{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8714596949891068,
  "eval_steps": 500,
  "global_step": 4000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02178649237472767,
      "grad_norm": 1.472805380821228,
      "learning_rate": 4.945533769063181e-05,
      "loss": 0.6911,
      "step": 100
    },
    {
      "epoch": 0.04357298474945534,
      "grad_norm": 1.3399823904037476,
      "learning_rate": 4.891067538126362e-05,
      "loss": 0.4494,
      "step": 200
    },
    {
      "epoch": 0.06535947712418301,
      "grad_norm": 1.9283204078674316,
      "learning_rate": 4.8366013071895424e-05,
      "loss": 0.4761,
      "step": 300
    },
    {
      "epoch": 0.08714596949891068,
      "grad_norm": 3.021352529525757,
      "learning_rate": 4.7821350762527234e-05,
      "loss": 0.4803,
      "step": 400
    },
    {
      "epoch": 0.10893246187363835,
      "grad_norm": 0.3251399099826813,
      "learning_rate": 4.7276688453159044e-05,
      "loss": 0.438,
      "step": 500
    },
    {
      "epoch": 0.13071895424836602,
      "grad_norm": 1.289565920829773,
      "learning_rate": 4.673202614379085e-05,
      "loss": 0.4677,
      "step": 600
    },
    {
      "epoch": 0.15250544662309368,
      "grad_norm": 1.5132582187652588,
      "learning_rate": 4.6187363834422656e-05,
      "loss": 0.5276,
      "step": 700
    },
    {
      "epoch": 0.17429193899782136,
      "grad_norm": 0.4088970720767975,
      "learning_rate": 4.564270152505447e-05,
      "loss": 0.444,
      "step": 800
    },
    {
      "epoch": 0.19607843137254902,
      "grad_norm": 2.157912015914917,
      "learning_rate": 4.5098039215686275e-05,
      "loss": 0.4502,
      "step": 900
    },
    {
      "epoch": 0.2178649237472767,
      "grad_norm": 1.5439516305923462,
      "learning_rate": 4.4553376906318085e-05,
      "loss": 0.4248,
      "step": 1000
    },
    {
      "epoch": 0.23965141612200436,
      "grad_norm": 1.3628387451171875,
      "learning_rate": 4.400871459694989e-05,
      "loss": 0.4223,
      "step": 1100
    },
    {
      "epoch": 0.26143790849673204,
      "grad_norm": 1.5868219137191772,
      "learning_rate": 4.3464052287581704e-05,
      "loss": 0.4877,
      "step": 1200
    },
    {
      "epoch": 0.28322440087145967,
      "grad_norm": 1.0417579412460327,
      "learning_rate": 4.291938997821351e-05,
      "loss": 0.4705,
      "step": 1300
    },
    {
      "epoch": 0.30501089324618735,
      "grad_norm": 1.6881535053253174,
      "learning_rate": 4.2374727668845316e-05,
      "loss": 0.4305,
      "step": 1400
    },
    {
      "epoch": 0.32679738562091504,
      "grad_norm": 1.3759115934371948,
      "learning_rate": 4.1830065359477126e-05,
      "loss": 0.3975,
      "step": 1500
    },
    {
      "epoch": 0.3485838779956427,
      "grad_norm": 2.2703583240509033,
      "learning_rate": 4.1285403050108935e-05,
      "loss": 0.4246,
      "step": 1600
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 1.0483826398849487,
      "learning_rate": 4.074074074074074e-05,
      "loss": 0.4994,
      "step": 1700
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 1.2435953617095947,
      "learning_rate": 4.0196078431372555e-05,
      "loss": 0.4337,
      "step": 1800
    },
    {
      "epoch": 0.4139433551198257,
      "grad_norm": 1.4106743335723877,
      "learning_rate": 3.965141612200436e-05,
      "loss": 0.4338,
      "step": 1900
    },
    {
      "epoch": 0.4357298474945534,
      "grad_norm": 0.9341331720352173,
      "learning_rate": 3.910675381263617e-05,
      "loss": 0.4683,
      "step": 2000
    },
