{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006,
  "eval_steps": 100,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2e-05,
      "grad_norm": 1.8784615993499756,
      "learning_rate": 4e-10,
      "loss": 1.247075080871582,
      "memory(GiB)": 45.58,
      "step": 1,
      "token_acc": 0.7174163783160323,
      "train_speed(iter/s)": 0.013609
    },
    {
      "epoch": 0.0001,
      "grad_norm": 1.7829604148864746,
      "learning_rate": 2e-09,
      "loss": 1.2329106330871582,
      "memory(GiB)": 47.68,
      "step": 5,
      "token_acc": 0.7190702324418895,
      "train_speed(iter/s)": 0.056616
    },
    {
      "epoch": 0.0002,
      "grad_norm": 1.8510538339614868,
      "learning_rate": 4e-09,
      "loss": 1.2224847793579101,
      "memory(GiB)": 47.68,
      "step": 10,
      "token_acc": 0.7056490003173596,
      "train_speed(iter/s)": 0.093003
    },
    {
      "epoch": 0.0003,
      "grad_norm": 1.9363449811935425,
      "learning_rate": 5.6e-09,
      "loss": 1.2302563667297364,
      "memory(GiB)": 48.7,
      "step": 15,
      "token_acc": 0.7107342772472836,
      "train_speed(iter/s)": 0.119381
    },
    {
      "epoch": 0.0004,
      "grad_norm": 1.935133695602417,
      "learning_rate": 7.6e-09,
      "loss": 1.2335556983947753,
      "memory(GiB)": 48.7,
      "step": 20,
      "token_acc": 0.7361481714016638,
      "train_speed(iter/s)": 0.137465
    },
    {
      "epoch": 0.0005,
      "grad_norm": 1.7830060720443726,
      "learning_rate": 9.599999999999998e-09,
      "loss": 1.2144426345825194,
      "memory(GiB)": 48.7,
      "step": 25,
      "token_acc": 0.7571428571428571,
      "train_speed(iter/s)": 0.150572
    },
    {
      "epoch": 0.0006,
      "grad_norm": 1.7309236526489258,
      "learning_rate": 1.1599999999999998e-08,
      "loss": 1.2357244491577148,
      "memory(GiB)": 48.7,
      "step": 30,
      "token_acc": 0.7153189910979229,
      "train_speed(iter/s)": 0.162512
    },
    {
      "epoch": 0.0007,
      "grad_norm": 1.7474730014801025,
      "learning_rate": 1.36e-08,
      "loss": 1.231928825378418,
      "memory(GiB)": 48.7,
      "step": 35,
      "token_acc": 0.7078455355582737,
      "train_speed(iter/s)": 0.171663
    },
    {
      "epoch": 0.0008,
      "grad_norm": 1.780007004737854,
      "learning_rate": 1.5599999999999997e-08,
      "loss": 1.2193016052246093,
      "memory(GiB)": 48.7,
      "step": 40,
      "token_acc": 0.6932599724896836,
      "train_speed(iter/s)": 0.178935
    },
    {
      "epoch": 0.0009,
      "grad_norm": 1.723268747329712,
      "learning_rate": 1.72e-08,
      "loss": 1.204256820678711,
      "memory(GiB)": 48.7,
      "step": 45,
      "token_acc": 0.6967172137977004,
      "train_speed(iter/s)": 0.186547
    },
    {
      "epoch": 0.001,
      "grad_norm": 1.7750556468963623,
      "learning_rate": 1.9199999999999997e-08,
      "loss": 1.2007877349853515,
      "memory(GiB)": 48.7,
      "step": 50,
      "token_acc": 0.6921988682295878,
      "train_speed(iter/s)": 0.19125
    },
    {
      "epoch": 0.0011,
      "grad_norm": 1.299729585647583,
      "learning_rate": 2.1199999999999998e-08,
      "loss": 0.8069381713867188,
      "memory(GiB)": 48.7,
      "step": 55,
      "token_acc": 0.7952855847688123,
      "train_speed(iter/s)": 0.195908
    },
    {
      "epoch": 0.0012,
