{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7339750153594102,
  "eval_steps": 1,
  "global_step": 70,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010485357362277289,
      "grad_norm": 498.0,
      "learning_rate": 0.0,
      "loss": 1.6033425331115723,
      "step": 1
    },
    {
      "epoch": 0.020970714724554577,
      "grad_norm": 139.0,
      "learning_rate": 4e-08,
      "loss": 1.5843058824539185,
      "step": 2
    },
    {
      "epoch": 0.03145607208683186,
      "grad_norm": 158.0,
      "learning_rate": 8e-08,
      "loss": 1.624650239944458,
      "step": 3
    },
    {
      "epoch": 0.041941429449109155,
      "grad_norm": 201.0,
      "learning_rate": 1.2000000000000002e-07,
      "loss": 1.5930713415145874,
      "step": 4
    },
    {
      "epoch": 0.05242678681138644,
      "grad_norm": 1392.0,
      "learning_rate": 1.6e-07,
      "loss": 1.6284583806991577,
      "step": 5
    },
    {
      "epoch": 0.06291214417366373,
      "grad_norm": 644.0,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 1.5755040645599365,
      "step": 6
    },
    {
      "epoch": 0.07339750153594102,
      "grad_norm": 358.0,
      "learning_rate": 2.4000000000000003e-07,
      "loss": 1.5862637758255005,
      "step": 7
    },
    {
      "epoch": 0.08388285889821831,
      "grad_norm": 1012.0,
      "learning_rate": 2.8e-07,
      "loss": 1.6306817531585693,
      "step": 8
    },
    {
      "epoch": 0.0943682162604956,
      "grad_norm": 187.0,
      "learning_rate": 3.2e-07,
      "loss": 1.5844253301620483,
      "step": 9
    },
    {
      "epoch": 0.10485357362277288,
      "grad_norm": 342.0,
      "learning_rate": 3.6e-07,
      "loss": 1.5895334482192993,
      "step": 10
    },
    {
      "epoch": 0.11533893098505017,
      "grad_norm": 816.0,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 1.5861637592315674,
      "step": 11
    },
    {
      "epoch": 0.12582428834732745,
      "grad_norm": 260.0,
      "learning_rate": 4.4e-07,
      "loss": 1.57806396484375,
      "step": 12
    },
    {
      "epoch": 0.13630964570960474,
      "grad_norm": 326.0,
      "learning_rate": 4.800000000000001e-07,
      "loss": 1.5836868286132812,
      "step": 13
    },
    {
      "epoch": 0.14679500307188204,
      "grad_norm": 668.0,
      "learning_rate": 5.2e-07,
      "loss": 1.5597259998321533,
      "step": 14
    },
    {
      "epoch": 0.15728036043415933,
      "grad_norm": 256.0,
      "learning_rate": 5.6e-07,
      "loss": 1.5852601528167725,
      "step": 15
    },
    {
      "epoch": 0.16776571779643662,
      "grad_norm": 205.0,
      "learning_rate": 6.000000000000001e-07,
      "loss": 1.5899027585983276,
      "step": 16
    },
    {
      "epoch": 0.1782510751587139,
      "grad_norm": 188.0,
      "learning_rate": 6.4e-07,
      "loss": 1.5692049264907837,
      "step": 17
    },
    {
      "epoch": 0.1887364325209912,
      "grad_norm": 426.0,
      "learning_rate": 6.800000000000001e-07,
      "loss": 1.55263090133667,
      "step": 18
    },
    {
      "epoch": 0.1992217898832685,
      "grad_norm": 245.0,
      "learning_rate": 7.2e-07,
      "loss": 1.5602704286575317,
      "step": 19
    },
    {
      "epoch": 0.20970714724554576,
      "grad_norm": 158.0,
      "learning_rate": 7.6e-07,
      "loss": 1.5857173204421997,
      "step": 20
    },
    {
      "epoch": 0.22019250460782305,
      "grad_norm": 90.0,
      "learning_rate": 8.000000000000001e-07,
      "loss": 1.5650298595428467,
      "step": 21
    },
    {
      "epoch": 0.23067786197010035,
      "grad_norm": 148.0,
      "learning_rate": 8.400000000000001e-07,
      "loss": 1.548302173614502,
      "step": 22
    },
    {
      "epoch": 0.24116321933237764,
      "grad_norm": 187.0,
      "learning_rate": 8.8e-07,
      "loss": 1.5342053174972534,
      "step": 23
    },
    {
      "epoch": 0.2516485766946549,
