{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07146260123868509,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009528346831824678,
      "grad_norm": 0.6638647317886353,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.7136,
      "step": 1
    },
    {
      "epoch": 0.0009528346831824678,
      "eval_loss": NaN,
      "eval_runtime": 190.8211,
      "eval_samples_per_second": 4.633,
      "eval_steps_per_second": 2.316,
      "step": 1
    },
    {
      "epoch": 0.0019056693663649356,
      "grad_norm": 1.9228756427764893,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.09,
      "step": 2
    },
    {
      "epoch": 0.0028585040495474035,
      "grad_norm": 1.071838617324829,
      "learning_rate": 0.0001,
      "loss": 2.5374,
      "step": 3
    },
    {
      "epoch": 0.003811338732729871,
      "grad_norm": 1.0017715692520142,
      "learning_rate": 9.99524110790929e-05,
      "loss": 2.434,
      "step": 4
    },
    {
      "epoch": 0.004764173415912339,
      "grad_norm": 0.9518014788627625,
      "learning_rate": 9.980973490458728e-05,
      "loss": 2.4302,
      "step": 5
    },
    {
      "epoch": 0.005717008099094807,
      "grad_norm": 1.4896080493927002,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.3739,
      "step": 6
    },
    {
      "epoch": 0.006669842782277275,
      "grad_norm": 0.9383845329284668,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.6915,
      "step": 7
    },
    {
      "epoch": 0.007622677465459742,
      "grad_norm": 1.1015162467956543,
      "learning_rate": 9.881480035599667e-05,
      "loss": 2.5915,
      "step": 8
    },
    {
      "epoch": 0.00857551214864221,
      "grad_norm": 1.1465002298355103,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.4781,
      "step": 9
    },
    {
      "epoch": 0.009528346831824679,
      "grad_norm": 1.1309946775436401,
      "learning_rate": 9.768584753741134e-05,
      "loss": 2.4019,
      "step": 10
    },
    {
      "epoch": 0.010481181515007145,
      "grad_norm": 1.258188009262085,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.5504,
      "step": 11
    },
    {
      "epoch": 0.011434016198189614,
      "grad_norm": 1.2431732416152954,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.3838,
      "step": 12
    },
    {
      "epoch": 0.012386850881372083,
      "grad_norm": 1.3730213642120361,
      "learning_rate": 9.53153893518325e-05,
      "loss": 2.3747,
      "step": 13
    },
    {
      "epoch": 0.01333968556455455,
      "grad_norm": 1.4390398263931274,
      "learning_rate": 9.435054165891109e-05,
      "loss": 2.4125,
      "step": 14
    },
    {
      "epoch": 0.014292520247737018,
      "grad_norm": 1.2996867895126343,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.2455,
      "step": 15
    },
    {
      "epoch": 0.015245354930919485,
      "grad_norm": 1.3530491590499878,
      "learning_rate": 9.21695722906443e-05,
      "loss": 2.5976,
      "step": 16
    },
    {
      "epoch": 0.016198189614101955,
      "grad_norm": 1.3274792432785034,
      "learning_rate": 9.09576022144496e-05,
      "loss": 2.5624,
      "step": 17
    },
    {
      "epoch": 0.01715102429728442,
      "grad_norm": 1.6145275831222534,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.4993,
      "step": 18
    },
    {
      "epoch": 0.01810385898046689,
      "grad_norm": 1.4638392925262451,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.4422,
      "step": 19
    },
    {
      "epoch": 0.019056693663649357,
      "grad_norm": 1.3674169778823853,
      "learning_rate": 8.68638668405062e-05,
      "loss": 2.4834,
      "step": 20
    },
    {
      "epoch": 0.020009528346831826,
      "grad_norm": 1.5228791236877441,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.5919,
      "step": 21
    },
    {
      "epoch": 0.02096236303001429,
      "grad_norm": 1.3580362796783447,
      "learning_rate": 8.377951038078302e-05,
      "loss": 2.401,
      "step": 22
    },
    {
      "epoch": 0.02191519771319676,
      "grad_norm": 1.3920480012893677,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.3787,
      "step": 23
    },
    {
      "epoch": 0.022868032396379228,
      "grad_norm": 1.4610280990600586,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.3116,
      "step": 24
    },
    {
      "epoch": 0.023820867079561697,
      "grad_norm": 1.4679853916168213,
      "learning_rate": 7.86788218175523e-05,