      "grad_norm": 1.3525291681289673,
      "learning_rate": 2.3199999999999996e-08,
      "loss": 0.42714319229125974,
      "memory(GiB)": 48.7,
      "step": 60,
      "token_acc": 0.8841448189762796,
      "train_speed(iter/s)": 0.201
    },
    {
      "epoch": 0.0013,
      "grad_norm": 1.080306053161621,
      "learning_rate": 2.52e-08,
      "loss": 0.4192944526672363,
      "memory(GiB)": 48.7,
      "step": 65,
      "token_acc": 0.8929637526652452,
      "train_speed(iter/s)": 0.204749
    },
    {
      "epoch": 0.0014,
      "grad_norm": 1.177667498588562,
      "learning_rate": 2.72e-08,
      "loss": 0.4133622169494629,
      "memory(GiB)": 48.7,
      "step": 70,
      "token_acc": 0.8836150845253576,
      "train_speed(iter/s)": 0.20853
    },
    {
      "epoch": 0.0015,
      "grad_norm": 1.4200434684753418,
      "learning_rate": 2.92e-08,
      "loss": 0.4155101776123047,
      "memory(GiB)": 48.7,
      "step": 75,
      "token_acc": 0.8933333333333333,
      "train_speed(iter/s)": 0.211872
    },
    {
      "epoch": 0.0016,
      "grad_norm": 1.1931238174438477,
      "learning_rate": 3.1199999999999995e-08,
      "loss": 0.40213637351989745,
      "memory(GiB)": 48.7,
      "step": 80,
      "token_acc": 0.9073569482288828,
      "train_speed(iter/s)": 0.214198
    },
    {
      "epoch": 0.0017,
      "grad_norm": 1.2268942594528198,
      "learning_rate": 3.32e-08,
      "loss": 0.4193448543548584,
      "memory(GiB)": 48.7,
      "step": 85,
      "token_acc": 0.890360895386021,
      "train_speed(iter/s)": 0.217149
    },
    {
      "epoch": 0.0018,
      "grad_norm": 1.168769121170044,
      "learning_rate": 3.52e-08,
      "loss": 0.4069235324859619,
      "memory(GiB)": 48.7,
      "step": 90,
      "token_acc": 0.8803038239916187,
      "train_speed(iter/s)": 0.219373
    },
    {
      "epoch": 0.0019,
      "grad_norm": 1.1890403032302856,
      "learning_rate": 3.7199999999999996e-08,
      "loss": 0.4017478942871094,
      "memory(GiB)": 48.7,
      "step": 95,
      "token_acc": 0.8852933438568797,
      "train_speed(iter/s)": 0.221331
    },
    {
      "epoch": 0.002,
      "grad_norm": 1.0330846309661865,
      "learning_rate": 3.9199999999999994e-08,
      "loss": 0.3853747844696045,
      "memory(GiB)": 48.7,
      "step": 100,
      "token_acc": 0.8942406230784997,
      "train_speed(iter/s)": 0.223547
    },
    {
      "epoch": 0.0021,
      "grad_norm": 0.8882772922515869,
      "learning_rate": 4.12e-08,
      "loss": 0.38479089736938477,
      "memory(GiB)": 48.7,
      "step": 105,
      "token_acc": 0.888404744613895,
      "train_speed(iter/s)": 0.165159
    },
    {
      "epoch": 0.0022,
      "grad_norm": 0.9768219590187073,
      "learning_rate": 4.32e-08,
      "loss": 0.3818492889404297,
      "memory(GiB)": 48.7,
      "step": 110,
      "token_acc": 0.8976019604410993,
      "train_speed(iter/s)": 0.168006
    },
    {
      "epoch": 0.0023,
      "grad_norm": 1.0652796030044556,
      "learning_rate": 4.5199999999999994e-08,
      "loss": 0.37880630493164064,
      "memory(GiB)": 48.7,
      "step": 115,
      "token_acc": 0.8944169293111212,
      "train_speed(iter/s)": 0.170961
    },
    {
      "epoch": 0.0024,
      "grad_norm": 0.9667234420776367,
      "learning_rate": 4.72e-08,
      "loss": 0.3773456573486328,
