{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.913811007268951,
  "eval_steps": 500,
  "global_step": 360,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08307372793354102,
      "grad_norm": 0.5125107169151306,
      "learning_rate": 2.0833333333333334e-06,
      "loss": 3.5515,
      "step": 5
    },
    {
      "epoch": 0.16614745586708204,
      "grad_norm": 0.4532736539840698,
      "learning_rate": 4.166666666666667e-06,
      "loss": 3.6807,
      "step": 10
    },
    {
      "epoch": 0.24922118380062305,
      "grad_norm": 0.4483909606933594,
      "learning_rate": 6.25e-06,
      "loss": 3.5357,
      "step": 15
    },
    {
      "epoch": 0.3322949117341641,
      "grad_norm": 0.5020395517349243,
      "learning_rate": 8.333333333333334e-06,
      "loss": 3.645,
      "step": 20
    },
    {
      "epoch": 0.4153686396677051,
      "grad_norm": 0.8230155110359192,
      "learning_rate": 1.0416666666666668e-05,
      "loss": 3.5682,
      "step": 25
    },
    {
      "epoch": 0.4984423676012461,
      "grad_norm": 1.3333394527435303,
      "learning_rate": 1.25e-05,
      "loss": 3.5155,
      "step": 30
    },
    {
      "epoch": 0.5815160955347871,
      "grad_norm": 0.7118450999259949,
      "learning_rate": 1.4583333333333335e-05,
      "loss": 3.4724,
      "step": 35
    },
    {
      "epoch": 0.6645898234683282,
      "grad_norm": 1.0282073020935059,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 3.4205,
      "step": 40
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 1.0468826293945312,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 3.3295,
      "step": 45
    },
    {
      "epoch": 0.8307372793354102,
      "grad_norm": 0.8730693459510803,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 3.0831,
      "step": 50
    },
    {
      "epoch": 0.9138110072689511,
      "grad_norm": 0.9377574324607849,
      "learning_rate": 2.2916666666666667e-05,
      "loss": 2.8412,
      "step": 55
    },
    {
      "epoch": 0.9968847352024922,
      "grad_norm": 1.0129190683364868,
      "learning_rate": 2.5e-05,
      "loss": 2.3229,
      "step": 60
    },
    {
      "epoch": 1.066458982346833,
      "grad_norm": 0.8808080554008484,
      "learning_rate": 2.7083333333333332e-05,
      "loss": 2.0489,
      "step": 65
    },
    {
      "epoch": 1.1495327102803738,
      "grad_norm": 0.8092290759086609,
      "learning_rate": 2.916666666666667e-05,
      "loss": 1.9307,
      "step": 70
    },
    {
      "epoch": 1.2326064382139148,
      "grad_norm": 0.8002105951309204,
      "learning_rate": 3.125e-05,
      "loss": 1.7402,
      "step": 75
    },
    {
      "epoch": 1.3156801661474558,
      "grad_norm": 0.8581973314285278,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.6696,
      "step": 80
    },
    {
      "epoch": 1.398753894080997,
      "grad_norm": 0.7443532347679138,
      "learning_rate": 3.541666666666667e-05,
      "loss": 1.5175,
      "step": 85
    },
    {
      "epoch": 1.4818276220145379,
      "grad_norm": 0.9584633708000183,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.3968,
      "step": 90
    },
    {
      "epoch": 1.5649013499480788,
      "grad_norm": 0.8683136105537415,
      "learning_rate": 3.958333333333333e-05,
      "loss": 1.299,
      "step": 95
    },
    {
      "epoch": 1.64797507788162,
      "grad_norm": 0.7825261950492859,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.1271,
      "step": 100
    },
    {
      "epoch": 1.731048805815161,
      "grad_norm": 0.654670000076294,
      "learning_rate": 4.375e-05,
      "loss": 1.14,
      "step": 105
    },
    {
      "epoch": 1.814122533748702,
      "grad_norm": 0.7511588335037231,
      "learning_rate": 4.5833333333333334e-05,
      "loss": 1.1614,
      "step": 110
    },
    {
      "epoch": 1.897196261682243,
      "grad_norm": 0.6596113443374634,
      "learning_rate": 4.791666666666667e-05,
      "loss": 1.0587,
      "step": 115
    },
    {
      "epoch": 1.980269989615784,
      "grad_norm": 0.7166474461555481,
      "learning_rate": 5e-05,
      "loss": 1.0169,
      "step": 120
    },
    {
      "epoch": 2.0498442367601246,
      "grad_norm": 0.6620935797691345,
