{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 12.192307692307692,
  "eval_steps": 500,
  "global_step": 78,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 4.947939872741699,
      "learning_rate": 2e-05,
      "loss": 2.7425,
      "step": 1
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 5.395760536193848,
      "learning_rate": 4e-05,
      "loss": 3.0917,
      "step": 2
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 4.972382068634033,
      "learning_rate": 6e-05,
      "loss": 2.5889,
      "step": 3
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 4.1436309814453125,
      "learning_rate": 8e-05,
      "loss": 2.6749,
      "step": 4
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 3.4529764652252197,
      "learning_rate": 0.0001,
      "loss": 3.0256,
      "step": 5
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 3.0711050033569336,
      "learning_rate": 0.00012,
      "loss": 2.5193,
      "step": 6
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 6.622050762176514,
      "learning_rate": 0.00014,
      "loss": 3.7169,
      "step": 7
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 1.689590334892273,
      "learning_rate": 0.00016,
      "loss": 1.8293,
      "step": 8
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 1.1921875476837158,
      "learning_rate": 0.00018,
      "loss": 2.1506,
      "step": 9
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 1.3741947412490845,
      "learning_rate": 0.0002,
      "loss": 1.7855,
      "step": 10
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 1.1680189371109009,
      "learning_rate": 0.00019990989662046818,
      "loss": 1.8602,
      "step": 11
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 2.420065402984619,
      "learning_rate": 0.00019963974885425266,
      "loss": 1.6481,
      "step": 12
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.954460144042969,
      "learning_rate": 0.00019919004352588767,
      "loss": 2.3852,
      "step": 13
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 1.9217047691345215,
      "learning_rate": 0.00019856159103477086,
      "loss": 1.3094,
      "step": 14
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 2.4744794368743896,
      "learning_rate": 0.00019775552389476864,
      "loss": 1.4755,
      "step": 15
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 1.807592511177063,
      "learning_rate": 0.0001967732946933499,
      "loss": 1.2384,
      "step": 16
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 1.5733166933059692,
      "learning_rate": 0.00019561667347392508,
      "loss": 1.36,
      "step": 17
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 0.5816245079040527,
      "learning_rate": 0.00019428774454610843,
      "loss": 1.1345,
      "step": 18
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.3857601583003998,
      "learning_rate": 0.00019278890272965096,
      "loss": 1.0873,
      "step": 19
    },
    {
      "epoch": 3.1153846153846154,
      "grad_norm": 1.011568307876587,
      "learning_rate": 0.0001911228490388136,
      "loss": 1.8665,
      "step": 20
    },
    {
      "epoch": 3.269230769230769,
      "grad_norm": 2.7151846885681152,
      "learning_rate": 0.00018929258581495685,
      "loss": 0.8705,
      "step": 21
    },
    {
      "epoch": 3.423076923076923,
      "grad_norm": 0.3418419361114502,
      "learning_rate": 0.00018730141131611882,
      "loss": 0.6694,
      "step": 22
    },
    {
      "epoch": 3.5769230769230766,
      "grad_norm": 0.581399142742157,
      "learning_rate": 0.00018515291377333112,
      "loss": 1.1754,
      "step": 23
    },
    {
      "epoch": 3.730769230769231,
      "grad_norm": 0.3654610514640808,
      "learning_rate": 0.00018285096492438424,
      "loss": 0.6974,
      "step": 24
    },
    {
      "epoch": 3.8846153846153846,
      "grad_norm": 0.3354414701461792,
      "learning_rate": 0.00018039971303669407,
      "loss": 0.7878,
      "step": 25
    },
    {
      "epoch": 4.076923076923077,
      "grad_norm": 1.0409477949142456,
      "learning_rate": 0.00017780357543184397,
      "loss": 1.7312,
      "step": 26
    },
    {
      "epoch": 4.230769230769231,
      "grad_norm": 0.2807375192642212,
      "learning_rate": 0.00017506723052527242,
      "loss": 0.6799,
      "step": 27
    },
    {
      "epoch": 4.384615384615385,
      "grad_norm": 0.3576838970184326,