      "grad_norm": 282.0,
      "learning_rate": 9.200000000000001e-07,
      "loss": 1.5395140647888184,
      "step": 24
    },
    {
      "epoch": 0.2621339340569322,
      "grad_norm": 212.0,
      "learning_rate": 9.600000000000001e-07,
      "loss": 1.5411065816879272,
      "step": 25
    },
    {
      "epoch": 0.2726192914192095,
      "grad_norm": 1640.0,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.520958423614502,
      "step": 26
    },
    {
      "epoch": 0.2831046487814868,
      "grad_norm": 161.0,
      "learning_rate": 1.04e-06,
      "loss": 1.516421914100647,
      "step": 27
    },
    {
      "epoch": 0.29359000614376407,
      "grad_norm": 175.0,
      "learning_rate": 1.08e-06,
      "loss": 1.492469310760498,
      "step": 28
    },
    {
      "epoch": 0.30407536350604136,
      "grad_norm": 115.0,
      "learning_rate": 1.12e-06,
      "loss": 1.5238401889801025,
      "step": 29
    },
    {
      "epoch": 0.31456072086831866,
      "grad_norm": 96.5,
      "learning_rate": 1.1600000000000001e-06,
      "loss": 1.4782272577285767,
      "step": 30
    },
    {
      "epoch": 0.32504607823059595,
      "grad_norm": 197.0,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.4808753728866577,
      "step": 31
    },
    {
      "epoch": 0.33553143559287324,
      "grad_norm": 125.0,
      "learning_rate": 1.2400000000000002e-06,
      "loss": 1.4171360731124878,
      "step": 32
    },
    {
      "epoch": 0.34601679295515053,
      "grad_norm": 580.0,
      "learning_rate": 1.28e-06,
      "loss": 1.4474064111709595,
      "step": 33
    },
    {
      "epoch": 0.3565021503174278,
      "grad_norm": 83.5,
      "learning_rate": 1.32e-06,
      "loss": 1.4120572805404663,
      "step": 34
    },
    {
      "epoch": 0.3669875076797051,
      "grad_norm": 201.0,
      "learning_rate": 1.3600000000000001e-06,
      "loss": 1.4311250448226929,
      "step": 35
    },
    {
      "epoch": 0.3774728650419824,
      "grad_norm": 121.0,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 1.4023066759109497,
      "step": 36
    },
    {
      "epoch": 0.3879582224042597,
      "grad_norm": 51.25,
      "learning_rate": 1.44e-06,
      "loss": 1.3962011337280273,
      "step": 37
    },
    {
      "epoch": 0.398443579766537,
      "grad_norm": 67.0,
      "learning_rate": 1.48e-06,
      "loss": 1.409425139427185,
      "step": 38
    },
    {
      "epoch": 0.40892893712881423,
      "grad_norm": 60.5,
      "learning_rate": 1.52e-06,
      "loss": 1.3721140623092651,
      "step": 39
    },
    {
      "epoch": 0.4194142944910915,
      "grad_norm": 58.5,
      "learning_rate": 1.56e-06,
      "loss": 1.375535011291504,
      "step": 40
    },
    {
      "epoch": 0.4298996518533688,
      "grad_norm": 144.0,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 1.3638286590576172,
      "step": 41
    },
    {
      "epoch": 0.4403850092156461,
      "grad_norm": 348.0,
      "learning_rate": 1.6400000000000002e-06,
      "loss": 1.3767451047897339,
      "step": 42
    },
    {
      "epoch": 0.4508703665779234,
      "grad_norm": 102.0,
      "learning_rate": 1.6800000000000002e-06,
      "loss": 1.3871445655822754,
      "step": 43
    },
    {
      "epoch": 0.4613557239402007,
      "grad_norm": 83.5,
      "learning_rate": 1.72e-06,
      "loss": 1.3462551832199097,
      "step": 44
    },
    {
      "epoch": 0.471841081302478,
      "grad_norm": 75.0,
      "learning_rate": 1.76e-06,
      "loss": 1.3668186664581299,
      "step": 45
    },
    {
      "epoch": 0.4823264386647553,
      "grad_norm": 51.75,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 1.3438992500305176,
      "step": 46
    },
    {
      "epoch": 0.49281179602703257,
      "grad_norm": 64.0,
      "learning_rate": 1.8400000000000002e-06,
      "loss": 1.3390253782272339,
      "step": 47
    },
    {
