{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 87,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 2.067296788002129,
      "learning_rate": 0.0,
      "loss": 0.866,
      "step": 1
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 2.290485750060095,
      "learning_rate": 7.142857142857143e-06,
      "loss": 1.043,
      "step": 2
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 1.8761831403153433,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.9406,
      "step": 3
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 1.5348726385452636,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.9753,
      "step": 4
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 2.451336617862282,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.9902,
      "step": 5
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 3.321340013917274,
      "learning_rate": 3.571428571428572e-05,
      "loss": 0.9761,
      "step": 6
    },
    {
      "epoch": 0.24561403508771928,
      "grad_norm": 2.813148280382836,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.9736,
      "step": 7
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 1.5924965375006837,
      "learning_rate": 5e-05,
      "loss": 0.9838,
      "step": 8
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 1.5690611350244767,
      "learning_rate": 4.9993025930300686e-05,
      "loss": 0.9958,
      "step": 9
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 1.3166502579359358,
      "learning_rate": 4.99721076122146e-05,
      "loss": 0.9588,
      "step": 10
    },
    {
      "epoch": 0.38596491228070173,
      "grad_norm": 1.136691779583638,
      "learning_rate": 4.9937256716606394e-05,
      "loss": 0.8503,
      "step": 11
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.8350469358137226,
      "learning_rate": 4.9888492687682096e-05,
      "loss": 0.8724,
      "step": 12
    },
    {
      "epoch": 0.45614035087719296,
      "grad_norm": 0.7872759895415901,
      "learning_rate": 4.982584273214061e-05,
      "loss": 0.9391,
      "step": 13
    },
    {
      "epoch": 0.49122807017543857,
      "grad_norm": 0.7631657638189762,
      "learning_rate": 4.9749341803994465e-05,
      "loss": 0.8446,
      "step": 14
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.6807894928709346,
      "learning_rate": 4.965903258506806e-05,
      "loss": 0.8727,
      "step": 15
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 0.5683155258085846,
      "learning_rate": 4.955496546118439e-05,
      "loss": 0.8189,
      "step": 16
    },
    {
      "epoch": 0.5964912280701754,
      "grad_norm": 0.7801939464768173,
      "learning_rate": 4.9437198494053464e-05,
      "loss": 0.9303,
      "step": 17
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.5867664533954665,
      "learning_rate": 4.9305797388878264e-05,
      "loss": 0.83,
      "step": 18
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.5567512617299766,
      "learning_rate": 4.916083545769607e-05,
      "loss": 0.8938,
      "step": 19
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 0.5135799351938194,
      "learning_rate": 4.9002393578475816e-05,
      "loss": 0.8907,
      "step": 20
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.5604879970565443,
      "learning_rate": 4.883056014999423e-05,
      "loss": 0.8582,
      "step": 21
    },
    {
      "epoch": 0.7719298245614035,
      "grad_norm": 0.5008974828940795,
      "learning_rate": 4.864543104251587e-05,
      "loss": 0.8132,
      "step": 22
    },
    {
      "epoch": 0.8070175438596491,
      "grad_norm": 0.5351207184045396,
      "learning_rate": 4.8447109544304636e-05,
