{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8355964069354502,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016711928138709004,
      "grad_norm": 1.12109375,
      "learning_rate": 5e-06,
      "loss": 1.1894,
      "step": 10
    },
    {
      "epoch": 0.03342385627741801,
      "grad_norm": 0.7248284816741943,
      "learning_rate": 1.0555555555555555e-05,
      "loss": 1.1506,
      "step": 20
    },
    {
      "epoch": 0.05013578441612701,
      "grad_norm": 1.1556353569030762,
      "learning_rate": 1.6111111111111115e-05,
      "loss": 1.1033,
      "step": 30
    },
    {
      "epoch": 0.06684771255483601,
      "grad_norm": 0.4772647023200989,
      "learning_rate": 2.1666666666666667e-05,
      "loss": 0.9371,
      "step": 40
    },
    {
      "epoch": 0.08355964069354502,
      "grad_norm": 0.27529847621917725,
      "learning_rate": 2.7222222222222223e-05,
      "loss": 0.8313,
      "step": 50
    },
    {
      "epoch": 0.10027156883225402,
      "grad_norm": 0.22090303897857666,
      "learning_rate": 3.277777777777778e-05,
      "loss": 0.7724,
      "step": 60
    },
    {
      "epoch": 0.11698349697096302,
      "grad_norm": 0.21275630593299866,
      "learning_rate": 3.8333333333333334e-05,
      "loss": 0.733,
      "step": 70
    },
    {
      "epoch": 0.13369542510967203,
      "grad_norm": 0.2134302407503128,
      "learning_rate": 4.388888888888889e-05,
      "loss": 0.7134,
      "step": 80
    },
    {
      "epoch": 0.15040735324838103,
      "grad_norm": 0.18984167277812958,
      "learning_rate": 4.9444444444444446e-05,
      "loss": 0.6959,
      "step": 90
    },
    {
      "epoch": 0.16711928138709004,
      "grad_norm": 0.2290167659521103,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.6518,
      "step": 100
    },
    {
      "epoch": 0.18383120952579904,
      "grad_norm": 0.2181967943906784,
      "learning_rate": 6.055555555555555e-05,
      "loss": 0.6313,
      "step": 110
    },
    {
      "epoch": 0.20054313766450804,
      "grad_norm": 0.26380836963653564,
      "learning_rate": 6.611111111111111e-05,
      "loss": 0.6059,
      "step": 120
    },
    {
      "epoch": 0.21725506580321705,
      "grad_norm": 0.25219714641571045,
      "learning_rate": 7.166666666666667e-05,
      "loss": 0.6613,
      "step": 130
    },
    {
      "epoch": 0.23396699394192605,
      "grad_norm": 0.24282532930374146,
      "learning_rate": 7.722222222222223e-05,
      "loss": 0.6676,
      "step": 140
    },
    {
      "epoch": 0.2506789220806351,
      "grad_norm": 0.28735119104385376,
      "learning_rate": 8.277777777777778e-05,
      "loss": 0.647,
      "step": 150
    },
    {
      "epoch": 0.26739085021934406,
      "grad_norm": 0.3064824938774109,
      "learning_rate": 8.833333333333333e-05,
      "loss": 0.6222,
      "step": 160
    },
    {
      "epoch": 0.2841027783580531,
      "grad_norm": 0.33395013213157654,
      "learning_rate": 9.388888888888889e-05,
      "loss": 0.6109,
      "step": 170
    },
    {
      "epoch": 0.30081470649676206,
      "grad_norm": 0.32029104232788086,
      "learning_rate": 9.944444444444446e-05,
      "loss": 0.6942,
      "step": 180
    },
    {
      "epoch": 0.3175266346354711,
      "grad_norm": 0.29911231994628906,
      "learning_rate": 9.999235647539953e-05,
      "loss": 0.6312,
      "step": 190
    },
    {
      "epoch": 0.33423856277418007,
      "grad_norm": 0.3333311676979065,
      "learning_rate": 9.996593741531468e-05,
      "loss": 0.6118,
      "step": 200
    },
    {
      "epoch": 0.3509504909128891,
      "grad_norm": 0.31720009446144104,
      "learning_rate": 9.992065842489567e-05,
      "loss": 0.5505,
      "step": 210
    },
    {
      "epoch": 0.3676624190515981,
      "grad_norm": 0.30165988206863403,
      "learning_rate": 9.985653659495773e-05,
      "loss": 0.6274,
      "step": 220
    },
    {
      "epoch": 0.3843743471903071,
      "grad_norm": 0.31748878955841064,
      "learning_rate": 9.977359612865423e-05,
      "loss": 0.5831,
      "step": 230
    },
    {
      "epoch": 0.4010862753290161,
      "grad_norm": 0.5018420815467834,
      "learning_rate": 9.967186833234101e-05,
      "loss": 0.6331,
      "step": 240
    },
    {
      "epoch": 0.4177982034677251,
      "grad_norm": 0.3082675635814667,
      "learning_rate": 9.955139160375959e-05,
      "loss": 0.5884,
      "step": 250
    },
    {
      "epoch": 0.4345101316064341,
