{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 2004,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0499001996007984,
      "grad_norm": 3.5520248413085938,
      "learning_rate": 5.414364640883978e-06,
      "loss": 0.4617,
      "step": 50
    },
    {
      "epoch": 0.0998003992015968,
      "grad_norm": 4.260124206542969,
      "learning_rate": 1.0939226519337018e-05,
      "loss": 0.4357,
      "step": 100
    },
    {
      "epoch": 0.1497005988023952,
      "grad_norm": 2.909259080886841,
      "learning_rate": 1.6464088397790058e-05,
      "loss": 0.4064,
      "step": 150
    },
    {
      "epoch": 0.1996007984031936,
      "grad_norm": 1.7840492725372314,
      "learning_rate": 1.9997996619906375e-05,
      "loss": 0.4212,
      "step": 200
    },
    {
      "epoch": 0.249500998003992,
      "grad_norm": 3.765916585922241,
      "learning_rate": 1.9971421218881642e-05,
      "loss": 0.4019,
      "step": 250
    },
    {
      "epoch": 0.2994011976047904,
      "grad_norm": 3.896864652633667,
      "learning_rate": 1.9914024726308284e-05,
      "loss": 0.3965,
      "step": 300
    },
    {
      "epoch": 0.34930139720558884,
      "grad_norm": 8.40927505493164,
      "learning_rate": 1.9825984551455585e-05,
      "loss": 0.3949,
      "step": 350
    },
    {
      "epoch": 0.3992015968063872,
      "grad_norm": 4.71005916595459,
      "learning_rate": 1.970757282145864e-05,
      "loss": 0.4092,
      "step": 400
    },
    {
      "epoch": 0.4491017964071856,
      "grad_norm": 4.222394943237305,
      "learning_rate": 1.9559155540188965e-05,
      "loss": 0.3905,
      "step": 450
    },
    {
      "epoch": 0.499001996007984,
      "grad_norm": 4.025149822235107,
      "learning_rate": 1.9381191456957516e-05,
      "loss": 0.3853,
      "step": 500
    },
    {
      "epoch": 0.5489021956087824,
      "grad_norm": 2.301793336868286,
      "learning_rate": 1.9174230648546855e-05,
      "loss": 0.3757,
      "step": 550
    },
    {
      "epoch": 0.5988023952095808,
      "grad_norm": 11.234354972839355,
      "learning_rate": 1.893891281895534e-05,
      "loss": 0.3907,
      "step": 600
    },
    {
      "epoch": 0.6487025948103793,
      "grad_norm": 4.995813369750977,
      "learning_rate": 1.8675965322108713e-05,
      "loss": 0.4029,
      "step": 650
    },
    {
      "epoch": 0.6986027944111777,
      "grad_norm": 3.2409844398498535,
      "learning_rate": 1.838620091365083e-05,
      "loss": 0.3961,
      "step": 700
    },
    {
      "epoch": 0.7485029940119761,
      "grad_norm": 3.947786569595337,
      "learning_rate": 1.80705152387625e-05,
      "loss": 0.3693,
      "step": 750
    },
    {
      "epoch": 0.7984031936127745,
      "grad_norm": 2.521354913711548,
      "learning_rate": 1.7729884063773596e-05,
      "loss": 0.3717,
      "step": 800
    },
    {
      "epoch": 0.8483033932135728,
      "grad_norm": 2.0015060901641846,
      "learning_rate": 1.7365360260125233e-05,
      "loss": 0.3771,
      "step": 850
    },
    {
      "epoch": 0.8982035928143712,
      "grad_norm": 2.748753786087036,
      "learning_rate": 1.697807055000447e-05,
      "loss": 0.3756,
      "step": 900
    },
    {
      "epoch": 0.9481037924151696,
      "grad_norm": 6.853181838989258,
      "learning_rate": 1.6569212023710624e-05,
      "loss": 0.3834,
      "step": 950
    },
    {
      "epoch": 0.998003992015968,
      "grad_norm": 3.869363307952881,
      "learning_rate": 1.614004843951774e-05,
      "loss": 0.3708,
      "step": 1000
    },
    {
      "epoch": 1.0479041916167664,
