{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3496014543420501,
  "eval_steps": 5000,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006992029086841001,
      "grad_norm": 75.90129852294922,
      "learning_rate": 6.780845858091577e-07,
      "loss": 16.865,
      "step": 100
    },
    {
      "epoch": 0.013984058173682002,
      "grad_norm": 71.16612243652344,
      "learning_rate": 1.3771408598392172e-06,
      "loss": 16.1556,
      "step": 200
    },
    {
      "epoch": 0.020976087260523003,
      "grad_norm": 130.67613220214844,
      "learning_rate": 2.0761971338692767e-06,
      "loss": 14.8008,
      "step": 300
    },
    {
      "epoch": 0.027968116347364003,
      "grad_norm": 36.4179801940918,
      "learning_rate": 2.7682628451590356e-06,
      "loss": 12.4025,
      "step": 400
    },
    {
      "epoch": 0.034960145434205,
      "grad_norm": 34.748844146728516,
      "learning_rate": 3.467319119189095e-06,
      "loss": 9.7465,
      "step": 500
    },
    {
      "epoch": 0.04195217452104601,
      "grad_norm": 8.039146423339844,
      "learning_rate": 4.166375393219155e-06,
      "loss": 8.448,
      "step": 600
    },
    {
      "epoch": 0.04894420360788701,
      "grad_norm": 10.288451194763184,
      "learning_rate": 4.865431667249214e-06,
      "loss": 8.1951,
      "step": 700
    },
    {
      "epoch": 0.05593623269472801,
      "grad_norm": 6.3236308097839355,
      "learning_rate": 5.564487941279273e-06,
      "loss": 8.1093,
      "step": 800
    },
    {
      "epoch": 0.06292826178156902,
      "grad_norm": 15.230368614196777,
      "learning_rate": 6.263544215309333e-06,
      "loss": 8.0567,
      "step": 900
    },
    {
      "epoch": 0.06992029086841,
      "grad_norm": 5.573168754577637,
      "learning_rate": 6.962600489339393e-06,
      "loss": 8.0401,
      "step": 1000
    },
    {
      "epoch": 0.07691231995525101,
      "grad_norm": 6.7740325927734375,
      "learning_rate": 7.661656763369451e-06,
      "loss": 7.9491,
      "step": 1100
    },
    {
      "epoch": 0.08390434904209201,
      "grad_norm": 6.167610168457031,
      "learning_rate": 8.360713037399512e-06,
      "loss": 7.9494,
      "step": 1200
    },
    {
      "epoch": 0.09089637812893302,
      "grad_norm": 5.53561544418335,
      "learning_rate": 9.05976931142957e-06,
      "loss": 7.9386,
      "step": 1300
    },
    {
      "epoch": 0.09788840721577402,
      "grad_norm": 6.056953430175781,
      "learning_rate": 9.758825585459631e-06,
      "loss": 7.9033,
      "step": 1400
    },
    {
      "epoch": 0.10488043630261502,
      "grad_norm": 5.160706043243408,
      "learning_rate": 1.045788185948969e-05,
      "loss": 7.9055,
      "step": 1500
    },
    {
      "epoch": 0.11187246538945601,
      "grad_norm": 5.525616645812988,
      "learning_rate": 1.115693813351975e-05,
      "loss": 7.9203,
      "step": 1600
    },
    {
      "epoch": 0.11886449447629702,
      "grad_norm": 5.553597927093506,
      "learning_rate": 1.185599440754981e-05,
      "loss": 7.8381,
      "step": 1700
    },
    {
      "epoch": 0.12585652356313803,
      "grad_norm": 4.8832478523254395,
      "learning_rate": 1.2555050681579868e-05,
      "loss": 7.8679,
      "step": 1800
    },
    {
      "epoch": 0.13284855264997902,
      "grad_norm": 5.308164596557617,
      "learning_rate": 1.3254106955609927e-05,
      "loss": 7.8686,
      "step": 1900
    },
    {
      "epoch": 0.13984058173682,
      "grad_norm": 6.790646553039551,
      "learning_rate": 1.3953163229639988e-05,
      "loss": 7.8252,
      "step": 2000
    },
    {
      "epoch": 0.14683261082366103,
      "grad_norm": 5.003779888153076,
      "learning_rate": 1.4652219503670046e-05,
      "loss": 7.856,
      "step": 2100
    },
    {
      "epoch": 0.15382463991050202,
      "grad_norm": 5.0926642417907715,
      "learning_rate": 1.5351275777700107e-05,
      "loss": 7.8301,
      "step": 2200
    },
    {
      "epoch": 0.16081666899734304,
      "grad_norm": 4.154193878173828,
      "learning_rate": 1.6050332051730168e-05,
      "loss": 7.8595,
      "step": 2300
    },
    {
      "epoch": 0.16780869808418403,
      "grad_norm": 4.168135166168213,
      "learning_rate": 1.6749388325760225e-05,
      "loss": 7.8138,
      "step": 2400
    },
    {
      "epoch": 0.17480072717102504,
      "grad_norm": 4.69076681137085,
      "learning_rate": 1.7448444599790285e-05,
      "loss": 7.812,
      "step": 2500
    },
    {
      "epoch": 0.18179275625786603,
      "grad_norm": 4.386991500854492,
