{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04,
  "eval_steps": 1000,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002,
      "grad_norm": 0.728621244430542,
      "learning_rate": 0.00066,
      "loss": 7.944070434570312,
      "step": 100
    },
    {
      "epoch": 0.004,
      "grad_norm": 0.6194736361503601,
      "learning_rate": 0.0009999976160274871,
      "loss": 6.688648071289062,
      "step": 200
    },
    {
      "epoch": 0.006,
      "grad_norm": 0.42749303579330444,
      "learning_rate": 0.000999977956590203,
      "loss": 6.362667846679687,
      "step": 300
    },
    {
      "epoch": 0.008,
      "grad_norm": 0.6455233693122864,
      "learning_rate": 0.0009999384399149713,
      "loss": 6.1362109375,
      "step": 400
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.38843703269958496,
      "learning_rate": 0.0009998790675712448,
      "loss": 5.9013720703125,
      "step": 500
    },
    {
      "epoch": 0.012,
      "grad_norm": 0.37035471200942993,
      "learning_rate": 0.000999799841917069,
      "loss": 5.723118896484375,
      "step": 600
    },
    {
      "epoch": 0.014,
      "grad_norm": 0.3410094380378723,
      "learning_rate": 0.0009997007660989881,
      "loss": 5.57857666015625,
      "step": 700
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.33731603622436523,
      "learning_rate": 0.0009995818440519195,
      "loss": 5.440355224609375,
      "step": 800
    },
    {
      "epoch": 0.018,
      "grad_norm": 0.39496415853500366,
      "learning_rate": 0.0009994430804989986,
      "loss": 5.352986450195313,
      "step": 900
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.3883383870124817,
      "learning_rate": 0.0009992844809513896,
      "loss": 5.53045166015625,
      "step": 1000
    },
    {
      "epoch": 0.02,
      "eval_accuracy": 0.19006987944761863,
      "eval_loss": 5.351119041442871,
      "eval_runtime": 5.7942,
      "eval_samples_per_second": 334.99,
      "eval_steps_per_second": 21.056,
      "step": 1000
    },
    {
      "epoch": 0.022,
      "grad_norm": 0.5580651760101318,
      "learning_rate": 0.0009991060517080686,
      "loss": 5.3906793212890625,
      "step": 1100
    },
    {
      "epoch": 0.024,
      "grad_norm": 4.792799472808838,
      "learning_rate": 0.0009989077998555718,
      "loss": 5.624612426757812,
      "step": 1200
    },
    {
      "epoch": 0.026,
      "grad_norm": 5.352905750274658,
      "learning_rate": 0.0009986897332677144,
      "loss": 6.0997509765625,
      "step": 1300
    },
    {
      "epoch": 0.028,
      "grad_norm": 5.617880344390869,
      "learning_rate": 0.0009984518606052791,
      "loss": 7.137509765625,
      "step": 1400
    },
    {
      "epoch": 0.03,
      "grad_norm": 6.961197853088379,
      "learning_rate": 0.0009981941913156701,
      "loss": 6.8974456787109375,
      "step": 1500
    },
    {
      "epoch": 0.032,
      "grad_norm": 7.469847679138184,
      "learning_rate": 0.0009979167356325394,
      "loss": 6.911260375976562,
      "step": 1600
    },
    {
      "epoch": 0.034,
      "grad_norm": 21.165908813476562,
      "learning_rate": 0.0009976195045753797,
      "loss": 6.70553466796875,
      "step": 1700
    },
    {
      "epoch": 0.036,
      "grad_norm": 10.395805358886719,
      "learning_rate": 0.0009973025099490876,
      "loss": 6.70605712890625,
      "step": 1800
    },
    {
      "epoch": 0.038,
      "grad_norm": 2.6919143199920654,
      "learning_rate": 0.0009969657643434933,
      "loss": 6.605548706054687,
      "step": 1900
    },
    {
      "epoch": 0.04,
      "grad_norm": 470.6007080078125,
      "learning_rate": 0.0009966092811328612,
      "loss": 6.552777099609375,
      "step": 2000
    },
    {
      "epoch": 0.04,
      "eval_accuracy": 0.10447133692459855,
      "eval_loss": 6.653895378112793,
      "eval_runtime": 5.1208,
      "eval_samples_per_second": 379.042,
      "eval_steps_per_second": 23.824,
      "step": 2000
    }
  ],
  "logging_steps": 100,
  "max_steps": 50000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.271008768e+16,
  "train_batch_size": 120,
  "trial_name": null,
  "trial_params": null
}