      "epoch": 0.5032971533893098,
      "grad_norm": 45.5,
      "learning_rate": 1.8800000000000002e-06,
      "loss": 1.365052580833435,
      "step": 48
    },
    {
      "epoch": 0.5137825107515871,
      "grad_norm": 66.0,
      "learning_rate": 1.9200000000000003e-06,
      "loss": 1.3313298225402832,
      "step": 49
    },
    {
      "epoch": 0.5242678681138644,
      "grad_norm": 50.25,
      "learning_rate": 1.9600000000000003e-06,
      "loss": 1.335034966468811,
      "step": 50
    },
    {
      "epoch": 0.5347532254761417,
      "grad_norm": 155.0,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.3607136011123657,
      "step": 51
    },
    {
      "epoch": 0.545238582838419,
      "grad_norm": 56.0,
      "learning_rate": 2.04e-06,
      "loss": 1.3396861553192139,
      "step": 52
    },
    {
      "epoch": 0.5557239402006963,
      "grad_norm": 74.0,
      "learning_rate": 2.08e-06,
      "loss": 1.3398594856262207,
      "step": 53
    },
    {
      "epoch": 0.5662092975629736,
      "grad_norm": 46.0,
      "learning_rate": 2.12e-06,
      "loss": 1.3325151205062866,
      "step": 54
    },
    {
      "epoch": 0.5766946549252508,
      "grad_norm": 66.0,
      "learning_rate": 2.16e-06,
      "loss": 1.306301236152649,
      "step": 55
    },
    {
      "epoch": 0.5871800122875281,
      "grad_norm": 35.75,
      "learning_rate": 2.2e-06,
      "loss": 1.324842929840088,
      "step": 56
    },
    {
      "epoch": 0.5976653696498054,
      "grad_norm": 25.875,
      "learning_rate": 2.24e-06,
      "loss": 1.2961994409561157,
      "step": 57
    },
    {
      "epoch": 0.6081507270120827,
      "grad_norm": 198.0,
      "learning_rate": 2.28e-06,
      "loss": 1.2753080129623413,
      "step": 58
    },
    {
      "epoch": 0.61863608437436,
      "grad_norm": 173.0,
      "learning_rate": 2.3200000000000002e-06,
      "loss": 1.3008363246917725,
      "step": 59
    },
    {
      "epoch": 0.6291214417366373,
      "grad_norm": 109.5,
      "learning_rate": 2.3600000000000003e-06,
      "loss": 1.2845975160598755,
      "step": 60
    },
    {
      "epoch": 0.6396067990989146,
      "grad_norm": 35.5,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.253173589706421,
      "step": 61
    },
    {
      "epoch": 0.6500921564611919,
      "grad_norm": 41.0,
      "learning_rate": 2.4400000000000004e-06,
      "loss": 1.2949249744415283,
      "step": 62
    },
    {
      "epoch": 0.6605775138234692,
      "grad_norm": 36.5,
      "learning_rate": 2.4800000000000004e-06,
      "loss": 1.268322229385376,
      "step": 63
    },
    {
      "epoch": 0.6710628711857465,
      "grad_norm": 57.0,
      "learning_rate": 2.52e-06,
      "loss": 1.2876548767089844,
      "step": 64
    },
    {
      "epoch": 0.6815482285480238,
      "grad_norm": 75.0,
      "learning_rate": 2.56e-06,
      "loss": 1.2799946069717407,
      "step": 65
    },
    {
      "epoch": 0.6920335859103011,
      "grad_norm": 26.125,
      "learning_rate": 2.6e-06,
      "loss": 1.2793971300125122,
      "step": 66
    },
    {
      "epoch": 0.7025189432725784,
      "grad_norm": 28.625,
      "learning_rate": 2.64e-06,
      "loss": 1.2701070308685303,
      "step": 67
    },
    {
      "epoch": 0.7130043006348556,
      "grad_norm": 115.0,
      "learning_rate": 2.68e-06,
      "loss": 1.260026216506958,
      "step": 68
    },
    {
      "epoch": 0.7234896579971329,
      "grad_norm": 24.75,
      "learning_rate": 2.7200000000000002e-06,
      "loss": 1.2556943893432617,
      "step": 69
    },
    {
      "epoch": 0.7339750153594102,
      "grad_norm": 56.75,
      "learning_rate": 2.7600000000000003e-06,
      "loss": 1.2900102138519287,
      "step": 70
    }
  ],
  "logging_steps": 1,
  "max_steps": 96,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.9208453609724314e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}