{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 229,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02188183807439825,
      "grad_norm": 1.2056468725204468,
      "learning_rate": 2.068965517241379e-06,
      "loss": 1.3589,
      "step": 5
    },
    {
      "epoch": 0.0437636761487965,
      "grad_norm": 0.7383206486701965,
      "learning_rate": 4.655172413793104e-06,
      "loss": 1.3299,
      "step": 10
    },
    {
      "epoch": 0.06564551422319474,
      "grad_norm": 0.5696788430213928,
      "learning_rate": 7.241379310344828e-06,
      "loss": 1.3287,
      "step": 15
    },
    {
      "epoch": 0.087527352297593,
      "grad_norm": 0.4898790419101715,
      "learning_rate": 9.827586206896551e-06,
      "loss": 1.3286,
      "step": 20
    },
    {
      "epoch": 0.10940919037199125,
      "grad_norm": 0.6403371691703796,
      "learning_rate": 1.2413793103448277e-05,
      "loss": 1.3167,
      "step": 25
    },
    {
      "epoch": 0.13129102844638948,
      "grad_norm": 0.6023938655853271,
      "learning_rate": 1.5e-05,
      "loss": 1.3163,
      "step": 30
    },
    {
      "epoch": 0.15317286652078774,
      "grad_norm": 0.4848966598510742,
      "learning_rate": 1.7586206896551724e-05,
      "loss": 1.27,
      "step": 35
    },
    {
      "epoch": 0.175054704595186,
      "grad_norm": 0.6767584681510925,
      "learning_rate": 2.017241379310345e-05,
      "loss": 1.2358,
      "step": 40
    },
    {
      "epoch": 0.19693654266958424,
      "grad_norm": 0.42833346128463745,
      "learning_rate": 2.275862068965517e-05,
      "loss": 1.2356,
      "step": 45
    },
    {
      "epoch": 0.2188183807439825,
      "grad_norm": 0.5033416152000427,
      "learning_rate": 2.5344827586206897e-05,
      "loss": 1.1764,
      "step": 50
    },
    {
      "epoch": 0.24070021881838075,
      "grad_norm": 0.5110407471656799,
      "learning_rate": 2.793103448275862e-05,
      "loss": 1.1782,
      "step": 55
    },
    {
      "epoch": 0.26258205689277897,
      "grad_norm": 0.5004281997680664,
      "learning_rate": 2.9999937352806748e-05,
      "loss": 1.2135,
      "step": 60
    },
    {
      "epoch": 0.2844638949671772,
      "grad_norm": 0.5905261039733887,
      "learning_rate": 2.9997744755987852e-05,
      "loss": 1.1598,
      "step": 65
    },
    {
      "epoch": 0.3063457330415755,
      "grad_norm": 0.46601855754852295,
      "learning_rate": 2.999242032277618e-05,
      "loss": 1.1192,
      "step": 70
    },
    {
      "epoch": 0.3282275711159737,
      "grad_norm": 0.5664127469062805,
      "learning_rate": 2.9983965165022473e-05,
      "loss": 1.135,
      "step": 75
    },
    {
      "epoch": 0.350109409190372,
      "grad_norm": 0.5967416763305664,
      "learning_rate": 2.9972381048336917e-05,
      "loss": 1.1354,
      "step": 80
    },
    {
      "epoch": 0.37199124726477023,
      "grad_norm": 0.5042751431465149,
      "learning_rate": 2.995767039172042e-05,
      "loss": 1.0858,
      "step": 85
    },
    {
      "epoch": 0.3938730853391685,
      "grad_norm": 0.5433419942855835,
      "learning_rate": 2.9939836267059482e-05,
      "loss": 1.0781,
      "step": 90
    },
    {
      "epoch": 0.41575492341356673,
      "grad_norm": 0.5662135481834412,
      "learning_rate": 2.9918882398484742e-05,
      "loss": 1.0949,
      "step": 95
    },
    {
      "epoch": 0.437636761487965,
      "grad_norm": 0.6487781405448914,
      "learning_rate": 2.989481316159328e-05,
      "loss": 1.0721,
      "step": 100
    },
    {
      "epoch": 0.45951859956236324,
      "grad_norm": 0.5745230317115784,
      "learning_rate": 2.9867633582534904e-05,
      "loss": 1.0192,
      "step": 105
    },
    {
      "epoch": 0.4814004376367615,
      "grad_norm": 0.7092564702033997,
      "learning_rate": 2.9837349336962612e-05,
      "loss": 1.0884,
      "step": 110
    },
    {
      "epoch": 0.5032822757111597,
      "grad_norm": 0.6593285202980042,
      "learning_rate": 2.9803966748847366e-05,
      "loss": 0.9648,