      "memory(GiB)": 48.7,
      "step": 120,
      "token_acc": 0.9041720990873533,
      "train_speed(iter/s)": 0.17359
    },
    {
      "epoch": 0.0025,
      "grad_norm": 1.1004765033721924,
      "learning_rate": 4.92e-08,
      "loss": 0.37454307079315186,
      "memory(GiB)": 48.7,
      "step": 125,
      "token_acc": 0.8971794358871774,
      "train_speed(iter/s)": 0.17613
    },
    {
      "epoch": 0.0026,
      "grad_norm": 0.9110294580459595,
      "learning_rate": 5.12e-08,
      "loss": 0.35935871601104735,
      "memory(GiB)": 48.7,
      "step": 130,
      "token_acc": 0.9002339927674963,
      "train_speed(iter/s)": 0.178791
    },
    {
      "epoch": 0.0027,
      "grad_norm": 0.8307713270187378,
      "learning_rate": 5.319999999999999e-08,
      "loss": 0.3583024501800537,
      "memory(GiB)": 48.7,
      "step": 135,
      "token_acc": 0.9001166861143524,
      "train_speed(iter/s)": 0.181064
    },
    {
      "epoch": 0.0028,
      "grad_norm": 0.8742683529853821,
      "learning_rate": 5.52e-08,
      "loss": 0.34030709266662595,
      "memory(GiB)": 48.7,
      "step": 140,
      "token_acc": 0.8936170212765957,
      "train_speed(iter/s)": 0.183337
    },
    {
      "epoch": 0.0029,
      "grad_norm": 0.8469884395599365,
      "learning_rate": 5.7199999999999996e-08,
      "loss": 0.3286393404006958,
      "memory(GiB)": 48.7,
      "step": 145,
      "token_acc": 0.9112193294624461,
      "train_speed(iter/s)": 0.185295
    },
    {
      "epoch": 0.003,
      "grad_norm": 0.7903546094894409,
      "learning_rate": 5.92e-08,
      "loss": 0.34013702869415285,
      "memory(GiB)": 48.7,
      "step": 150,
      "token_acc": 0.9123177283192633,
      "train_speed(iter/s)": 0.187277
    },
    {
      "epoch": 0.0031,
      "grad_norm": 0.7647843956947327,
      "learning_rate": 6.119999999999999e-08,
      "loss": 0.32967448234558105,
      "memory(GiB)": 48.7,
      "step": 155,
      "token_acc": 0.9061872909698997,
      "train_speed(iter/s)": 0.189242
    },
    {
      "epoch": 0.0032,
      "grad_norm": 0.7588908076286316,
      "learning_rate": 6.32e-08,
      "loss": 0.31885499954223634,
      "memory(GiB)": 48.7,
      "step": 160,
      "token_acc": 0.9148387096774193,
      "train_speed(iter/s)": 0.190988
    },
    {
      "epoch": 0.0033,
      "grad_norm": 0.7278595566749573,
      "learning_rate": 6.519999999999999e-08,
      "loss": 0.3225527048110962,
      "memory(GiB)": 48.7,
      "step": 165,
      "token_acc": 0.9134559535333979,
      "train_speed(iter/s)": 0.192579
    },
    {
      "epoch": 0.0034,
      "grad_norm": 0.7548233270645142,
      "learning_rate": 6.719999999999999e-08,
      "loss": 0.3111454725265503,
      "memory(GiB)": 48.7,
      "step": 170,
      "token_acc": 0.9035423647678315,
      "train_speed(iter/s)": 0.194372
    },
    {
      "epoch": 0.0035,
      "grad_norm": 0.7382190823554993,
      "learning_rate": 6.92e-08,
      "loss": 0.30791687965393066,
      "memory(GiB)": 48.7,
      "step": 175,
      "token_acc": 0.9182072829131652,
      "train_speed(iter/s)": 0.195886
    },
    {
      "epoch": 0.0036,
      "grad_norm": 0.6201812028884888,
      "learning_rate": 7.12e-08,
      "loss": 0.30755660533905027,
      "memory(GiB)": 48.7,
      "step": 180,
      "token_acc": 0.9121319199057715,
