{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10358668911044931,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00025896672277612325,
      "eval_loss": 2.429945707321167,
      "eval_runtime": 128.6072,
      "eval_samples_per_second": 12.643,
      "eval_steps_per_second": 6.322,
      "step": 1
    },
    {
      "epoch": 0.0012948336138806163,
      "grad_norm": 2.0355920791625977,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.4889,
      "step": 5
    },
    {
      "epoch": 0.0025896672277612325,
      "grad_norm": 2.8041932582855225,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.8388,
      "step": 10
    },
    {
      "epoch": 0.003884500841641849,
      "grad_norm": 3.1450560092926025,
      "learning_rate": 5e-05,
      "loss": 1.6455,
      "step": 15
    },
    {
      "epoch": 0.005179334455522465,
      "grad_norm": 3.1131961345672607,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.4675,
      "step": 20
    },
    {
      "epoch": 0.006474168069403082,
      "grad_norm": 3.105552911758423,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.1591,
      "step": 25
    },
    {
      "epoch": 0.007769001683283698,
      "grad_norm": 3.133176803588867,
      "learning_rate": 0.0001,
      "loss": 0.9308,
      "step": 30
    },
    {
      "epoch": 0.009063835297164315,
      "grad_norm": 3.0689797401428223,
      "learning_rate": 9.995494831023409e-05,
      "loss": 0.6691,
      "step": 35
    },
    {
      "epoch": 0.01035866891104493,
      "grad_norm": 5.8070220947265625,
      "learning_rate": 9.981987442712633e-05,
      "loss": 0.9514,
      "step": 40
    },
    {
      "epoch": 0.011653502524925547,
      "grad_norm": 4.279685974121094,
      "learning_rate": 9.959502176294383e-05,
      "loss": 0.8945,
      "step": 45
    },
    {
      "epoch": 0.012948336138806164,
      "grad_norm": 6.091928005218506,
      "learning_rate": 9.928079551738543e-05,
      "loss": 0.8196,
      "step": 50
    },
    {
      "epoch": 0.01424316975268678,
      "grad_norm": 2.6002321243286133,
      "learning_rate": 9.887776194738432e-05,
      "loss": 0.7675,
      "step": 55
    },
    {
      "epoch": 0.015538003366567396,
      "grad_norm": 2.435842275619507,
      "learning_rate": 9.838664734667495e-05,
      "loss": 0.9432,
      "step": 60
    },
    {
      "epoch": 0.01683283698044801,
      "grad_norm": 2.1579127311706543,
      "learning_rate": 9.780833673696254e-05,
      "loss": 0.6512,
      "step": 65
    },
    {
      "epoch": 0.01812767059432863,
      "grad_norm": 1.7469655275344849,
      "learning_rate": 9.714387227305422e-05,
      "loss": 0.6825,
      "step": 70
    },
    {
      "epoch": 0.019422504208209245,
      "grad_norm": 1.9260777235031128,
      "learning_rate": 9.639445136482548e-05,
      "loss": 0.4535,
      "step": 75
    },
    {
      "epoch": 0.02071733782208986,
      "grad_norm": 2.065256118774414,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.6342,
      "step": 80
    },
    {
      "epoch": 0.02201217143597048,
      "grad_norm": 2.436000347137451,
      "learning_rate": 9.464629290747842e-05,
      "loss": 0.4641,
      "step": 85
    },
    {
      "epoch": 0.023307005049851094,
      "grad_norm": 2.4210498332977295,
      "learning_rate": 9.365070565805941e-05,
      "loss": 0.5358,
      "step": 90
    },
    {
      "epoch": 0.02460183866373171,
      "grad_norm": 3.2171995639801025,
      "learning_rate": 9.257645688666556e-05,
      "loss": 0.4851,
      "step": 95
    },
    {
      "epoch": 0.025896672277612328,
      "grad_norm": 4.6157941818237305,
      "learning_rate": 9.142548246219212e-05,
      "loss": 0.814,
      "step": 100
    },
    {
      "epoch": 0.025896672277612328,
      "eval_loss": 0.5770405530929565,
      "eval_runtime": 130.0593,
      "eval_samples_per_second": 12.502,
      "eval_steps_per_second": 6.251,
      "step": 100
    },
    {
      "epoch": 0.027191505891492943,
      "grad_norm": 1.1890275478363037,
      "learning_rate": 9.019985651834703e-05,
      "loss": 0.6116,
      "step": 105
    },
    {
      "epoch": 0.02848633950537356,
      "grad_norm": 2.1260907649993896,
      "learning_rate": 8.890178771592199e-05,
      "loss": 0.7218,
      "step": 110
    },
    {
      "epoch": 0.029781173119254177,
      "grad_norm": 1.385692834854126,
      "learning_rate": 8.753361526263621e-05,
      "loss": 0.6289,
      "step": 115
    },
    {
      "epoch": 0.031076006733134792,
      "grad_norm": 1.3872414827346802,
      "learning_rate": 8.609780469772623e-05,
      "loss": 0.4376,
      "step": 120
    },
    {
      "epoch": 0.03237084034701541,
      "grad_norm": 2.719921350479126,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.4644,
      "step": 125
    },
    {
      "epoch": 0.03366567396089602,
      "grad_norm": 1.434913158416748,
      "learning_rate": 8.303373616950408e-05,
