{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07146260123868509,
  "eval_steps": 9,
  "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": 1.299138069152832,
      "learning_rate": 1e-05,
      "loss": 2.8561,
      "step": 1
    },
    {
      "epoch": 0.0009528346831824678,
      "eval_loss": 3.010896921157837,
      "eval_runtime": 195.3493,
      "eval_samples_per_second": 4.525,
      "eval_steps_per_second": 0.568,
      "step": 1
    },
    {
      "epoch": 0.0019056693663649356,
      "grad_norm": 1.0775965452194214,
      "learning_rate": 2e-05,
      "loss": 2.8611,
      "step": 2
    },
    {
      "epoch": 0.0028585040495474035,
      "grad_norm": 1.0691394805908203,
      "learning_rate": 3e-05,
      "loss": 2.9594,
      "step": 3
    },
    {
      "epoch": 0.003811338732729871,
      "grad_norm": 0.982935905456543,
      "learning_rate": 4e-05,
      "loss": 2.8709,
      "step": 4
    },
    {
      "epoch": 0.004764173415912339,
      "grad_norm": 1.0805885791778564,
      "learning_rate": 5e-05,
      "loss": 2.8401,
      "step": 5
    },
    {
      "epoch": 0.005717008099094807,
      "grad_norm": 1.0612759590148926,
      "learning_rate": 6e-05,
      "loss": 2.7195,
      "step": 6
    },
    {
      "epoch": 0.006669842782277275,
      "grad_norm": 1.2097413539886475,
      "learning_rate": 7e-05,
      "loss": 2.8155,
      "step": 7
    },
    {
      "epoch": 0.007622677465459742,
      "grad_norm": 1.3245927095413208,
      "learning_rate": 8e-05,
      "loss": 2.6753,
      "step": 8
    },
    {
      "epoch": 0.00857551214864221,
      "grad_norm": 1.2737631797790527,
      "learning_rate": 9e-05,
      "loss": 2.7696,
      "step": 9
    },
    {
      "epoch": 0.00857551214864221,
      "eval_loss": 2.809389114379883,
      "eval_runtime": 195.5632,
      "eval_samples_per_second": 4.52,
      "eval_steps_per_second": 0.568,
      "step": 9
    },
    {
      "epoch": 0.009528346831824679,
      "grad_norm": 1.277371883392334,
      "learning_rate": 0.0001,
      "loss": 2.8938,
      "step": 10
    },
    {
      "epoch": 0.010481181515007145,
      "grad_norm": 1.1133867502212524,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.7638,
      "step": 11
    },
    {
      "epoch": 0.011434016198189614,
      "grad_norm": 1.2571532726287842,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.4968,
      "step": 12
    },
    {
      "epoch": 0.012386850881372083,
      "grad_norm": 1.0732775926589966,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.3647,
      "step": 13
    },
    {
      "epoch": 0.01333968556455455,
      "grad_norm": 1.4276105165481567,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.6106,
      "step": 14
    },
    {
      "epoch": 0.014292520247737018,
      "grad_norm": 1.4259613752365112,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.4836,
      "step": 15
    },
    {
      "epoch": 0.015245354930919485,
      "grad_norm": 1.3352410793304443,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.4822,
      "step": 16
    },
    {
      "epoch": 0.016198189614101955,
      "grad_norm": 1.274780035018921,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.4272,
      "step": 17
    },
    {
      "epoch": 0.01715102429728442,
      "grad_norm": 1.0535167455673218,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.465,
      "step": 18
    },
    {
      "epoch": 0.01715102429728442,
      "eval_loss": 2.526502847671509,
      "eval_runtime": 195.3502,
      "eval_samples_per_second": 4.525,
      "eval_steps_per_second": 0.568,
      "step": 18
    },
    {
      "epoch": 0.01810385898046689,
      "grad_norm": 1.1656160354614258,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.3156,
      "step": 19
    },
    {
      "epoch": 0.019056693663649357,
      "grad_norm": 1.2742457389831543,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.4936,
      "step": 20
    },
    {
      "epoch": 0.020009528346831826,
      "grad_norm": 1.2091561555862427,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.4467,
      "step": 21
    },
    {
      "epoch": 0.02096236303001429,
      "grad_norm": 1.6974114179611206,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.6585,
      "step": 22
    },
    {
      "epoch": 0.02191519771319676,
      "grad_norm": 1.2182083129882812,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.0146,
      "step": 23
    },
    {
      "epoch": 0.022868032396379228,
      "grad_norm": 1.3905271291732788,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.8601,
      "step": 24
    },
    {
      "epoch": 0.023820867079561697,
      "grad_norm": 1.1157796382904053,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.2298,
      "step": 25
    },
    {
