{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.950108459869848,
  "eval_steps": 500,
  "global_step": 84,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03470715835140998,
      "grad_norm": 6.300277096992606,
      "learning_rate": 8.888888888888888e-06,
      "loss": 1.1898,
      "step": 1
    },
    {
      "epoch": 0.06941431670281996,
      "grad_norm": 6.329585685276253,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 1.1873,
      "step": 2
    },
    {
      "epoch": 0.10412147505422993,
      "grad_norm": 2.501481021126002,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.0822,
      "step": 3
    },
    {
      "epoch": 0.13882863340563992,
      "grad_norm": 5.685457142160091,
      "learning_rate": 3.555555555555555e-05,
      "loss": 1.0872,
      "step": 4
    },
    {
      "epoch": 0.1735357917570499,
      "grad_norm": 9.472859854111334,
      "learning_rate": 4.444444444444445e-05,
      "loss": 1.1525,
      "step": 5
    },
    {
      "epoch": 0.20824295010845986,
      "grad_norm": 6.569946608517327,
      "learning_rate": 5.333333333333333e-05,
      "loss": 1.1009,
      "step": 6
    },
    {
      "epoch": 0.24295010845986983,
      "grad_norm": 3.450270474507439,
      "learning_rate": 6.222222222222223e-05,
      "loss": 1.0244,
      "step": 7
    },
    {
      "epoch": 0.27765726681127983,
      "grad_norm": 4.362696170141236,
      "learning_rate": 7.11111111111111e-05,
      "loss": 0.9832,
      "step": 8
    },
    {
      "epoch": 0.3123644251626898,
      "grad_norm": 2.502106333125194,
      "learning_rate": 8e-05,
      "loss": 0.949,
      "step": 9
    },
    {
      "epoch": 0.3470715835140998,
      "grad_norm": 4.093217491327189,
      "learning_rate": 7.996491320395435e-05,
      "loss": 0.9748,
      "step": 10
    },
    {
      "epoch": 0.38177874186550975,
      "grad_norm": 2.5858453011572746,
      "learning_rate": 7.985971436998019e-05,
      "loss": 0.9239,
      "step": 11
    },
    {
      "epoch": 0.4164859002169197,
      "grad_norm": 2.203682105160326,
      "learning_rate": 7.968458805257913e-05,
      "loss": 0.9064,
      "step": 12
    },
    {
      "epoch": 0.4511930585683297,
      "grad_norm": 1.5811510985617325,
      "learning_rate": 7.94398414828202e-05,
      "loss": 0.8827,
      "step": 13
    },
    {
      "epoch": 0.48590021691973967,
      "grad_norm": 2.803169201898971,
      "learning_rate": 7.912590402935223e-05,
      "loss": 0.892,
      "step": 14
    },
    {
      "epoch": 0.5206073752711496,
      "grad_norm": 1.693289513455263,
      "learning_rate": 7.874332644514525e-05,
      "loss": 0.887,
      "step": 15
    },
    {
      "epoch": 0.5553145336225597,
      "grad_norm": 1.086358307999921,
      "learning_rate": 7.829277990128269e-05,
      "loss": 0.8647,
      "step": 16
    },
    {
      "epoch": 0.5900216919739696,
      "grad_norm": 1.9102839923766066,
      "learning_rate": 7.777505480949924e-05,
      "loss": 0.8804,
      "step": 17
    },
    {
      "epoch": 0.6247288503253796,
      "grad_norm": 1.4012123751616394,
      "learning_rate": 7.719105943553007e-05,
      "loss": 0.8601,
      "step": 18
    },
    {
      "epoch": 0.6594360086767896,
      "grad_norm": 3775.810932593552,
      "learning_rate": 7.654181830570404e-05,
      "loss": 8.0147,
      "step": 19
    },
    {
      "epoch": 0.6941431670281996,
      "grad_norm": 597.812195875499,
      "learning_rate": 7.582847040957652e-05,
      "loss": 1.8169,
      "step": 20
    },
    {
      "epoch": 0.7288503253796096,
      "grad_norm": 5.978836278642803,
      "learning_rate": 7.505226720175455e-05,
      "loss": 1.0828,
      "step": 21
    },
    {
      "epoch": 0.7635574837310195,
