{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.859598853868195,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05730659025787966,
      "grad_norm": 10.106540722187765,
      "learning_rate": 5.142857142857143e-07,
      "loss": 1.5746,
      "step": 10
    },
    {
      "epoch": 0.11461318051575932,
      "grad_norm": 6.586136263761276,
      "learning_rate": 1.0857142857142858e-06,
      "loss": 1.4523,
      "step": 20
    },
    {
      "epoch": 0.17191977077363896,
      "grad_norm": 3.0707962293997366,
      "learning_rate": 1.657142857142857e-06,
      "loss": 1.146,
      "step": 30
    },
    {
      "epoch": 0.22922636103151864,
      "grad_norm": 2.3548379062361624,
      "learning_rate": 2.228571428571429e-06,
      "loss": 0.952,
      "step": 40
    },
    {
      "epoch": 0.28653295128939826,
      "grad_norm": 1.9627642658101132,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.8935,
      "step": 50
    },
    {
      "epoch": 0.3438395415472779,
      "grad_norm": 2.0814135363278248,
      "learning_rate": 3.3714285714285716e-06,
      "loss": 0.8779,
      "step": 60
    },
    {
      "epoch": 0.40114613180515757,
      "grad_norm": 1.88380326807941,
      "learning_rate": 3.942857142857143e-06,
      "loss": 0.8562,
      "step": 70
    },
    {
      "epoch": 0.4584527220630373,
      "grad_norm": 1.6116668676175776,
      "learning_rate": 4.514285714285714e-06,
      "loss": 0.8523,
      "step": 80
    },
    {
      "epoch": 0.5157593123209169,
      "grad_norm": 1.6683198279460352,
      "learning_rate": 5.085714285714286e-06,
      "loss": 0.8436,
      "step": 90
    },
    {
      "epoch": 0.5730659025787965,
      "grad_norm": 1.7566538916367258,
      "learning_rate": 5.6571428571428576e-06,
      "loss": 0.8488,
      "step": 100
    },
    {
      "epoch": 0.6303724928366762,
      "grad_norm": 2.125615333677828,
      "learning_rate": 6.22857142857143e-06,
      "loss": 0.8498,
      "step": 110
    },
    {
      "epoch": 0.6876790830945558,
      "grad_norm": 1.8303892904929213,
      "learning_rate": 6.800000000000001e-06,
      "loss": 0.8405,
      "step": 120
    },
    {
      "epoch": 0.7449856733524355,
      "grad_norm": 1.9619910074521034,
      "learning_rate": 7.371428571428571e-06,
      "loss": 0.8441,
      "step": 130
    },
    {
      "epoch": 0.8022922636103151,
      "grad_norm": 2.2442912448835397,
      "learning_rate": 7.942857142857144e-06,
      "loss": 0.8422,
      "step": 140
    },
    {
      "epoch": 0.8595988538681948,
      "grad_norm": 1.7858895568365396,
      "learning_rate": 8.514285714285715e-06,
      "loss": 0.8454,
      "step": 150
    },
    {
      "epoch": 0.9169054441260746,
      "grad_norm": 1.9619084977160475,
      "learning_rate": 9.085714285714286e-06,
      "loss": 0.8417,
      "step": 160
    },
    {
      "epoch": 0.9742120343839542,
      "grad_norm": 2.669334620274088,
      "learning_rate": 9.657142857142859e-06,
      "loss": 0.8385,
      "step": 170
    },
    {
      "epoch": 1.0286532951289398,
      "grad_norm": 1.6909504353944882,
      "learning_rate": 9.999840853784125e-06,
      "loss": 0.7796,
      "step": 180
    },
    {
      "epoch": 1.0859598853868195,
      "grad_norm": 1.8668973254520025,
      "learning_rate": 9.998050575201772e-06,
      "loss": 0.7748,
      "step": 190
    },
    {
      "epoch": 1.143266475644699,
      "grad_norm": 1.8883027368057261,
      "learning_rate": 9.994271799912004e-06,
      "loss": 0.7796,
      "step": 200
    },
    {
      "epoch": 1.2005730659025788,
      "grad_norm": 1.5699435632265302,
      "learning_rate": 9.988506031317416e-06,
      "loss": 0.7741,
      "step": 210
    },
    {
      "epoch": 1.2578796561604584,
      "grad_norm": 1.9834006089125242,
      "learning_rate": 9.980755563354755e-06,
      "loss": 0.7705,
      "step": 220
    },
    {
      "epoch": 1.3151862464183381,
      "grad_norm": 1.8829423034816772,
      "learning_rate": 9.971023479582258e-06,
      "loss": 0.7797,
      "step": 230
    },
    {
      "epoch": 1.3724928366762177,
      "grad_norm": 2.2032493897453884,
      "learning_rate": 9.95931365195285e-06,
      "loss": 0.7809,
      "step": 240
    },
    {
      "epoch": 1.4297994269340975,
      "grad_norm": 1.7197069451450147,
      "learning_rate": 9.945630739273665e-06,
      "loss": 0.7863,
      "step": 250
    },
    {
      "epoch": 1.487106017191977,
      "grad_norm": 1.8502133094152093,
      "learning_rate": 9.929980185352525e-06,