      "grad_norm": 1.820420742034912,
      "learning_rate": 1.5691906317470182e-05,
      "loss": 0.3728,
      "step": 1050
    },
    {
      "epoch": 1.0978043912175648,
      "grad_norm": 2.278934955596924,
      "learning_rate": 1.522617083918523e-05,
      "loss": 0.3675,
      "step": 1100
    },
    {
      "epoch": 1.1477045908183632,
      "grad_norm": 4.441009998321533,
      "learning_rate": 1.4744281566336039e-05,
      "loss": 0.3524,
      "step": 1150
    },
    {
      "epoch": 1.1976047904191618,
      "grad_norm": 3.737205982208252,
      "learning_rate": 1.4247727991049036e-05,
      "loss": 0.3407,
      "step": 1200
    },
    {
      "epoch": 1.24750499001996,
      "grad_norm": 6.3948540687561035,
      "learning_rate": 1.3738044931969103e-05,
      "loss": 0.3556,
      "step": 1250
    },
    {
      "epoch": 1.2974051896207586,
      "grad_norm": 2.192323923110962,
      "learning_rate": 1.3216807790223108e-05,
      "loss": 0.359,
      "step": 1300
    },
    {
      "epoch": 1.347305389221557,
      "grad_norm": 3.622485637664795,
      "learning_rate": 1.2685627679945297e-05,
      "loss": 0.3594,
      "step": 1350
    },
    {
      "epoch": 1.3972055888223553,
      "grad_norm": 3.1616196632385254,
      "learning_rate": 1.2146146448415847e-05,
      "loss": 0.3384,
      "step": 1400
    },
    {
      "epoch": 1.4471057884231537,
      "grad_norm": 4.088330268859863,
      "learning_rate": 1.1600031601205001e-05,
      "loss": 0.3614,
      "step": 1450
    },
    {
      "epoch": 1.4970059880239521,
      "grad_norm": 4.012702465057373,
      "learning_rate": 1.1048971148008917e-05,
      "loss": 0.3435,
      "step": 1500
    },
    {
      "epoch": 1.5469061876247505,
      "grad_norm": 4.387750625610352,
      "learning_rate": 1.0494668385108433e-05,
      "loss": 0.3495,
      "step": 1550
    },
    {
      "epoch": 1.596806387225549,
      "grad_norm": 4.125097751617432,
      "learning_rate": 9.938836630577868e-06,
      "loss": 0.345,
      "step": 1600
    },
    {
      "epoch": 1.6467065868263473,
      "grad_norm": 6.880813121795654,
      "learning_rate": 9.38319392851706e-06,
      "loss": 0.3514,
      "step": 1650
    },
    {
      "epoch": 1.6966067864271457,
      "grad_norm": 2.5724949836730957,
      "learning_rate": 8.829457738675486e-06,
      "loss": 0.3343,
      "step": 1700
    },
    {
      "epoch": 1.746506986027944,
      "grad_norm": 5.649964332580566,
      "learning_rate": 8.279339627882612e-06,
      "loss": 0.3232,
      "step": 1750
    },
    {
      "epoch": 1.7964071856287425,
      "grad_norm": 2.4297564029693604,
      "learning_rate": 7.734539979692912e-06,
      "loss": 0.3304,
      "step": 1800
    },
    {
      "epoch": 1.846307385229541,
      "grad_norm": 1.9791656732559204,
      "learning_rate": 7.196742738597746e-06,
      "loss": 0.3379,
      "step": 1850
    },
    {
      "epoch": 1.8962075848303392,
      "grad_norm": 6.672551155090332,
      "learning_rate": 6.667610205049422e-06,
      "loss": 0.3265,
      "step": 1900
    },
    {
      "epoch": 1.9461077844311379,
      "grad_norm": 3.6431407928466797,
      "learning_rate": 6.148777897385789e-06,
      "loss": 0.3374,
      "step": 1950
    },
    {
      "epoch": 1.996007984031936,
      "grad_norm": 4.975691795349121,
      "learning_rate": 5.641849496536765e-06,
      "loss": 0.3387,
      "step": 2000
    }
  ],
  "logging_steps": 50,
  "max_steps": 3006,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6865793438173184e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}