      "grad_norm": 4.199965410848235,
      "learning_rate": 7.421457040642028e-05,
      "loss": 1.011,
      "step": 22
    },
    {
      "epoch": 0.7982646420824295,
      "grad_norm": 1.7290854744382491,
      "learning_rate": 7.331684962840398e-05,
      "loss": 0.9144,
      "step": 23
    },
    {
      "epoch": 0.8329718004338394,
      "grad_norm": 1.910958548071721,
      "learning_rate": 7.236067977499791e-05,
      "loss": 0.8651,
      "step": 24
    },
    {
      "epoch": 0.8676789587852495,
      "grad_norm": 1.764578753926621,
      "learning_rate": 7.13477382930336e-05,
      "loss": 0.8855,
      "step": 25
    },
    {
      "epoch": 0.9023861171366594,
      "grad_norm": 1.8041505018631134,
      "learning_rate": 7.027980222607026e-05,
      "loss": 0.8672,
      "step": 26
    },
    {
      "epoch": 0.9370932754880694,
      "grad_norm": 1.3191472044863197,
      "learning_rate": 6.915874509685646e-05,
      "loss": 0.8423,
      "step": 27
    },
    {
      "epoch": 0.9718004338394793,
      "grad_norm": 0.9189517507692654,
      "learning_rate": 6.798653362053462e-05,
      "loss": 0.8273,
      "step": 28
    },
    {
      "epoch": 1.0238611713665944,
      "grad_norm": 2.1289244779300835,
      "learning_rate": 6.676522425435433e-05,
      "loss": 1.3774,
      "step": 29
    },
    {
      "epoch": 1.0585683297180044,
      "grad_norm": 25.961017896043277,
      "learning_rate": 6.54969595899476e-05,
      "loss": 0.7943,
      "step": 30
    },
    {
      "epoch": 1.0932754880694142,
      "grad_norm": 1.529851042182263,
      "learning_rate": 6.418396459449501e-05,
      "loss": 0.8102,
      "step": 31
    },
    {
      "epoch": 1.1279826464208242,
      "grad_norm": 8.191973267629333,
      "learning_rate": 6.282854270737728e-05,
      "loss": 0.8152,
      "step": 32
    },
    {
      "epoch": 1.1626898047722343,
      "grad_norm": 1.209748771757014,
      "learning_rate": 6.143307179915987e-05,
      "loss": 0.7962,
      "step": 33
    },
    {
      "epoch": 1.1973969631236443,
      "grad_norm": 0.7840741589903159,
      "learning_rate": 6.000000000000001e-05,
      "loss": 0.7816,
      "step": 34
    },
    {
      "epoch": 1.2321041214750543,
      "grad_norm": 0.9740463452743966,
      "learning_rate": 5.853184140479448e-05,
      "loss": 0.7605,
      "step": 35
    },
    {
      "epoch": 1.2668112798264641,
      "grad_norm": 0.7045833732067921,
      "learning_rate": 5.703117166260291e-05,
      "loss": 0.7669,
      "step": 36
    },
    {
      "epoch": 1.3015184381778742,
      "grad_norm": 0.8969503221689408,
      "learning_rate": 5.5500623458084123e-05,
      "loss": 0.7662,
      "step": 37
    },
    {
      "epoch": 1.3362255965292842,
      "grad_norm": 0.6025365616410666,
      "learning_rate": 5.394288189287261e-05,
      "loss": 0.7564,
      "step": 38
    },
    {
      "epoch": 1.3709327548806942,
      "grad_norm": 0.7688283335699936,
      "learning_rate": 5.23606797749979e-05,
      "loss": 0.7631,
      "step": 39
    },
    {
      "epoch": 1.405639913232104,
      "grad_norm": 0.48261395895365083,
      "learning_rate": 5.075679282461063e-05,
      "loss": 0.7557,
      "step": 40
    },
    {
      "epoch": 1.440347071583514,
      "grad_norm": 0.5414576203146455,
      "learning_rate": 4.9134034804426235e-05,
      "loss": 0.741,
      "step": 41
    },
    {
      "epoch": 1.475054229934924,
      "grad_norm": 0.4233507247912478,
      "learning_rate": 4.7495252583429e-05,
      "loss": 0.7463,
      "step": 42
    },
    {
      "epoch": 1.509761388286334,
      "grad_norm": 0.37870693147142465,
      "learning_rate": 4.5843321142496474e-05,
      "loss": 0.7457,
      "step": 43
    },
    {