      "loss": 0.8775,
      "step": 23
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.48534815393327974,
      "learning_rate": 4.823570630399665e-05,
      "loss": 0.8478,
      "step": 24
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 0.4766396695563186,
      "learning_rate": 4.8011339268866505e-05,
      "loss": 0.8363,
      "step": 25
    },
    {
      "epoch": 0.9122807017543859,
      "grad_norm": 0.4856803005330466,
      "learning_rate": 4.7774133619021514e-05,
      "loss": 0.9035,
      "step": 26
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.3964013618666619,
      "learning_rate": 4.752422169756048e-05,
      "loss": 0.8033,
      "step": 27
    },
    {
      "epoch": 0.9824561403508771,
      "grad_norm": 0.48912255110703906,
      "learning_rate": 4.726174293673612e-05,
      "loss": 0.8316,
      "step": 28
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.48912255110703906,
      "learning_rate": 4.698684378016222e-05,
      "loss": 0.6913,
      "step": 29
    },
    {
      "epoch": 1.0350877192982457,
      "grad_norm": 0.9512574190630522,
      "learning_rate": 4.669967760110908e-05,
      "loss": 0.7426,
      "step": 30
    },
    {
      "epoch": 1.0701754385964912,
      "grad_norm": 0.5119153708536178,
      "learning_rate": 4.6400404616932505e-05,
      "loss": 0.705,
      "step": 31
    },
    {
      "epoch": 1.1052631578947367,
      "grad_norm": 0.5326897543607073,
      "learning_rate": 4.608919179968457e-05,
      "loss": 0.7502,
      "step": 32
    },
    {
      "epoch": 1.1403508771929824,
      "grad_norm": 0.7107030254650039,
      "learning_rate": 4.576621278295558e-05,
      "loss": 0.7215,
      "step": 33
    },
    {
      "epoch": 1.1754385964912282,
      "grad_norm": 0.6935703731339729,
      "learning_rate": 4.5431647764999455e-05,
      "loss": 0.6888,
      "step": 34
    },
    {
      "epoch": 1.2105263157894737,
      "grad_norm": 0.5468190267311956,
      "learning_rate": 4.5085683408196535e-05,
      "loss": 0.7342,
      "step": 35
    },
    {
      "epoch": 1.2456140350877192,
      "grad_norm": 0.6166217447509906,
      "learning_rate": 4.4728512734909844e-05,
      "loss": 0.7456,
      "step": 36
    },
    {
      "epoch": 1.280701754385965,
      "grad_norm": 0.9130217986036923,
      "learning_rate": 4.436033501979299e-05,
      "loss": 0.7106,
      "step": 37
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 0.5281267490436047,
      "learning_rate": 4.398135567860972e-05,
      "loss": 0.693,
      "step": 38
    },
    {
      "epoch": 1.3508771929824561,
      "grad_norm": 0.5213754312271124,
      "learning_rate": 4.3591786153627247e-05,
      "loss": 0.6418,
      "step": 39
    },
    {
      "epoch": 1.3859649122807016,
      "grad_norm": 0.5481623741259232,
      "learning_rate": 4.319184379564716e-05,
      "loss": 0.7452,
      "step": 40
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 0.6014133516410636,
      "learning_rate": 4.2781751742739885e-05,
      "loss": 0.686,
      "step": 41
    },
    {
      "epoch": 1.456140350877193,
      "grad_norm": 0.44416005870003245,
      "learning_rate": 4.2361738795750214e-05,
      "loss": 0.6433,
      "step": 42
    },
    {
      "epoch": 1.4912280701754386,
      "grad_norm": 0.46835862575073184,
      "learning_rate": 4.193203929064353e-05,
      "loss": 0.6381,
      "step": 43
    },
    {
      "epoch": 1.526315789473684,
      "grad_norm": 0.5015932878379395,
      "learning_rate": 4.1492892967763686e-05,
      "loss": 0.7615,
      "step": 44
    },
    {
      "epoch": 1.5614035087719298,
      "grad_norm": 0.49117089644567374,
      "learning_rate": 4.1044544838075794e-05,