      "loss": 2.5363,
      "step": 25
    },
    {
      "epoch": 0.023820867079561697,
      "eval_loss": NaN,
      "eval_runtime": 189.9742,
      "eval_samples_per_second": 4.653,
      "eval_steps_per_second": 2.327,
      "step": 25
    },
    {
      "epoch": 0.024773701762744165,
      "grad_norm": 1.4650429487228394,
      "learning_rate": 7.68649804173412e-05,
      "loss": 2.453,
      "step": 26
    },
    {
      "epoch": 0.02572653644592663,
      "grad_norm": 1.5379657745361328,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.4569,
      "step": 27
    },
    {
      "epoch": 0.0266793711291091,
      "grad_norm": 1.4416159391403198,
      "learning_rate": 7.308743066175172e-05,
      "loss": 2.0689,
      "step": 28
    },
    {
      "epoch": 0.027632205812291567,
      "grad_norm": 1.9543250799179077,
      "learning_rate": 7.113091308703498e-05,
      "loss": 2.7355,
      "step": 29
    },
    {
      "epoch": 0.028585040495474036,
      "grad_norm": 4.280240058898926,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.3589,
      "step": 30
    },
    {
      "epoch": 0.029537875178656504,
      "grad_norm": 2.5730347633361816,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.5142,
      "step": 31
    },
    {
      "epoch": 0.03049070986183897,
      "grad_norm": 1.9060622453689575,
      "learning_rate": 6.503528997521366e-05,
      "loss": 2.4468,
      "step": 32
    },
    {
      "epoch": 0.03144354454502144,
      "grad_norm": 2.6304562091827393,
      "learning_rate": 6.294095225512603e-05,
      "loss": 2.5699,
      "step": 33
    },
    {
      "epoch": 0.03239637922820391,
      "grad_norm": 2.1982674598693848,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 2.5823,
      "step": 34
    },
    {
      "epoch": 0.03334921391138637,
      "grad_norm": 1.9779804944992065,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.0681,
      "step": 35
    },
    {
      "epoch": 0.03430204859456884,
      "grad_norm": 2.2652299404144287,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 2.5656,
      "step": 36
    },
    {
      "epoch": 0.03525488327775131,
      "grad_norm": 2.288848400115967,
      "learning_rate": 5.435778713738292e-05,
      "loss": 2.442,
      "step": 37
    },
    {
      "epoch": 0.03620771796093378,
      "grad_norm": 2.1887640953063965,
      "learning_rate": 5.218096936826681e-05,
      "loss": 2.4672,
      "step": 38
    },
    {
      "epoch": 0.037160552644116246,
      "grad_norm": 2.69694185256958,
      "learning_rate": 5e-05,
      "loss": 2.8142,
      "step": 39
    },
    {
      "epoch": 0.038113387327298714,
      "grad_norm": 2.768056869506836,
      "learning_rate": 4.781903063173321e-05,
      "loss": 2.7236,
      "step": 40
    },
    {
      "epoch": 0.03906622201048118,
      "grad_norm": 4.088725566864014,
      "learning_rate": 4.564221286261709e-05,
      "loss": 2.5499,
      "step": 41
    },
    {
      "epoch": 0.04001905669366365,
      "grad_norm": 3.419790744781494,
      "learning_rate": 4.347369038899744e-05,
      "loss": 2.9799,
      "step": 42
    },
    {
      "epoch": 0.04097189137684612,
      "grad_norm": 6.255226135253906,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.883,
      "step": 43
    },
    {
      "epoch": 0.04192472606002858,
      "grad_norm": 0.0,
      "learning_rate": 3.917801930309486e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.04287756074321105,
      "grad_norm": 0.0,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.04383039542639352,
      "grad_norm": 0.0,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.04478323010957599,
      "grad_norm": 0.0,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.045736064792758456,
      "grad_norm": 8.734387397766113,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.4118,
      "step": 48
    },
    {
      "epoch": 0.046688899475940925,
      "grad_norm": 3.778465509414673,
      "learning_rate": 2.886908691296504e-05,
      "loss": 2.7381,
      "step": 49
    },
    {
      "epoch": 0.04764173415912339,
      "grad_norm": 2.9656107425689697,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 2.6656,
      "step": 50
    },
    {
      "epoch": 0.04764173415912339,
      "eval_loss": NaN,
      "eval_runtime": 190.1935,
      "eval_samples_per_second": 4.648,
      "eval_steps_per_second": 2.324,
      "step": 50
    },
    {
      "epoch": 0.04859456884230586,
