{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.875912408759124,
  "eval_steps": 1000,
  "global_step": 51,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.058394160583941604,
      "grad_norm": 4.656792954985782,
      "learning_rate": 0.0,
      "loss": 0.4427,
      "step": 1
    },
    {
      "epoch": 0.11678832116788321,
      "grad_norm": 4.86013370097108,
      "learning_rate": 1.6666666666666665e-07,
      "loss": 0.4479,
      "step": 2
    },
    {
      "epoch": 0.17518248175182483,
      "grad_norm": 4.890457886287774,
      "learning_rate": 3.333333333333333e-07,
      "loss": 0.4409,
      "step": 3
    },
    {
      "epoch": 0.23357664233576642,
      "grad_norm": 4.716105876070575,
      "learning_rate": 5e-07,
      "loss": 0.4431,
      "step": 4
    },
    {
      "epoch": 0.291970802919708,
      "grad_norm": 4.662120140818256,
      "learning_rate": 6.666666666666666e-07,
      "loss": 0.4399,
      "step": 5
    },
    {
      "epoch": 0.35036496350364965,
      "grad_norm": 4.595422118216669,
      "learning_rate": 8.333333333333333e-07,
      "loss": 0.4329,
      "step": 6
    },
    {
      "epoch": 0.40875912408759124,
      "grad_norm": 4.226730555329321,
      "learning_rate": 1e-06,
      "loss": 0.4309,
      "step": 7
    },
    {
      "epoch": 0.46715328467153283,
      "grad_norm": 4.171716322640935,
      "learning_rate": 9.98782025129912e-07,
      "loss": 0.4376,
      "step": 8
    },
    {
      "epoch": 0.5255474452554745,
      "grad_norm": 2.797761384697659,
      "learning_rate": 9.95134034370785e-07,
      "loss": 0.4133,
      "step": 9
    },
    {
      "epoch": 0.583941605839416,
      "grad_norm": 2.5830664759555444,
      "learning_rate": 9.890738003669027e-07,
      "loss": 0.406,
      "step": 10
    },
    {
      "epoch": 0.6423357664233577,
      "grad_norm": 2.3850526224388444,
      "learning_rate": 9.806308479691594e-07,
      "loss": 0.4163,
      "step": 11
    },
    {
      "epoch": 0.7007299270072993,
      "grad_norm": 2.3089181989651593,
      "learning_rate": 9.698463103929541e-07,
      "loss": 0.4158,
      "step": 12
    },
    {
      "epoch": 0.7591240875912408,
      "grad_norm": 2.134247320958559,
      "learning_rate": 9.567727288213004e-07,
      "loss": 0.4014,
      "step": 13
    },
    {
      "epoch": 0.8175182481751825,
      "grad_norm": 2.136565413176427,
      "learning_rate": 9.414737964294634e-07,
      "loss": 0.4,
      "step": 14
    },
    {
      "epoch": 0.8759124087591241,
      "grad_norm": 2.091829552338069,
      "learning_rate": 9.240240480782129e-07,
      "loss": 0.3939,
      "step": 15
    },
    {
      "epoch": 0.9343065693430657,
      "grad_norm": 2.0557987105811537,
      "learning_rate": 9.045084971874737e-07,
      "loss": 0.3961,
      "step": 16
    },
    {
      "epoch": 0.9927007299270073,
      "grad_norm": 1.9838338116938496,
      "learning_rate": 8.83022221559489e-07,
      "loss": 0.3936,
      "step": 17
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.9838338116938496,
      "learning_rate": 8.596699001693255e-07,
      "loss": 0.3953,
      "step": 18
    },
    {
      "epoch": 1.0583941605839415,
      "grad_norm": 3.7195402419448547,
      "learning_rate": 8.34565303179429e-07,
      "loss": 0.3889,
      "step": 19
    },
    {
      "epoch": 1.1167883211678833,
      "grad_norm": 2.0185142045130724,
      "learning_rate": 8.07830737662829e-07,
      "loss": 0.3945,
      "step": 20
    },
    {
      "epoch": 1.1751824817518248,
      "grad_norm": 1.776183202633764,
      "learning_rate": 7.795964517353733e-07,
      "loss": 0.3792,
      "step": 21
    },
    {
      "epoch": 1.2335766423357664,
      "grad_norm": 1.3920276083517107,
      "learning_rate": 7.5e-07,
      "loss": 0.3656,
      "step": 22
    },
    {
      "epoch": 1.2919708029197081,
      "grad_norm": 1.2863840146844603,
      "learning_rate": 7.191855733945386e-07,
      "loss": 0.3661,
      "step": 23
    },
    {
      "epoch": 1.3503649635036497,
      "grad_norm": 1.2539879708687325,
      "learning_rate": 6.87303296707956e-07,
      "loss": 0.3597,
      "step": 24
    },
    {
      "epoch": 1.4087591240875912,
      "grad_norm": 1.166120242178893,
      "learning_rate": 6.545084971874736e-07,
      "loss": 0.3516,
      "step": 25
    },
    {
      "epoch": 1.4671532846715327,
      "grad_norm": 1.1488662726861754,
      "learning_rate": 6.209609477998338e-07,
      "loss": 0.3565,