      "epoch": 1.5444685466377441,
      "grad_norm": 0.4059373324038044,
      "learning_rate": 4.418113853070614e-05,
      "loss": 0.7411,
      "step": 44
    },
    {
      "epoch": 1.579175704989154,
      "grad_norm": 0.33414673476249707,
      "learning_rate": 4.251162078117254e-05,
      "loss": 0.7298,
      "step": 45
    },
    {
      "epoch": 1.613882863340564,
      "grad_norm": 0.3398435439622563,
      "learning_rate": 4.0837696795334284e-05,
      "loss": 0.7371,
      "step": 46
    },
    {
      "epoch": 1.648590021691974,
      "grad_norm": 0.37740119571438335,
      "learning_rate": 3.916230320466573e-05,
      "loss": 0.7303,
      "step": 47
    },
    {
      "epoch": 1.6832971800433838,
      "grad_norm": 0.3247066964457289,
      "learning_rate": 3.7488379218827466e-05,
      "loss": 0.7386,
      "step": 48
    },
    {
      "epoch": 1.718004338394794,
      "grad_norm": 0.3379048377668955,
      "learning_rate": 3.581886146929387e-05,
      "loss": 0.7259,
      "step": 49
    },
    {
      "epoch": 1.7527114967462039,
      "grad_norm": 0.3181669649842156,
      "learning_rate": 3.415667885750354e-05,
      "loss": 0.7209,
      "step": 50
    },
    {
      "epoch": 1.7874186550976139,
      "grad_norm": 0.32411152865418363,
      "learning_rate": 3.250474741657101e-05,
      "loss": 0.7251,
      "step": 51
    },
    {
      "epoch": 1.822125813449024,
      "grad_norm": 0.23388485665108716,
      "learning_rate": 3.086596519557377e-05,
      "loss": 0.723,
      "step": 52
    },
    {
      "epoch": 1.8568329718004337,
      "grad_norm": 0.3048906277879464,
      "learning_rate": 2.9243207175389377e-05,
      "loss": 0.7245,
      "step": 53
    },
    {
      "epoch": 1.891540130151844,
      "grad_norm": 0.21182971362551556,
      "learning_rate": 2.7639320225002108e-05,
      "loss": 0.7262,
      "step": 54
    },
    {
      "epoch": 1.9262472885032538,
      "grad_norm": 0.25916446139863025,
      "learning_rate": 2.6057118107127402e-05,
      "loss": 0.7228,
      "step": 55
    },
    {
      "epoch": 1.9609544468546638,
      "grad_norm": 0.17974296947054186,
      "learning_rate": 2.4499376541915883e-05,
      "loss": 0.7208,
      "step": 56
    },
    {
      "epoch": 2.013015184381779,
      "grad_norm": 0.36891336506559885,
      "learning_rate": 2.2968828337397095e-05,
      "loss": 1.1849,
      "step": 57
    },
    {
      "epoch": 2.0477223427331888,
      "grad_norm": 0.220956290587299,
      "learning_rate": 2.1468158595205543e-05,
      "loss": 0.6845,
      "step": 58
    },
    {
      "epoch": 2.0824295010845986,
      "grad_norm": 0.19743211488551957,
      "learning_rate": 2.0000000000000012e-05,
      "loss": 0.681,
      "step": 59
    },
    {
      "epoch": 2.117136659436009,
      "grad_norm": 0.22014276891240445,
      "learning_rate": 1.8566928200840128e-05,
      "loss": 0.6803,
      "step": 60
    },
    {
      "epoch": 2.1518438177874186,
      "grad_norm": 0.24004715720654304,
      "learning_rate": 1.7171457292622736e-05,
      "loss": 0.6756,
      "step": 61
    },
    {
      "epoch": 2.1865509761388284,
      "grad_norm": 0.16300098008860384,
      "learning_rate": 1.5816035405505007e-05,
      "loss": 0.6713,
      "step": 62
    },
    {
      "epoch": 2.2212581344902387,
      "grad_norm": 0.2029252686694922,
      "learning_rate": 1.4503040410052412e-05,
      "loss": 0.6778,
      "step": 63
    },
    {
      "epoch": 2.2559652928416485,
      "grad_norm": 0.16175699949865352,
      "learning_rate": 1.3234775745645684e-05,
      "loss": 0.6733,
      "step": 64
    },
    {
      "epoch": 2.2906724511930587,
      "grad_norm": 0.15518204077737663,
      "learning_rate": 1.201346637946538e-05,
