{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 0,
  "global_step": 66,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04745762711864407,
      "grad_norm": 0.5666637420654297,
      "learning_rate": 0.0,
      "loss": 2.5416,
      "step": 1
    },
    {
      "epoch": 0.09491525423728814,
      "grad_norm": 0.5534914135932922,
      "learning_rate": 0.0001,
      "loss": 2.3799,
      "step": 2
    },
    {
      "epoch": 0.1423728813559322,
      "grad_norm": 0.45777013897895813,
      "learning_rate": 0.0002,
      "loss": 2.1236,
      "step": 3
    },
    {
      "epoch": 0.18983050847457628,
      "grad_norm": 0.30857300758361816,
      "learning_rate": 0.00019987954562051725,
      "loss": 1.7514,
      "step": 4
    },
    {
      "epoch": 0.23728813559322035,
      "grad_norm": 0.22516803443431854,
      "learning_rate": 0.0001995184726672197,
      "loss": 1.7157,
      "step": 5
    },
    {
      "epoch": 0.2847457627118644,
      "grad_norm": 0.17006772756576538,
      "learning_rate": 0.0001989176509964781,
      "loss": 1.5111,
      "step": 6
    },
    {
      "epoch": 0.33220338983050846,
      "grad_norm": 0.19116045534610748,
      "learning_rate": 0.00019807852804032305,
      "loss": 1.494,
      "step": 7
    },
    {
      "epoch": 0.37966101694915255,
      "grad_norm": 0.21142518520355225,
      "learning_rate": 0.00019700312531945442,
      "loss": 1.4591,
      "step": 8
    },
    {
      "epoch": 0.4271186440677966,
      "grad_norm": 0.16470277309417725,
      "learning_rate": 0.0001956940335732209,
      "loss": 1.5168,
      "step": 9
    },
    {
      "epoch": 0.4745762711864407,
      "grad_norm": 0.10271213203668594,
      "learning_rate": 0.00019415440651830208,
      "loss": 1.4512,
      "step": 10
    },
    {
      "epoch": 0.5220338983050847,
      "grad_norm": 0.07245385646820068,
      "learning_rate": 0.0001923879532511287,
      "loss": 1.4667,
      "step": 11
    },
    {
      "epoch": 0.5694915254237288,
      "grad_norm": 0.06880194693803787,
      "learning_rate": 0.00019039892931234435,
      "loss": 1.534,
      "step": 12
    },
    {
      "epoch": 0.6169491525423729,
      "grad_norm": 0.0787321925163269,
      "learning_rate": 0.0001881921264348355,
      "loss": 1.2502,
      "step": 13
    },
    {
      "epoch": 0.6644067796610169,
      "grad_norm": 0.07283733785152435,
      "learning_rate": 0.00018577286100002723,
      "loss": 1.3162,
      "step": 14
    },
    {
      "epoch": 0.711864406779661,
      "grad_norm": 0.0586356446146965,
      "learning_rate": 0.00018314696123025454,
      "loss": 1.4223,
      "step": 15
    },
    {
      "epoch": 0.7593220338983051,
      "grad_norm": 0.04856429994106293,
      "learning_rate": 0.00018032075314806448,
      "loss": 1.419,
      "step": 16
    },
    {
      "epoch": 0.8067796610169492,
      "grad_norm": 0.03977855294942856,
      "learning_rate": 0.0001773010453362737,
      "loss": 1.3578,
      "step": 17
    },
    {
      "epoch": 0.8542372881355932,
      "grad_norm": 0.03746713697910309,
      "learning_rate": 0.00017409511253549593,
      "loss": 1.3136,
      "step": 18
    },
    {
      "epoch": 0.9016949152542373,
      "grad_norm": 0.03860131651163101,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.3196,
      "step": 19
    },
    {
      "epoch": 0.9491525423728814,
      "grad_norm": 0.03926350176334381,
      "learning_rate": 0.00016715589548470185,
      "loss": 1.3854,
      "step": 20
    },
    {
      "epoch": 0.9966101694915255,
      "grad_norm": 0.03751453012228012,
      "learning_rate": 0.00016343932841636456,
      "loss": 1.3029,
      "step": 21
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.07039777934551239,
      "learning_rate": 0.00015956993044924334,
      "loss": 1.3613,
      "step": 22
    },
    {
      "checkpoint_runtime": 4.3103
    },
    {
