{
  "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": 1.4144182205200195,
      "learning_rate": 1e-05,
      "loss": 18.4388,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.4249975681304932,
      "learning_rate": 1e-05,
      "loss": 18.1874,
      "step": 100
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.4133256673812866,
      "learning_rate": 1e-05,
      "loss": 18.5653,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.4150230884552002,
      "learning_rate": 1e-05,
      "loss": 18.2896,
      "step": 200
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.3994524478912354,
      "learning_rate": 1e-05,
      "loss": 18.2811,
      "step": 250
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.411582589149475,
      "learning_rate": 1e-05,
      "loss": 18.2745,
      "step": 300
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.412042260169983,
      "learning_rate": 1e-05,
      "loss": 18.3006,
      "step": 350
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.3946020603179932,
      "learning_rate": 1e-05,
      "loss": 18.2483,
      "step": 400
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.426118016242981,
      "learning_rate": 1e-05,
      "loss": 18.3318,
      "step": 450
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.406415581703186,
      "learning_rate": 1e-05,
      "loss": 18.3778,
      "step": 500
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.3917016983032227,
      "learning_rate": 1e-05,
      "loss": 18.3467,
      "step": 550
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.3939944505691528,
      "learning_rate": 1e-05,
      "loss": 18.2646,
      "step": 600
    },
    {
      "epoch": 5.2,
      "grad_norm": 1.4108140468597412,
      "learning_rate": 1e-05,
      "loss": 18.1088,
      "step": 650
    },
    {
      "epoch": 5.6,
      "grad_norm": 1.3781177997589111,
      "learning_rate": 1e-05,
      "loss": 18.4145,
      "step": 700
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.396727442741394,
      "learning_rate": 1e-05,
      "loss": 18.2402,
      "step": 750
    },
    {
      "epoch": 6.4,
      "grad_norm": 1.3952558040618896,
      "learning_rate": 1e-05,
      "loss": 18.3918,
      "step": 800
    },
    {
      "epoch": 6.8,
      "grad_norm": 1.3488835096359253,
      "learning_rate": 1e-05,
      "loss": 18.5743,
      "step": 850
    },
    {
      "epoch": 7.2,
      "grad_norm": 1.2782988548278809,
      "learning_rate": 1e-05,
      "loss": 18.3489,
      "step": 900
    },
    {
      "epoch": 7.6,
      "grad_norm": 1.2682045698165894,
      "learning_rate": 1e-05,
      "loss": 18.8168,
      "step": 950
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.2467010021209717,
      "learning_rate": 1e-05,
      "loss": 18.5312,
      "step": 1000
    },
    {
      "epoch": 8.4,
      "grad_norm": 1.239147663116455,
      "learning_rate": 1e-05,
      "loss": 18.543,
      "step": 1050
    },
    {
      "epoch": 8.8,
      "grad_norm": 1.0708495378494263,
      "learning_rate": 1e-05,
      "loss": 18.9617,
      "step": 1100
    },
    {
      "epoch": 9.2,
      "grad_norm": 0.7776874303817749,
      "learning_rate": 1e-05,
      "loss": 19.1334,
      "step": 1150
    },
    {
      "epoch": 9.6,
      "grad_norm": 0.7262330651283264,
      "learning_rate": 1e-05,
      "loss": 19.6455,
      "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
}