{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.215486280706795,
  "eval_steps": 500,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007182876023559833,
      "grad_norm": 102.55565643310547,
      "learning_rate": 3.339317773788151e-07,
      "loss": 4.51,
      "step": 100
    },
    {
      "epoch": 0.014365752047119667,
      "grad_norm": 20.8671875,
      "learning_rate": 6.929982046678636e-07,
      "loss": 1.3058,
      "step": 200
    },
    {
      "epoch": 0.0215486280706795,
      "grad_norm": 16.238826751708984,
      "learning_rate": 1.0520646319569122e-06,
      "loss": 0.7671,
      "step": 300
    },
    {
      "epoch": 0.028731504094239333,
      "grad_norm": 12.669879913330078,
      "learning_rate": 1.4111310592459606e-06,
      "loss": 0.639,
      "step": 400
    },
    {
      "epoch": 0.03591438011779917,
      "grad_norm": 13.375199317932129,
      "learning_rate": 1.770197486535009e-06,
      "loss": 0.5396,
      "step": 500
    },
    {
      "epoch": 0.043097256141359,
      "grad_norm": 36.680416107177734,
      "learning_rate": 2.1292639138240576e-06,
      "loss": 0.4649,
      "step": 600
    },
    {
      "epoch": 0.050280132164918834,
      "grad_norm": 15.553112983703613,
      "learning_rate": 2.488330341113106e-06,
      "loss": 0.4561,
      "step": 700
    },
    {
      "epoch": 0.057463008188478666,
      "grad_norm": 28.032434463500977,
      "learning_rate": 2.847396768402155e-06,
      "loss": 0.4152,
      "step": 800
    },
    {
      "epoch": 0.0646458842120385,
      "grad_norm": 40.55122756958008,
      "learning_rate": 3.2064631956912027e-06,
      "loss": 0.412,
      "step": 900
    },
    {
      "epoch": 0.07182876023559834,
      "grad_norm": 48.380340576171875,
      "learning_rate": 3.5655296229802514e-06,
      "loss": 0.4159,
      "step": 1000
    },
    {
      "epoch": 0.07901163625915816,
      "grad_norm": 18.708255767822266,
      "learning_rate": 3.9245960502693e-06,
      "loss": 0.3397,
      "step": 1100
    },
    {
      "epoch": 0.086194512282718,
      "grad_norm": 10.165841102600098,
      "learning_rate": 4.283662477558348e-06,
      "loss": 0.355,
      "step": 1200
    },
    {
      "epoch": 0.09337738830627783,
      "grad_norm": 17.107013702392578,
      "learning_rate": 4.6427289048473974e-06,
      "loss": 0.3312,
      "step": 1300
    },
    {
      "epoch": 0.10056026432983767,
      "grad_norm": 38.87083053588867,
      "learning_rate": 5.001795332136446e-06,
      "loss": 0.2452,
      "step": 1400
    },
    {
      "epoch": 0.1077431403533975,
      "grad_norm": 17.743247985839844,
      "learning_rate": 5.360861759425494e-06,
      "loss": 0.2204,
      "step": 1500
    },
    {
      "epoch": 0.11492601637695733,
      "grad_norm": 35.18050765991211,
      "learning_rate": 5.719928186714543e-06,
      "loss": 0.2338,
      "step": 1600
    },
    {
      "epoch": 0.12210889240051717,
      "grad_norm": 8.888273239135742,
      "learning_rate": 6.078994614003591e-06,
      "loss": 0.2269,
      "step": 1700
    },
    {
      "epoch": 0.129291768424077,
      "grad_norm": 6.807362079620361,
      "learning_rate": 6.4380610412926396e-06,
      "loss": 0.233,
      "step": 1800
    },
    {
      "epoch": 0.13647464444763682,
      "grad_norm": 3.313542366027832,
      "learning_rate": 6.797127468581688e-06,
      "loss": 0.2033,
      "step": 1900
    },
    {
      "epoch": 0.14365752047119668,
      "grad_norm": 4.184378623962402,
      "learning_rate": 7.156193895870737e-06,
      "loss": 0.1904,
      "step": 2000
    },
    {
      "epoch": 0.1508403964947565,
      "grad_norm": 29.64693832397461,
      "learning_rate": 7.515260323159785e-06,
      "loss": 0.2063,
      "step": 2100
    },
    {
      "epoch": 0.15802327251831633,
      "grad_norm": 19.15960121154785,
      "learning_rate": 7.874326750448834e-06,
      "loss": 0.2206,
      "step": 2200
    },
    {
      "epoch": 0.16520614854187618,
      "grad_norm": 12.115074157714844,
      "learning_rate": 8.233393177737883e-06,
      "loss": 0.1949,
      "step": 2300
    },
    {
      "epoch": 0.172389024565436,
      "grad_norm": 9.53875732421875,
      "learning_rate": 8.59245960502693e-06,
      "loss": 0.2,
      "step": 2400
    },
    {
      "epoch": 0.17957190058899583,
      "grad_norm": 3.5382916927337646,
      "learning_rate": 8.951526032315979e-06,
      "loss": 0.1875,
      "step": 2500
    },
    {
      "epoch": 0.18675477661255566,
      "grad_norm": 1.2547463178634644,
      "learning_rate": 9.310592459605027e-06,
      "loss": 0.2033,
      "step": 2600
    },
    {
      "epoch": 0.1939376526361155,
      "grad_norm": 1.9213370084762573,
      "learning_rate": 9.669658886894077e-06,
      "loss": 0.1946,
      "step": 2700
    },
    {
      "epoch": 0.20112052865967533,
      "grad_norm": 35.58647155761719,
      "learning_rate": 9.996807534219244e-06,
      "loss": 0.2231,
      "step": 2800
    },
    {
      "epoch": 0.20830340468323516,
      "grad_norm": 3.3178770542144775,
      "learning_rate": 9.956901711959775e-06,
      "loss": 0.1868,
      "step": 2900
    },
    {
      "epoch": 0.215486280706795,
      "grad_norm": 22.328224182128906,
      "learning_rate": 9.916995889700309e-06,
      "loss": 0.2107,
      "step": 3000
    }
  ],
  "logging_steps": 100,
  "max_steps": 27844,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}