{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1477824549898515,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036945613747462877,
      "grad_norm": 2.2292165756225586,
      "learning_rate": 5.911330049261084e-06,
      "loss": 0.9395,
      "step": 25
    },
    {
      "epoch": 0.007389122749492575,
      "grad_norm": 0.8381065130233765,
      "learning_rate": 1.206896551724138e-05,
      "loss": 0.89,
      "step": 50
    },
    {
      "epoch": 0.011083684124238862,
      "grad_norm": 0.9238471984863281,
      "learning_rate": 1.8226600985221676e-05,
      "loss": 0.8384,
      "step": 75
    },
    {
      "epoch": 0.01477824549898515,
      "grad_norm": 0.6837311387062073,
      "learning_rate": 2.438423645320197e-05,
      "loss": 0.784,
      "step": 100
    },
    {
      "epoch": 0.01847280687373144,
      "grad_norm": 0.7093706727027893,
      "learning_rate": 3.0541871921182266e-05,
      "loss": 0.7675,
      "step": 125
    },
    {
      "epoch": 0.022167368248477724,
      "grad_norm": 0.6208077073097229,
      "learning_rate": 3.669950738916256e-05,
      "loss": 0.7466,
      "step": 150
    },
    {
      "epoch": 0.025861929623224013,
      "grad_norm": 0.8929094076156616,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.7386,
      "step": 175
    },
    {
      "epoch": 0.0295564909979703,
      "grad_norm": 0.7828120589256287,
      "learning_rate": 4.901477832512316e-05,
      "loss": 0.7173,
      "step": 200
    },
    {
      "epoch": 0.03325105237271659,
      "grad_norm": 0.7134449481964111,
      "learning_rate": 5.517241379310345e-05,
      "loss": 0.7108,
      "step": 225
    },
    {
      "epoch": 0.03694561374746288,
      "grad_norm": 0.7464851140975952,
      "learning_rate": 6.133004926108375e-05,
      "loss": 0.7332,
      "step": 250
    },
    {
      "epoch": 0.04064017512220916,
      "grad_norm": 0.677793025970459,
      "learning_rate": 6.748768472906404e-05,
      "loss": 0.7194,
      "step": 275
    },
    {
      "epoch": 0.04433473649695545,
      "grad_norm": 0.7936354875564575,
      "learning_rate": 7.364532019704434e-05,
      "loss": 0.7253,
      "step": 300
    },
    {
      "epoch": 0.04802929787170174,
      "grad_norm": 0.6711100935935974,
      "learning_rate": 7.980295566502463e-05,
      "loss": 0.7018,
      "step": 325
    },
    {
      "epoch": 0.051723859246448026,
      "grad_norm": 0.5816489458084106,
      "learning_rate": 8.596059113300493e-05,
      "loss": 0.7298,
      "step": 350
    },
    {
      "epoch": 0.055418420621194314,
      "grad_norm": 0.6680681705474854,
      "learning_rate": 9.211822660098522e-05,
      "loss": 0.7149,
      "step": 375
    },
    {
      "epoch": 0.0591129819959406,
      "grad_norm": 0.5643934607505798,
      "learning_rate": 9.827586206896552e-05,
      "loss": 0.763,
      "step": 400
    },
    {
      "epoch": 0.06280754337068689,
      "grad_norm": 0.5739309191703796,
      "learning_rate": 9.986286759104069e-05,
      "loss": 0.7345,
      "step": 425
    },
    {
      "epoch": 0.06650210474543318,
      "grad_norm": 0.5929909944534302,
      "learning_rate": 9.967240591193052e-05,
      "loss": 0.7364,
      "step": 450
    },
    {
      "epoch": 0.07019666612017947,
      "grad_norm": 0.609235405921936,
      "learning_rate": 9.948194423282036e-05,
      "loss": 0.7294,
      "step": 475
    },
    {
      "epoch": 0.07389122749492576,
      "grad_norm": 0.4643324613571167,
      "learning_rate": 9.92914825537102e-05,
      "loss": 0.7344,
      "step": 500
    },
    {
      "epoch": 0.07758578886967203,
