{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 266,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018832391713747645,
      "grad_norm": 1.1089932918548584,
      "learning_rate": 1.791044776119403e-06,
      "loss": 1.365,
      "step": 5
    },
    {
      "epoch": 0.03766478342749529,
      "grad_norm": 0.8269509673118591,
      "learning_rate": 4.029850746268657e-06,
      "loss": 1.3307,
      "step": 10
    },
    {
      "epoch": 0.05649717514124294,
      "grad_norm": 0.6606281995773315,
      "learning_rate": 6.268656716417911e-06,
      "loss": 1.2869,
      "step": 15
    },
    {
      "epoch": 0.07532956685499058,
      "grad_norm": 0.5472633242607117,
      "learning_rate": 8.507462686567164e-06,
      "loss": 1.2774,
      "step": 20
    },
    {
      "epoch": 0.09416195856873823,
      "grad_norm": 0.6873501539230347,
      "learning_rate": 1.0746268656716418e-05,
      "loss": 1.2985,
      "step": 25
    },
    {
      "epoch": 0.11299435028248588,
      "grad_norm": 0.5600975751876831,
      "learning_rate": 1.2985074626865672e-05,
      "loss": 1.217,
      "step": 30
    },
    {
      "epoch": 0.1318267419962335,
      "grad_norm": 0.7250403761863708,
      "learning_rate": 1.5223880597014927e-05,
      "loss": 1.233,
      "step": 35
    },
    {
      "epoch": 0.15065913370998116,
      "grad_norm": 0.5497453808784485,
      "learning_rate": 1.746268656716418e-05,
      "loss": 1.2169,
      "step": 40
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 0.6821231842041016,
      "learning_rate": 1.9701492537313435e-05,
      "loss": 1.1701,
      "step": 45
    },
    {
      "epoch": 0.18832391713747645,
      "grad_norm": 0.5772640705108643,
      "learning_rate": 2.194029850746269e-05,
      "loss": 1.1552,
      "step": 50
    },
    {
      "epoch": 0.2071563088512241,
      "grad_norm": 0.5170062780380249,
      "learning_rate": 2.417910447761194e-05,
      "loss": 1.1947,
      "step": 55
    },
    {
      "epoch": 0.22598870056497175,
      "grad_norm": 0.5546678304672241,
      "learning_rate": 2.6417910447761193e-05,
      "loss": 1.0869,
      "step": 60
    },
    {
      "epoch": 0.2448210922787194,
      "grad_norm": 0.6221190690994263,
      "learning_rate": 2.8656716417910447e-05,
      "loss": 1.1683,
      "step": 65
    },
    {
      "epoch": 0.263653483992467,
      "grad_norm": 0.7900596857070923,
      "learning_rate": 2.9999814384857414e-05,
      "loss": 1.1623,
      "step": 70
    },
    {
      "epoch": 0.2824858757062147,
      "grad_norm": 0.5770227909088135,
      "learning_rate": 2.99977262672591e-05,
      "loss": 1.1033,
      "step": 75
    },
    {
      "epoch": 0.3013182674199623,
      "grad_norm": 0.5991471409797668,
      "learning_rate": 2.9993318337195934e-05,
      "loss": 1.1221,
      "step": 80
    },
    {
      "epoch": 0.32015065913371,
      "grad_norm": 0.6063827872276306,
      "learning_rate": 2.998659127647601e-05,
      "loss": 1.0186,
      "step": 85
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 0.690599262714386,
      "learning_rate": 2.9977546125625006e-05,
      "loss": 1.0455,
      "step": 90
    },
    {
      "epoch": 0.3578154425612053,
      "grad_norm": 0.681769073009491,
      "learning_rate": 2.9966184283725243e-05,
      "loss": 1.014,
      "step": 95
    },
    {
      "epoch": 0.3766478342749529,
      "grad_norm": 0.6798896789550781,
      "learning_rate": 2.9952507508199284e-05,
      "loss": 0.9816,
      "step": 100
    },
    {
      "epoch": 0.3954802259887006,
      "grad_norm": 0.6588433384895325,
      "learning_rate": 2.9936517914538085e-05,
      "loss": 1.0095,
      "step": 105
    },
    {
      "epoch": 0.4143126177024482,
      "grad_norm": 0.7236828207969666,
      "learning_rate": 2.991821797597379e-05,
      "loss": 0.9913,
      "step": 110
    },
    {
      "epoch": 0.4331450094161959,
      "grad_norm": 0.6340996026992798,
      "learning_rate": 2.989761052309717e-05,
      "loss": 0.9752,
      "step": 115
    },
    {
      "epoch": 0.4519774011299435,
      "grad_norm": 0.7232135534286499,
      "learning_rate": 2.98746987434198e-05,
      "loss": 0.965,
      "step": 120
    },
    {
      "epoch": 0.4708097928436911,
      "grad_norm": 0.7878739237785339,
      "learning_rate": 2.9849486180881017e-05,
      "loss": 0.9779,
      "step": 125
    },
    {
      "epoch": 0.4896421845574388,
      "grad_norm": 0.7223129868507385,
      "learning_rate": 2.982197673529976e-05,
      "loss": 0.9159,
      "step": 130
    },
    {
      "epoch": 0.5084745762711864,
      "grad_norm": 0.7257573008537292,
      "learning_rate": 2.9792174661771332e-05,
      "loss": 0.9403,