      "learning_rate": 0.00017219560939545246,
      "loss": 0.8706,
      "step": 28
    },
    {
      "epoch": 4.538461538461538,
      "grad_norm": 0.28981831669807434,
      "learning_rate": 0.00016919388689775464,
      "loss": 0.7189,
      "step": 29
    },
    {
      "epoch": 4.6923076923076925,
      "grad_norm": 0.258354514837265,
      "learning_rate": 0.00016606747233900815,
      "loss": 0.6547,
      "step": 30
    },
    {
      "epoch": 4.846153846153846,
      "grad_norm": 0.5264655351638794,
      "learning_rate": 0.00016282199972956425,
      "loss": 0.7603,
      "step": 31
    },
    {
      "epoch": 5.038461538461538,
      "grad_norm": 0.6122850179672241,
      "learning_rate": 0.00015946331763042867,
      "loss": 1.2304,
      "step": 32
    },
    {
      "epoch": 5.1923076923076925,
      "grad_norm": 0.32399341464042664,
      "learning_rate": 0.00015599747861375955,
      "loss": 0.5769,
      "step": 33
    },
    {
      "epoch": 5.346153846153846,
      "grad_norm": 0.36697638034820557,
      "learning_rate": 0.00015243072835572318,
      "loss": 0.5996,
      "step": 34
    },
    {
      "epoch": 5.5,
      "grad_norm": 0.2546577751636505,
      "learning_rate": 0.00014876949438136347,
      "loss": 0.6029,
      "step": 35
    },
    {
      "epoch": 5.653846153846154,
      "grad_norm": 0.275869756937027,
      "learning_rate": 0.00014502037448176734,
      "loss": 0.7286,
      "step": 36
    },
    {
      "epoch": 5.8076923076923075,
      "grad_norm": 0.2754996418952942,
      "learning_rate": 0.0001411901248243993,
      "loss": 0.5506,
      "step": 37
    },
    {
      "epoch": 5.961538461538462,
      "grad_norm": 0.4771808683872223,
      "learning_rate": 0.00013728564777803088,
      "loss": 0.868,
      "step": 38
    },
    {
      "epoch": 6.153846153846154,
      "grad_norm": 0.29702961444854736,
      "learning_rate": 0.00013331397947420576,
      "loss": 0.5534,
      "step": 39
    },
    {
      "epoch": 6.3076923076923075,
      "grad_norm": 0.24644634127616882,
      "learning_rate": 0.00012928227712765504,
      "loss": 0.5194,
      "step": 40
    },
    {
      "epoch": 6.461538461538462,
      "grad_norm": 0.2727232277393341,
      "learning_rate": 0.00012519780613851254,
      "loss": 0.373,
      "step": 41
    },
    {
      "epoch": 6.615384615384615,
      "grad_norm": 0.22836743295192719,
      "learning_rate": 0.00012106792699957263,
      "loss": 0.4847,
      "step": 42
    },
    {
      "epoch": 6.769230769230769,
      "grad_norm": 0.2520367205142975,
      "learning_rate": 0.00011690008203218493,
      "loss": 0.4785,
      "step": 43
    },
    {
      "epoch": 6.923076923076923,
      "grad_norm": 0.2718031406402588,
      "learning_rate": 0.00011270178197468789,
      "loss": 0.5619,
      "step": 44
    },
    {
      "epoch": 7.076923076923077,
      "grad_norm": 0.3759967088699341,
      "learning_rate": 0.00010848059244755093,
      "loss": 0.6291,
      "step": 45
    },
    {
      "epoch": 7.230769230769231,
      "grad_norm": 0.20126377046108246,
      "learning_rate": 0.00010424412031961484,
      "loss": 0.3597,
      "step": 46
    },
    {
      "epoch": 7.384615384615385,
      "grad_norm": 0.2589998245239258,
      "learning_rate": 0.0001,
      "loss": 0.467,
      "step": 47
    },
    {
      "epoch": 7.538461538461538,
      "grad_norm": 0.2349349856376648,
      "learning_rate": 9.57558796803852e-05,
      "loss": 0.4365,
      "step": 48
    },
    {
      "epoch": 7.6923076923076925,
      "grad_norm": 0.22222279012203217,
      "learning_rate": 9.151940755244912e-05,
      "loss": 0.3549,
      "step": 49
    },
    {
      "epoch": 7.846153846153846,
      "grad_norm": 0.222075954079628,
      "learning_rate": 8.729821802531212e-05,
      "loss": 0.3699,
      "step": 50
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.3602772653102875,
      "learning_rate": 8.309991796781511e-05,
      "loss": 0.5873,
      "step": 51
    },
    {
      "epoch": 8.153846153846153,
      "grad_norm": 0.22580599784851074,
      "learning_rate": 7.89320730004274e-05,
      "loss": 0.3826,
      "step": 52
    },
    {
      "epoch": 8.307692307692308,
      "grad_norm": 0.25292614102363586,
      "learning_rate": 7.48021938614875e-05,
      "loss": 0.3367,
      "step": 53
    },
    {
      "epoch": 8.461538461538462,
      "grad_norm": 0.24913984537124634,