      "loss": 0.3999,
      "step": 130
    },
    {
      "epoch": 0.03496050757477664,
      "grad_norm": 1.5214489698410034,
      "learning_rate": 8.141099986478212e-05,
      "loss": 0.2526,
      "step": 135
    },
    {
      "epoch": 0.03625534118865726,
      "grad_norm": 2.125997543334961,
      "learning_rate": 7.973165881521434e-05,
      "loss": 0.4678,
      "step": 140
    },
    {
      "epoch": 0.037550174802537875,
      "grad_norm": 1.8807339668273926,
      "learning_rate": 7.799873930687978e-05,
      "loss": 0.3238,
      "step": 145
    },
    {
      "epoch": 0.03884500841641849,
      "grad_norm": 1.5058170557022095,
      "learning_rate": 7.621536417786159e-05,
      "loss": 0.4016,
      "step": 150
    },
    {
      "epoch": 0.040139842030299105,
      "grad_norm": 1.655715823173523,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.7613,
      "step": 155
    },
    {
      "epoch": 0.04143467564417972,
      "grad_norm": 2.365912914276123,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.5694,
      "step": 160
    },
    {
      "epoch": 0.042729509258060336,
      "grad_norm": 1.4638949632644653,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.4832,
      "step": 165
    },
    {
      "epoch": 0.04402434287194096,
      "grad_norm": 3.604722738265991,
      "learning_rate": 6.864282388901544e-05,
      "loss": 0.375,
      "step": 170
    },
    {
      "epoch": 0.04531917648582157,
      "grad_norm": 1.4864394664764404,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.4243,
      "step": 175
    },
    {
      "epoch": 0.04661401009970219,
      "grad_norm": 1.6707390546798706,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.3858,
      "step": 180
    },
    {
      "epoch": 0.047908843713582804,
      "grad_norm": 1.2720017433166504,
      "learning_rate": 6.259890306925627e-05,
      "loss": 0.2828,
      "step": 185
    },
    {
      "epoch": 0.04920367732746342,
      "grad_norm": 3.1049351692199707,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 0.4495,
      "step": 190
    },
    {
      "epoch": 0.050498510941344034,
      "grad_norm": 1.2727268934249878,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 0.259,
      "step": 195
    },
    {
      "epoch": 0.051793344555224656,
      "grad_norm": 1.8646743297576904,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 0.425,
      "step": 200
    },
    {
      "epoch": 0.051793344555224656,
      "eval_loss": 0.4503786563873291,
      "eval_runtime": 130.0568,
      "eval_samples_per_second": 12.502,
      "eval_steps_per_second": 6.251,
      "step": 200
    },
    {
      "epoch": 0.05308817816910527,
      "grad_norm": 1.6708872318267822,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 0.5951,
      "step": 205
    },
    {
      "epoch": 0.054383011782985886,
      "grad_norm": 1.4012404680252075,
      "learning_rate": 5.212206015980742e-05,
      "loss": 0.4933,
      "step": 210
    },
    {
      "epoch": 0.0556778453968665,
      "grad_norm": 1.1201272010803223,
      "learning_rate": 5e-05,
      "loss": 0.3669,
      "step": 215
    },
    {
      "epoch": 0.05697267901074712,
      "grad_norm": 1.3455181121826172,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.3226,
      "step": 220
    },
    {
      "epoch": 0.05826751262462773,
      "grad_norm": 1.8701527118682861,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.4886,
      "step": 225
    },
    {
      "epoch": 0.059562346238508354,
      "grad_norm": 1.9327068328857422,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.4693,
      "step": 230
    },
    {
      "epoch": 0.06085717985238897,
      "grad_norm": 1.1282538175582886,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.1738,
      "step": 235
    },
    {
      "epoch": 0.062152013466269584,
      "grad_norm": 2.8107926845550537,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.4254,
      "step": 240
    },
    {
      "epoch": 0.0634468470801502,
      "grad_norm": 0.9322945475578308,
      "learning_rate": 3.740109693074375e-05,
      "loss": 0.2301,
      "step": 245
    },
    {
      "epoch": 0.06474168069403081,
      "grad_norm": 1.32906174659729,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 0.2101,
      "step": 250
    },
    {
      "epoch": 0.06603651430791144,
      "grad_norm": 1.4520397186279297,
      "learning_rate": 3.334301026289712e-05,
      "loss": 0.6398,
      "step": 255
    },
    {
      "epoch": 0.06733134792179205,
      "grad_norm": 1.7414826154708862,
      "learning_rate": 3.135717611098458e-05,
      "loss": 0.5926,
      "step": 260
    },
    {
      "epoch": 0.06862618153567267,
      "grad_norm": 1.9224941730499268,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.441,
      "step": 265
    },
    {
      "epoch": 0.06992101514955328,
      "grad_norm": 1.8170069456100464,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.3139,