      "loss": 0.673,
      "step": 65
    },
    {
      "epoch": 2.3253796095444685,
      "grad_norm": 0.15484153932844605,
      "learning_rate": 1.0841254903143547e-05,
      "loss": 0.6758,
      "step": 66
    },
    {
      "epoch": 2.3600867678958783,
      "grad_norm": 0.1425511720931603,
      "learning_rate": 9.720197773929749e-06,
      "loss": 0.6708,
      "step": 67
    },
    {
      "epoch": 2.3947939262472886,
      "grad_norm": 0.1315080719342115,
      "learning_rate": 8.652261706966412e-06,
      "loss": 0.6694,
      "step": 68
    },
    {
      "epoch": 2.4295010845986984,
      "grad_norm": 0.13003673674800192,
      "learning_rate": 7.639320225002106e-06,
      "loss": 0.6749,
      "step": 69
    },
    {
      "epoch": 2.4642082429501087,
      "grad_norm": 0.12937383195418148,
      "learning_rate": 6.6831503715960235e-06,
      "loss": 0.6752,
      "step": 70
    },
    {
      "epoch": 2.4989154013015185,
      "grad_norm": 0.12141271020145257,
      "learning_rate": 5.785429593579736e-06,
      "loss": 0.6781,
      "step": 71
    },
    {
      "epoch": 2.5336225596529283,
      "grad_norm": 0.11519870379159697,
      "learning_rate": 4.947732798245466e-06,
      "loss": 0.6716,
      "step": 72
    },
    {
      "epoch": 2.5683297180043385,
      "grad_norm": 0.11773898061730143,
      "learning_rate": 4.171529590423484e-06,
      "loss": 0.6779,
      "step": 73
    },
    {
      "epoch": 2.6030368763557483,
      "grad_norm": 0.10608208259960443,
      "learning_rate": 3.458181694295961e-06,
      "loss": 0.6805,
      "step": 74
    },
    {
      "epoch": 2.6377440347071586,
      "grad_norm": 0.10236639050094021,
      "learning_rate": 2.8089405644699463e-06,
      "loss": 0.6719,
      "step": 75
    },
    {
      "epoch": 2.6724511930585684,
      "grad_norm": 0.10603330100678318,
      "learning_rate": 2.2249451905007603e-06,
      "loss": 0.675,
      "step": 76
    },
    {
      "epoch": 2.707158351409978,
      "grad_norm": 0.09832873419536761,
      "learning_rate": 1.7072200987173105e-06,
      "loss": 0.6767,
      "step": 77
    },
    {
      "epoch": 2.7418655097613884,
      "grad_norm": 0.0983832265038647,
      "learning_rate": 1.256673554854757e-06,
      "loss": 0.6633,
      "step": 78
    },
    {
      "epoch": 2.7765726681127982,
      "grad_norm": 0.10299057334518875,
      "learning_rate": 8.740959706477725e-07,
      "loss": 0.6672,
      "step": 79
    },
    {
      "epoch": 2.811279826464208,
      "grad_norm": 0.09743605608109047,
      "learning_rate": 5.601585171798052e-07,
      "loss": 0.6708,
      "step": 80
    },
    {
      "epoch": 2.8459869848156183,
      "grad_norm": 0.10075730943046303,
      "learning_rate": 3.154119474208894e-07,
      "loss": 0.6748,
      "step": 81
    },
    {
      "epoch": 2.880694143167028,
      "grad_norm": 0.09556334296668786,
      "learning_rate": 1.402856300198252e-07,
      "loss": 0.6686,
      "step": 82
    },
    {
      "epoch": 2.915401301518438,
      "grad_norm": 0.09223259109939756,
      "learning_rate": 3.5086796045664674e-08,
      "loss": 0.662,
      "step": 83
    },
    {
      "epoch": 2.950108459869848,
      "grad_norm": 0.09460606099922247,
      "learning_rate": 0.0,
      "loss": 0.673,
      "step": 84
    },
    {
      "epoch": 2.950108459869848,
      "step": 84,
      "total_flos": 2.1615691655827948e+18,
      "train_loss": 0.9045009151810691,
      "train_runtime": 13253.2478,
      "train_samples_per_second": 3.337,
      "train_steps_per_second": 0.006
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 84,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.1615691655827948e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}