{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.35714285714285715,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014285714285714285,
      "grad_norm": 14.128439903259277,
      "learning_rate": 9.857142857142858e-05,
      "loss": 5.5604,
      "step": 20
    },
    {
      "epoch": 0.02857142857142857,
      "grad_norm": 14.23494815826416,
      "learning_rate": 9.714285714285715e-05,
      "loss": 4.6719,
      "step": 40
    },
    {
      "epoch": 0.04285714285714286,
      "grad_norm": 13.843968391418457,
      "learning_rate": 9.571428571428573e-05,
      "loss": 4.4492,
      "step": 60
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 12.36043643951416,
      "learning_rate": 9.428571428571429e-05,
      "loss": 4.1471,
      "step": 80
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 11.155304908752441,
      "learning_rate": 9.285714285714286e-05,
      "loss": 3.9922,
      "step": 100
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 12.575331687927246,
      "learning_rate": 9.142857142857143e-05,
      "loss": 4.1232,
      "step": 120
    },
    {
      "epoch": 0.1,
      "grad_norm": 14.813372611999512,
      "learning_rate": 9e-05,
      "loss": 4.0796,
      "step": 140
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 15.004693984985352,
      "learning_rate": 8.857142857142857e-05,
      "loss": 3.7742,
      "step": 160
    },
    {
      "epoch": 0.12857142857142856,
      "grad_norm": 15.635838508605957,
      "learning_rate": 8.714285714285715e-05,
      "loss": 3.8024,
      "step": 180
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 12.239358901977539,
      "learning_rate": 8.571428571428571e-05,
      "loss": 3.7662,
      "step": 200
    },
    {
      "epoch": 0.15714285714285714,
      "grad_norm": 17.418853759765625,
      "learning_rate": 8.428571428571429e-05,
      "loss": 3.8781,
      "step": 220
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 18.593626022338867,
      "learning_rate": 8.285714285714287e-05,
      "loss": 3.9188,
      "step": 240
    },
    {
      "epoch": 0.18571428571428572,
      "grad_norm": 11.001754760742188,
      "learning_rate": 8.142857142857143e-05,
      "loss": 3.6587,
      "step": 260
    },
    {
      "epoch": 0.2,
      "grad_norm": 14.99055290222168,
      "learning_rate": 8e-05,
      "loss": 3.7494,
      "step": 280
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 13.02241039276123,
      "learning_rate": 7.857142857142858e-05,
      "loss": 3.7421,
      "step": 300
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 19.851003646850586,
      "learning_rate": 7.714285714285715e-05,
      "loss": 3.6926,
      "step": 320
    },
    {
      "epoch": 0.24285714285714285,
      "grad_norm": 14.331436157226562,
      "learning_rate": 7.571428571428571e-05,
      "loss": 3.6418,
      "step": 340
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 15.481107711791992,
      "learning_rate": 7.428571428571429e-05,
      "loss": 3.6614,
      "step": 360
    },
    {
      "epoch": 0.2714285714285714,
      "grad_norm": 13.689815521240234,
      "learning_rate": 7.285714285714286e-05,
      "loss": 3.6289,
      "step": 380
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 16.152088165283203,
      "learning_rate": 7.142857142857143e-05,
      "loss": 3.7508,
      "step": 400
    },
    {
      "epoch": 0.3,
      "grad_norm": 11.060943603515625,
      "learning_rate": 7e-05,
      "loss": 3.7885,
      "step": 420
    },
    {
      "epoch": 0.3142857142857143,
      "grad_norm": 12.639877319335938,
      "learning_rate": 6.857142857142858e-05,
      "loss": 3.528,
      "step": 440
    },
    {
      "epoch": 0.32857142857142857,
      "grad_norm": 14.593839645385742,
      "learning_rate": 6.714285714285714e-05,
      "loss": 3.6221,
      "step": 460
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 13.310423851013184,
      "learning_rate": 6.571428571428571e-05,
      "loss": 3.617,
      "step": 480
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 31.857540130615234,
      "learning_rate": 6.428571428571429e-05,
      "loss": 3.5771,
      "step": 500
    }
  ],
  "logging_steps": 20,
  "max_steps": 1400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 184798603714560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}