      "epoch": 1.047457627118644,
      "grad_norm": 0.03488069400191307,
      "learning_rate": 0.00015555702330196023,
      "loss": 1.4433,
      "step": 23
    },
    {
      "epoch": 1.0949152542372882,
      "grad_norm": 0.03361388295888901,
      "learning_rate": 0.00015141027441932216,
      "loss": 1.3485,
      "step": 24
    },
    {
      "epoch": 1.1423728813559322,
      "grad_norm": 0.031049979850649834,
      "learning_rate": 0.0001471396736825998,
      "loss": 1.2919,
      "step": 25
    },
    {
      "epoch": 1.1898305084745764,
      "grad_norm": 0.030062519013881683,
      "learning_rate": 0.00014275550934302823,
      "loss": 1.2397,
      "step": 26
    },
    {
      "epoch": 1.2372881355932204,
      "grad_norm": 0.028769535943865776,
      "learning_rate": 0.000138268343236509,
      "loss": 1.3418,
      "step": 27
    },
    {
      "epoch": 1.2847457627118644,
      "grad_norm": 0.027847912162542343,
      "learning_rate": 0.000133688985339222,
      "loss": 1.2585,
      "step": 28
    },
    {
      "epoch": 1.3322033898305086,
      "grad_norm": 0.0264479611068964,
      "learning_rate": 0.00012902846772544624,
      "loss": 1.2611,
      "step": 29
    },
    {
      "epoch": 1.3796610169491526,
      "grad_norm": 0.02695614844560623,
      "learning_rate": 0.0001242980179903264,
      "loss": 1.2326,
      "step": 30
    },
    {
      "epoch": 1.4271186440677965,
      "grad_norm": 0.025646759197115898,
      "learning_rate": 0.00011950903220161285,
      "loss": 1.3281,
      "step": 31
    },
    {
      "epoch": 1.4745762711864407,
      "grad_norm": 0.026183350011706352,
      "learning_rate": 0.00011467304744553618,
      "loss": 1.2929,
      "step": 32
    },
    {
      "epoch": 1.5220338983050847,
      "grad_norm": 0.02581079490482807,
      "learning_rate": 0.0001098017140329561,
      "loss": 1.3322,
      "step": 33
    },
    {
      "epoch": 1.5694915254237287,
      "grad_norm": 0.025374768301844597,
      "learning_rate": 0.00010490676743274181,
      "loss": 1.4044,
      "step": 34
    },
    {
      "epoch": 1.616949152542373,
      "grad_norm": 0.02298927679657936,
      "learning_rate": 0.0001,
      "loss": 1.1362,
      "step": 35
    },
    {
      "epoch": 1.664406779661017,
      "grad_norm": 0.023663582280278206,
      "learning_rate": 9.509323256725821e-05,
      "loss": 1.197,
      "step": 36
    },
    {
      "epoch": 1.711864406779661,
      "grad_norm": 0.0226344745606184,
      "learning_rate": 9.019828596704394e-05,
      "loss": 1.3175,
      "step": 37
    },
    {
      "epoch": 1.759322033898305,
      "grad_norm": 0.022588199004530907,
      "learning_rate": 8.532695255446383e-05,
      "loss": 1.3229,
      "step": 38
    },
    {
      "epoch": 1.8067796610169493,
      "grad_norm": 0.021748200058937073,
      "learning_rate": 8.049096779838719e-05,
      "loss": 1.273,
      "step": 39
    },
    {
      "epoch": 1.854237288135593,
      "grad_norm": 0.021934621036052704,
      "learning_rate": 7.570198200967362e-05,
      "loss": 1.2297,
      "step": 40
    },
    {
      "epoch": 1.9016949152542373,
      "grad_norm": 0.022006280720233917,
      "learning_rate": 7.097153227455379e-05,
      "loss": 1.2406,
      "step": 41
    },
    {
      "epoch": 1.9491525423728815,
      "grad_norm": 0.021933482959866524,
      "learning_rate": 6.6311014660778e-05,
      "loss": 1.308,
      "step": 42
    },
    {
      "epoch": 1.9966101694915255,
      "grad_norm": 0.021198999136686325,
      "learning_rate": 6.173165676349103e-05,
      "loss": 1.2292,
      "step": 43
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.05841302499175072,
      "learning_rate": 5.7244490656971815e-05,
      "loss": 1.2705,
      "step": 44
    },
    {
      "checkpoint_runtime": 4.0325
    },
    {
      "epoch": 2.047457627118644,
      "grad_norm": 0.022102631628513336,
