{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 0.7171631455421448,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.738,
      "step": 10
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.6291916370391846,
      "learning_rate": 0.00038,
      "loss": 0.576,
      "step": 20
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.711400032043457,
      "learning_rate": 0.00058,
      "loss": 0.5621,
      "step": 30
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.7226306200027466,
      "learning_rate": 0.0007800000000000001,
      "loss": 0.5347,
      "step": 40
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.7293037176132202,
      "learning_rate": 0.00098,
      "loss": 0.5287,
      "step": 50
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.492329478263855,
      "learning_rate": 0.0009990133642141358,
      "loss": 0.5951,
      "step": 60
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.9376721978187561,
      "learning_rate": 0.0009956077701257708,
      "loss": 0.5181,
      "step": 70
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.8607097268104553,
      "learning_rate": 0.000989787624799672,
      "loss": 0.5919,
      "step": 80
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.1687450408935547,
      "learning_rate": 0.0009815812833988292,
      "loss": 0.6227,
      "step": 90
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.9768692851066589,
      "learning_rate": 0.0009710287263936483,
      "loss": 0.5733,
      "step": 100
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.0083130598068237,
      "learning_rate": 0.0009581813647811198,
      "loss": 0.5704,
      "step": 110
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.0848993062973022,
      "learning_rate": 0.0009431017896156073,
      "loss": 0.5714,
      "step": 120
    },
    {
      "epoch": 1.04,
      "grad_norm": 1.2620114088058472,
      "learning_rate": 0.0009258634670715238,
      "loss": 0.5629,
      "step": 130
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.8126377463340759,
      "learning_rate": 0.0009065503805235138,
      "loss": 0.4443,
      "step": 140
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.2117948532104492,
      "learning_rate": 0.0008852566213878947,
      "loss": 0.4317,
      "step": 150
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.9739482402801514,
      "learning_rate": 0.0008620859307187339,
      "loss": 0.458,
      "step": 160
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 1.2082128524780273,
      "learning_rate": 0.0008371511937918616,
      "loss": 0.4182,
      "step": 170
    },
    {
      "epoch": 1.44,
      "grad_norm": 1.371351957321167,
      "learning_rate": 0.0008105738901391552,
      "loss": 0.489,
      "step": 180
    },
    {
      "epoch": 1.52,
      "grad_norm": 1.154181957244873,
      "learning_rate": 0.0007824835017124689,
      "loss": 0.4378,
      "step": 190
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.1466692686080933,
      "learning_rate": 0.0007530168820605818,
      "loss": 0.456,
      "step": 200
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 1.0234856605529785,
      "learning_rate": 0.0007223175895924637,
      "loss": 0.4724,
      "step": 210
    },
    {
      "epoch": 1.76,
      "grad_norm": 1.0541609525680542,
      "learning_rate": 0.0006905351881751372,
      "loss": 0.393,
      "step": 220
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 1.285465121269226,
      "learning_rate": 0.0006578245184735513,
      "loss": 0.4404,
      "step": 230
    },
    {
      "epoch": 1.92,
      "grad_norm": 1.226035714149475,
      "learning_rate": 0.0006243449435824276,
      "loss": 0.4397,
      "step": 240
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.3251399993896484,
      "learning_rate": 0.0005902595726252801,
      "loss": 0.4566,
      "step": 250
    },
    {
      "epoch": 2.08,
      "grad_norm": 1.7789580821990967,
      "learning_rate": 0.0005557344661031627,
      "loss": 0.2441,
      "step": 260
    },
    {
      "epoch": 2.16,
      "grad_norm": 1.0361311435699463,
