{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 4125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024242424242424242,
      "grad_norm": 0.08251222968101501,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.4006,
      "step": 100
    },
    {
      "epoch": 0.048484848484848485,
      "grad_norm": 0.23244759440422058,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.3802,
      "step": 200
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 0.2762894332408905,
      "learning_rate": 2e-05,
      "loss": 2.3613,
      "step": 300
    },
    {
      "epoch": 0.09696969696969697,
      "grad_norm": 0.3933228552341461,
      "learning_rate": 1.9966289692316944e-05,
      "loss": 2.2924,
      "step": 400
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.45315420627593994,
      "learning_rate": 1.9865386046236597e-05,
      "loss": 2.2223,
      "step": 500
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 0.4649055302143097,
      "learning_rate": 1.9697969360350098e-05,
      "loss": 2.2044,
      "step": 600
    },
    {
      "epoch": 0.1696969696969697,
      "grad_norm": 0.5842418670654297,
      "learning_rate": 1.9465168368255946e-05,
      "loss": 2.1239,
      "step": 700
    },
    {
      "epoch": 0.19393939393939394,
      "grad_norm": 0.676047146320343,
      "learning_rate": 1.9168552628568632e-05,
      "loss": 2.1596,
      "step": 800
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 0.6532862186431885,
      "learning_rate": 1.8810121942857848e-05,
      "loss": 2.134,
      "step": 900
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.7170696258544922,
      "learning_rate": 1.839229287286327e-05,
      "loss": 2.1441,
      "step": 1000
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.7590866684913635,
      "learning_rate": 1.7917882447886585e-05,
      "loss": 2.0895,
      "step": 1100
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 0.6926172375679016,
      "learning_rate": 1.7390089172206594e-05,
      "loss": 2.0802,
      "step": 1200
    },
    {
      "epoch": 0.3151515151515151,
      "grad_norm": 0.8891839981079102,
      "learning_rate": 1.681247146056654e-05,
      "loss": 2.0769,
      "step": 1300
    },
    {
      "epoch": 0.3393939393939394,
      "grad_norm": 0.7070772647857666,
      "learning_rate": 1.6188923647122946e-05,
      "loss": 2.0446,
      "step": 1400
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.8614781498908997,
      "learning_rate": 1.552364972960506e-05,
      "loss": 2.0567,
      "step": 1500
    },
    {
      "epoch": 0.3878787878787879,
      "grad_norm": 0.7985982894897461,
      "learning_rate": 1.4821135025703491e-05,
      "loss": 2.0322,
      "step": 1600
    },
    {
      "epoch": 0.4121212121212121,
      "grad_norm": 0.8504014611244202,
      "learning_rate": 1.4086115932782316e-05,
      "loss": 2.0247,
      "step": 1700
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.8554436564445496,
      "learning_rate": 1.3323547994796597e-05,
      "loss": 2.0462,
      "step": 1800
    },
    {
      "epoch": 0.46060606060606063,
      "grad_norm": 0.8365380764007568,
      "learning_rate": 1.2538572491710079e-05,
      "loss": 2.0412,
      "step": 1900
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.9090964794158936,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 1.9871,
      "step": 2000
    },
    {
      "epoch": 0.509090909090909,
      "grad_norm": 0.9732162356376648,
      "learning_rate": 1.092268359463302e-05,
      "loss": 2.0424,
      "step": 2100
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.8215560913085938,
      "learning_rate": 1.01026646230229e-05,
      "loss": 2.026,
      "step": 2200
    },
    {
      "epoch": 0.5575757575757576,
      "grad_norm": 0.802616536617279,
      "learning_rate": 9.281953480206725e-06,
      "loss": 2.0041,
      "step": 2300
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 0.9250068068504333,
      "learning_rate": 8.466083451213145e-06,
      "loss": 2.0377,
      "step": 2400
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 1.0361137390136719,
      "learning_rate": 7.660555181983517e-06,
      "loss": 1.9966,
      "step": 2500
    },
    {
      "epoch": 0.6303030303030303,
      "grad_norm": 0.9372274279594421,
      "learning_rate": 6.870799593678459e-06,
      "loss": 1.9911,
      "step": 2600
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 0.8156213164329529,
      "learning_rate": 6.102141267073207e-06,
      "loss": 1.9825,
      "step": 2700
    },
    {
      "epoch": 0.6787878787878788,
      "grad_norm": 1.2848368883132935,
      "learning_rate": 5.3597625439063685e-06,
      "loss": 2.0076,
      "step": 2800
    },
    {
      "epoch": 0.703030303030303,
      "grad_norm": 1.0307776927947998,
      "learning_rate": 4.648668587212998e-06,
      "loss": 1.9921,
      "step": 2900
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.89860600233078,
      "learning_rate": 3.973653636207437e-06,
      "loss": 1.9687,
      "step": 3000
    },
    {
      "epoch": 0.7515151515151515,
      "grad_norm": 0.991875410079956,
      "learning_rate": 3.339268683227499e-06,
      "loss": 2.0015,
      "step": 3100
    },
    {
      "epoch": 0.7757575757575758,
      "grad_norm": 1.1908742189407349,
      "learning_rate": 2.749790790664074e-06,
      "loss": 1.9698,
      "step": 3200
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.0616734027862549,
      "learning_rate": 2.209194254743295e-06,
      "loss": 2.0068,
      "step": 3300
    },
    {
      "epoch": 0.8242424242424242,
      "grad_norm": 1.0849283933639526,
      "learning_rate": 1.7211238105768213e-06,
      "loss": 2.0146,
      "step": 3400
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 0.9579031467437744,
      "learning_rate": 1.2888700591334225e-06,
      "loss": 2.0373,
      "step": 3500
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 0.9680696725845337,
      "learning_rate": 9.153472818047627e-07,
      "loss": 2.0193,
      "step": 3600
    },
    {
      "epoch": 0.896969696969697,
      "grad_norm": 0.988714337348938,
      "learning_rate": 6.030737921409169e-07,
      "loss": 1.9609,
      "step": 3700
    },
    {
      "epoch": 0.9212121212121213,
      "grad_norm": 0.9824697971343994,
      "learning_rate": 3.541549572254488e-07,
      "loss": 1.9667,
      "step": 3800
    },
    {
      "epoch": 0.9454545454545454,
      "grad_norm": 0.9895309209823608,
      "learning_rate": 1.7026900316098217e-07,
      "loss": 2.0066,
      "step": 3900
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.8761349320411682,
      "learning_rate": 5.265570036553813e-08,
      "loss": 1.9828,
      "step": 4000
    },
    {
      "epoch": 0.9939393939393939,
      "grad_norm": 1.041921854019165,
      "learning_rate": 2.108004964086474e-09,
      "loss": 1.9977,
      "step": 4100
    },
    {
      "epoch": 1.0,
      "step": 4125,
      "total_flos": 7.49645512704e+16,
      "train_loss": 2.070154784231475,
      "train_runtime": 1281.9871,
      "train_samples_per_second": 6.435,
      "train_steps_per_second": 3.218
    }
  ],
  "logging_steps": 100,
  "max_steps": 4125,
  "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": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.49645512704e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}