{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 12.421052631578947,
  "eval_steps": 500,
  "global_step": 56,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 19.218000411987305,
      "learning_rate": 2e-05,
      "loss": 3.886,
      "step": 1
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 19.777868270874023,
      "learning_rate": 4e-05,
      "loss": 4.4615,
      "step": 2
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 17.180343627929688,
      "learning_rate": 6e-05,
      "loss": 3.7595,
      "step": 3
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 17.781330108642578,
      "learning_rate": 8e-05,
      "loss": 3.3302,
      "step": 4
    },
    {
      "epoch": 1.1052631578947367,
      "grad_norm": 20.543649673461914,
      "learning_rate": 0.0001,
      "loss": 4.6154,
      "step": 5
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 11.29702091217041,
      "learning_rate": 0.00012,
      "loss": 2.5755,
      "step": 6
    },
    {
      "epoch": 1.526315789473684,
      "grad_norm": 8.194554328918457,
      "learning_rate": 0.00014,
      "loss": 1.6726,
      "step": 7
    },
    {
      "epoch": 1.736842105263158,
      "grad_norm": 6.040785312652588,
      "learning_rate": 0.00016,
      "loss": 1.2606,
      "step": 8
    },
    {
      "epoch": 1.9473684210526314,
      "grad_norm": 12.296614646911621,
      "learning_rate": 0.00018,
      "loss": 1.9246,
      "step": 9
    },
    {
      "epoch": 2.2105263157894735,
      "grad_norm": 6.707492828369141,
      "learning_rate": 0.0002,
      "loss": 1.0017,
      "step": 10
    },
    {
      "epoch": 2.4210526315789473,
      "grad_norm": 4.79848575592041,
      "learning_rate": 0.00019976687691905393,
      "loss": 0.6978,
      "step": 11
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 3.3441014289855957,
      "learning_rate": 0.00019906859460363307,
      "loss": 0.5996,
      "step": 12
    },
    {
      "epoch": 2.8421052631578947,
      "grad_norm": 3.113868474960327,
      "learning_rate": 0.00019790840876823232,
      "loss": 0.5782,
      "step": 13
    },
    {
      "epoch": 3.1052631578947367,
      "grad_norm": 7.5327229499816895,
      "learning_rate": 0.00019629172873477995,
      "loss": 0.8014,
      "step": 14
    },
    {
      "epoch": 3.3157894736842106,
      "grad_norm": 2.6903626918792725,
      "learning_rate": 0.00019422609221188207,
      "loss": 0.3285,
      "step": 15
    },
    {
      "epoch": 3.526315789473684,
      "grad_norm": 3.672346591949463,
      "learning_rate": 0.00019172113015054532,
      "loss": 0.3814,
      "step": 16
    },
    {
      "epoch": 3.736842105263158,
      "grad_norm": 1.4505695104599,
      "learning_rate": 0.0001887885218402375,
      "loss": 0.2401,
      "step": 17
    },
    {
      "epoch": 3.9473684210526314,
      "grad_norm": 2.6290504932403564,
      "learning_rate": 0.00018544194045464886,
      "loss": 0.3272,
      "step": 18
    },
    {
      "epoch": 4.2105263157894735,
      "grad_norm": 1.3445160388946533,
      "learning_rate": 0.0001816969893010442,
      "loss": 0.1871,
      "step": 19
    },
    {
      "epoch": 4.421052631578947,
      "grad_norm": 1.851083755493164,
      "learning_rate": 0.000177571129070442,
      "loss": 0.1781,
      "step": 20
    },
    {
      "epoch": 4.631578947368421,
      "grad_norm": 1.0952624082565308,
      "learning_rate": 0.00017308359642781242,
      "loss": 0.1966,
      "step": 21
    },
    {
      "epoch": 4.842105263157895,
      "grad_norm": 2.4012107849121094,
      "learning_rate": 0.00016825531432186543,
      "loss": 0.1738,
      "step": 22
    },
    {
      "epoch": 5.105263157894737,
      "grad_norm": 1.6361955404281616,
      "learning_rate": 0.00016310879443260528,
      "loss": 0.2131,
      "step": 23
    },
    {
      "epoch": 5.315789473684211,
      "grad_norm": 2.245840072631836,
      "learning_rate": 0.00015766803221148673,
      "loss": 0.1646,
      "step": 24
    },
    {
      "epoch": 5.526315789473684,
      "grad_norm": 1.684137225151062,
      "learning_rate": 0.00015195839500354335,
      "loss": 0.184,
      "step": 25
    },
    {
      "epoch": 5.7368421052631575,
      "grad_norm": 0.9733522534370422,
      "learning_rate": 0.00014600650377311522,
      "loss": 0.1465,
      "step": 26
    },
    {
      "epoch": 5.947368421052632,
      "grad_norm": 2.4283876419067383,
      "learning_rate": 0.00013984010898462416,
      "loss": 0.2177,
      "step": 27
    },
    {
      "epoch": 6.2105263157894735,
      "grad_norm": 1.4879282712936401,
      "learning_rate": 0.00013348796121709862,
      "loss": 0.1299,
      "step": 28
    },
    {
      "epoch": 6.421052631578947,
      "grad_norm": 1.0862969160079956,
      "learning_rate": 0.00012697967711570242,
      "loss": 0.1115,
      "step": 29