      "step": 26
    },
    {
      "epoch": 1.5255474452554745,
      "grad_norm": 1.1401441355458104,
      "learning_rate": 5.868240888334652e-07,
      "loss": 0.3593,
      "step": 27
    },
    {
      "epoch": 1.583941605839416,
      "grad_norm": 1.1098917532126118,
      "learning_rate": 5.522642316338268e-07,
      "loss": 0.3553,
      "step": 28
    },
    {
      "epoch": 1.6423357664233578,
      "grad_norm": 1.0608300492190985,
      "learning_rate": 5.174497483512505e-07,
      "loss": 0.3468,
      "step": 29
    },
    {
      "epoch": 1.7007299270072993,
      "grad_norm": 1.0513121541995292,
      "learning_rate": 4.825502516487496e-07,
      "loss": 0.3512,
      "step": 30
    },
    {
      "epoch": 1.7591240875912408,
      "grad_norm": 1.0321496985153071,
      "learning_rate": 4.477357683661733e-07,
      "loss": 0.3462,
      "step": 31
    },
    {
      "epoch": 1.8175182481751824,
      "grad_norm": 0.9664124061777448,
      "learning_rate": 4.131759111665348e-07,
      "loss": 0.3453,
      "step": 32
    },
    {
      "epoch": 1.8759124087591241,
      "grad_norm": 0.9864302519260517,
      "learning_rate": 3.790390522001662e-07,
      "loss": 0.3548,
      "step": 33
    },
    {
      "epoch": 1.9343065693430657,
      "grad_norm": 0.9284627064839345,
      "learning_rate": 3.454915028125263e-07,
      "loss": 0.3369,
      "step": 34
    },
    {
      "epoch": 1.9927007299270074,
      "grad_norm": 0.9113524544646622,
      "learning_rate": 3.1269670329204393e-07,
      "loss": 0.3452,
      "step": 35
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9113524544646622,
      "learning_rate": 2.808144266054612e-07,
      "loss": 0.3717,
      "step": 36
    },
    {
      "epoch": 2.0583941605839415,
      "grad_norm": 1.606883667124614,
      "learning_rate": 2.500000000000001e-07,
      "loss": 0.3407,
      "step": 37
    },
    {
      "epoch": 2.116788321167883,
      "grad_norm": 0.8931807344006792,
      "learning_rate": 2.2040354826462664e-07,
      "loss": 0.3421,
      "step": 38
    },
    {
      "epoch": 2.1751824817518246,
      "grad_norm": 0.9177610844452588,
      "learning_rate": 1.9216926233717084e-07,
      "loss": 0.3475,
      "step": 39
    },
    {
      "epoch": 2.2335766423357666,
      "grad_norm": 0.8877519183136245,
      "learning_rate": 1.6543469682057104e-07,
      "loss": 0.3428,
      "step": 40
    },
    {
      "epoch": 2.291970802919708,
      "grad_norm": 0.8786726057000499,
      "learning_rate": 1.4033009983067452e-07,
      "loss": 0.3369,
      "step": 41
    },
    {
      "epoch": 2.3503649635036497,
      "grad_norm": 0.8740350065054695,
      "learning_rate": 1.1697777844051104e-07,
      "loss": 0.3432,
      "step": 42
    },
    {
      "epoch": 2.408759124087591,
      "grad_norm": 0.8767663235746571,
      "learning_rate": 9.549150281252632e-08,
      "loss": 0.3448,
      "step": 43
    },
    {
      "epoch": 2.4671532846715327,
      "grad_norm": 0.8554900558425669,
      "learning_rate": 7.597595192178702e-08,
      "loss": 0.3366,
      "step": 44
    },
    {
      "epoch": 2.5255474452554747,
      "grad_norm": 0.8931022618355365,
      "learning_rate": 5.8526203570536504e-08,
      "loss": 0.3413,
      "step": 45
    },
    {
      "epoch": 2.5839416058394162,
      "grad_norm": 0.8653492886520165,
      "learning_rate": 4.322727117869951e-08,
      "loss": 0.3427,
      "step": 46
    },
    {
      "epoch": 2.6423357664233578,
      "grad_norm": 0.8828223465494373,
      "learning_rate": 3.015368960704584e-08,
      "loss": 0.3401,
      "step": 47
    },
    {
      "epoch": 2.7007299270072993,
      "grad_norm": 0.8436117670189993,
      "learning_rate": 1.936915203084055e-08,
      "loss": 0.344,
      "step": 48
    },
    {
      "epoch": 2.759124087591241,
      "grad_norm": 0.870664029954303,
      "learning_rate": 1.0926199633097154e-08,
      "loss": 0.3367,
      "step": 49
    },
    {
      "epoch": 2.8175182481751824,
      "grad_norm": 0.8533210535483198,
      "learning_rate": 4.865965629214819e-09,
      "loss": 0.3326,
      "step": 50
    },
    {
      "epoch": 2.875912408759124,
      "grad_norm": 0.8603385788586924,
      "learning_rate": 1.217974870087901e-09,
      "loss": 0.3353,
      "step": 51
    }
  ],
  "logging_steps": 1,
  "max_steps": 51,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 121368125374464.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}