      "learning_rate": 1.8147500873820346e-05,
      "loss": 7.8261,
      "step": 2600
    },
    {
      "epoch": 0.18878478534470702,
      "grad_norm": 5.777139186859131,
      "learning_rate": 1.8846557147850403e-05,
      "loss": 7.7988,
      "step": 2700
    },
    {
      "epoch": 0.19577681443154804,
      "grad_norm": 18.3277645111084,
      "learning_rate": 1.9545613421880464e-05,
      "loss": 7.7965,
      "step": 2800
    },
    {
      "epoch": 0.20276884351838903,
      "grad_norm": 4.5356669425964355,
      "learning_rate": 1.997280814201919e-05,
      "loss": 7.783,
      "step": 2900
    },
    {
      "epoch": 0.20976087260523005,
      "grad_norm": 5.4392476081848145,
      "learning_rate": 1.9895117119216877e-05,
      "loss": 7.7752,
      "step": 3000
    },
    {
      "epoch": 0.21675290169207104,
      "grad_norm": 5.365427017211914,
      "learning_rate": 1.981742609641456e-05,
      "loss": 7.7715,
      "step": 3100
    },
    {
      "epoch": 0.22374493077891203,
      "grad_norm": 4.111672401428223,
      "learning_rate": 1.9739735073612244e-05,
      "loss": 7.7903,
      "step": 3200
    },
    {
      "epoch": 0.23073695986575304,
      "grad_norm": 4.107003211975098,
      "learning_rate": 1.9662044050809928e-05,
      "loss": 7.7656,
      "step": 3300
    },
    {
      "epoch": 0.23772898895259403,
      "grad_norm": 4.667971611022949,
      "learning_rate": 1.9584353028007615e-05,
      "loss": 7.749,
      "step": 3400
    },
    {
      "epoch": 0.24472101803943505,
      "grad_norm": 4.010958194732666,
      "learning_rate": 1.95066620052053e-05,
      "loss": 7.7662,
      "step": 3500
    },
    {
      "epoch": 0.25171304712627607,
      "grad_norm": 4.07546329498291,
      "learning_rate": 1.9428970982402986e-05,
      "loss": 7.7492,
      "step": 3600
    },
    {
      "epoch": 0.25870507621311706,
      "grad_norm": 5.414000988006592,
      "learning_rate": 1.935127995960067e-05,
      "loss": 7.737,
      "step": 3700
    },
    {
      "epoch": 0.26569710529995805,
      "grad_norm": 4.4744648933410645,
      "learning_rate": 1.9273588936798357e-05,
      "loss": 7.7232,
      "step": 3800
    },
    {
      "epoch": 0.27268913438679904,
      "grad_norm": 4.141202926635742,
      "learning_rate": 1.919589791399604e-05,
      "loss": 7.7616,
      "step": 3900
    },
    {
      "epoch": 0.27968116347364,
      "grad_norm": 4.493043899536133,
      "learning_rate": 1.9118206891193724e-05,
      "loss": 7.7391,
      "step": 4000
    },
    {
      "epoch": 0.28667319256048107,
      "grad_norm": 4.083165168762207,
      "learning_rate": 1.904051586839141e-05,
      "loss": 7.7552,
      "step": 4100
    },
    {
      "epoch": 0.29366522164732206,
      "grad_norm": 8.303427696228027,
      "learning_rate": 1.8962824845589095e-05,
      "loss": 7.7273,
      "step": 4200
    },
    {
      "epoch": 0.30065725073416305,
      "grad_norm": 4.003914833068848,
      "learning_rate": 1.888513382278678e-05,
      "loss": 7.7216,
      "step": 4300
    },
    {
      "epoch": 0.30764927982100404,
      "grad_norm": 4.859315395355225,
      "learning_rate": 1.8807442799984462e-05,
      "loss": 7.7371,
      "step": 4400
    },
    {
      "epoch": 0.31464130890784503,
      "grad_norm": 4.693440914154053,
      "learning_rate": 1.872975177718215e-05,
      "loss": 7.7426,
      "step": 4500
    },
    {
      "epoch": 0.3216333379946861,
      "grad_norm": 4.81652307510376,
      "learning_rate": 1.8652060754379833e-05,
      "loss": 7.7406,
      "step": 4600
    },
    {
      "epoch": 0.32862536708152706,
      "grad_norm": 3.861663341522217,
      "learning_rate": 1.8574369731577516e-05,
      "loss": 7.712,
      "step": 4700
    },
    {
      "epoch": 0.33561739616836805,
      "grad_norm": 4.218888282775879,
      "learning_rate": 1.8496678708775203e-05,
      "loss": 7.7466,
      "step": 4800
    },
    {
      "epoch": 0.34260942525520904,
      "grad_norm": 8.032899856567383,
      "learning_rate": 1.8418987685972887e-05,
      "loss": 7.7058,
      "step": 4900
    },
    {
      "epoch": 0.3496014543420501,
      "grad_norm": 4.292692184448242,
      "learning_rate": 1.8342073573398596e-05,
      "loss": 7.7139,
      "step": 5000
    },
    {
      "epoch": 0.3496014543420501,
      "eval_loss": 7.6895527839660645,
      "eval_runtime": 261.6657,
      "eval_samples_per_second": 1752.27,
      "eval_steps_per_second": 13.693,
      "step": 5000
    }
  ],
  "logging_steps": 100,
  "max_steps": 28604,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}