      "learning_rate": 5.286032631740023e-05,
      "loss": 1.3759,
      "step": 45
    },
    {
      "epoch": 2.094915254237288,
      "grad_norm": 0.0213454756885767,
      "learning_rate": 4.8589725580677835e-05,
      "loss": 1.2856,
      "step": 46
    },
    {
      "epoch": 2.142372881355932,
      "grad_norm": 0.02086574397981167,
      "learning_rate": 4.444297669803981e-05,
      "loss": 1.2335,
      "step": 47
    },
    {
      "epoch": 2.1898305084745764,
      "grad_norm": 0.020753612741827965,
      "learning_rate": 4.0430069550756665e-05,
      "loss": 1.1841,
      "step": 48
    },
    {
      "epoch": 2.23728813559322,
      "grad_norm": 0.02086016535758972,
      "learning_rate": 3.6560671583635467e-05,
      "loss": 1.2889,
      "step": 49
    },
    {
      "epoch": 2.2847457627118644,
      "grad_norm": 0.02073688432574272,
      "learning_rate": 3.2844104515298155e-05,
      "loss": 1.2107,
      "step": 50
    },
    {
      "epoch": 2.3322033898305086,
      "grad_norm": 0.019877444952726364,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 1.2178,
      "step": 51
    },
    {
      "epoch": 2.3796610169491528,
      "grad_norm": 0.020804161205887794,
      "learning_rate": 2.5904887464504114e-05,
      "loss": 1.19,
      "step": 52
    },
    {
      "epoch": 2.4271186440677965,
      "grad_norm": 0.020287157967686653,
      "learning_rate": 2.26989546637263e-05,
      "loss": 1.2899,
      "step": 53
    },
    {
      "epoch": 2.4745762711864407,
      "grad_norm": 0.021143628284335136,
      "learning_rate": 1.967924685193552e-05,
      "loss": 1.2541,
      "step": 54
    },
    {
      "epoch": 2.522033898305085,
      "grad_norm": 0.021268026903271675,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 1.2969,
      "step": 55
    },
    {
      "epoch": 2.5694915254237287,
      "grad_norm": 0.021998854354023933,
      "learning_rate": 1.42271389999728e-05,
      "loss": 1.3716,
      "step": 56
    },
    {
      "epoch": 2.616949152542373,
      "grad_norm": 0.019691836088895798,
      "learning_rate": 1.1807873565164506e-05,
      "loss": 1.1084,
      "step": 57
    },
    {
      "epoch": 2.664406779661017,
      "grad_norm": 0.020427711308002472,
      "learning_rate": 9.601070687655667e-06,
      "loss": 1.1698,
      "step": 58
    },
    {
      "epoch": 2.711864406779661,
      "grad_norm": 0.020260948687791824,
      "learning_rate": 7.612046748871327e-06,
      "loss": 1.2929,
      "step": 59
    },
    {
      "epoch": 2.759322033898305,
      "grad_norm": 0.02082715928554535,
      "learning_rate": 5.8455934816979305e-06,
      "loss": 1.3,
      "step": 60
    },
    {
      "epoch": 2.8067796610169493,
      "grad_norm": 0.01996796205639839,
      "learning_rate": 4.305966426779118e-06,
      "loss": 1.2527,
      "step": 61
    },
    {
      "epoch": 2.854237288135593,
      "grad_norm": 0.020209863781929016,
      "learning_rate": 2.996874680545603e-06,
      "loss": 1.211,
      "step": 62
    },
    {
      "epoch": 2.9016949152542373,
      "grad_norm": 0.020035937428474426,
      "learning_rate": 1.921471959676957e-06,
      "loss": 1.2242,
      "step": 63
    },
    {
      "epoch": 2.9491525423728815,
      "grad_norm": 0.020211510360240936,
      "learning_rate": 1.0823490035218987e-06,
      "loss": 1.2917,
      "step": 64
    },
    {
      "epoch": 2.9966101694915253,
      "grad_norm": 0.019637765362858772,
      "learning_rate": 4.815273327803182e-07,
      "loss": 1.2152,
      "step": 65
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.05813812464475632,
      "learning_rate": 1.204543794827595e-07,
      "loss": 1.2534,
      "step": 66
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 66,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 22,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.75679606902227e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}