      "step": 270
    },
    {
      "epoch": 0.0712158487634339,
      "grad_norm": 1.8220938444137573,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.3689,
      "step": 275
    },
    {
      "epoch": 0.07251068237731452,
      "grad_norm": 1.344126582145691,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.3298,
      "step": 280
    },
    {
      "epoch": 0.07380551599119513,
      "grad_norm": 1.2731266021728516,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.3126,
      "step": 285
    },
    {
      "epoch": 0.07510034960507575,
      "grad_norm": 2.8344573974609375,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.5506,
      "step": 290
    },
    {
      "epoch": 0.07639518321895636,
      "grad_norm": 0.9187384247779846,
      "learning_rate": 1.858900013521788e-05,
      "loss": 0.2124,
      "step": 295
    },
    {
      "epoch": 0.07769001683283698,
      "grad_norm": 1.8385587930679321,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.2854,
      "step": 300
    },
    {
      "epoch": 0.07769001683283698,
      "eval_loss": 0.39213624596595764,
      "eval_runtime": 130.1069,
      "eval_samples_per_second": 12.497,
      "eval_steps_per_second": 6.249,
      "step": 300
    },
    {
      "epoch": 0.0789848504467176,
      "grad_norm": 1.807713508605957,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.5029,
      "step": 305
    },
    {
      "epoch": 0.08027968406059821,
      "grad_norm": 1.7962974309921265,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 0.4625,
      "step": 310
    },
    {
      "epoch": 0.08157451767447883,
      "grad_norm": 1.0811614990234375,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.3378,
      "step": 315
    },
    {
      "epoch": 0.08286935128835944,
      "grad_norm": 1.3859697580337524,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.3228,
      "step": 320
    },
    {
      "epoch": 0.08416418490224006,
      "grad_norm": 1.6735330820083618,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.3701,
      "step": 325
    },
    {
      "epoch": 0.08545901851612067,
      "grad_norm": 1.7748876810073853,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.3616,
      "step": 330
    },
    {
      "epoch": 0.0867538521300013,
      "grad_norm": 1.7126069068908691,
      "learning_rate": 7.423543113334436e-06,
      "loss": 0.281,
      "step": 335
    },
    {
      "epoch": 0.08804868574388192,
      "grad_norm": 1.7981863021850586,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.3946,
      "step": 340
    },
    {
      "epoch": 0.08934351935776252,
      "grad_norm": 0.986768901348114,
      "learning_rate": 5.353707092521582e-06,
      "loss": 0.2403,
      "step": 345
    },
    {
      "epoch": 0.09063835297164315,
      "grad_norm": 4.029610633850098,
      "learning_rate": 4.43857548059321e-06,
      "loss": 0.4817,
      "step": 350
    },
    {
      "epoch": 0.09193318658552375,
      "grad_norm": 1.2335231304168701,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.5626,
      "step": 355
    },
    {
      "epoch": 0.09322802019940438,
      "grad_norm": 1.689747929573059,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.3735,
      "step": 360
    },
    {
      "epoch": 0.094522853813285,
      "grad_norm": 1.7561933994293213,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.4144,
      "step": 365
    },
    {
      "epoch": 0.09581768742716561,
      "grad_norm": 1.1773916482925415,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.3302,
      "step": 370
    },
    {
      "epoch": 0.09711252104104623,
      "grad_norm": 2.0340840816497803,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.3831,
      "step": 375
    },
    {
      "epoch": 0.09840735465492684,
      "grad_norm": 1.7500150203704834,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.321,
      "step": 380
    },
    {
      "epoch": 0.09970218826880746,
      "grad_norm": 1.9498361349105835,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.2401,
      "step": 385
    },
    {
      "epoch": 0.10099702188268807,
      "grad_norm": 0.9651708006858826,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.2151,
      "step": 390
    },
    {
      "epoch": 0.10229185549656869,
      "grad_norm": 0.49590951204299927,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.1835,
      "step": 395
    },
    {
      "epoch": 0.10358668911044931,
      "grad_norm": 2.0442728996276855,
      "learning_rate": 0.0,
      "loss": 0.6201,
      "step": 400
    },
    {
      "epoch": 0.10358668911044931,
      "eval_loss": 0.3742162585258484,
      "eval_runtime": 130.0959,
      "eval_samples_per_second": 12.498,
      "eval_steps_per_second": 6.249,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.302987314036736e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}