{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1978021978021978,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.195170283317566,
      "learning_rate": 0.0,
      "loss": 1.0821,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.0331945419311523,
      "learning_rate": 9.56e-05,
      "loss": 1.0763,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.1415084600448608,
      "learning_rate": 0.0001912,
      "loss": 1.0495,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.063579797744751,
      "learning_rate": 0.0002868,
      "loss": 0.956,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.6625626087188721,
      "learning_rate": 0.0003824,
      "loss": 0.8477,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.6782878637313843,
      "learning_rate": 0.000478,
      "loss": 1.0343,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.6161335110664368,
      "learning_rate": 0.00047694013303769406,
      "loss": 0.9727,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.41984498500823975,
      "learning_rate": 0.00047588026607538804,
      "loss": 0.8698,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.3116914927959442,
      "learning_rate": 0.0004748203991130821,
      "loss": 0.8446,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.29025012254714966,
      "learning_rate": 0.00047376053215077607,
      "loss": 0.7877,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.39959046244621277,
      "learning_rate": 0.00047270066518847006,
      "loss": 0.8688,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5689778923988342,
      "learning_rate": 0.0004716407982261641,
      "loss": 0.8847,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.40798476338386536,
      "learning_rate": 0.00047058093126385814,
      "loss": 0.7254,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.6968982219696045,
      "learning_rate": 0.0004695210643015521,
      "loss": 0.8179,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5194700360298157,
      "learning_rate": 0.00046846119733924617,
      "loss": 0.7156,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.43927809596061707,
      "learning_rate": 0.00046740133037694015,
      "loss": 0.8273,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.3979283571243286,
      "learning_rate": 0.00046634146341463414,
      "loss": 0.7288,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.4314859211444855,
      "learning_rate": 0.0004652815964523282,
      "loss": 0.7677,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.3548160791397095,
      "learning_rate": 0.0004642217294900222,
      "loss": 0.6472,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.38769328594207764,
      "learning_rate": 0.0004631618625277162,
      "loss": 0.6578,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3017254173755646,
      "learning_rate": 0.00046210199556541025,
      "loss": 0.7163,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.33315712213516235,
      "learning_rate": 0.00046104212860310423,
      "loss": 0.6951,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3334329426288605,
      "learning_rate": 0.0004599822616407982,
      "loss": 0.7464,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.301981121301651,
      "learning_rate": 0.00045892239467849226,
      "loss": 0.667,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3768517076969147,
      "learning_rate": 0.0004578625277161863,
      "loss": 0.6719,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3810518980026245,
      "learning_rate": 0.0004568026607538803,
      "loss": 0.7687,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.4689561128616333,
      "learning_rate": 0.00045574279379157433,
      "loss": 0.7114,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3895481824874878,
      "learning_rate": 0.00045468292682926826,
      "loss": 0.7328,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.44972071051597595,
      "learning_rate": 0.0004536230598669623,
      "loss": 0.708,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.39502742886543274,
      "learning_rate": 0.00045256319290465634,
      "loss": 0.7672,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3823579561121792e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}