{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 1.4164599180221558,
      "learning_rate": 1e-05,
      "loss": 18.3269,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.4089831113815308,
      "learning_rate": 1e-05,
      "loss": 18.151,
      "step": 100
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.413036584854126,
      "learning_rate": 1e-05,
      "loss": 18.295,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.4174010753631592,
      "learning_rate": 1e-05,
      "loss": 18.335,
      "step": 200
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4115498065948486,
      "learning_rate": 1e-05,
      "loss": 18.282,
      "step": 250
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.4158031940460205,
      "learning_rate": 1e-05,
      "loss": 18.2876,
      "step": 300
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.4230202436447144,
      "learning_rate": 1e-05,
      "loss": 18.218,
      "step": 350
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.408000111579895,
      "learning_rate": 1e-05,
      "loss": 18.1501,
      "step": 400
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.402531623840332,
      "learning_rate": 1e-05,
      "loss": 18.1445,
      "step": 450
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.4140069484710693,
      "learning_rate": 1e-05,
      "loss": 18.4638,
      "step": 500
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.4163990020751953,
      "learning_rate": 1e-05,
      "loss": 18.2091,
      "step": 550
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.4168442487716675,
      "learning_rate": 1e-05,
      "loss": 18.3754,
      "step": 600
    },
    {
      "epoch": 5.2,
      "grad_norm": 1.4224120378494263,
      "learning_rate": 1e-05,
      "loss": 18.3218,
      "step": 650
    },
    {
      "epoch": 5.6,
      "grad_norm": 1.4239962100982666,
      "learning_rate": 1e-05,
      "loss": 18.1367,
      "step": 700
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.4145816564559937,
      "learning_rate": 1e-05,
      "loss": 18.5159,
      "step": 750
    },
    {
      "epoch": 6.4,
      "grad_norm": 1.3733835220336914,
      "learning_rate": 1e-05,
      "loss": 18.5352,
      "step": 800
    },
    {
      "epoch": 6.8,
      "grad_norm": 1.3447598218917847,
      "learning_rate": 1e-05,
      "loss": 18.4848,
      "step": 850
    },
    {
      "epoch": 7.2,
      "grad_norm": 1.352599024772644,
      "learning_rate": 1e-05,
      "loss": 18.362,
      "step": 900
    },
    {
      "epoch": 7.6,
      "grad_norm": 1.241695761680603,
      "learning_rate": 1e-05,
      "loss": 18.3924,
      "step": 950
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.2154422998428345,
      "learning_rate": 1e-05,
      "loss": 18.5302,
      "step": 1000
    }
  ],
  "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
}