      "loss": 0.7809,
      "step": 260
    },
    {
      "epoch": 1.5444126074498568,
      "grad_norm": 1.8675068788636697,
      "learning_rate": 9.912368216832094e-06,
      "loss": 0.7872,
      "step": 270
    },
    {
      "epoch": 1.6017191977077365,
      "grad_norm": 1.8956782839664204,
      "learning_rate": 9.892801840712576e-06,
      "loss": 0.7829,
      "step": 280
    },
    {
      "epoch": 1.659025787965616,
      "grad_norm": 1.7611480413309337,
      "learning_rate": 9.871288841563956e-06,
      "loss": 0.7791,
      "step": 290
    },
    {
      "epoch": 1.7163323782234956,
      "grad_norm": 1.8503576125588526,
      "learning_rate": 9.847837778428873e-06,
      "loss": 0.7831,
      "step": 300
    },
    {
      "epoch": 1.7736389684813754,
      "grad_norm": 1.7418957645569824,
      "learning_rate": 9.822457981417362e-06,
      "loss": 0.7816,
      "step": 310
    },
    {
      "epoch": 1.8309455587392551,
      "grad_norm": 1.5527795499202368,
      "learning_rate": 9.79515954799483e-06,
      "loss": 0.7886,
      "step": 320
    },
    {
      "epoch": 1.8882521489971347,
      "grad_norm": 1.6373526820097914,
      "learning_rate": 9.765953338964736e-06,
      "loss": 0.7817,
      "step": 330
    },
    {
      "epoch": 1.9455587392550142,
      "grad_norm": 1.6298673659139973,
      "learning_rate": 9.734850974147573e-06,
      "loss": 0.7816,
      "step": 340
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.6034876035879577,
      "learning_rate": 9.701864827757868e-06,
      "loss": 0.7558,
      "step": 350
    },
    {
      "epoch": 2.0573065902578795,
      "grad_norm": 1.550929714181552,
      "learning_rate": 9.667008023481045e-06,
      "loss": 0.5813,
      "step": 360
    },
    {
      "epoch": 2.1146131805157595,
      "grad_norm": 1.6888908937399765,
      "learning_rate": 9.630294429252112e-06,
      "loss": 0.5526,
      "step": 370
    },
    {
      "epoch": 2.171919770773639,
      "grad_norm": 1.5855707234018377,
      "learning_rate": 9.591738651738235e-06,
      "loss": 0.5575,
      "step": 380
    },
    {
      "epoch": 2.2292263610315186,
      "grad_norm": 1.6064410424084354,
      "learning_rate": 9.551356030527417e-06,
      "loss": 0.5609,
      "step": 390
    },
    {
      "epoch": 2.286532951289398,
      "grad_norm": 1.4496809814777507,
      "learning_rate": 9.50916263202557e-06,
      "loss": 0.5548,
      "step": 400
    },
    {
      "epoch": 2.343839541547278,
      "grad_norm": 1.5401653091904366,
      "learning_rate": 9.465175243064428e-06,
      "loss": 0.5636,
      "step": 410
    },
    {
      "epoch": 2.4011461318051577,
      "grad_norm": 1.582349105341671,
      "learning_rate": 9.419411364222826e-06,
      "loss": 0.5648,
      "step": 420
    },
    {
      "epoch": 2.458452722063037,
      "grad_norm": 1.5842844192259247,
      "learning_rate": 9.37188920286402e-06,
      "loss": 0.5679,
      "step": 430
    },
    {
      "epoch": 2.5157593123209168,
      "grad_norm": 1.6807187813727524,
      "learning_rate": 9.322627665891807e-06,
      "loss": 0.5681,
      "step": 440
    },
    {
      "epoch": 2.5730659025787963,
      "grad_norm": 1.6284486737168171,
      "learning_rate": 9.271646352228324e-06,
      "loss": 0.5711,
      "step": 450
    },
    {
      "epoch": 2.6303724928366763,
      "grad_norm": 1.6028282865624421,
      "learning_rate": 9.218965545016538e-06,
      "loss": 0.5742,
      "step": 460
    },
    {
      "epoch": 2.687679083094556,
      "grad_norm": 1.7636115949396163,
      "learning_rate": 9.164606203550498e-06,
      "loss": 0.5721,
      "step": 470
    },
    {
      "epoch": 2.7449856733524354,
      "grad_norm": 1.594464961248534,
      "learning_rate": 9.108589954936592e-06,
      "loss": 0.5758,
      "step": 480
    },
    {
      "epoch": 2.8022922636103154,
      "grad_norm": 1.7158796247386685,
      "learning_rate": 9.050939085489104e-06,
      "loss": 0.569,
      "step": 490
    },
    {
      "epoch": 2.859598853868195,
      "grad_norm": 1.6082086064967192,
      "learning_rate": 8.991676531863507e-06,
      "loss": 0.575,
      "step": 500
    },
    {
      "epoch": 2.859598853868195,
      "eval_loss": 0.9605590105056763,
      "eval_runtime": 655.0431,
      "eval_samples_per_second": 7.574,
      "eval_steps_per_second": 1.895,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 1750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 466778166657024.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}