{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.997779422649889,
  "eval_steps": 100,
  "global_step": 337,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014803849000740192,
      "grad_norm": 2.5992181301116943,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.09,
      "step": 5
    },
    {
      "epoch": 0.029607698001480384,
      "grad_norm": 1.5087730884552002,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.0788,
      "step": 10
    },
    {
      "epoch": 0.04441154700222058,
      "grad_norm": 1.2677146196365356,
      "learning_rate": 8.823529411764707e-06,
      "loss": 1.0147,
      "step": 15
    },
    {
      "epoch": 0.05921539600296077,
      "grad_norm": 0.9016809463500977,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.9334,
      "step": 20
    },
    {
      "epoch": 0.07401924500370097,
      "grad_norm": 0.7976483106613159,
      "learning_rate": 1.4705882352941179e-05,
      "loss": 0.9001,
      "step": 25
    },
    {
      "epoch": 0.08882309400444116,
      "grad_norm": 0.6809649467468262,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.8802,
      "step": 30
    },
    {
      "epoch": 0.10362694300518134,
      "grad_norm": 0.6254366040229797,
      "learning_rate": 1.9999462497359468e-05,
      "loss": 0.8536,
      "step": 35
    },
    {
      "epoch": 0.11843079200592153,
      "grad_norm": 0.5435229539871216,
      "learning_rate": 1.9980655971335944e-05,
      "loss": 0.8348,
      "step": 40
    },
    {
      "epoch": 0.13323464100666174,
      "grad_norm": 0.5121663212776184,
      "learning_rate": 1.993503206718859e-05,
      "loss": 0.8136,
      "step": 45
    },
    {
      "epoch": 0.14803849000740193,
      "grad_norm": 0.6101697683334351,
      "learning_rate": 1.986271337340182e-05,
      "loss": 0.8198,
      "step": 50
    },
    {
      "epoch": 0.16284233900814213,
      "grad_norm": 0.5170488357543945,
      "learning_rate": 1.976389420563607e-05,
      "loss": 0.8029,
      "step": 55
    },
    {
      "epoch": 0.17764618800888232,
      "grad_norm": 0.4948929250240326,
      "learning_rate": 1.9638840084614182e-05,
      "loss": 0.7894,
      "step": 60
    },
    {
      "epoch": 0.19245003700962252,
      "grad_norm": 0.5749170780181885,
      "learning_rate": 1.9487887022684336e-05,
      "loss": 0.7994,
      "step": 65
    },
    {
      "epoch": 0.20725388601036268,
      "grad_norm": 0.5195707082748413,
      "learning_rate": 1.9311440620976597e-05,
      "loss": 0.7927,
      "step": 70
    },
    {
      "epoch": 0.22205773501110287,
      "grad_norm": 0.5418318510055542,
      "learning_rate": 1.9109974979578852e-05,
      "loss": 0.7837,
      "step": 75
    },
    {
      "epoch": 0.23686158401184307,
      "grad_norm": 0.5383281111717224,
      "learning_rate": 1.8884031423660492e-05,
      "loss": 0.8122,
      "step": 80
    },
    {
      "epoch": 0.25166543301258326,
      "grad_norm": 0.5377805829048157,
      "learning_rate": 1.8634217048966638e-05,
      "loss": 0.7951,
      "step": 85
    },
    {
      "epoch": 0.2664692820133235,
      "grad_norm": 0.5460654497146606,
      "learning_rate": 1.836120309059107e-05,
      "loss": 0.7778,
      "step": 90
    },
    {
      "epoch": 0.28127313101406365,
      "grad_norm": 0.5279029607772827,
      "learning_rate": 1.8065723119410885e-05,
      "loss": 0.7756,
      "step": 95
    },
    {
      "epoch": 0.29607698001480387,
      "grad_norm": 0.5558004379272461,
      "learning_rate": 1.77485710710289e-05,
      "loss": 0.7824,
      "step": 100
    },
    {
      "epoch": 0.29607698001480387,
      "eval_loss": 0.798744797706604,
      "eval_runtime": 4.9568,
      "eval_samples_per_second": 25.823,
      "eval_steps_per_second": 1.614,
      "step": 100
    },
    {
      "epoch": 0.31088082901554404,
      "grad_norm": 0.49692487716674805,
      "learning_rate": 1.741059911251997e-05,
      "loss": 0.7732,
      "step": 105
    },
    {
      "epoch": 0.32568467801628426,
      "grad_norm": 0.5316541790962219,
      "learning_rate": 1.7052715352713076e-05,
      "loss": 0.7674,
      "step": 110
    },
    {
      "epoch": 0.3404885270170244,
      "grad_norm": 0.530269980430603,
      "learning_rate": 1.667588140216154e-05,
