{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.8251366120218577,
  "eval_steps": 500,
  "global_step": 3500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0546448087431694,
      "grad_norm": 2.1467645168304443,
      "learning_rate": 0.0004973224043715847,
      "loss": 5.4078,
      "step": 50
    },
    {
      "epoch": 0.1092896174863388,
      "grad_norm": 0.8721267580986023,
      "learning_rate": 0.0004945901639344262,
      "loss": 1.2654,
      "step": 100
    },
    {
      "epoch": 0.16393442622950818,
      "grad_norm": 0.8103071451187134,
      "learning_rate": 0.0004918579234972678,
      "loss": 1.0538,
      "step": 150
    },
    {
      "epoch": 0.2185792349726776,
      "grad_norm": 1.3929318189620972,
      "learning_rate": 0.0004891256830601093,
      "loss": 1.0236,
      "step": 200
    },
    {
      "epoch": 0.273224043715847,
      "grad_norm": 0.970960259437561,
      "learning_rate": 0.00048639344262295083,
      "loss": 1.075,
      "step": 250
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 0.9727946519851685,
      "learning_rate": 0.00048366120218579234,
      "loss": 1.0434,
      "step": 300
    },
    {
      "epoch": 0.3825136612021858,
      "grad_norm": 0.6411604285240173,
      "learning_rate": 0.0004809289617486339,
      "loss": 0.9285,
      "step": 350
    },
    {
      "epoch": 0.4371584699453552,
      "grad_norm": 0.8864787817001343,
      "learning_rate": 0.0004781967213114754,
      "loss": 0.9315,
      "step": 400
    },
    {
      "epoch": 0.4918032786885246,
      "grad_norm": 0.8886504173278809,
      "learning_rate": 0.0004754644808743169,
      "loss": 0.8818,
      "step": 450
    },
    {
      "epoch": 0.546448087431694,
      "grad_norm": 0.7289233803749084,
      "learning_rate": 0.0004727322404371585,
      "loss": 0.92,
      "step": 500
    },
    {
      "epoch": 0.6010928961748634,
      "grad_norm": 1.0301029682159424,
      "learning_rate": 0.00047,
      "loss": 0.8222,
      "step": 550
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 0.808475136756897,
      "learning_rate": 0.00046726775956284155,
      "loss": 0.8767,
      "step": 600
    },
    {
      "epoch": 0.7103825136612022,
      "grad_norm": 0.8232861161231995,
      "learning_rate": 0.0004645355191256831,
      "loss": 0.835,
      "step": 650
    },
    {
      "epoch": 0.7650273224043715,
      "grad_norm": 0.9552908539772034,
      "learning_rate": 0.0004618032786885246,
      "loss": 0.8203,
      "step": 700
    },
    {
      "epoch": 0.819672131147541,
      "grad_norm": 0.7888686656951904,
      "learning_rate": 0.00045907103825136613,
      "loss": 0.8296,
      "step": 750
    },
    {
      "epoch": 0.8743169398907104,
      "grad_norm": 0.7473599910736084,
      "learning_rate": 0.0004563387978142077,
      "loss": 0.7801,
      "step": 800
    },
    {
      "epoch": 0.9289617486338798,
      "grad_norm": 0.8543986678123474,
      "learning_rate": 0.0004536065573770492,
      "loss": 0.9248,
      "step": 850
    },
    {
      "epoch": 0.9836065573770492,
      "grad_norm": 0.7910193204879761,
      "learning_rate": 0.0004508743169398907,
      "loss": 0.8386,
      "step": 900
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6989373564720154,
      "eval_runtime": 35.1236,
      "eval_samples_per_second": 23.175,
      "eval_steps_per_second": 2.904,
      "step": 915
    },
    {
      "epoch": 1.0382513661202186,
      "grad_norm": 1.1451815366744995,
      "learning_rate": 0.00044814207650273227,
      "loss": 0.7198,
      "step": 950
    },
    {
      "epoch": 1.092896174863388,
      "grad_norm": 0.7096536755561829,
      "learning_rate": 0.0004454098360655738,
      "loss": 0.7374,
      "step": 1000
    },
    {
      "epoch": 1.1475409836065573,
      "grad_norm": 0.8436596393585205,
      "learning_rate": 0.0004426775956284153,
      "loss": 0.7471,
      "step": 1050
    },
    {
      "epoch": 1.2021857923497268,
      "grad_norm": 0.8844044208526611,
      "learning_rate": 0.00043994535519125685,
      "loss": 0.7072,
      "step": 1100
    },
    {
      "epoch": 1.2568306010928962,
      "grad_norm": 0.9547187089920044,
      "learning_rate": 0.00043721311475409836,
      "loss": 0.7618,
      "step": 1150
    },
    {
      "epoch": 1.3114754098360657,
