{
  "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": 1.4172989130020142,
      "learning_rate": 1e-05,
      "loss": 18.4591,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.419463872909546,
      "learning_rate": 1e-05,
      "loss": 18.2901,
      "step": 100
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.4208306074142456,
      "learning_rate": 1e-05,
      "loss": 18.5831,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.408556580543518,
      "learning_rate": 1e-05,
      "loss": 18.2578,
      "step": 200
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4126293659210205,
      "learning_rate": 1e-05,
      "loss": 18.4533,
      "step": 250
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.40609610080719,
      "learning_rate": 1e-05,
      "loss": 18.3359,
      "step": 300
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.406099557876587,
      "learning_rate": 1e-05,
      "loss": 18.4176,
      "step": 350
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.4220800399780273,
      "learning_rate": 1e-05,
      "loss": 18.3445,
      "step": 400
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.4044008255004883,
      "learning_rate": 1e-05,
      "loss": 18.1322,
      "step": 450
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.4127113819122314,
      "learning_rate": 1e-05,
      "loss": 18.5979,
      "step": 500
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.4114793539047241,
      "learning_rate": 1e-05,
      "loss": 18.2958,
      "step": 550
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.4228249788284302,
      "learning_rate": 1e-05,
      "loss": 18.4158,
      "step": 600
    },
    {
      "epoch": 5.2,
      "grad_norm": 1.404493808746338,
      "learning_rate": 1e-05,
      "loss": 18.4116,
      "step": 650
    },
    {
      "epoch": 5.6,
      "grad_norm": 1.4135618209838867,
      "learning_rate": 1e-05,
      "loss": 18.3257,
      "step": 700
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.3994121551513672,
      "learning_rate": 1e-05,
      "loss": 18.6609,
      "step": 750
    },
    {
      "epoch": 6.4,
      "grad_norm": 1.3721892833709717,
      "learning_rate": 1e-05,
      "loss": 18.6825,
      "step": 800
    },
    {
      "epoch": 6.8,
      "grad_norm": 1.3903437852859497,
      "learning_rate": 1e-05,
      "loss": 18.4883,
      "step": 850
    },
    {
      "epoch": 7.2,
      "grad_norm": 1.367257833480835,
      "learning_rate": 1e-05,
      "loss": 18.5246,
      "step": 900
    },
    {
      "epoch": 7.6,
      "grad_norm": 1.2732200622558594,
      "learning_rate": 1e-05,
      "loss": 18.6031,
      "step": 950
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.2526229619979858,
      "learning_rate": 1e-05,
      "loss": 18.6961,
      "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
}