{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 14.4,
  "eval_steps": 500,
  "global_step": 1800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 1.4095439910888672,
      "learning_rate": 1e-05,
      "loss": 19.02,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.4067671298980713,
      "learning_rate": 1e-05,
      "loss": 18.7936,
      "step": 100
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.415981411933899,
      "learning_rate": 1e-05,
      "loss": 19.1206,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.4117282629013062,
      "learning_rate": 1e-05,
      "loss": 18.8048,
      "step": 200
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4245758056640625,
      "learning_rate": 1e-05,
      "loss": 19.173,
      "step": 250
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.4133721590042114,
      "learning_rate": 1e-05,
      "loss": 19.0712,
      "step": 300
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.4103721380233765,
      "learning_rate": 1e-05,
      "loss": 19.1209,
      "step": 350
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.4230144023895264,
      "learning_rate": 1e-05,
      "loss": 18.9683,
      "step": 400
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.4083384275436401,
      "learning_rate": 1e-05,
      "loss": 19.3656,
      "step": 450
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.3991148471832275,
      "learning_rate": 1e-05,
      "loss": 19.1857,
      "step": 500
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.404693365097046,
      "learning_rate": 1e-05,
      "loss": 19.3599,
      "step": 550
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.4012234210968018,
      "learning_rate": 1e-05,
      "loss": 19.2505,
      "step": 600
    },
    {
      "epoch": 5.2,
      "grad_norm": 1.3942335844039917,
      "learning_rate": 1e-05,
      "loss": 19.2448,
      "step": 650
    },
    {
      "epoch": 5.6,
      "grad_norm": 1.4199410676956177,
      "learning_rate": 1e-05,
      "loss": 19.3727,
      "step": 700
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.4002327919006348,
      "learning_rate": 1e-05,
      "loss": 19.7333,
      "step": 750
    },
    {
      "epoch": 6.4,
      "grad_norm": 1.4205961227416992,
      "learning_rate": 1e-05,
      "loss": 19.6552,
      "step": 800
    },
    {
      "epoch": 6.8,
      "grad_norm": 1.4098219871520996,
      "learning_rate": 1e-05,
      "loss": 19.9566,
      "step": 850
    },
    {
      "epoch": 7.2,
      "grad_norm": 1.3988615274429321,
      "learning_rate": 1e-05,
      "loss": 20.0284,
      "step": 900
    },
    {
      "epoch": 7.6,
      "grad_norm": 1.4089635610580444,
      "learning_rate": 1e-05,
      "loss": 20.1581,
      "step": 950
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.4102603197097778,
      "learning_rate": 1e-05,
      "loss": 20.2274,
      "step": 1000
    },
    {
      "epoch": 8.4,
      "grad_norm": 1.4135903120040894,
      "learning_rate": 1e-05,
      "loss": 20.4219,
      "step": 1050
    },
    {
      "epoch": 8.8,
      "grad_norm": 1.397956371307373,
      "learning_rate": 1e-05,
      "loss": 20.7166,
      "step": 1100
    },
    {
      "epoch": 9.2,
      "grad_norm": 1.3939450979232788,
      "learning_rate": 1e-05,
      "loss": 20.7159,
      "step": 1150
    },
    {
      "epoch": 9.6,
      "grad_norm": 1.3623358011245728,
      "learning_rate": 1e-05,
      "loss": 20.9827,
      "step": 1200
    },
    {
      "epoch": 10.0,
      "grad_norm": 1.3958908319473267,
      "learning_rate": 1e-05,
      "loss": 21.1753,
      "step": 1250
    },
    {
      "epoch": 10.4,
      "grad_norm": 1.3938192129135132,
      "learning_rate": 1e-05,
      "loss": 20.9305,
      "step": 1300
    },
    {
      "epoch": 10.8,
      "grad_norm": 1.4077519178390503,
      "learning_rate": 1e-05,
      "loss": 21.5608,
      "step": 1350
    },
    {
      "epoch": 11.2,
      "grad_norm": 1.381304383277893,
      "learning_rate": 1e-05,
      "loss": 22.2291,
      "step": 1400
    },
    {
      "epoch": 11.6,
      "grad_norm": 1.2582303285598755,
      "learning_rate": 1e-05,
      "loss": 21.9737,
      "step": 1450
    },
    {
      "epoch": 12.0,
      "grad_norm": 1.3962666988372803,
      "learning_rate": 1e-05,
      "loss": 22.211,
      "step": 1500
    },
    {
      "epoch": 12.4,
      "grad_norm": 1.3676923513412476,
      "learning_rate": 1e-05,
      "loss": 23.2834,
      "step": 1550
    },
    {
      "epoch": 12.8,
      "grad_norm": 1.3159232139587402,
      "learning_rate": 1e-05,
      "loss": 22.313,
      "step": 1600
    },
    {
      "epoch": 13.2,
      "grad_norm": 1.2676888704299927,
      "learning_rate": 1e-05,
      "loss": 23.0728,
      "step": 1650
    },
    {
      "epoch": 13.6,
      "grad_norm": 1.271669626235962,
      "learning_rate": 1e-05,
      "loss": 22.452,
      "step": 1700
    },
    {
      "epoch": 14.0,
      "grad_norm": 1.308357834815979,
      "learning_rate": 1e-05,
      "loss": 24.039,
      "step": 1750
    },
    {
      "epoch": 14.4,
      "grad_norm": 0.8994763493537903,
      "learning_rate": 1e-05,
      "loss": 24.0429,
      "step": 1800
    }
  ],
  "logging_steps": 50,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 40,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}