      "grad_norm": 0.36464694142341614,
      "learning_rate": 9.941221141754385e-05,
      "loss": 0.5993,
      "step": 260
    },
    {
      "epoch": 0.4512220597451431,
      "grad_norm": 0.36485177278518677,
      "learning_rate": 9.925438030805518e-05,
      "loss": 0.5846,
      "step": 270
    },
    {
      "epoch": 0.4679339878838521,
      "grad_norm": 0.3401179015636444,
      "learning_rate": 9.907795784955327e-05,
      "loss": 0.61,
      "step": 280
    },
    {
      "epoch": 0.48464591602256113,
      "grad_norm": 0.31191331148147583,
      "learning_rate": 9.888301063370934e-05,
      "loss": 0.5872,
      "step": 290
    },
    {
      "epoch": 0.5013578441612702,
      "grad_norm": 0.2694801688194275,
      "learning_rate": 9.866961224447075e-05,
      "loss": 0.5905,
      "step": 300
    },
    {
      "epoch": 0.5180697722999791,
      "grad_norm": 0.323143869638443,
      "learning_rate": 9.843784323028638e-05,
      "loss": 0.6213,
      "step": 310
    },
    {
      "epoch": 0.5347817004386881,
      "grad_norm": 0.30978456139564514,
      "learning_rate": 9.818779107370309e-05,
      "loss": 0.5602,
      "step": 320
    },
    {
      "epoch": 0.5514936285773971,
      "grad_norm": 0.36156347393989563,
      "learning_rate": 9.791955015834492e-05,
      "loss": 0.617,
      "step": 330
    },
    {
      "epoch": 0.5682055567161062,
      "grad_norm": 0.3188885450363159,
      "learning_rate": 9.763322173328753e-05,
      "loss": 0.6133,
      "step": 340
    },
    {
      "epoch": 0.5849174848548151,
      "grad_norm": 3.012507915496826,
      "learning_rate": 9.732891387484104e-05,
      "loss": 0.5401,
      "step": 350
    },
    {
      "epoch": 0.6016294129935241,
      "grad_norm": 0.3500335216522217,
      "learning_rate": 9.700674144575614e-05,
      "loss": 0.5994,
      "step": 360
    },
    {
      "epoch": 0.6183413411322332,
      "grad_norm": 0.38718223571777344,
      "learning_rate": 9.666682605186835e-05,
      "loss": 0.5362,
      "step": 370
    },
    {
      "epoch": 0.6350532692709422,
      "grad_norm": 0.32986128330230713,
      "learning_rate": 9.63092959961973e-05,
      "loss": 0.596,
      "step": 380
    },
    {
      "epoch": 0.6517651974096511,
      "grad_norm": 0.29063621163368225,
      "learning_rate": 9.593428623051792e-05,
      "loss": 0.5578,
      "step": 390
    },
    {
      "epoch": 0.6684771255483601,
      "grad_norm": 0.3483268916606903,
      "learning_rate": 9.554193830442229e-05,
      "loss": 0.6073,
      "step": 400
    },
    {
      "epoch": 0.6851890536870692,
      "grad_norm": 0.33267414569854736,
      "learning_rate": 9.513240031189067e-05,
      "loss": 0.5327,
      "step": 410
    },
    {
      "epoch": 0.7019009818257782,
      "grad_norm": 0.3286801874637604,
      "learning_rate": 9.470582683539285e-05,
      "loss": 0.5884,
      "step": 420
    },
    {
      "epoch": 0.7186129099644871,
      "grad_norm": 0.359754353761673,
      "learning_rate": 9.42623788875399e-05,
      "loss": 0.6042,
      "step": 430
    },
    {
      "epoch": 0.7353248381031962,
      "grad_norm": 0.36169129610061646,
      "learning_rate": 9.380222385030915e-05,
      "loss": 0.4902,
      "step": 440
    },
    {
      "epoch": 0.7520367662419052,
      "grad_norm": 0.31606003642082214,
      "learning_rate": 9.332553541186485e-05,
      "loss": 0.5816,
      "step": 450
    },
    {
      "epoch": 0.7687486943806142,
      "grad_norm": 0.3151916265487671,
      "learning_rate": 9.283249350099859e-05,
      "loss": 0.6368,
      "step": 460
    },
    {
      "epoch": 0.7854606225193231,
      "grad_norm": 0.2840172350406647,
      "learning_rate": 9.23232842192142e-05,
      "loss": 0.5906,
      "step": 470
    },
    {
      "epoch": 0.8021725506580322,
      "grad_norm": 0.30779144167900085,
      "learning_rate": 9.179809977048248e-05,
      "loss": 0.5955,
      "step": 480
    },
    {
      "epoch": 0.8188844787967412,
      "grad_norm": 0.31077197194099426,
      "learning_rate": 9.125713838869299e-05,
      "loss": 0.5831,
      "step": 490
    },
    {
      "epoch": 0.8355964069354502,
      "grad_norm": 0.33284345269203186,
      "learning_rate": 9.070060426282925e-05,
      "loss": 0.6071,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 1797,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.8837442456711987e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}