      "learning_rate": 4.999735579817769e-05,
      "loss": 0.985,
      "step": 125
    },
    {
      "epoch": 2.132917964693666,
      "grad_norm": 0.7846258878707886,
      "learning_rate": 4.998942375205502e-05,
      "loss": 0.9594,
      "step": 130
    },
    {
      "epoch": 2.2159916926272065,
      "grad_norm": 0.652454137802124,
      "learning_rate": 4.997620553954645e-05,
      "loss": 0.9322,
      "step": 135
    },
    {
      "epoch": 2.2990654205607477,
      "grad_norm": 0.7020059823989868,
      "learning_rate": 4.995770395678171e-05,
      "loss": 0.9242,
      "step": 140
    },
    {
      "epoch": 2.382139148494289,
      "grad_norm": 0.8148695826530457,
      "learning_rate": 4.993392291751431e-05,
      "loss": 0.8394,
      "step": 145
    },
    {
      "epoch": 2.4652128764278296,
      "grad_norm": 0.8813133835792542,
      "learning_rate": 4.990486745229364e-05,
      "loss": 0.992,
      "step": 150
    },
    {
      "epoch": 2.5482866043613708,
      "grad_norm": 0.7893730401992798,
      "learning_rate": 4.987054370740083e-05,
      "loss": 0.899,
      "step": 155
    },
    {
      "epoch": 2.6313603322949115,
      "grad_norm": 0.7719221711158752,
      "learning_rate": 4.983095894354858e-05,
      "loss": 0.9416,
      "step": 160
    },
    {
      "epoch": 2.7144340602284527,
      "grad_norm": 0.8439667820930481,
      "learning_rate": 4.9786121534345265e-05,
      "loss": 0.8401,
      "step": 165
    },
    {
      "epoch": 2.797507788161994,
      "grad_norm": 0.833251953125,
      "learning_rate": 4.973604096452361e-05,
      "loss": 0.817,
      "step": 170
    },
    {
      "epoch": 2.8805815160955346,
      "grad_norm": 0.7526916265487671,
      "learning_rate": 4.9680727827934354e-05,
      "loss": 0.8191,
      "step": 175
    },
    {
      "epoch": 2.9636552440290758,
      "grad_norm": 1.0640058517456055,
      "learning_rate": 4.962019382530521e-05,
      "loss": 0.8607,
      "step": 180
    },
    {
      "epoch": 3.0332294911734166,
      "grad_norm": 0.784114420413971,
      "learning_rate": 4.9554451761765766e-05,
      "loss": 0.761,
      "step": 185
    },
    {
      "epoch": 3.1163032191069573,
      "grad_norm": 0.9396352767944336,
      "learning_rate": 4.948351554413879e-05,
      "loss": 0.6821,
      "step": 190
    },
    {
      "epoch": 3.1993769470404985,
      "grad_norm": 0.9770582914352417,
      "learning_rate": 4.940740017799833e-05,
      "loss": 0.742,
      "step": 195
    },
    {
      "epoch": 3.2824506749740396,
      "grad_norm": 0.8752853870391846,
      "learning_rate": 4.9326121764495596e-05,
      "loss": 0.69,
      "step": 200
    },
    {
      "epoch": 3.3655244029075804,
      "grad_norm": 0.8496589064598083,
      "learning_rate": 4.92396974969529e-05,
      "loss": 0.769,
      "step": 205
    },
    {
      "epoch": 3.4485981308411215,
      "grad_norm": 0.8192639350891113,
      "learning_rate": 4.914814565722671e-05,
      "loss": 0.7298,
      "step": 210
    },
    {
      "epoch": 3.5316718587746623,
      "grad_norm": 1.00070059299469,
      "learning_rate": 4.905148561184033e-05,
      "loss": 0.7815,
      "step": 215
    },
    {
      "epoch": 3.6147455867082035,
      "grad_norm": 1.1614112854003906,
      "learning_rate": 4.894973780788722e-05,
      "loss": 0.7975,
      "step": 220
    },
    {
      "epoch": 3.6978193146417446,
      "grad_norm": 1.014397382736206,
      "learning_rate": 4.884292376870567e-05,
      "loss": 0.696,
      "step": 225
    },
    {
      "epoch": 3.7808930425752854,
      "grad_norm": 0.9468530416488647,
      "learning_rate": 4.873106608932585e-05,
      "loss": 0.7194,
      "step": 230
    },
    {
      "epoch": 3.8639667705088265,
      "grad_norm": 1.2201341390609741,
      "learning_rate": 4.8614188431690125e-05,
      "loss": 0.7795,
      "step": 235
    },
    {
      "epoch": 3.9470404984423677,
      "grad_norm": 0.9476346373558044,
      "learning_rate": 4.849231551964771e-05,
      "loss": 0.7202,
      "step": 240
    },
    {
      "epoch": 4.0166147455867085,
      "grad_norm": 0.9945451021194458,
      "learning_rate": 4.836547313372471e-05,