    },
    {
      "epoch": 6.631578947368421,
      "grad_norm": 0.7216919660568237,
      "learning_rate": 0.0001203456013052634,
      "loss": 0.0971,
      "step": 30
    },
    {
      "epoch": 6.842105263157895,
      "grad_norm": 1.4882885217666626,
      "learning_rate": 0.00011361666490962468,
      "loss": 0.1453,
      "step": 31
    },
    {
      "epoch": 7.105263157894737,
      "grad_norm": 1.220837950706482,
      "learning_rate": 0.0001068242413364671,
      "loss": 0.1634,
      "step": 32
    },
    {
      "epoch": 7.315789473684211,
      "grad_norm": 0.6117944121360779,
      "learning_rate": 0.0001,
      "loss": 0.1026,
      "step": 33
    },
    {
      "epoch": 7.526315789473684,
      "grad_norm": 0.9110010266304016,
      "learning_rate": 9.317575866353292e-05,
      "loss": 0.103,
      "step": 34
    },
    {
      "epoch": 7.7368421052631575,
      "grad_norm": 0.9700250625610352,
      "learning_rate": 8.638333509037536e-05,
      "loss": 0.1205,
      "step": 35
    },
    {
      "epoch": 7.947368421052632,
      "grad_norm": 0.9124184250831604,
      "learning_rate": 7.965439869473664e-05,
      "loss": 0.1095,
      "step": 36
    },
    {
      "epoch": 8.210526315789474,
      "grad_norm": 0.49950140714645386,
      "learning_rate": 7.302032288429756e-05,
      "loss": 0.0796,
      "step": 37
    },
    {
      "epoch": 8.421052631578947,
      "grad_norm": 0.8700776100158691,
      "learning_rate": 6.651203878290139e-05,
      "loss": 0.0774,
      "step": 38
    },
    {
      "epoch": 8.631578947368421,
      "grad_norm": 0.7889358401298523,
      "learning_rate": 6.015989101537586e-05,
      "loss": 0.0835,
      "step": 39
    },
    {
      "epoch": 8.842105263157894,
      "grad_norm": 0.5236338973045349,
      "learning_rate": 5.399349622688479e-05,
      "loss": 0.0581,
      "step": 40
    },
    {
      "epoch": 9.105263157894736,
      "grad_norm": 0.9376251697540283,
      "learning_rate": 4.804160499645667e-05,
      "loss": 0.0936,
      "step": 41
    },
    {
      "epoch": 9.31578947368421,
      "grad_norm": 0.7259882092475891,
      "learning_rate": 4.2331967788513295e-05,
      "loss": 0.0712,
      "step": 42
    },
    {
      "epoch": 9.526315789473685,
      "grad_norm": 0.5035570859909058,
      "learning_rate": 3.689120556739475e-05,
      "loss": 0.0776,
      "step": 43
    },
    {
      "epoch": 9.736842105263158,
      "grad_norm": 0.4928078055381775,
      "learning_rate": 3.174468567813461e-05,
      "loss": 0.0483,
      "step": 44
    },
    {
      "epoch": 9.947368421052632,
      "grad_norm": 1.1208339929580688,
      "learning_rate": 2.691640357218759e-05,
      "loss": 0.1032,
      "step": 45
    },
    {
      "epoch": 10.210526315789474,
      "grad_norm": 0.5036032795906067,
      "learning_rate": 2.242887092955801e-05,
      "loss": 0.0745,
      "step": 46
    },
    {
      "epoch": 10.421052631578947,
      "grad_norm": 0.4454878866672516,
      "learning_rate": 1.8303010698955804e-05,
      "loss": 0.0526,
      "step": 47
    },
    {
      "epoch": 10.631578947368421,
      "grad_norm": 0.48385077714920044,
      "learning_rate": 1.4558059545351143e-05,
      "loss": 0.0609,
      "step": 48
    },
    {
      "epoch": 10.842105263157894,
      "grad_norm": 0.8407765030860901,
      "learning_rate": 1.1211478159762478e-05,
      "loss": 0.0638,
      "step": 49
    },
    {
      "epoch": 11.105263157894736,
      "grad_norm": 0.4083283841609955,
      "learning_rate": 8.278869849454718e-06,
      "loss": 0.065,
      "step": 50
    },
    {
      "epoch": 11.31578947368421,
      "grad_norm": 0.4340791702270508,
      "learning_rate": 5.77390778811796e-06,
      "loss": 0.0545,
      "step": 51
    },
    {
      "epoch": 11.526315789473685,
      "grad_norm": 0.5537849068641663,
      "learning_rate": 3.7082712652200867e-06,
      "loss": 0.0511,
      "step": 52
    },
    {
      "epoch": 11.736842105263158,
      "grad_norm": 0.36356380581855774,
      "learning_rate": 2.091591231767709e-06,
      "loss": 0.0553,
      "step": 53
    },
    {
      "epoch": 11.947368421052632,
      "grad_norm": 1.3945286273956299,
      "learning_rate": 9.314053963669245e-07,
      "loss": 0.1255,
      "step": 54
    },
    {
      "epoch": 12.210526315789474,
      "grad_norm": 0.5195576548576355,
      "learning_rate": 2.3312308094607382e-07,
      "loss": 0.0559,
      "step": 55
    },
    {
      "epoch": 12.421052631578947,
      "grad_norm": 0.5838670134544373,
      "learning_rate": 0.0,
      "loss": 0.0631,
      "step": 56
    }
  ],
  "logging_steps": 1,
  "max_steps": 56,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 14,
  "save_steps": 4,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 50350673362944.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}