{
  "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": 1.4047811031341553,
      "learning_rate": 1e-05,
      "loss": 19.0289,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.4063372611999512,
      "learning_rate": 1e-05,
      "loss": 19.0743,
      "step": 100
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.4205735921859741,
      "learning_rate": 1e-05,
      "loss": 19.2142,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.4195704460144043,
      "learning_rate": 1e-05,
      "loss": 19.135,
      "step": 200
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4022976160049438,
      "learning_rate": 1e-05,
      "loss": 19.123,
      "step": 250
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.4196256399154663,
      "learning_rate": 1e-05,
      "loss": 19.0494,
      "step": 300
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.4219794273376465,
      "learning_rate": 1e-05,
      "loss": 19.0662,
      "step": 350
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.4115924835205078,
      "learning_rate": 1e-05,
      "loss": 18.9115,
      "step": 400
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.4089257717132568,
      "learning_rate": 1e-05,
      "loss": 18.8372,
      "step": 450
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.410565972328186,
      "learning_rate": 1e-05,
      "loss": 19.3381,
      "step": 500
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.4226503372192383,
      "learning_rate": 1e-05,
      "loss": 19.0086,
      "step": 550
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.4153313636779785,
      "learning_rate": 1e-05,
      "loss": 19.0687,
      "step": 600
    },
    {
      "epoch": 5.2,
      "grad_norm": 1.4151759147644043,
      "learning_rate": 1e-05,
      "loss": 19.1714,
      "step": 650
    },
    {
      "epoch": 5.6,
      "grad_norm": 1.4260205030441284,
      "learning_rate": 1e-05,
      "loss": 19.0273,
      "step": 700
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.3912925720214844,
      "learning_rate": 1e-05,
      "loss": 19.1773,
      "step": 750
    },
    {
      "epoch": 6.4,
      "grad_norm": 1.3890074491500854,
      "learning_rate": 1e-05,
      "loss": 19.38,
      "step": 800
    },
    {
      "epoch": 6.8,
      "grad_norm": 1.4133774042129517,
      "learning_rate": 1e-05,
      "loss": 19.1865,
      "step": 850
    },
    {
      "epoch": 7.2,
      "grad_norm": 1.379645586013794,
      "learning_rate": 1e-05,
      "loss": 19.0296,
      "step": 900
    },
    {
      "epoch": 7.6,
      "grad_norm": 1.4168747663497925,
      "learning_rate": 1e-05,
      "loss": 19.1475,
      "step": 950
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.356919527053833,
      "learning_rate": 1e-05,
      "loss": 19.1616,
      "step": 1000
    },
    {
      "epoch": 8.4,
      "grad_norm": 1.3100676536560059,
      "learning_rate": 1e-05,
      "loss": 19.3496,
      "step": 1050
    },
    {
      "epoch": 8.8,
      "grad_norm": 1.206251621246338,
      "learning_rate": 1e-05,
      "loss": 19.1178,
      "step": 1100
    },
    {
      "epoch": 9.2,
      "grad_norm": 1.134185791015625,
      "learning_rate": 1e-05,
      "loss": 19.1303,
      "step": 1150
    },
    {
      "epoch": 9.6,
      "grad_norm": 0.99580979347229,
      "learning_rate": 1e-05,
      "loss": 19.398,
      "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
}