      "loss": 0.7944,
      "step": 115
    },
    {
      "epoch": 0.35529237601776464,
      "grad_norm": 0.5283094644546509,
      "learning_rate": 1.628110978935756e-05,
      "loss": 0.7688,
      "step": 120
    },
    {
      "epoch": 0.3700962250185048,
      "grad_norm": 0.5419968366622925,
      "learning_rate": 1.586946124013354e-05,
      "loss": 0.7683,
      "step": 125
    },
    {
      "epoch": 0.38490007401924503,
      "grad_norm": 0.5174740552902222,
      "learning_rate": 1.5442041827560274e-05,
      "loss": 0.745,
      "step": 130
    },
    {
      "epoch": 0.3997039230199852,
      "grad_norm": 0.5500133633613586,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.7559,
      "step": 135
    },
    {
      "epoch": 0.41450777202072536,
      "grad_norm": 0.5237729549407959,
      "learning_rate": 1.4544523495299843e-05,
      "loss": 0.7621,
      "step": 140
    },
    {
      "epoch": 0.4293116210214656,
      "grad_norm": 0.5662232041358948,
      "learning_rate": 1.4076836149416889e-05,
      "loss": 0.778,
      "step": 145
    },
    {
      "epoch": 0.44411547002220575,
      "grad_norm": 0.5192484259605408,
      "learning_rate": 1.3598194608050011e-05,
      "loss": 0.7627,
      "step": 150
    },
    {
      "epoch": 0.45891931902294597,
      "grad_norm": 0.47917070984840393,
      "learning_rate": 1.3109884950114007e-05,
      "loss": 0.7521,
      "step": 155
    },
    {
      "epoch": 0.47372316802368614,
      "grad_norm": 0.4877147972583771,
      "learning_rate": 1.2613219232128608e-05,
      "loss": 0.752,
      "step": 160
    },
    {
      "epoch": 0.48852701702442636,
      "grad_norm": 0.4902460277080536,
      "learning_rate": 1.2109531962807333e-05,
      "loss": 0.7537,
      "step": 165
    },
    {
      "epoch": 0.5033308660251665,
      "grad_norm": 0.4749601483345032,
      "learning_rate": 1.1600176517318742e-05,
      "loss": 0.7581,
      "step": 170
    },
    {
      "epoch": 0.5181347150259067,
      "grad_norm": 0.49789533019065857,
      "learning_rate": 1.1086521500854746e-05,
      "loss": 0.7452,
      "step": 175
    },
    {
      "epoch": 0.532938564026647,
      "grad_norm": 0.49085575342178345,
      "learning_rate": 1.0569947071276847e-05,
      "loss": 0.766,
      "step": 180
    },
    {
      "epoch": 0.5477424130273871,
      "grad_norm": 0.5533766150474548,
      "learning_rate": 1.0051841230721065e-05,
      "loss": 0.7591,
      "step": 185
    },
    {
      "epoch": 0.5625462620281273,
      "grad_norm": 0.4962024390697479,
      "learning_rate": 9.533596096125826e-06,
      "loss": 0.7656,
      "step": 190
    },
    {
      "epoch": 0.5773501110288675,
      "grad_norm": 0.47751423716545105,
      "learning_rate": 9.016604158703654e-06,
      "loss": 0.7398,
      "step": 195
    },
    {
      "epoch": 0.5921539600296077,
      "grad_norm": 0.48585522174835205,
      "learning_rate": 8.502254542407186e-06,
      "loss": 0.7375,
      "step": 200
    },
    {
      "epoch": 0.5921539600296077,
      "eval_loss": 0.7733819484710693,
      "eval_runtime": 4.9465,
      "eval_samples_per_second": 25.877,
      "eval_steps_per_second": 1.617,
      "step": 200
    },
    {
      "epoch": 0.6069578090303479,
      "grad_norm": 0.4782666563987732,
      "learning_rate": 7.991929271442817e-06,
      "loss": 0.7415,
      "step": 205
    },
    {
      "epoch": 0.6217616580310881,
      "grad_norm": 0.4925994575023651,
      "learning_rate": 7.48699955686089e-06,
      "loss": 0.7437,
      "step": 210
    },
    {
      "epoch": 0.6365655070318282,
      "grad_norm": 0.4650406241416931,
      "learning_rate": 6.988822112200157e-06,
      "loss": 0.7518,
      "step": 215
    },
    {
      "epoch": 0.6513693560325685,
      "grad_norm": 0.4966399669647217,
      "learning_rate": 6.498735508086094e-06,
      "loss": 0.755,
      "step": 220
    },
    {
      "epoch": 0.6661732050333087,
      "grad_norm": 0.443478524684906,
      "learning_rate": 6.018056575578075e-06,
      "loss": 0.7487,
      "step": 225
    },
    {
      "epoch": 0.6809770540340488,
      "grad_norm": 0.412899374961853,
      "learning_rate": 5.548076867929331e-06,
      "loss": 0.7455,
      "step": 230
    },
    {