      "loss": 0.7258,
      "step": 45
    },
    {
      "epoch": 1.5964912280701755,
      "grad_norm": 0.4310052429661563,
      "learning_rate": 4.058724504646834e-05,
      "loss": 0.6558,
      "step": 46
    },
    {
      "epoch": 1.631578947368421,
      "grad_norm": 0.46975098597348564,
      "learning_rate": 4.012124873219094e-05,
      "loss": 0.6587,
      "step": 47
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.46564012035747604,
      "learning_rate": 3.964681588650562e-05,
      "loss": 0.7071,
      "step": 48
    },
    {
      "epoch": 1.7017543859649122,
      "grad_norm": 0.4292070243922818,
      "learning_rate": 3.916421120763106e-05,
      "loss": 0.7292,
      "step": 49
    },
    {
      "epoch": 1.736842105263158,
      "grad_norm": 0.4700066192248402,
      "learning_rate": 3.867370395306068e-05,
      "loss": 0.7118,
      "step": 50
    },
    {
      "epoch": 1.7719298245614035,
      "grad_norm": 0.41414590310746596,
      "learning_rate": 3.817556778933698e-05,
      "loss": 0.7187,
      "step": 51
    },
    {
      "epoch": 1.807017543859649,
      "grad_norm": 0.4934164034770572,
      "learning_rate": 3.7670080639366004e-05,
      "loss": 0.7425,
      "step": 52
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 0.4258237994121863,
      "learning_rate": 3.715752452735704e-05,
      "loss": 0.5943,
      "step": 53
    },
    {
      "epoch": 1.8771929824561404,
      "grad_norm": 0.5078698766882597,
      "learning_rate": 3.6638185421474084e-05,
      "loss": 0.7346,
      "step": 54
    },
    {
      "epoch": 1.912280701754386,
      "grad_norm": 0.44841215920564664,
      "learning_rate": 3.61123530742869e-05,
      "loss": 0.6742,
      "step": 55
    },
    {
      "epoch": 1.9473684210526314,
      "grad_norm": 0.39580481306947396,
      "learning_rate": 3.5580320861110625e-05,
      "loss": 0.7273,
      "step": 56
    },
    {
      "epoch": 1.9824561403508771,
      "grad_norm": 0.48313542261877046,
      "learning_rate": 3.504238561632424e-05,
      "loss": 0.732,
      "step": 57
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8524767663864421,
      "learning_rate": 3.4498847467759e-05,
      "loss": 0.6104,
      "step": 58
    },
    {
      "epoch": 2.0350877192982457,
      "grad_norm": 0.9497059015721913,
      "learning_rate": 3.3950009669249497e-05,
      "loss": 0.5313,
      "step": 59
    },
    {
      "epoch": 2.0701754385964914,
      "grad_norm": 2.6382740891339025,
      "learning_rate": 3.339617843144057e-05,
      "loss": 0.6382,
      "step": 60
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 2.9127895766727887,
      "learning_rate": 3.2837662750944535e-05,
      "loss": 0.557,
      "step": 61
    },
    {
      "epoch": 2.1403508771929824,
      "grad_norm": 0.5994326492557629,
      "learning_rate": 3.227477423794412e-05,
      "loss": 0.5275,
      "step": 62
    },
    {
      "epoch": 2.175438596491228,
      "grad_norm": 0.7402586486266488,
      "learning_rate": 3.170782694233712e-05,
      "loss": 0.5685,
      "step": 63
    },
    {
      "epoch": 2.2105263157894735,
      "grad_norm": 0.8114992716723906,
      "learning_rate": 3.1137137178519985e-05,
      "loss": 0.5608,
      "step": 64
    },
    {
      "epoch": 2.245614035087719,
      "grad_norm": 0.4638568586846813,
      "learning_rate": 3.056302334890786e-05,
      "loss": 0.5008,
      "step": 65
    },
    {
      "epoch": 2.280701754385965,
      "grad_norm": 0.5045959497131294,
      "learning_rate": 2.9985805766289817e-05,
      "loss": 0.5395,
      "step": 66
    },
    {
      "epoch": 2.3157894736842106,
      "grad_norm": 0.5579563118760068,
