{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.6,
  "eval_steps": 500,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 1.4107602834701538,
      "learning_rate": 1e-05,
      "loss": 18.0011,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.4118013381958008,
      "learning_rate": 1e-05,
      "loss": 18.1074,
      "step": 100
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.4094215631484985,
      "learning_rate": 1e-05,
      "loss": 17.8548,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.4178941249847412,
      "learning_rate": 1e-05,
      "loss": 18.2321,
      "step": 200
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.3967334032058716,
      "learning_rate": 1e-05,
      "loss": 18.0726,
      "step": 250
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.4012211561203003,
      "learning_rate": 1e-05,
      "loss": 17.9975,
      "step": 300
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.4091300964355469,
      "learning_rate": 1e-05,
      "loss": 17.9819,
      "step": 350
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.4035604000091553,
      "learning_rate": 1e-05,
      "loss": 17.88,
      "step": 400
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.407544732093811,
      "learning_rate": 1e-05,
      "loss": 17.904,
      "step": 450
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.4047907590866089,
      "learning_rate": 1e-05,
      "loss": 18.0957,
      "step": 500
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.4020367860794067,
      "learning_rate": 1e-05,
      "loss": 17.985,
      "step": 550
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.4153640270233154,
      "learning_rate": 1e-05,
      "loss": 18.0277,
      "step": 600
    },
    {
      "epoch": 5.2,
      "grad_norm": 1.4067825078964233,
      "learning_rate": 1e-05,
      "loss": 17.9143,
      "step": 650
    },
    {
      "epoch": 5.6,
      "grad_norm": 1.4077836275100708,
      "learning_rate": 1e-05,
      "loss": 18.0297,
      "step": 700
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.4031282663345337,
      "learning_rate": 1e-05,
      "loss": 18.143,
      "step": 750
    },
    {
      "epoch": 6.4,
      "grad_norm": 1.4233338832855225,
      "learning_rate": 1e-05,
      "loss": 18.2716,
      "step": 800
    },
    {
      "epoch": 6.8,
      "grad_norm": 1.4083062410354614,
      "learning_rate": 1e-05,
      "loss": 18.1286,
      "step": 850
    },
    {
      "epoch": 7.2,
      "grad_norm": 1.397931456565857,
      "learning_rate": 1e-05,
      "loss": 17.9444,
      "step": 900
    },
    {
      "epoch": 7.6,
      "grad_norm": 1.4177525043487549,
      "learning_rate": 1e-05,
      "loss": 17.981,
      "step": 950
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.3989773988723755,
      "learning_rate": 1e-05,
      "loss": 18.1666,
      "step": 1000
    },
    {
      "epoch": 8.4,
      "grad_norm": 1.3849033117294312,
      "learning_rate": 1e-05,
      "loss": 18.0085,
      "step": 1050
    },
    {
      "epoch": 8.8,
      "grad_norm": 1.362139105796814,
      "learning_rate": 1e-05,
      "loss": 18.1793,
      "step": 1100
    },
    {
      "epoch": 9.2,
      "grad_norm": 1.270612359046936,
      "learning_rate": 1e-05,
      "loss": 18.0745,
      "step": 1150
    },
    {
      "epoch": 9.6,
      "grad_norm": 1.3089044094085693,
      "learning_rate": 1e-05,
      "loss": 18.1972,
      "step": 1200
    }
  ],
  "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
}