      "epoch": 0.695780903034789,
      "grad_norm": 0.4347788989543915,
      "learning_rate": 5.090059190266779e-06,
      "loss": 0.7336,
      "step": 235
    },
    {
      "epoch": 0.7105847520355293,
      "grad_norm": 0.43398064374923706,
      "learning_rate": 4.645234206515171e-06,
      "loss": 0.7388,
      "step": 240
    },
    {
      "epoch": 0.7253886010362695,
      "grad_norm": 0.4548566937446594,
      "learning_rate": 4.214797132682597e-06,
      "loss": 0.7352,
      "step": 245
    },
    {
      "epoch": 0.7401924500370096,
      "grad_norm": 0.4564402997493744,
      "learning_rate": 3.799904525392251e-06,
      "loss": 0.7422,
      "step": 250
    },
    {
      "epoch": 0.7549962990377498,
      "grad_norm": 0.4452548325061798,
      "learning_rate": 3.401671174289469e-06,
      "loss": 0.7323,
      "step": 255
    },
    {
      "epoch": 0.7698001480384901,
      "grad_norm": 0.44198399782180786,
      "learning_rate": 3.021167106673928e-06,
      "loss": 0.7483,
      "step": 260
    },
    {
      "epoch": 0.7846039970392302,
      "grad_norm": 0.43686527013778687,
      "learning_rate": 2.6594147124053983e-06,
      "loss": 0.7371,
      "step": 265
    },
    {
      "epoch": 0.7994078460399704,
      "grad_norm": 0.4451473653316498,
      "learning_rate": 2.317385996808195e-06,
      "loss": 0.7488,
      "step": 270
    },
    {
      "epoch": 0.8142116950407106,
      "grad_norm": 0.4142710566520691,
      "learning_rate": 1.9959999689556407e-06,
      "loss": 0.7413,
      "step": 275
    },
    {
      "epoch": 0.8290155440414507,
      "grad_norm": 0.4243415594100952,
      "learning_rate": 1.6961201723520248e-06,
      "loss": 0.7272,
      "step": 280
    },
    {
      "epoch": 0.843819393042191,
      "grad_norm": 0.4001702666282654,
      "learning_rate": 1.4185523646469822e-06,
      "loss": 0.752,
      "step": 285
    },
    {
      "epoch": 0.8586232420429312,
      "grad_norm": 0.4234675168991089,
      "learning_rate": 1.1640423526166987e-06,
      "loss": 0.7298,
      "step": 290
    },
    {
      "epoch": 0.8734270910436713,
      "grad_norm": 0.40520840883255005,
      "learning_rate": 9.332739882292752e-07,
      "loss": 0.7559,
      "step": 295
    },
    {
      "epoch": 0.8882309400444115,
      "grad_norm": 0.40351057052612305,
      "learning_rate": 7.268673311786378e-07,
      "loss": 0.7456,
      "step": 300
    },
    {
      "epoch": 0.8882309400444115,
      "eval_loss": 0.7648847103118896,
      "eval_runtime": 4.9484,
      "eval_samples_per_second": 25.867,
      "eval_steps_per_second": 1.617,
      "step": 300
    },
    {
      "epoch": 0.9030347890451518,
      "grad_norm": 0.388411283493042,
      "learning_rate": 5.453769828241872e-07,
      "loss": 0.7295,
      "step": 305
    },
    {
      "epoch": 0.9178386380458919,
      "grad_norm": 0.415742963552475,
      "learning_rate": 3.8929059601275463e-07,
      "loss": 0.7617,
      "step": 310
    },
    {
      "epoch": 0.9326424870466321,
      "grad_norm": 0.39539769291877747,
      "learning_rate": 2.5902756478688674e-07,
      "loss": 0.7441,
      "step": 315
    },
    {
      "epoch": 0.9474463360473723,
      "grad_norm": 0.40046682953834534,
      "learning_rate": 1.5493789750014032e-07,
      "loss": 0.7459,
      "step": 320
    },
    {
      "epoch": 0.9622501850481125,
      "grad_norm": 0.42745569348335266,
      "learning_rate": 7.730127636723539e-08,
      "loss": 0.7266,
      "step": 325
    },
    {
      "epoch": 0.9770540340488527,
      "grad_norm": 0.42035773396492004,
      "learning_rate": 2.6326305976001054e-08,
      "loss": 0.7313,
      "step": 330
    },
    {
      "epoch": 0.9918578830495929,
      "grad_norm": 0.44245919585227966,
      "learning_rate": 2.149952780321485e-09,
      "loss": 0.7525,
      "step": 335
    },
    {
      "epoch": 0.997779422649889,
      "step": 337,
      "total_flos": 76745898196992.0,
      "train_loss": 0.7814815865072369,
      "train_runtime": 4121.13,
      "train_samples_per_second": 5.244,
      "train_steps_per_second": 0.082
    }
  ],
  "logging_steps": 5,
  "max_steps": 337,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 76745898196992.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}