      "step": 115
    },
    {
      "epoch": 0.5251641137855579,
      "grad_norm": 0.751462996006012,
      "learning_rate": 2.976749278915754e-05,
      "loss": 0.9229,
      "step": 120
    },
    {
      "epoch": 0.5470459518599562,
      "grad_norm": 0.6278636455535889,
      "learning_rate": 2.9727935074403228e-05,
      "loss": 1.0129,
      "step": 125
    },
    {
      "epoch": 0.5689277899343544,
      "grad_norm": 0.7625859379768372,
      "learning_rate": 2.9685301865045768e-05,
      "loss": 0.9795,
      "step": 130
    },
    {
      "epoch": 0.5908096280087527,
      "grad_norm": 0.7692922949790955,
      "learning_rate": 2.9639602063772777e-05,
      "loss": 0.9894,
      "step": 135
    },
    {
      "epoch": 0.612691466083151,
      "grad_norm": 0.7171132564544678,
      "learning_rate": 2.959084521363911e-05,
      "loss": 0.9059,
      "step": 140
    },
    {
      "epoch": 0.6345733041575492,
      "grad_norm": 0.9169694781303406,
      "learning_rate": 2.9539041496074043e-05,
      "loss": 0.9285,
      "step": 145
    },
    {
      "epoch": 0.6564551422319475,
      "grad_norm": 0.8271639347076416,
      "learning_rate": 2.9484201728755205e-05,
      "loss": 0.8914,
      "step": 150
    },
    {
      "epoch": 0.6783369803063457,
      "grad_norm": 0.8969722986221313,
      "learning_rate": 2.9426337363349627e-05,
      "loss": 0.8813,
      "step": 155
    },
    {
      "epoch": 0.700218818380744,
      "grad_norm": 0.8180518746376038,
      "learning_rate": 2.9365460483122385e-05,
      "loss": 0.8638,
      "step": 160
    },
    {
      "epoch": 0.7221006564551422,
      "grad_norm": 0.9082233905792236,
      "learning_rate": 2.9301583800413363e-05,
      "loss": 0.9084,
      "step": 165
    },
    {
      "epoch": 0.7439824945295405,
      "grad_norm": 0.8155914545059204,
      "learning_rate": 2.923472065398268e-05,
      "loss": 0.8917,
      "step": 170
    },
    {
      "epoch": 0.7658643326039387,
      "grad_norm": 0.8886885643005371,
      "learning_rate": 2.916488500622527e-05,
      "loss": 0.8079,
      "step": 175
    },
    {
      "epoch": 0.787746170678337,
      "grad_norm": 0.8544840812683105,
      "learning_rate": 2.909209144025524e-05,
      "loss": 0.8317,
      "step": 180
    },
    {
      "epoch": 0.8096280087527352,
      "grad_norm": 0.8505244851112366,
      "learning_rate": 2.9016355156860625e-05,
      "loss": 0.7849,
      "step": 185
    },
    {
      "epoch": 0.8315098468271335,
      "grad_norm": 0.9838951826095581,
      "learning_rate": 2.8937691971329155e-05,
      "loss": 0.8021,
      "step": 190
    },
    {
      "epoch": 0.8533916849015317,
      "grad_norm": 0.9686183333396912,
      "learning_rate": 2.8856118310145687e-05,
      "loss": 0.8038,
      "step": 195
    },
    {
      "epoch": 0.87527352297593,
      "grad_norm": 0.9777634739875793,
      "learning_rate": 2.8771651207562043e-05,
      "loss": 0.773,
      "step": 200
    },
    {
      "epoch": 0.8971553610503282,
      "grad_norm": 1.0718952417373657,
      "learning_rate": 2.8684308302039878e-05,
      "loss": 0.723,
      "step": 205
    },
    {
      "epoch": 0.9190371991247265,
      "grad_norm": 1.031557321548462,
      "learning_rate": 2.8594107832567424e-05,
      "loss": 0.6804,
      "step": 210
    },
    {
      "epoch": 0.9409190371991247,
      "grad_norm": 0.9825000762939453,
      "learning_rate": 2.850106863485082e-05,
      "loss": 0.7704,
      "step": 215
    },
    {
      "epoch": 0.962800875273523,
      "grad_norm": 1.1034126281738281,
      "learning_rate": 2.840521013738083e-05,
      "loss": 0.7545,
      "step": 220
    },
    {
      "epoch": 0.9846827133479212,
      "grad_norm": 1.1799556016921997,
      "learning_rate": 2.8306552357375753e-05,
      "loss": 0.7517,
      "step": 225
    }
  ],
  "logging_steps": 5,
  "max_steps": 1145,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.164877723722056e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}