{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0002110261144816671,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.110261144816671e-05,
      "grad_norm": 156.0476531982422,
      "learning_rate": 2e-05,
      "loss": 27.5043,
      "step": 1
    },
    {
      "epoch": 2.110261144816671e-05,
      "eval_loss": 4.941006183624268,
      "eval_runtime": 218.7524,
      "eval_samples_per_second": 91.213,
      "eval_steps_per_second": 45.609,
      "step": 1
    },
    {
      "epoch": 4.220522289633342e-05,
      "grad_norm": 90.08502960205078,
      "learning_rate": 4e-05,
      "loss": 20.0848,
      "step": 2
    },
    {
      "epoch": 6.330783434450013e-05,
      "grad_norm": 103.71065521240234,
      "learning_rate": 6e-05,
      "loss": 16.5587,
      "step": 3
    },
    {
      "epoch": 6.330783434450013e-05,
      "eval_loss": 4.937582015991211,
      "eval_runtime": 217.3586,
      "eval_samples_per_second": 91.798,
      "eval_steps_per_second": 45.901,
      "step": 3
    },
    {
      "epoch": 8.441044579266685e-05,
      "grad_norm": 115.48094177246094,
      "learning_rate": 8e-05,
      "loss": 22.4045,
      "step": 4
    },
    {
      "epoch": 0.00010551305724083355,
      "grad_norm": 106.41868591308594,
      "learning_rate": 0.0001,
      "loss": 21.763,
      "step": 5
    },
    {
      "epoch": 0.00012661566868900026,
      "grad_norm": 92.7852554321289,
      "learning_rate": 0.00012,
      "loss": 17.0887,
      "step": 6
    },
    {
      "epoch": 0.00012661566868900026,
      "eval_loss": 4.908989906311035,
      "eval_runtime": 216.1028,
      "eval_samples_per_second": 92.331,
      "eval_steps_per_second": 46.168,
      "step": 6
    },
    {
      "epoch": 0.000147718280137167,
      "grad_norm": 116.92227172851562,
      "learning_rate": 0.00014,
      "loss": 24.662,
      "step": 7
    },
    {
      "epoch": 0.0001688208915853337,
      "grad_norm": 80.14395141601562,
      "learning_rate": 0.00016,
      "loss": 16.5548,
      "step": 8
    },
    {
      "epoch": 0.0001899235030335004,
      "grad_norm": 67.32865142822266,
      "learning_rate": 0.00018,
      "loss": 16.5324,
      "step": 9
    },
    {
      "epoch": 0.0001899235030335004,
      "eval_loss": 4.816751956939697,
      "eval_runtime": 219.6859,
      "eval_samples_per_second": 90.825,
      "eval_steps_per_second": 45.415,
      "step": 9
    },
    {
      "epoch": 0.0002110261144816671,
      "grad_norm": 183.16184997558594,
      "learning_rate": 0.0002,
      "loss": 28.0161,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 129399634526208.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}