      "grad_norm": 5.057662487030029,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.1957,
      "step": 51
    },
    {
      "epoch": 0.04954740352548833,
      "grad_norm": 2.368539571762085,
      "learning_rate": 2.3135019582658802e-05,
      "loss": 2.2245,
      "step": 52
    },
    {
      "epoch": 0.0505002382086708,
      "grad_norm": 2.0508615970611572,
      "learning_rate": 2.132117818244771e-05,
      "loss": 2.2957,
      "step": 53
    },
    {
      "epoch": 0.05145307289185326,
      "grad_norm": 1.9854440689086914,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 2.1347,
      "step": 54
    },
    {
      "epoch": 0.05240590757503573,
      "grad_norm": 1.7406495809555054,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.2859,
      "step": 55
    },
    {
      "epoch": 0.0533587422582182,
      "grad_norm": 1.5683196783065796,
      "learning_rate": 1.622048961921699e-05,
      "loss": 2.342,
      "step": 56
    },
    {
      "epoch": 0.054311576941400666,
      "grad_norm": 1.467210292816162,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.331,
      "step": 57
    },
    {
      "epoch": 0.055264411624583135,
      "grad_norm": 1.634995698928833,
      "learning_rate": 1.3136133159493802e-05,
      "loss": 2.1551,
      "step": 58
    },
    {
      "epoch": 0.0562172463077656,
      "grad_norm": 1.3047391176223755,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.2066,
      "step": 59
    },
    {
      "epoch": 0.05717008099094807,
      "grad_norm": 1.1119383573532104,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 2.0849,
      "step": 60
    },
    {
      "epoch": 0.05812291567413054,
      "grad_norm": 1.1421319246292114,
      "learning_rate": 9.042397785550405e-06,
      "loss": 2.1172,
      "step": 61
    },
    {
      "epoch": 0.05907575035731301,
      "grad_norm": 1.152631402015686,
      "learning_rate": 7.830427709355725e-06,
      "loss": 2.4149,
      "step": 62
    },
    {
      "epoch": 0.06002858504049548,
      "grad_norm": 1.3147021532058716,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.3454,
      "step": 63
    },
    {
      "epoch": 0.06098141972367794,
      "grad_norm": 1.3595980405807495,
      "learning_rate": 5.649458341088915e-06,
      "loss": 2.0931,
      "step": 64
    },
    {
      "epoch": 0.06193425440686041,
      "grad_norm": 2.0441415309906006,
      "learning_rate": 4.684610648167503e-06,
      "loss": 2.3878,
      "step": 65
    },
    {
      "epoch": 0.06288708909004288,
      "grad_norm": 1.2968662977218628,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.1372,
      "step": 66
    },
    {
      "epoch": 0.06383992377322535,
      "grad_norm": 1.2718733549118042,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.2646,
      "step": 67
    },
    {
      "epoch": 0.06479275845640782,
      "grad_norm": 1.2259955406188965,
      "learning_rate": 2.314152462588659e-06,
      "loss": 2.2772,
      "step": 68
    },
    {
      "epoch": 0.06574559313959027,
      "grad_norm": 1.2223516702651978,
      "learning_rate": 1.70370868554659e-06,
      "loss": 2.2698,
      "step": 69
    },
    {
      "epoch": 0.06669842782277274,
      "grad_norm": 1.2529011964797974,
      "learning_rate": 1.1851996440033319e-06,
      "loss": 2.2766,
      "step": 70
    },
    {
      "epoch": 0.06765126250595521,
      "grad_norm": 1.4887171983718872,
      "learning_rate": 7.596123493895991e-07,
      "loss": 2.2977,
      "step": 71
    },
    {
      "epoch": 0.06860409718913768,
      "grad_norm": 1.5588957071304321,
      "learning_rate": 4.277569313094809e-07,
      "loss": 2.3476,
      "step": 72
    },
    {
      "epoch": 0.06955693187232015,
      "grad_norm": 1.3241275548934937,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 2.3195,
      "step": 73
    },
    {
      "epoch": 0.07050976655550262,
      "grad_norm": 1.6149224042892456,
      "learning_rate": 4.7588920907110094e-08,
      "loss": 2.4973,
      "step": 74
    },
    {
      "epoch": 0.07146260123868509,
      "grad_norm": 1.5767426490783691,
      "learning_rate": 0.0,
      "loss": 2.4994,
      "step": 75
    },
    {
      "epoch": 0.07146260123868509,
      "eval_loss": NaN,
      "eval_runtime": 189.8117,
      "eval_samples_per_second": 4.657,
      "eval_steps_per_second": 2.329,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.1242647625387213e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}