      "train_speed(iter/s)": 0.197365
    },
    {
      "epoch": 0.0037,
      "grad_norm": 0.680054247379303,
      "learning_rate": 7.32e-08,
      "loss": 0.3023200511932373,
      "memory(GiB)": 48.7,
      "step": 185,
      "token_acc": 0.9189243427654024,
      "train_speed(iter/s)": 0.198991
    },
    {
      "epoch": 0.0038,
      "grad_norm": 0.7230331301689148,
      "learning_rate": 7.52e-08,
      "loss": 0.29792306423187254,
      "memory(GiB)": 48.7,
      "step": 190,
      "token_acc": 0.9166977960403436,
      "train_speed(iter/s)": 0.200242
    },
    {
      "epoch": 0.0039,
      "grad_norm": 0.6341392397880554,
      "learning_rate": 7.72e-08,
      "loss": 0.2936398983001709,
      "memory(GiB)": 48.7,
      "step": 195,
      "token_acc": 0.916235294117647,
      "train_speed(iter/s)": 0.20159
    },
    {
      "epoch": 0.004,
      "grad_norm": 0.6513913869857788,
      "learning_rate": 7.920000000000001e-08,
      "loss": 0.29084038734436035,
      "memory(GiB)": 48.7,
      "step": 200,
      "token_acc": 0.915651358950328,
      "train_speed(iter/s)": 0.202853
    },
    {
      "epoch": 0.0041,
      "grad_norm": 0.5849307775497437,
      "learning_rate": 8.119999999999999e-08,
      "loss": 0.28313345909118653,
      "memory(GiB)": 48.7,
      "step": 205,
      "token_acc": 0.9201498422712934,
      "train_speed(iter/s)": 0.174461
    },
    {
      "epoch": 0.0042,
      "grad_norm": 0.5864230990409851,
      "learning_rate": 8.319999999999999e-08,
      "loss": 0.27917160987854006,
      "memory(GiB)": 48.7,
      "step": 210,
      "token_acc": 0.9227850926132559,
      "train_speed(iter/s)": 0.176086
    },
    {
      "epoch": 0.0043,
      "grad_norm": 0.5705774426460266,
      "learning_rate": 8.52e-08,
      "loss": 0.27348690032958983,
      "memory(GiB)": 48.7,
      "step": 215,
      "token_acc": 0.9209313047487321,
      "train_speed(iter/s)": 0.177517
    },
    {
      "epoch": 0.0044,
      "grad_norm": 0.5566577911376953,
      "learning_rate": 8.72e-08,
      "loss": 0.2738009214401245,
      "memory(GiB)": 48.7,
      "step": 220,
      "token_acc": 0.9212003454231433,
      "train_speed(iter/s)": 0.178985
    },
    {
      "epoch": 0.0045,
      "grad_norm": 0.5548610091209412,
      "learning_rate": 8.919999999999999e-08,
      "loss": 0.270387601852417,
      "memory(GiB)": 48.7,
      "step": 225,
      "token_acc": 0.9163515016685205,
      "train_speed(iter/s)": 0.180404
    },
    {
      "epoch": 0.0046,
      "grad_norm": 0.5132172107696533,
      "learning_rate": 9.12e-08,
      "loss": 0.2689182758331299,
      "memory(GiB)": 48.7,
      "step": 230,
      "token_acc": 0.9161837748344371,
      "train_speed(iter/s)": 0.181679
    },
    {
      "epoch": 0.0047,
      "grad_norm": 0.5392292141914368,
      "learning_rate": 9.32e-08,
      "loss": 0.2692979335784912,
      "memory(GiB)": 48.7,
      "step": 235,
      "token_acc": 0.9189686924493554,
      "train_speed(iter/s)": 0.18288
    },
    {
      "epoch": 0.0048,
      "grad_norm": 0.5800856947898865,
      "learning_rate": 9.52e-08,
      "loss": 0.2671097755432129,
      "memory(GiB)": 48.7,
      "step": 240,
      "token_acc": 0.9276693455797933,
      "train_speed(iter/s)": 0.184197
    },
    {
      "epoch": 0.0049,
      "grad_norm": 0.5248638391494751,
