007,
      "eval_steps_per_second": 0.734,
      "step": 35
    },
    {
      "epoch": 0.3711340206185567,
      "grad_norm": 0.06974003463983536,
      "learning_rate": 0.00028045977011494257,
      "loss": 1.0128,
      "step": 36
    },
    {
      "epoch": 0.3711340206185567,
      "eval_loss": 1.4087179899215698,
      "eval_runtime": 12.2407,
      "eval_samples_per_second": 11.029,
      "eval_steps_per_second": 0.735,
      "step": 36
    },
    {
      "epoch": 0.38144329896907214,
      "grad_norm": 0.08603405207395554,
      "learning_rate": 0.00027586206896551725,
      "loss": 0.9776,
      "step": 37
    },
    {
      "epoch": 0.38144329896907214,
      "eval_loss": 1.4067703485488892,
      "eval_runtime": 12.173,
      "eval_samples_per_second": 11.09,
      "eval_steps_per_second": 0.739,
      "step": 37
    },
    {
      "epoch": 0.3917525773195876,
      "grad_norm": 0.07761300355195999,
      "learning_rate": 0.00027126436781609194,
      "loss": 0.9655,
      "step": 38
    },
    {
      "epoch": 0.3917525773195876,
      "eval_loss": 1.3932013511657715,
      "eval_runtime": 12.1941,
      "eval_samples_per_second": 11.071,
      "eval_steps_per_second": 0.738,
      "step": 38
    },
    {
      "epoch": 0.4020618556701031,
      "grad_norm": 0.06392566114664078,
      "learning_rate": 0.0002666666666666667,
      "loss": 0.974,
      "step": 39
    },
    {
      "epoch": 0.4020618556701031,
      "eval_loss": 1.3819767236709595,
      "eval_runtime": 12.1765,
      "eval_samples_per_second": 11.087,
      "eval_steps_per_second": 0.739,
      "step": 39
    },
    {
      "epoch": 0.41237113402061853,
      "grad_norm": 0.05517549812793732,
      "learning_rate": 0.00026206896551724137,
      "loss": 0.9793,
      "step": 40
    },
    {
      "epoch": 0.41237113402061853,
      "eval_loss": 1.3717000484466553,
      "eval_runtime": 12.2217,
      "eval_samples_per_second": 11.046,
      "eval_steps_per_second": 0.736,
      "step": 40
    },
    {
      "epoch": 0.422680412371134,
      "grad_norm": 0.0804053246974945,
      "learning_rate": 0.0002574712643678161,
      "loss": 0.9585,
      "step": 41
    },
    {
      "epoch": 0.422680412371134,
      "eval_loss": 1.3579998016357422,
      "eval_runtime": 12.182,
      "eval_samples_per_second": 11.082,
      "eval_steps_per_second": 0.739,
      "step": 41
    },
    {
      "epoch": 0.4329896907216495,
      "grad_norm": 0.07214821875095367,
      "learning_rate": 0.0002528735632183908,
      "loss": 0.9332,
      "step": 42
    },
    {
      "epoch": 0.4329896907216495,
      "eval_loss": 1.3583327531814575,
      "eval_runtime": 12.1257,
      "eval_samples_per_second": 11.133,
      "eval_steps_per_second": 0.742,
      "step": 42
    },
    {
      "epoch": 0.44329896907216493,
      "grad_norm": 0.07595060020685196,
      "learning_rate": 0.00024827586206896553,
      "loss": 0.8998,
      "step": 43
    },
    {
      "epoch": 0.44329896907216493,
      "eval_loss": 1.3721704483032227,
      "eval_runtime": 12.2745,
      "eval_samples_per_second": 10.998,
      "eval_steps_per_second": 0.733,
      "step": 43
    },
    {
      "epoch": 0.4536082474226804,
      "grad_norm": 0.07757716625928879,
      "learning_rate": 0.00024367816091954025,
      "loss": 0.9661,
      "step": 44
    },
    {
      "epoch": 0.4536082474226804,
      "eval_loss": 1.3984168767929077,
      "eval_runtime": 12.1398,
      "eval_samples_per_second": 11.12,
      "eval_steps_per_second": 0.741,
      "step": 44
    },
    {
      "epoch": 0.4639175257731959,
      "grad_norm": 0.053873661905527115,
      "learning_rate": 0.00023908045977011496,
      "loss": 0.9418,
      "step": 45
    },
    {
      "epoch": 0.4639175257731959,
      "eval_loss": 1.4266961812973022,
      "eval_runtime": 12.1955,
      "eval_samples_per_second": 11.07,
      "eval_steps_per_second": 0.738,
      "step": 45
    },
    {
      "epoch": 0.4742268041237113,
      "grad_norm": 0.08943776786327362,
      "learning_rate": 0.00023448275862068965,
      "loss": 0.9309,
      "step": 46
    },
    {
      "epoch": 0.4742268041237113,
      "eval_loss": 1.4349451065063477,
      "eval_runtime": 12.1983,
      "eval_samples_per_second": 11.067,
      "eval_steps_per_second": 0.738,
      "step": 46
    },
    {
      "epoch": 0.4845360824742268,
      "grad_norm": 0.0885058343410492,
      "learning_rate": 0.00022988505747126436,
      "loss": 1.0245,
      "step": 47
    },
    {
      "epoch": 0.4845360824742268,
      "eval_loss": 1.4226434230804443,
      "eval_runtime": 12.1753,
      "eval_samples_per_second": 11.088,
      "eval_steps_per_second": 0.739,
      "step": 47
    },
    {
      "epoch": 0.4948453608247423,
      "grad_norm": 0.058818139135837555,
      "learning_rate": 0.00022528735632183907,
      "loss": 0.9007,
      "step": 48
    },
    {
      "epoch": 0.4948453608247423,
      "eval_loss": 1.4033018350601196,
      "eval_runtime": 12.267,
      "eval_samples_per_second": 11.005,
      "eval_steps_per_second": 0.734,
      "step": 48
    },
    {
      "epoch": 0.5051546391752577,
      "grad_norm": 0.07104739546775818,
      "learning_rate": 0.0002206896551724138,
      "loss": 0.9469,
      "step": 49
    },
    {
      "epoch": 0.5051546391752577,
      "eval_loss": 1.3786002397537231,
      "eval_runtime": 12.2731,
      "eval_samples_per_second": 11.0,
      "eval_steps_per_second": 0.733,
      "step": 49
    },
    {
      "epoch": 0.5154639175257731,
      "grad_norm": 0.05872216075658798,
      "learning_rate": 0.00021609195402298853,
      "loss": 0.9671,
      "step": 50
    },
    {
      "epoch": 0.5154639175257731,
      "eval_loss": 1.3649392127990723,
      "eval_runtime": 12.1662,
      "eval_samples_per_second": 11.096,
      "eval_steps_per_second": 0.74,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 97,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.85446101417984e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}