{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.6,
  "eval_steps": 500,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 3.241444727559499,
      "learning_rate": 4.166666666666667e-06,
      "loss": -0.0588,
      "step": 5
    },
    {
      "epoch": 0.8,
      "grad_norm": 5.32623822233065,
      "learning_rate": 8.333333333333334e-06,
      "loss": -0.0873,
      "step": 10
    },
    {
      "epoch": 1.2,
      "grad_norm": 15.8041464722526,
      "learning_rate": 9.722222222222223e-06,
      "loss": -0.6934,
      "step": 15
    },
    {
      "epoch": 1.6,
      "grad_norm": 120.16174141145932,
      "learning_rate": 9.25925925925926e-06,
      "loss": -4.1973,
      "step": 20
    },
    {
      "epoch": 2.0,
      "grad_norm": 50.08612513681741,
      "learning_rate": 8.796296296296297e-06,
      "loss": -13.405,
      "step": 25
    },
    {
      "epoch": 2.4,
      "grad_norm": 295.424478128771,
      "learning_rate": 8.333333333333334e-06,
      "loss": -18.7935,
      "step": 30
    },
    {
      "epoch": 2.8,
      "grad_norm": 493.9640362150348,
      "learning_rate": 7.870370370370372e-06,
      "loss": -31.1509,
      "step": 35
    },
    {
      "epoch": 3.2,
      "grad_norm": 93.87000957824152,
      "learning_rate": 7.4074074074074075e-06,
      "loss": -44.4191,
      "step": 40
    },
    {
      "epoch": 3.6,
      "grad_norm": 134.99093438726675,
      "learning_rate": 6.944444444444445e-06,
      "loss": -53.0336,
      "step": 45
    },
    {
      "epoch": 4.0,
      "grad_norm": 131.78440529588994,
      "learning_rate": 6.481481481481482e-06,
      "loss": -65.837,
      "step": 50
    },
    {
      "epoch": 4.4,
      "grad_norm": 117.73681125892666,
      "learning_rate": 6.018518518518519e-06,
      "loss": -77.5102,
      "step": 55
    },
    {
      "epoch": 4.8,
      "grad_norm": 117.05560407621871,
      "learning_rate": 5.555555555555557e-06,
      "loss": -85.0267,
      "step": 60
    },
    {
      "epoch": 5.2,
      "grad_norm": 98.14939761160105,
      "learning_rate": 5.092592592592593e-06,
      "loss": -89.3683,
      "step": 65
    },
    {
      "epoch": 5.6,
      "grad_norm": 105.40446186084566,
      "learning_rate": 4.62962962962963e-06,
      "loss": -91.3682,
      "step": 70
    },
    {
      "epoch": 6.0,
      "grad_norm": 91.22462461648249,
      "learning_rate": 4.166666666666667e-06,
      "loss": -92.3792,
      "step": 75
    },
    {
      "epoch": 6.4,
      "grad_norm": 91.1265822704548,
      "learning_rate": 3.7037037037037037e-06,
      "loss": -92.9222,
      "step": 80
    },
    {
      "epoch": 6.8,
      "grad_norm": 89.86170978575277,
      "learning_rate": 3.240740740740741e-06,
      "loss": -93.476,
      "step": 85
    },
    {
      "epoch": 7.2,
      "grad_norm": 89.77140905804795,
      "learning_rate": 2.7777777777777783e-06,
      "loss": -93.6957,
      "step": 90
    },
    {
      "epoch": 7.6,
      "grad_norm": 90.3030070947644,
      "learning_rate": 2.314814814814815e-06,
      "loss": -93.8858,
      "step": 95
    },
    {
      "epoch": 8.0,
      "grad_norm": 89.67057158817525,
      "learning_rate": 1.8518518518518519e-06,
      "loss": -94.1347,
      "step": 100
    },
    {
      "epoch": 8.4,
      "grad_norm": 89.30029196668944,
      "learning_rate": 1.3888888888888892e-06,
      "loss": -94.0645,
      "step": 105
    },
    {
      "epoch": 8.8,
      "grad_norm": 89.43075418962819,
      "learning_rate": 9.259259259259259e-07,
      "loss": -94.3247,
      "step": 110
    },
    {
      "epoch": 9.2,
      "grad_norm": 89.7643319124866,
      "learning_rate": 4.6296296296296297e-07,
      "loss": -94.3944,
      "step": 115
    },
    {
      "epoch": 9.6,
      "grad_norm": 89.26033644280638,
      "learning_rate": 0.0,
      "loss": -94.0103,
      "step": 120
    },
    {
      "epoch": 9.6,
      "step": 120,
      "total_flos": 0.0,
      "train_loss": -63.00987243900696,
      "train_runtime": 401.6667,
      "train_samples_per_second": 9.959,
      "train_steps_per_second": 0.299
    }
  ],
  "logging_steps": 5,
  "max_steps": 120,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}