      "loss": 0.6931,
      "step": 245
    },
    {
      "epoch": 4.099688473520249,
      "grad_norm": 1.1113696098327637,
      "learning_rate": 4.823368810567056e-05,
      "loss": 0.6557,
      "step": 250
    },
    {
      "epoch": 4.18276220145379,
      "grad_norm": 1.3515146970748901,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 0.6295,
      "step": 255
    },
    {
      "epoch": 4.265835929387332,
      "grad_norm": 1.375272274017334,
      "learning_rate": 4.7955402672006854e-05,
      "loss": 0.6423,
      "step": 260
    },
    {
      "epoch": 4.348909657320872,
      "grad_norm": 1.1683202981948853,
      "learning_rate": 4.780896113382536e-05,
      "loss": 0.6167,
      "step": 265
    },
    {
      "epoch": 4.431983385254413,
      "grad_norm": 1.2091785669326782,
      "learning_rate": 4.765769467591625e-05,
      "loss": 0.6373,
      "step": 270
    },
    {
      "epoch": 4.515057113187955,
      "grad_norm": 1.3007235527038574,
      "learning_rate": 4.750163529660303e-05,
      "loss": 0.5941,
      "step": 275
    },
    {
      "epoch": 4.598130841121495,
      "grad_norm": 1.2785530090332031,
      "learning_rate": 4.734081600808531e-05,
      "loss": 0.6384,
      "step": 280
    },
    {
      "epoch": 4.681204569055036,
      "grad_norm": 1.2808083295822144,
      "learning_rate": 4.717527082945554e-05,
      "loss": 0.6592,
      "step": 285
    },
    {
      "epoch": 4.764278296988578,
      "grad_norm": 1.1978651285171509,
      "learning_rate": 4.700503477950278e-05,
      "loss": 0.6285,
      "step": 290
    },
    {
      "epoch": 4.8473520249221185,
      "grad_norm": 1.3983532190322876,
      "learning_rate": 4.68301438693049e-05,
      "loss": 0.5941,
      "step": 295
    },
    {
      "epoch": 4.930425752855659,
      "grad_norm": 1.286287784576416,
      "learning_rate": 4.665063509461097e-05,
      "loss": 0.5652,
      "step": 300
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.1714959144592285,
      "learning_rate": 4.6466546428015336e-05,
      "loss": 0.5657,
      "step": 305
    },
    {
      "epoch": 5.083073727933541,
      "grad_norm": 1.0886554718017578,
      "learning_rate": 4.627791681092499e-05,
      "loss": 0.4776,
      "step": 310
    },
    {
      "epoch": 5.166147455867082,
      "grad_norm": 1.3735958337783813,
      "learning_rate": 4.608478614532215e-05,
      "loss": 0.5114,
      "step": 315
    },
    {
      "epoch": 5.249221183800623,
      "grad_norm": 1.5809016227722168,
      "learning_rate": 4.588719528532342e-05,
      "loss": 0.5537,
      "step": 320
    },
    {
      "epoch": 5.332294911734164,
      "grad_norm": 1.401424765586853,
      "learning_rate": 4.568518602853776e-05,
      "loss": 0.5299,
      "step": 325
    },
    {
      "epoch": 5.415368639667705,
      "grad_norm": 1.467054009437561,
      "learning_rate": 4.54788011072248e-05,
      "loss": 0.5236,
      "step": 330
    },
    {
      "epoch": 5.498442367601246,
      "grad_norm": 1.253794550895691,
      "learning_rate": 4.526808417925531e-05,
      "loss": 0.5632,
      "step": 335
    },
    {
      "epoch": 5.581516095534787,
      "grad_norm": 1.4579623937606812,
      "learning_rate": 4.50530798188761e-05,
      "loss": 0.5556,
      "step": 340
    },
    {
      "epoch": 5.6645898234683285,
      "grad_norm": 1.171007513999939,
      "learning_rate": 4.4833833507280884e-05,
      "loss": 0.4934,
      "step": 345
    },
    {
      "epoch": 5.747663551401869,
      "grad_norm": 1.4656859636306763,
      "learning_rate": 4.4610391622989396e-05,
      "loss": 0.5697,
      "step": 350
    },
    {
      "epoch": 5.83073727933541,
      "grad_norm": 1.4671518802642822,
      "learning_rate": 4.438280143203665e-05,
      "loss": 0.5289,
      "step": 355
    },
    {
      "epoch": 5.913811007268951,
      "grad_norm": 1.4010504484176636,
      "learning_rate": 4.415111107797445e-05,
      "loss": 0.5205,
      "step": 360
    }
  ],
  "logging_steps": 5,
  "max_steps": 1200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 60,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.55508799438848e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}