{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9922480620155039,
  "eval_steps": 3,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06201550387596899,
      "grad_norm": 1.324246883392334,
      "learning_rate": 0.0,
      "loss": 95.471,
      "step": 1
    },
    {
      "epoch": 0.12403100775193798,
      "grad_norm": 1.289596676826477,
      "learning_rate": 0.0002,
      "loss": 95.437,
      "step": 2
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 1.3081743717193604,
      "learning_rate": 0.00019781476007338058,
      "loss": 95.3922,
      "step": 3
    },
    {
      "epoch": 0.18604651162790697,
      "eval_loss": 11.929765701293945,
      "eval_runtime": 0.1016,
      "eval_samples_per_second": 49.2,
      "eval_steps_per_second": 19.68,
      "step": 3
    },
    {
      "epoch": 0.24806201550387597,
      "grad_norm": 1.3165432214736938,
      "learning_rate": 0.0001913545457642601,
      "loss": 95.3637,
      "step": 4
    },
    {
      "epoch": 0.31007751937984496,
      "grad_norm": 1.312530755996704,
      "learning_rate": 0.00018090169943749476,
      "loss": 95.3947,
      "step": 5
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 1.3151068687438965,
      "learning_rate": 0.00016691306063588583,
      "loss": 95.3294,
      "step": 6
    },
    {
      "epoch": 0.37209302325581395,
      "eval_loss": 11.918438911437988,
      "eval_runtime": 0.0905,
      "eval_samples_per_second": 55.233,
      "eval_steps_per_second": 22.093,
      "step": 6
    },
    {
      "epoch": 0.43410852713178294,
      "grad_norm": 1.3396779298782349,
      "learning_rate": 0.00015000000000000001,
      "loss": 95.2012,
      "step": 7
    },
    {
      "epoch": 0.49612403100775193,
      "grad_norm": 1.3890634775161743,
      "learning_rate": 0.00013090169943749476,
      "loss": 95.2384,
      "step": 8
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 1.3167331218719482,
      "learning_rate": 0.00011045284632676536,
      "loss": 95.1952,
      "step": 9
    },
    {
      "epoch": 0.5581395348837209,
      "eval_loss": 11.909274101257324,
      "eval_runtime": 0.083,
      "eval_samples_per_second": 60.261,
      "eval_steps_per_second": 24.104,
      "step": 9
    },
    {
      "epoch": 0.6201550387596899,
      "grad_norm": 1.3647342920303345,
      "learning_rate": 8.954715367323468e-05,
      "loss": 95.1965,
      "step": 10
    },
    {
      "epoch": 0.6821705426356589,
      "grad_norm": 1.311335563659668,
      "learning_rate": 6.909830056250527e-05,
      "loss": 95.1483,
      "step": 11
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 1.2832609415054321,
      "learning_rate": 5.000000000000002e-05,
      "loss": 95.1862,
      "step": 12
    },
    {
      "epoch": 0.7441860465116279,
      "eval_loss": 11.905265808105469,
      "eval_runtime": 0.0675,
      "eval_samples_per_second": 74.071,
      "eval_steps_per_second": 29.628,
      "step": 12
    },
    {
      "epoch": 0.8062015503875969,
      "grad_norm": 1.3671646118164062,
      "learning_rate": 3.308693936411421e-05,
      "loss": 95.1522,
      "step": 13
    },
    {
      "epoch": 0.8682170542635659,
      "grad_norm": 1.2626255750656128,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 95.1792,
      "step": 14
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 1.3233616352081299,
      "learning_rate": 8.645454235739903e-06,
      "loss": 95.0949,
      "step": 15
    },
    {
      "epoch": 0.9302325581395349,
      "eval_loss": 11.903751373291016,
      "eval_runtime": 0.0733,
      "eval_samples_per_second": 68.257,
      "eval_steps_per_second": 27.303,
      "step": 15
    },
    {
      "epoch": 0.9922480620155039,
      "grad_norm": 1.3294514417648315,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 95.1233,
      "step": 16
    },
    {
      "epoch": 0.9922480620155039,
      "step": 16,
      "total_flos": 26286684635136.0,
      "train_loss": 95.25646018981934,
      "train_runtime": 18.4927,
      "train_samples_per_second": 27.849,
      "train_steps_per_second": 0.865
    },
    {
      "epoch": 0.9922480620155039,
      "eval_loss": 11.903702735900879,
      "eval_runtime": 0.5035,
      "eval_samples_per_second": 9.931,
      "eval_steps_per_second": 3.972,
      "step": 16
    }
  ],
  "logging_steps": 1,
  "max_steps": 16,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 26286684635136.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}