      "epoch": 0.024773701762744165,
      "grad_norm": 1.220881462097168,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.4306,
      "step": 26
    },
    {
      "epoch": 0.02572653644592663,
      "grad_norm": 1.5156694650650024,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.7689,
      "step": 27
    },
    {
      "epoch": 0.02572653644592663,
      "eval_loss": 2.390195369720459,
      "eval_runtime": 195.5478,
      "eval_samples_per_second": 4.521,
      "eval_steps_per_second": 0.568,
      "step": 27
    },
    {
      "epoch": 0.0266793711291091,
      "grad_norm": 1.081608772277832,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.0068,
      "step": 28
    },
    {
      "epoch": 0.027632205812291567,
      "grad_norm": 1.2319940328598022,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.3822,
      "step": 29
    },
    {
      "epoch": 0.028585040495474036,
      "grad_norm": 1.1373631954193115,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.1743,
      "step": 30
    },
    {
      "epoch": 0.029537875178656504,
      "grad_norm": 1.7887684106826782,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.7599,
      "step": 31
    },
    {
      "epoch": 0.03049070986183897,
      "grad_norm": 2.468310594558716,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.4588,
      "step": 32
    },
    {
      "epoch": 0.03144354454502144,
      "grad_norm": 1.4182935953140259,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.5963,
      "step": 33
    },
    {
      "epoch": 0.03239637922820391,
      "grad_norm": 1.6286972761154175,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.385,
      "step": 34
    },
    {
      "epoch": 0.03334921391138637,
      "grad_norm": 1.6932363510131836,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.3984,
      "step": 35
    },
    {
      "epoch": 0.03430204859456884,
      "grad_norm": 1.6212579011917114,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.559,
      "step": 36
    },
    {
      "epoch": 0.03430204859456884,
      "eval_loss": 2.326164484024048,
      "eval_runtime": 195.2942,
      "eval_samples_per_second": 4.527,
      "eval_steps_per_second": 0.568,
      "step": 36
    },
    {
      "epoch": 0.03525488327775131,
      "grad_norm": 3.3297510147094727,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.2348,
      "step": 37
    },
    {
      "epoch": 0.03620771796093378,
      "grad_norm": 1.1248424053192139,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.3229,
      "step": 38
    },
    {
      "epoch": 0.037160552644116246,
      "grad_norm": 1.1936289072036743,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.1951,
      "step": 39
    },
    {
      "epoch": 0.038113387327298714,
      "grad_norm": 1.2495434284210205,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.2668,
      "step": 40
    },
    {
      "epoch": 0.03906622201048118,
      "grad_norm": 1.079162359237671,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.2035,
      "step": 41
    },
    {
      "epoch": 0.04001905669366365,
      "grad_norm": 1.159868836402893,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.9719,
      "step": 42
    },
    {
      "epoch": 0.04097189137684612,
      "grad_norm": 1.2213239669799805,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.2513,
      "step": 43
    },
    {
      "epoch": 0.04192472606002858,
      "grad_norm": 1.4291725158691406,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.2991,
      "step": 44
    },
    {
      "epoch": 0.04287756074321105,
      "grad_norm": 1.114621877670288,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.1182,
      "step": 45
    },
    {
      "epoch": 0.04287756074321105,
      "eval_loss": 2.283418655395508,
      "eval_runtime": 195.3577,
      "eval_samples_per_second": 4.525,
      "eval_steps_per_second": 0.568,
      "step": 45
    },
    {
      "epoch": 0.04383039542639352,
      "grad_norm": 1.91363525390625,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.2587,
      "step": 46
    },
    {
      "epoch": 0.04478323010957599,
      "grad_norm": 1.2641960382461548,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.187,
      "step": 47
    },
    {
      "epoch": 0.045736064792758456,
      "grad_norm": 1.4268271923065186,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.3428,
      "step": 48
    },
    {
      "epoch": 0.046688899475940925,
      "grad_norm": 1.0803133249282837,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.1408,
      "step": 49
    },
    {
      "epoch": 0.04764173415912339,
      "grad_norm": 0.9304092526435852,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.003,
      "step": 50
    },
    {
      "epoch": 0.04859456884230586,