      "grad_norm": 0.8470160961151123,
      "learning_rate": 0.00043448087431693987,
      "loss": 0.7719,
      "step": 1200
    },
    {
      "epoch": 1.366120218579235,
      "grad_norm": 0.8797179460525513,
      "learning_rate": 0.00043174863387978143,
      "loss": 0.7172,
      "step": 1250
    },
    {
      "epoch": 1.4207650273224044,
      "grad_norm": 0.6831291317939758,
      "learning_rate": 0.00042901639344262294,
      "loss": 0.7254,
      "step": 1300
    },
    {
      "epoch": 1.4754098360655736,
      "grad_norm": 0.7458399534225464,
      "learning_rate": 0.00042628415300546445,
      "loss": 0.7219,
      "step": 1350
    },
    {
      "epoch": 1.530054644808743,
      "grad_norm": 0.7829724550247192,
      "learning_rate": 0.000423551912568306,
      "loss": 0.6969,
      "step": 1400
    },
    {
      "epoch": 1.5846994535519126,
      "grad_norm": 0.914277970790863,
      "learning_rate": 0.0004208196721311475,
      "loss": 0.7088,
      "step": 1450
    },
    {
      "epoch": 1.639344262295082,
      "grad_norm": 0.9189252853393555,
      "learning_rate": 0.00041808743169398913,
      "loss": 0.7574,
      "step": 1500
    },
    {
      "epoch": 1.6939890710382515,
      "grad_norm": 0.8233757019042969,
      "learning_rate": 0.00041535519125683064,
      "loss": 0.7248,
      "step": 1550
    },
    {
      "epoch": 1.748633879781421,
      "grad_norm": 0.5294966101646423,
      "learning_rate": 0.00041262295081967215,
      "loss": 0.7173,
      "step": 1600
    },
    {
      "epoch": 1.8032786885245902,
      "grad_norm": 0.7432788014411926,
      "learning_rate": 0.0004098907103825137,
      "loss": 0.731,
      "step": 1650
    },
    {
      "epoch": 1.8579234972677594,
      "grad_norm": 0.9326347708702087,
      "learning_rate": 0.0004071584699453552,
      "loss": 0.6559,
      "step": 1700
    },
    {
      "epoch": 1.9125683060109289,
      "grad_norm": 0.6357129216194153,
      "learning_rate": 0.00040442622950819673,
      "loss": 0.7079,
      "step": 1750
    },
    {
      "epoch": 1.9672131147540983,
      "grad_norm": 0.6454396843910217,
      "learning_rate": 0.0004016939890710383,
      "loss": 0.6284,
      "step": 1800
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6172024607658386,
      "eval_runtime": 34.4665,
      "eval_samples_per_second": 23.617,
      "eval_steps_per_second": 2.959,
      "step": 1830
    },
    {
      "epoch": 2.021857923497268,
      "grad_norm": 0.9404008388519287,
      "learning_rate": 0.0003989617486338798,
      "loss": 0.6996,
      "step": 1850
    },
    {
      "epoch": 2.0765027322404372,
      "grad_norm": 0.7585016489028931,
      "learning_rate": 0.0003962295081967213,
      "loss": 0.6634,
      "step": 1900
    },
    {
      "epoch": 2.1311475409836067,
      "grad_norm": 0.9319397807121277,
      "learning_rate": 0.00039349726775956287,
      "loss": 0.6439,
      "step": 1950
    },
    {
      "epoch": 2.185792349726776,
      "grad_norm": 0.7812663912773132,
      "learning_rate": 0.0003907650273224044,
      "loss": 0.6807,
      "step": 2000
    },
    {
      "epoch": 2.240437158469945,
      "grad_norm": 0.8016160726547241,
      "learning_rate": 0.0003880327868852459,
      "loss": 0.6121,
      "step": 2050
    },
    {
      "epoch": 2.2950819672131146,
      "grad_norm": 0.5846936106681824,
      "learning_rate": 0.00038530054644808745,
      "loss": 0.6501,
      "step": 2100
    },
    {
      "epoch": 2.349726775956284,
      "grad_norm": 0.6993207931518555,
      "learning_rate": 0.00038256830601092896,
      "loss": 0.6242,
      "step": 2150
    },
    {
      "epoch": 2.4043715846994536,
      "grad_norm": 0.5866222381591797,
      "learning_rate": 0.00037983606557377047,
      "loss": 0.5766,
      "step": 2200
    },
    {
      "epoch": 2.459016393442623,
      "grad_norm": 0.8375122547149658,
      "learning_rate": 0.00037710382513661203,
      "loss": 0.6395,
      "step": 2250
    },
    {
      "epoch": 2.5136612021857925,
      "grad_norm": 0.9567583799362183,
      "learning_rate": 0.00037437158469945354,
      "loss": 0.6829,
      "step": 2300
    },
    {
      "epoch": 2.5683060109289615,
      "grad_norm": 0.829088032245636,
      "learning_rate": 0.00037163934426229505,
      "loss": 0.6138,
      "step": 2350
    },
    {