      "learning_rate": 2.9405806475118048e-05,
      "loss": 0.5138,
      "step": 67
    },
    {
      "epoch": 2.3508771929824563,
      "grad_norm": 0.5637466858166899,
      "learning_rate": 2.882334907183115e-05,
      "loss": 0.5698,
      "step": 68
    },
    {
      "epoch": 2.3859649122807016,
      "grad_norm": 0.4578787068510027,
      "learning_rate": 2.8238758524311314e-05,
      "loss": 0.5291,
      "step": 69
    },
    {
      "epoch": 2.4210526315789473,
      "grad_norm": 0.761131940332416,
      "learning_rate": 2.7652360990576453e-05,
      "loss": 0.6047,
      "step": 70
    },
    {
      "epoch": 2.456140350877193,
      "grad_norm": 0.5221912763262103,
      "learning_rate": 2.7064483636808313e-05,
      "loss": 0.5368,
      "step": 71
    },
    {
      "epoch": 2.4912280701754383,
      "grad_norm": 0.469481484634673,
      "learning_rate": 2.6475454454818073e-05,
      "loss": 0.5374,
      "step": 72
    },
    {
      "epoch": 2.526315789473684,
      "grad_norm": 0.48764324851448193,
      "learning_rate": 2.5885602079051353e-05,
      "loss": 0.4709,
      "step": 73
    },
    {
      "epoch": 2.56140350877193,
      "grad_norm": 0.5222547729689572,
      "learning_rate": 2.529525560323462e-05,
      "loss": 0.5577,
      "step": 74
    },
    {
      "epoch": 2.5964912280701755,
      "grad_norm": 0.48783850266999607,
      "learning_rate": 2.470474439676539e-05,
      "loss": 0.5425,
      "step": 75
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 0.5489576835164317,
      "learning_rate": 2.4114397920948657e-05,
      "loss": 0.5442,
      "step": 76
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.43701838993444003,
      "learning_rate": 2.3524545545181933e-05,
      "loss": 0.5711,
      "step": 77
    },
    {
      "epoch": 2.7017543859649122,
      "grad_norm": 0.3981876016589946,
      "learning_rate": 2.2935516363191693e-05,
      "loss": 0.5559,
      "step": 78
    },
    {
      "epoch": 2.736842105263158,
      "grad_norm": 0.43288188752005125,
      "learning_rate": 2.2347639009423553e-05,
      "loss": 0.5459,
      "step": 79
    },
    {
      "epoch": 2.7719298245614032,
      "grad_norm": 0.3879671575828641,
      "learning_rate": 2.1761241475688695e-05,
      "loss": 0.4994,
      "step": 80
    },
    {
      "epoch": 2.807017543859649,
      "grad_norm": 0.36710005595302997,
      "learning_rate": 2.117665092816885e-05,
      "loss": 0.4588,
      "step": 81
    },
    {
      "epoch": 2.8421052631578947,
      "grad_norm": 0.4298634595452112,
      "learning_rate": 2.059419352488196e-05,
      "loss": 0.5301,
      "step": 82
    },
    {
      "epoch": 2.8771929824561404,
      "grad_norm": 0.37298113858035087,
      "learning_rate": 2.0014194233710193e-05,
      "loss": 0.5323,
      "step": 83
    },
    {
      "epoch": 2.912280701754386,
      "grad_norm": 0.4497970060495327,
      "learning_rate": 1.9436976651092144e-05,
      "loss": 0.564,
      "step": 84
    },
    {
      "epoch": 2.9473684210526314,
      "grad_norm": 0.4115774413493238,
      "learning_rate": 1.8862862821480025e-05,
      "loss": 0.4881,
      "step": 85
    },
    {
      "epoch": 2.982456140350877,
      "grad_norm": 0.3499066739001436,
      "learning_rate": 1.829217305766289e-05,
      "loss": 0.5444,
      "step": 86
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.3499066739001436,
      "learning_rate": 1.7725225762055887e-05,
      "loss": 0.3119,
      "step": 87
    }
  ],
  "logging_steps": 1,
  "max_steps": 140,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 39139677044736.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}