      "grad_norm": 1.0506590604782104,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.2448,
      "step": 51
    },
    {
      "epoch": 0.04954740352548833,
      "grad_norm": 1.165993571281433,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.057,
      "step": 52
    },
    {
      "epoch": 0.0505002382086708,
      "grad_norm": 1.1454460620880127,
      "learning_rate": 5.348782368720626e-05,
      "loss": 2.043,
      "step": 53
    },
    {
      "epoch": 0.05145307289185326,
      "grad_norm": 1.139070987701416,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.441,
      "step": 54
    },
    {
      "epoch": 0.05145307289185326,
      "eval_loss": 2.270153522491455,
      "eval_runtime": 195.4006,
      "eval_samples_per_second": 4.524,
      "eval_steps_per_second": 0.568,
      "step": 54
    },
    {
      "epoch": 0.05240590757503573,
      "grad_norm": 1.4192317724227905,
      "learning_rate": 5e-05,
      "loss": 2.1888,
      "step": 55
    },
    {
      "epoch": 0.0533587422582182,
      "grad_norm": 1.4029229879379272,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.6344,
      "step": 56
    },
    {
      "epoch": 0.054311576941400666,
      "grad_norm": 1.2530521154403687,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.2003,
      "step": 57
    },
    {
      "epoch": 0.055264411624583135,
      "grad_norm": 8.52709674835205,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.0568,
      "step": 58
    },
    {
      "epoch": 0.0562172463077656,
      "grad_norm": 1.2079765796661377,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 2.2747,
      "step": 59
    },
    {
      "epoch": 0.05717008099094807,
      "grad_norm": 1.1588507890701294,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.4211,
      "step": 60
    },
    {
      "epoch": 0.05812291567413054,
      "grad_norm": 1.0553061962127686,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.2825,
      "step": 61
    },
    {
      "epoch": 0.05907575035731301,
      "grad_norm": 0.9334769248962402,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.2447,
      "step": 62
    },
    {
      "epoch": 0.06002858504049548,
      "grad_norm": 1.0937581062316895,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.024,
      "step": 63
    },
    {
      "epoch": 0.06002858504049548,
      "eval_loss": 2.261378049850464,
      "eval_runtime": 195.3363,
      "eval_samples_per_second": 4.526,
      "eval_steps_per_second": 0.568,
      "step": 63
    },
    {
      "epoch": 0.06098141972367794,
      "grad_norm": 2.8231825828552246,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.3215,
      "step": 64
    },
    {
      "epoch": 0.06193425440686041,
      "grad_norm": 1.4724355936050415,
      "learning_rate": 3.289899283371657e-05,
      "loss": 2.1722,
      "step": 65
    },
    {
      "epoch": 0.06288708909004288,
      "grad_norm": 4.071575164794922,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.2437,
      "step": 66
    },
    {
      "epoch": 0.06383992377322535,
      "grad_norm": 1.1286451816558838,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 2.1099,
      "step": 67
    },
    {
      "epoch": 0.06479275845640782,
      "grad_norm": 1.3559694290161133,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.261,
      "step": 68
    },
    {
      "epoch": 0.06574559313959027,
      "grad_norm": 1.2074459791183472,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.172,
      "step": 69
    },
    {
      "epoch": 0.06669842782277274,
      "grad_norm": 1.2289658784866333,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.3035,
      "step": 70
    },
    {
      "epoch": 0.06765126250595521,
      "grad_norm": 1.2221287488937378,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.2006,
      "step": 71
    },
    {
      "epoch": 0.06860409718913768,
      "grad_norm": 1.2182445526123047,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.2886,
      "step": 72
    },
    {
      "epoch": 0.06860409718913768,
      "eval_loss": 2.2531282901763916,
      "eval_runtime": 195.3498,
      "eval_samples_per_second": 4.525,
      "eval_steps_per_second": 0.568,
      "step": 72
    },
    {
      "epoch": 0.06955693187232015,
      "grad_norm": 0.7799471020698547,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.0113,
      "step": 73
    },
    {
      "epoch": 0.07050976655550262,
      "grad_norm": 0.9231268763542175,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.1421,
      "step": 74
    },
    {
      "epoch": 0.07146260123868509,
      "grad_norm": 0.8884665966033936,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.1019,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.112830925340672e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}