      "learning_rate": 9.72e-08,
      "loss": 0.2651660442352295,
      "memory(GiB)": 48.7,
      "step": 245,
      "token_acc": 0.9340950826361967,
      "train_speed(iter/s)": 0.185361
    },
    {
      "epoch": 0.005,
      "grad_norm": 0.4779960811138153,
      "learning_rate": 9.919999999999999e-08,
      "loss": 0.2598712921142578,
      "memory(GiB)": 48.7,
      "step": 250,
      "token_acc": 0.9171786120591582,
      "train_speed(iter/s)": 0.186527
    },
    {
      "epoch": 0.0051,
      "grad_norm": 0.5446517467498779,
      "learning_rate": 1.0119999999999999e-07,
      "loss": 0.2589933633804321,
      "memory(GiB)": 48.7,
      "step": 255,
      "token_acc": 0.919714165615805,
      "train_speed(iter/s)": 0.187704
    },
    {
      "epoch": 0.0052,
      "grad_norm": 0.5014457702636719,
      "learning_rate": 1.032e-07,
      "loss": 0.2622577667236328,
      "memory(GiB)": 48.7,
      "step": 260,
      "token_acc": 0.9149246475449684,
      "train_speed(iter/s)": 0.188846
    },
    {
      "epoch": 0.0053,
      "grad_norm": 0.486289918422699,
      "learning_rate": 1.052e-07,
      "loss": 0.2525398969650269,
      "memory(GiB)": 48.7,
      "step": 265,
      "token_acc": 0.9272396543883583,
      "train_speed(iter/s)": 0.189871
    },
    {
      "epoch": 0.0054,
      "grad_norm": 0.5184631943702698,
      "learning_rate": 1.072e-07,
      "loss": 0.2508587121963501,
      "memory(GiB)": 48.7,
      "step": 270,
      "token_acc": 0.9343525179856115,
      "train_speed(iter/s)": 0.190895
    },
    {
      "epoch": 0.0055,
      "grad_norm": 0.7472315430641174,
      "learning_rate": 1.092e-07,
      "loss": 0.3759446620941162,
      "memory(GiB)": 48.7,
      "step": 275,
      "token_acc": 0.8695306284805091,
      "train_speed(iter/s)": 0.191441
    },
    {
      "epoch": 0.0056,
      "grad_norm": 0.6762179136276245,
      "learning_rate": 1.1119999999999999e-07,
      "loss": 0.5864349365234375,
      "memory(GiB)": 48.7,
      "step": 280,
      "token_acc": 0.8324331623008372,
      "train_speed(iter/s)": 0.191626
    },
    {
      "epoch": 0.0057,
      "grad_norm": 0.5527864694595337,
      "learning_rate": 1.132e-07,
      "loss": 0.5735197067260742,
      "memory(GiB)": 48.7,
      "step": 285,
      "token_acc": 0.8262280306444344,
      "train_speed(iter/s)": 0.19159
    },
    {
      "epoch": 0.0058,
      "grad_norm": 0.46731290221214294,
      "learning_rate": 1.1519999999999999e-07,
      "loss": 0.5600314140319824,
      "memory(GiB)": 48.7,
      "step": 290,
      "token_acc": 0.8467968392868804,
      "train_speed(iter/s)": 0.191504
    },
    {
      "epoch": 0.0059,
      "grad_norm": 0.42628228664398193,
      "learning_rate": 1.1719999999999999e-07,
      "loss": 0.5390614986419677,
      "memory(GiB)": 50.81,
      "step": 295,
      "token_acc": 0.8327679356703104,
      "train_speed(iter/s)": 0.191542
    },
    {
      "epoch": 0.006,
      "grad_norm": 0.3921428322792053,
      "learning_rate": 1.192e-07,
      "loss": 0.5223519325256347,
      "memory(GiB)": 50.81,
      "step": 300,
      "token_acc": 0.8428060564559081,
      "train_speed(iter/s)": 0.191529
    }
  ],
  "logging_steps": 5,
  "max_steps": 50000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.573770266594509e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}