      "learning_rate": 0.0005209378268645998,
      "loss": 0.254,
      "step": 270
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.9719555377960205,
      "learning_rate": 0.00048603918063821566,
      "loss": 0.2456,
      "step": 280
    },
    {
      "epoch": 2.32,
      "grad_norm": 1.2225875854492188,
      "learning_rate": 0.0004512085501204253,
      "loss": 0.2154,
      "step": 290
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.8809466361999512,
      "learning_rate": 0.0004166156266419489,
      "loss": 0.2113,
      "step": 300
    },
    {
      "epoch": 2.48,
      "grad_norm": 1.0200402736663818,
      "learning_rate": 0.000382428943448705,
      "loss": 0.2338,
      "step": 310
    },
    {
      "epoch": 2.56,
      "grad_norm": 1.0294510126113892,
      "learning_rate": 0.00034881505462477783,
      "loss": 0.225,
      "step": 320
    },
    {
      "epoch": 2.64,
      "grad_norm": 1.0166362524032593,
      "learning_rate": 0.00031593772365766105,
      "loss": 0.2494,
      "step": 330
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 1.0922179222106934,
      "learning_rate": 0.0002839571255990088,
      "loss": 0.2047,
      "step": 340
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.2643201351165771,
      "learning_rate": 0.0002530290667078846,
      "loss": 0.212,
      "step": 350
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.8040714859962463,
      "learning_rate": 0.000223304225378328,
      "loss": 0.2274,
      "step": 360
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.9333784580230713,
      "learning_rate": 0.00019492741804936621,
      "loss": 0.2093,
      "step": 370
    },
    {
      "epoch": 3.04,
      "grad_norm": 0.5495390892028809,
      "learning_rate": 0.0001680368936738792,
      "loss": 0.1401,
      "step": 380
    },
    {
      "epoch": 3.12,
      "grad_norm": 0.7462188601493835,
      "learning_rate": 0.00014276366018359842,
      "loss": 0.0869,
      "step": 390
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.5287328958511353,
      "learning_rate": 0.00011923084623163172,
      "loss": 0.0684,
      "step": 400
    },
    {
      "epoch": 3.2800000000000002,
      "grad_norm": 0.952439546585083,
      "learning_rate": 9.755310132204298e-05,
      "loss": 0.0752,
      "step": 410
    },
    {
      "epoch": 3.36,
      "grad_norm": 0.6919301152229309,
      "learning_rate": 7.783603724899258e-05,
      "loss": 0.066,
      "step": 420
    },
    {
      "epoch": 3.44,
      "grad_norm": 0.6896870732307434,
      "learning_rate": 6.0175713566691824e-05,
      "loss": 0.0645,
      "step": 430
    },
    {
      "epoch": 3.52,
      "grad_norm": 0.8325856328010559,
      "learning_rate": 4.465816959691149e-05,
      "loss": 0.0787,
      "step": 440
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.7463304400444031,
      "learning_rate": 3.1359005254054274e-05,
      "loss": 0.072,
      "step": 450
    },
    {
      "epoch": 3.68,
      "grad_norm": 0.7797716856002808,
      "learning_rate": 2.0343012729971243e-05,
      "loss": 0.0833,
      "step": 460
    },
    {
      "epoch": 3.76,
      "grad_norm": 1.173261284828186,
      "learning_rate": 1.166386083291604e-05,
      "loss": 0.0653,
      "step": 470
    },
    {
      "epoch": 3.84,
      "grad_norm": 0.7136673331260681,
      "learning_rate": 5.363833518505834e-06,
      "loss": 0.06,
      "step": 480
    },
    {
      "epoch": 3.92,
      "grad_norm": 0.7013105750083923,
      "learning_rate": 1.4736238865398766e-06,
      "loss": 0.0738,
      "step": 490
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.6790759563446045,
      "learning_rate": 1.2184647302626584e-08,
      "loss": 0.075,
      "step": 500
    },
    {
      "epoch": 4.0,
      "step": 500,
      "total_flos": 5591743584010240.0,
      "train_loss": 0.3324708139896393,
      "train_runtime": 676.5273,
      "train_samples_per_second": 5.913,
      "train_steps_per_second": 0.739
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 5591743584010240.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}