{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 0.6611918807029724,
      "learning_rate": 5.319148936170213e-05,
      "loss": 0.6932,
      "step": 25
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.9467485547065735,
      "learning_rate": 0.00010638297872340425,
      "loss": 0.6912,
      "step": 50
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.9465051889419556,
      "learning_rate": 0.00015957446808510637,
      "loss": 0.6893,
      "step": 75
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.5430934429168701,
      "learning_rate": 0.0002127659574468085,
      "loss": 0.6804,
      "step": 100
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.6103107929229736,
      "learning_rate": 0.00026595744680851064,
      "loss": 0.6806,
      "step": 125
    },
    {
      "epoch": 0.6,
      "grad_norm": 2.3773200511932373,
      "learning_rate": 0.00031914893617021275,
      "loss": 0.6801,
      "step": 150
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.8832203149795532,
      "learning_rate": 0.0003723404255319149,
      "loss": 0.6791,
      "step": 175
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.3350876569747925,
      "learning_rate": 0.0003992081821181128,
      "loss": 0.6746,
      "step": 200
    },
    {
      "epoch": 0.9,
      "grad_norm": 1.5796219110488892,
      "learning_rate": 0.0003975585615308479,
      "loss": 0.6771,
      "step": 225
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.884006381034851,
      "learning_rate": 0.00039590894094358297,
      "loss": 0.6649,
      "step": 250
    },
    {
      "epoch": 1.1,
      "grad_norm": 3.286440372467041,
      "learning_rate": 0.0003942593203563181,
      "loss": 0.6388,
      "step": 275
    },
    {
      "epoch": 1.2,
      "grad_norm": 8.244946479797363,
      "learning_rate": 0.0003926096997690532,
      "loss": 0.6238,
      "step": 300
    },
    {
      "epoch": 1.3,
      "grad_norm": 4.265683650970459,
      "learning_rate": 0.00039096007918178817,
      "loss": 0.6383,
      "step": 325
    },
    {
      "epoch": 1.4,
      "grad_norm": 4.115826606750488,
      "learning_rate": 0.0003893104585945233,
      "loss": 0.6194,
      "step": 350
    },
    {
      "epoch": 1.5,
      "grad_norm": 5.694250583648682,
      "learning_rate": 0.0003876608380072583,
      "loss": 0.6324,
      "step": 375
    },
    {
      "epoch": 1.6,
      "grad_norm": 3.463121175765991,
      "learning_rate": 0.00038601121741999343,
      "loss": 0.621,
      "step": 400
    },
    {
      "epoch": 1.7,
      "grad_norm": 4.582865238189697,
      "learning_rate": 0.0003843615968327285,
      "loss": 0.6116,
      "step": 425
    },
    {
      "epoch": 1.8,
      "grad_norm": 11.996281623840332,
      "learning_rate": 0.0003827119762454636,
      "loss": 0.6393,
      "step": 450
    },
    {
      "epoch": 1.9,
      "grad_norm": 3.0407373905181885,
      "learning_rate": 0.00038106235565819863,
      "loss": 0.628,
      "step": 475
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.917588233947754,
      "learning_rate": 0.0003794127350709337,
      "loss": 0.6078,
      "step": 500
    },
    {
      "epoch": 2.1,
      "grad_norm": 4.748379707336426,
      "learning_rate": 0.0003777631144836688,
      "loss": 0.4899,
      "step": 525
    },
    {
      "epoch": 2.2,
      "grad_norm": 3.8076977729797363,
      "learning_rate": 0.00037611349389640383,
      "loss": 0.5086,
      "step": 550
    },
    {
      "epoch": 2.3,
      "grad_norm": 5.2440714836120605,
      "learning_rate": 0.00037446387330913894,
      "loss": 0.5327,
      "step": 575
    },
    {
      "epoch": 2.4,
      "grad_norm": 7.110438346862793,
      "learning_rate": 0.000372814252721874,
      "loss": 0.5436,
      "step": 600
    },
    {
      "epoch": 2.5,
      "grad_norm": 5.46150541305542,
      "learning_rate": 0.00037116463213460903,
      "loss": 0.5294,
      "step": 625
    },
    {
      "epoch": 2.6,
      "grad_norm": 5.136163234710693,
      "learning_rate": 0.00036951501154734414,
      "loss": 0.5245,
      "step": 650
    },
    {
      "epoch": 2.7,
      "grad_norm": 8.735346794128418,
      "learning_rate": 0.0003678653909600792,
      "loss": 0.5449,
      "step": 675
    },
    {
      "epoch": 2.8,
      "grad_norm": 2.922825574874878,
      "learning_rate": 0.0003662157703728143,
      "loss": 0.5406,
      "step": 700
    },
    {
      "epoch": 2.9,
      "grad_norm": 7.744819641113281,
      "learning_rate": 0.00036456614978554934,
      "loss": 0.5447,
      "step": 725
    },
    {
      "epoch": 3.0,
      "grad_norm": 11.6185884475708,
      "learning_rate": 0.00036291652919828444,
      "loss": 0.5195,
      "step": 750
    },
    {
      "epoch": 3.1,
      "grad_norm": 3.73836088180542,
      "learning_rate": 0.00036126690861101944,
      "loss": 0.3824,
      "step": 775
    },
    {
      "epoch": 3.2,
      "grad_norm": 14.850343704223633,
      "learning_rate": 0.00035961728802375454,
      "loss": 0.4071,
      "step": 800
    },
    {
      "epoch": 3.3,
      "grad_norm": 5.7157440185546875,
      "learning_rate": 0.0003579676674364896,
      "loss": 0.3986,
      "step": 825
    },
    {
      "epoch": 3.4,
      "grad_norm": 12.418399810791016,
      "learning_rate": 0.0003563180468492247,
      "loss": 0.4282,
      "step": 850
    },
    {
      "epoch": 3.5,
      "grad_norm": 12.793001174926758,
      "learning_rate": 0.0003546684262619598,
      "loss": 0.4822,
      "step": 875
    },
    {
      "epoch": 3.6,
      "grad_norm": 6.489450931549072,
      "learning_rate": 0.00035301880567469485,
      "loss": 0.4239,
      "step": 900
    },
    {
      "epoch": 3.7,
      "grad_norm": 5.365822792053223,
      "learning_rate": 0.0003513691850874299,
      "loss": 0.421,
      "step": 925
    },
    {
      "epoch": 3.8,
      "grad_norm": 12.643745422363281,
      "learning_rate": 0.00034971956450016495,
      "loss": 0.3964,
      "step": 950
    },
    {
      "epoch": 3.9,
      "grad_norm": 14.334024429321289,
      "learning_rate": 0.00034806994391290005,
      "loss": 0.4634,
      "step": 975
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.819091320037842,
      "learning_rate": 0.0003464203233256351,
      "loss": 0.4139,
      "step": 1000
    }
  ],
  "logging_steps": 25,
  "max_steps": 6250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 25,
  "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": 50819481600000.0,
  "train_batch_size": 20,
  "trial_name": null,
  "trial_params": null
}