    {
      "epoch": 0.45751633986928103,
      "grad_norm": 1.9387885332107544,
      "learning_rate": 3.8562091503267977e-05,
      "loss": 0.4207,
      "step": 2100
    },
    {
      "epoch": 0.4793028322440087,
      "grad_norm": 0.12210940569639206,
      "learning_rate": 3.8017429193899786e-05,
      "loss": 0.4549,
      "step": 2200
    },
    {
      "epoch": 0.5010893246187363,
      "grad_norm": 1.2780179977416992,
      "learning_rate": 3.747276688453159e-05,
      "loss": 0.4325,
      "step": 2300
    },
    {
      "epoch": 0.5228758169934641,
      "grad_norm": 0.6933521032333374,
      "learning_rate": 3.6928104575163405e-05,
      "loss": 0.407,
      "step": 2400
    },
    {
      "epoch": 0.5446623093681917,
      "grad_norm": 1.5122122764587402,
      "learning_rate": 3.638344226579521e-05,
      "loss": 0.4629,
      "step": 2500
    },
    {
      "epoch": 0.5664488017429193,
      "grad_norm": 0.967708170413971,
      "learning_rate": 3.583877995642702e-05,
      "loss": 0.4102,
      "step": 2600
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 2.7059736251831055,
      "learning_rate": 3.529411764705883e-05,
      "loss": 0.4465,
      "step": 2700
    },
    {
      "epoch": 0.6100217864923747,
      "grad_norm": 1.3728137016296387,
      "learning_rate": 3.474945533769064e-05,
      "loss": 0.4225,
      "step": 2800
    },
    {
      "epoch": 0.6318082788671024,
      "grad_norm": 0.8513820767402649,
      "learning_rate": 3.420479302832244e-05,
      "loss": 0.3922,
      "step": 2900
    },
    {
      "epoch": 0.6535947712418301,
      "grad_norm": 1.2829489707946777,
      "learning_rate": 3.366013071895425e-05,
      "loss": 0.4202,
      "step": 3000
    },
    {
      "epoch": 0.6753812636165577,
      "grad_norm": 1.9668824672698975,
      "learning_rate": 3.311546840958606e-05,
      "loss": 0.4425,
      "step": 3100
    },
    {
      "epoch": 0.6971677559912854,
      "grad_norm": 0.9782924056053162,
      "learning_rate": 3.257080610021787e-05,
      "loss": 0.4407,
      "step": 3200
    },
    {
      "epoch": 0.7189542483660131,
      "grad_norm": 1.2658343315124512,
      "learning_rate": 3.202614379084967e-05,
      "loss": 0.4256,
      "step": 3300
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 1.1413471698760986,
      "learning_rate": 3.148148148148148e-05,
      "loss": 0.435,
      "step": 3400
    },
    {
      "epoch": 0.7625272331154684,
      "grad_norm": 0.6810837984085083,
      "learning_rate": 3.093681917211329e-05,
      "loss": 0.4662,
      "step": 3500
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 1.4281896352767944,
      "learning_rate": 3.0392156862745097e-05,
      "loss": 0.4148,
      "step": 3600
    },
    {
      "epoch": 0.8061002178649237,
      "grad_norm": 0.907742977142334,
      "learning_rate": 2.984749455337691e-05,
      "loss": 0.417,
      "step": 3700
    },
    {
      "epoch": 0.8278867102396514,
      "grad_norm": 1.6939854621887207,
      "learning_rate": 2.9302832244008716e-05,
      "loss": 0.3971,
      "step": 3800
    },
    {
      "epoch": 0.8496732026143791,
      "grad_norm": 2.122053384780884,
      "learning_rate": 2.8758169934640522e-05,
      "loss": 0.416,
      "step": 3900
    },
    {
      "epoch": 0.8714596949891068,
      "grad_norm": 2.520594596862793,
      "learning_rate": 2.8213507625272335e-05,
      "loss": 0.4205,
      "step": 4000
    }
  ],
  "logging_steps": 100,
  "max_steps": 9180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.478218866688e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}