      "step": 135
    },
    {
      "epoch": 0.527306967984934,
      "grad_norm": 0.8936464190483093,
      "learning_rate": 2.976008457000927e-05,
      "loss": 0.8969,
      "step": 140
    },
    {
      "epoch": 0.5461393596986818,
      "grad_norm": 0.9090555906295776,
      "learning_rate": 2.972571142363229e-05,
      "loss": 0.8963,
      "step": 145
    },
    {
      "epoch": 0.5649717514124294,
      "grad_norm": 0.8844392895698547,
      "learning_rate": 2.9689060539396545e-05,
      "loss": 0.8657,
      "step": 150
    },
    {
      "epoch": 0.583804143126177,
      "grad_norm": 0.8749438524246216,
      "learning_rate": 2.9650137586373236e-05,
      "loss": 0.8104,
      "step": 155
    },
    {
      "epoch": 0.6026365348399246,
      "grad_norm": 0.9088373184204102,
      "learning_rate": 2.9608948585071747e-05,
      "loss": 0.842,
      "step": 160
    },
    {
      "epoch": 0.6214689265536724,
      "grad_norm": 0.8506441116333008,
      "learning_rate": 2.9565499906508376e-05,
      "loss": 0.8132,
      "step": 165
    },
    {
      "epoch": 0.64030131826742,
      "grad_norm": 0.9221051335334778,
      "learning_rate": 2.9519798271220915e-05,
      "loss": 0.7725,
      "step": 170
    },
    {
      "epoch": 0.6591337099811676,
      "grad_norm": 1.0185768604278564,
      "learning_rate": 2.9471850748229117e-05,
      "loss": 0.7874,
      "step": 175
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 0.8905505537986755,
      "learning_rate": 2.9421664753941277e-05,
      "loss": 0.7491,
      "step": 180
    },
    {
      "epoch": 0.696798493408663,
      "grad_norm": 0.9472977519035339,
      "learning_rate": 2.936924805100708e-05,
      "loss": 0.7542,
      "step": 185
    },
    {
      "epoch": 0.7156308851224106,
      "grad_norm": 1.000342845916748,
      "learning_rate": 2.9314608747116894e-05,
      "loss": 0.7364,
      "step": 190
    },
    {
      "epoch": 0.7344632768361582,
      "grad_norm": 0.8593543171882629,
      "learning_rate": 2.9257755293747702e-05,
      "loss": 0.7712,
      "step": 195
    },
    {
      "epoch": 0.7532956685499058,
      "grad_norm": 0.9145693778991699,
      "learning_rate": 2.919869648485582e-05,
      "loss": 0.7399,
      "step": 200
    },
    {
      "epoch": 0.7721280602636534,
      "grad_norm": 0.9073010683059692,
      "learning_rate": 2.9137441455516706e-05,
      "loss": 0.6409,
      "step": 205
    },
    {
      "epoch": 0.7909604519774012,
      "grad_norm": 0.8353155851364136,
      "learning_rate": 2.9073999680511935e-05,
      "loss": 0.738,
      "step": 210
    },
    {
      "epoch": 0.8097928436911488,
      "grad_norm": 1.0048359632492065,
      "learning_rate": 2.9008380972863693e-05,
      "loss": 0.7345,
      "step": 215
    },
    {
      "epoch": 0.8286252354048964,
      "grad_norm": 1.1321660280227661,
      "learning_rate": 2.8940595482316883e-05,
      "loss": 0.6374,
      "step": 220
    },
    {
      "epoch": 0.847457627118644,
      "grad_norm": 0.9749424457550049,
      "learning_rate": 2.8870653693769233e-05,
      "loss": 0.6937,
      "step": 225
    },
    {
      "epoch": 0.8662900188323918,
      "grad_norm": 0.9839215874671936,
      "learning_rate": 2.8798566425649478e-05,
      "loss": 0.6885,
      "step": 230
    },
    {
      "epoch": 0.8851224105461394,
      "grad_norm": 1.0036780834197998,
      "learning_rate": 2.8724344828244014e-05,
      "loss": 0.6463,
      "step": 235
    },
    {
      "epoch": 0.903954802259887,
      "grad_norm": 0.9374542832374573,
      "learning_rate": 2.864800038197219e-05,
      "loss": 0.6853,
      "step": 240
    },
    {
      "epoch": 0.9227871939736346,
      "grad_norm": 1.1694684028625488,
      "learning_rate": 2.8569544895610536e-05,
      "loss": 0.6399,
      "step": 245
    },
    {
      "epoch": 0.9416195856873822,
      "grad_norm": 1.0283533334732056,
      "learning_rate": 2.848899050446624e-05,
      "loss": 0.6486,
      "step": 250
    },
    {
      "epoch": 0.96045197740113,
      "grad_norm": 0.9280611276626587,
      "learning_rate": 2.840634966850006e-05,
      "loss": 0.6377,
      "step": 255
    },
    {
      "epoch": 0.9792843691148776,
      "grad_norm": 0.8847799897193909,
      "learning_rate": 2.832163517039903e-05,
      "loss": 0.6585,
      "step": 260
    },
    {
      "epoch": 0.9981167608286252,
      "grad_norm": 1.08964204788208,
      "learning_rate": 2.8234860113599316e-05,
      "loss": 0.6149,
      "step": 265
    }
  ],
  "logging_steps": 5,
  "max_steps": 1330,
  "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": 3.639319352668324e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}