      "grad_norm": 0.5267598032951355,
      "learning_rate": 9.910102087460003e-05,
      "loss": 0.7249,
      "step": 525
    },
    {
      "epoch": 0.08128035024441832,
      "grad_norm": 0.47951069474220276,
      "learning_rate": 9.891055919548987e-05,
      "loss": 0.7256,
      "step": 550
    },
    {
      "epoch": 0.08497491161916461,
      "grad_norm": 0.4505012333393097,
      "learning_rate": 9.87200975163797e-05,
      "loss": 0.7359,
      "step": 575
    },
    {
      "epoch": 0.0886694729939109,
      "grad_norm": 0.5320091247558594,
      "learning_rate": 9.852963583726955e-05,
      "loss": 0.6856,
      "step": 600
    },
    {
      "epoch": 0.09236403436865719,
      "grad_norm": 0.5583036541938782,
      "learning_rate": 9.833917415815939e-05,
      "loss": 0.7235,
      "step": 625
    },
    {
      "epoch": 0.09605859574340347,
      "grad_norm": 0.5139252543449402,
      "learning_rate": 9.814871247904922e-05,
      "loss": 0.7272,
      "step": 650
    },
    {
      "epoch": 0.09975315711814976,
      "grad_norm": 0.4989326000213623,
      "learning_rate": 9.795825079993906e-05,
      "loss": 0.6952,
      "step": 675
    },
    {
      "epoch": 0.10344771849289605,
      "grad_norm": 0.47355732321739197,
      "learning_rate": 9.776778912082889e-05,
      "loss": 0.7266,
      "step": 700
    },
    {
      "epoch": 0.10714227986764234,
      "grad_norm": 0.3588508367538452,
      "learning_rate": 9.757732744171874e-05,
      "loss": 0.7406,
      "step": 725
    },
    {
      "epoch": 0.11083684124238863,
      "grad_norm": 0.4120556712150574,
      "learning_rate": 9.738686576260857e-05,
      "loss": 0.7443,
      "step": 750
    },
    {
      "epoch": 0.11453140261713492,
      "grad_norm": 0.5160555839538574,
      "learning_rate": 9.71964040834984e-05,
      "loss": 0.7134,
      "step": 775
    },
    {
      "epoch": 0.1182259639918812,
      "grad_norm": 0.5423145890235901,
      "learning_rate": 9.700594240438823e-05,
      "loss": 0.7289,
      "step": 800
    },
    {
      "epoch": 0.1219205253666275,
      "grad_norm": 0.5352346301078796,
      "learning_rate": 9.681548072527808e-05,
      "loss": 0.7144,
      "step": 825
    },
    {
      "epoch": 0.12561508674137378,
      "grad_norm": 0.47908860445022583,
      "learning_rate": 9.662501904616791e-05,
      "loss": 0.7175,
      "step": 850
    },
    {
      "epoch": 0.12930964811612006,
      "grad_norm": 0.47986069321632385,
      "learning_rate": 9.643455736705776e-05,
      "loss": 0.6983,
      "step": 875
    },
    {
      "epoch": 0.13300420949086636,
      "grad_norm": 0.6903620958328247,
      "learning_rate": 9.624409568794759e-05,
      "loss": 0.7086,
      "step": 900
    },
    {
      "epoch": 0.13669877086561263,
      "grad_norm": 0.44413208961486816,
      "learning_rate": 9.605363400883742e-05,
      "loss": 0.7306,
      "step": 925
    },
    {
      "epoch": 0.14039333224035894,
      "grad_norm": 0.4634678065776825,
      "learning_rate": 9.586317232972727e-05,
      "loss": 0.7061,
      "step": 950
    },
    {
      "epoch": 0.1440878936151052,
      "grad_norm": 0.5110129714012146,
      "learning_rate": 9.56727106506171e-05,
      "loss": 0.7406,
      "step": 975
    },
    {
      "epoch": 0.1477824549898515,
      "grad_norm": 0.5460866093635559,
      "learning_rate": 9.548224897150694e-05,
      "loss": 0.721,
      "step": 1000
    }
  ],
  "logging_steps": 25,
  "max_steps": 13532,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.0118777182918103e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}