      "epoch": 2.6229508196721314,
      "grad_norm": 0.7738655805587769,
      "learning_rate": 0.00036890710382513666,
      "loss": 0.5961,
      "step": 2400
    },
    {
      "epoch": 2.6775956284153004,
      "grad_norm": 0.6849051117897034,
      "learning_rate": 0.00036617486338797817,
      "loss": 0.6158,
      "step": 2450
    },
    {
      "epoch": 2.73224043715847,
      "grad_norm": 0.6353682279586792,
      "learning_rate": 0.0003634426229508197,
      "loss": 0.6077,
      "step": 2500
    },
    {
      "epoch": 2.7868852459016393,
      "grad_norm": 0.6507243514060974,
      "learning_rate": 0.00036071038251366124,
      "loss": 0.5881,
      "step": 2550
    },
    {
      "epoch": 2.841530054644809,
      "grad_norm": 0.7680765390396118,
      "learning_rate": 0.00035797814207650275,
      "loss": 0.64,
      "step": 2600
    },
    {
      "epoch": 2.8961748633879782,
      "grad_norm": 0.8768549561500549,
      "learning_rate": 0.00035524590163934426,
      "loss": 0.5946,
      "step": 2650
    },
    {
      "epoch": 2.9508196721311473,
      "grad_norm": 0.9345018267631531,
      "learning_rate": 0.0003525136612021858,
      "loss": 0.5986,
      "step": 2700
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5772798657417297,
      "eval_runtime": 34.1537,
      "eval_samples_per_second": 23.833,
      "eval_steps_per_second": 2.986,
      "step": 2745
    },
    {
      "epoch": 3.0054644808743167,
      "grad_norm": 0.8109590411186218,
      "learning_rate": 0.00034978142076502733,
      "loss": 0.6056,
      "step": 2750
    },
    {
      "epoch": 3.060109289617486,
      "grad_norm": 1.1651564836502075,
      "learning_rate": 0.00034704918032786884,
      "loss": 0.5321,
      "step": 2800
    },
    {
      "epoch": 3.1147540983606556,
      "grad_norm": 0.9508790969848633,
      "learning_rate": 0.0003443169398907104,
      "loss": 0.5405,
      "step": 2850
    },
    {
      "epoch": 3.169398907103825,
      "grad_norm": 0.7765358686447144,
      "learning_rate": 0.0003415846994535519,
      "loss": 0.6053,
      "step": 2900
    },
    {
      "epoch": 3.2240437158469946,
      "grad_norm": 1.0186572074890137,
      "learning_rate": 0.0003388524590163934,
      "loss": 0.6171,
      "step": 2950
    },
    {
      "epoch": 3.278688524590164,
      "grad_norm": 0.9198819398880005,
      "learning_rate": 0.000336120218579235,
      "loss": 0.5755,
      "step": 3000
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 1.0580278635025024,
      "learning_rate": 0.0003333879781420765,
      "loss": 0.5521,
      "step": 3050
    },
    {
      "epoch": 3.387978142076503,
      "grad_norm": 0.637541651725769,
      "learning_rate": 0.00033065573770491805,
      "loss": 0.5288,
      "step": 3100
    },
    {
      "epoch": 3.442622950819672,
      "grad_norm": 1.3321665525436401,
      "learning_rate": 0.00032792349726775956,
      "loss": 0.57,
      "step": 3150
    },
    {
      "epoch": 3.4972677595628414,
      "grad_norm": 1.1390025615692139,
      "learning_rate": 0.00032519125683060107,
      "loss": 0.588,
      "step": 3200
    },
    {
      "epoch": 3.551912568306011,
      "grad_norm": 0.6929836273193359,
      "learning_rate": 0.00032245901639344263,
      "loss": 0.5508,
      "step": 3250
    },
    {
      "epoch": 3.6065573770491803,
      "grad_norm": 0.6794707179069519,
      "learning_rate": 0.00031972677595628414,
      "loss": 0.5284,
      "step": 3300
    },
    {
      "epoch": 3.66120218579235,
      "grad_norm": 0.7672021985054016,
      "learning_rate": 0.0003169945355191257,
      "loss": 0.5968,
      "step": 3350
    },
    {
      "epoch": 3.7158469945355193,
      "grad_norm": 1.0557798147201538,
      "learning_rate": 0.00031426229508196726,
      "loss": 0.5586,
      "step": 3400
    },
    {
      "epoch": 3.7704918032786887,
      "grad_norm": 0.7945201992988586,
      "learning_rate": 0.00031153005464480877,
      "loss": 0.5042,
      "step": 3450
    },
    {
      "epoch": 3.8251366120218577,
      "grad_norm": 0.49171268939971924,
      "learning_rate": 0.0003087978142076503,
      "loss": 0.5695,
      "step": 3500
    }
  ],
  "logging_steps": 50,
  "max_steps": 9150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5204934131712000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}