{
  "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": 1.4062377214431763,
      "learning_rate": 1e-05,
      "loss": 17.9594,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.410114049911499,
      "learning_rate": 1e-05,
      "loss": 18.0145,
      "step": 100
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.4155189990997314,
      "learning_rate": 1e-05,
      "loss": 18.4522,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.413204550743103,
      "learning_rate": 1e-05,
      "loss": 18.0097,
      "step": 200
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4190232753753662,
      "learning_rate": 1e-05,
      "loss": 18.1188,
      "step": 250
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.4105501174926758,
      "learning_rate": 1e-05,
      "loss": 18.1525,
      "step": 300
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.4148707389831543,
      "learning_rate": 1e-05,
      "loss": 18.0536,
      "step": 350
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.4178122282028198,
      "learning_rate": 1e-05,
      "loss": 18.0798,
      "step": 400
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.4168564081192017,
      "learning_rate": 1e-05,
      "loss": 17.9514,
      "step": 450
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.4154655933380127,
      "learning_rate": 1e-05,
      "loss": 18.2477,
      "step": 500
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.4207638502120972,
      "learning_rate": 1e-05,
      "loss": 17.9624,
      "step": 550
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.4150888919830322,
      "learning_rate": 1e-05,
      "loss": 18.2141,
      "step": 600
    },
    {
      "epoch": 5.2,
      "grad_norm": 1.3999563455581665,
      "learning_rate": 1e-05,
      "loss": 18.1262,
      "step": 650
    },
    {
      "epoch": 5.6,
      "grad_norm": 1.4183685779571533,
      "learning_rate": 1e-05,
      "loss": 18.1485,
      "step": 700
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.4119173288345337,
      "learning_rate": 1e-05,
      "loss": 18.2776,
      "step": 750
    },
    {
      "epoch": 6.4,
      "grad_norm": 1.4120863676071167,
      "learning_rate": 1e-05,
      "loss": 18.4573,
      "step": 800
    },
    {
      "epoch": 6.8,
      "grad_norm": 1.4137214422225952,
      "learning_rate": 1e-05,
      "loss": 18.2415,
      "step": 850
    },
    {
      "epoch": 7.2,
      "grad_norm": 1.408633828163147,
      "learning_rate": 1e-05,
      "loss": 17.9907,
      "step": 900
    },
    {
      "epoch": 7.6,
      "grad_norm": 1.4081895351409912,
      "learning_rate": 1e-05,
      "loss": 18.3071,
      "step": 950
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.376461148262024,
      "learning_rate": 1e-05,
      "loss": 18.143,
      "step": 1000
    },
    {
      "epoch": 8.4,
      "grad_norm": 1.3912196159362793,
      "learning_rate": 1e-05,
      "loss": 18.2432,
      "step": 1050
    },
    {
      "epoch": 8.8,
      "grad_norm": 1.3867040872573853,
      "learning_rate": 1e-05,
      "loss": 18.1434,
      "step": 1100
    },
    {
      "epoch": 9.2,
      "grad_norm": 1.3476893901824951,
      "learning_rate": 1e-05,
      "loss": 18.3725,
      "step": 1150
    },
    {
      "epoch": 9.6,
      "grad_norm": 1.2195262908935547,
      "learning_rate": 1e-05,
      "loss": 18.3131,
      "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
}