      "learning_rate": 7.071772287234497e-05,
      "loss": 0.3329,
      "step": 54
    },
    {
      "epoch": 8.615384615384615,
      "grad_norm": 0.217300683259964,
      "learning_rate": 6.668602052579424e-05,
      "loss": 0.3753,
      "step": 55
    },
    {
      "epoch": 8.76923076923077,
      "grad_norm": 0.20688268542289734,
      "learning_rate": 6.271435222196916e-05,
      "loss": 0.3123,
      "step": 56
    },
    {
      "epoch": 8.923076923076923,
      "grad_norm": 0.2173534780740738,
      "learning_rate": 5.880987517560075e-05,
      "loss": 0.2578,
      "step": 57
    },
    {
      "epoch": 9.076923076923077,
      "grad_norm": 0.5606672167778015,
      "learning_rate": 5.497962551823266e-05,
      "loss": 0.5143,
      "step": 58
    },
    {
      "epoch": 9.23076923076923,
      "grad_norm": 0.1941177397966385,
      "learning_rate": 5.123050561863657e-05,
      "loss": 0.2446,
      "step": 59
    },
    {
      "epoch": 9.384615384615385,
      "grad_norm": 0.21033766865730286,
      "learning_rate": 4.756927164427685e-05,
      "loss": 0.313,
      "step": 60
    },
    {
      "epoch": 9.538461538461538,
      "grad_norm": 0.24171344935894012,
      "learning_rate": 4.4002521386240466e-05,
      "loss": 0.3002,
      "step": 61
    },
    {
      "epoch": 9.692307692307692,
      "grad_norm": 0.19194771349430084,
      "learning_rate": 4.053668236957134e-05,
      "loss": 0.2588,
      "step": 62
    },
    {
      "epoch": 9.846153846153847,
      "grad_norm": 0.22882544994354248,
      "learning_rate": 3.717800027043576e-05,
      "loss": 0.2999,
      "step": 63
    },
    {
      "epoch": 10.038461538461538,
      "grad_norm": 0.5228483080863953,
      "learning_rate": 3.393252766099187e-05,
      "loss": 0.5175,
      "step": 64
    },
    {
      "epoch": 10.192307692307692,
      "grad_norm": 0.188337504863739,
      "learning_rate": 3.080611310224539e-05,
      "loss": 0.2212,
      "step": 65
    },
    {
      "epoch": 10.346153846153847,
      "grad_norm": 0.22668048739433289,
      "learning_rate": 2.7804390604547557e-05,
      "loss": 0.2561,
      "step": 66
    },
    {
      "epoch": 10.5,
      "grad_norm": 0.2146831899881363,
      "learning_rate": 2.493276947472756e-05,
      "loss": 0.259,
      "step": 67
    },
    {
      "epoch": 10.653846153846153,
      "grad_norm": 0.20940867066383362,
      "learning_rate": 2.2196424568156073e-05,
      "loss": 0.2535,
      "step": 68
    },
    {
      "epoch": 10.807692307692308,
      "grad_norm": 0.19297531247138977,
      "learning_rate": 1.9600286963305957e-05,
      "loss": 0.2409,
      "step": 69
    },
    {
      "epoch": 10.961538461538462,
      "grad_norm": 0.4436163604259491,
      "learning_rate": 1.7149035075615794e-05,
      "loss": 0.4615,
      "step": 70
    },
    {
      "epoch": 11.115384615384615,
      "grad_norm": 0.2383939027786255,
      "learning_rate": 1.4847086226668872e-05,
      "loss": 0.2431,
      "step": 71
    },
    {
      "epoch": 11.26923076923077,
      "grad_norm": 0.2192695140838623,
      "learning_rate": 1.2698588683881186e-05,
      "loss": 0.2613,
      "step": 72
    },
    {
      "epoch": 11.423076923076923,
      "grad_norm": 0.19706690311431885,
      "learning_rate": 1.0707414185043163e-05,
      "loss": 0.2265,
      "step": 73
    },
    {
      "epoch": 11.576923076923077,
      "grad_norm": 0.2416417896747589,
      "learning_rate": 8.87715096118642e-06,
      "loss": 0.2464,
      "step": 74
    },
    {
      "epoch": 11.73076923076923,
      "grad_norm": 0.18953856825828552,
      "learning_rate": 7.211097270349066e-06,
      "loss": 0.1902,
      "step": 75
    },
    {
      "epoch": 11.884615384615385,
      "grad_norm": 0.24142511188983917,
      "learning_rate": 5.71225545389158e-06,
      "loss": 0.2684,
      "step": 76
    },
    {
      "epoch": 12.038461538461538,
      "grad_norm": 0.38491952419281006,
      "learning_rate": 4.383326526074916e-06,
      "loss": 0.417,
      "step": 77
    },
    {
      "epoch": 12.192307692307692,
      "grad_norm": 0.22990219295024872,
      "learning_rate": 3.226705306650113e-06,
      "loss": 0.273,
      "step": 78
    }
  ],
  "logging_steps": 1,
  "max_steps": 84,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 14,
  "save_steps": 6,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 160914305187840.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}