{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.020415662896574253,
  "eval_steps": 63,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.166265158629701e-05,
      "eval_loss": 10.840862274169922,
      "eval_runtime": 7.8991,
      "eval_samples_per_second": 326.366,
      "eval_steps_per_second": 163.183,
      "step": 1
    },
    {
      "epoch": 0.0008166265158629701,
      "grad_norm": 0.3761455714702606,
      "learning_rate": 0.00019979453927503364,
      "loss": 10.8359,
      "step": 10
    },
    {
      "epoch": 0.0016332530317259401,
      "grad_norm": 0.394729346036911,
      "learning_rate": 0.00019815591569910654,
      "loss": 10.815,
      "step": 20
    },
    {
      "epoch": 0.0024498795475889103,
      "grad_norm": 0.30855050683021545,
      "learning_rate": 0.00019490557470106686,
      "loss": 10.7786,
      "step": 30
    },
    {
      "epoch": 0.0032665060634518802,
      "grad_norm": 0.42155948281288147,
      "learning_rate": 0.0001900968867902419,
      "loss": 10.7552,
      "step": 40
    },
    {
      "epoch": 0.00408313257931485,
      "grad_norm": 0.2492990493774414,
      "learning_rate": 0.00018380881048918405,
      "loss": 10.7528,
      "step": 50
    },
    {
      "epoch": 0.0048997590951778205,
      "grad_norm": 0.2550627887248993,
      "learning_rate": 0.00017614459583691346,
      "loss": 10.7484,
      "step": 60
    },
    {
      "epoch": 0.005144747049936712,
      "eval_loss": 10.749500274658203,
      "eval_runtime": 7.3007,
      "eval_samples_per_second": 353.116,
      "eval_steps_per_second": 176.558,
      "step": 63
    },
    {
      "epoch": 0.005716385611040791,
      "grad_norm": 0.2560204565525055,
      "learning_rate": 0.0001672300890261317,
      "loss": 10.7501,
      "step": 70
    },
    {
      "epoch": 0.0065330121269037604,
      "grad_norm": 0.189836785197258,
      "learning_rate": 0.00015721166601221698,
      "loss": 10.7455,
      "step": 80
    },
    {
      "epoch": 0.007349638642766731,
      "grad_norm": 0.23742568492889404,
      "learning_rate": 0.00014625382902408356,
      "loss": 10.7458,
      "step": 90
    },
    {
      "epoch": 0.0081662651586297,
      "grad_norm": 0.2744472026824951,
      "learning_rate": 0.00013453650544213076,
      "loss": 10.7482,
      "step": 100
    },
    {
      "epoch": 0.008982891674492672,
      "grad_norm": 0.3114999532699585,
      "learning_rate": 0.00012225209339563145,
      "loss": 10.7417,
      "step": 110
    },
    {
      "epoch": 0.009799518190355641,
      "grad_norm": 0.24193626642227173,
      "learning_rate": 0.00010960230259076818,
      "loss": 10.7392,
      "step": 120
    },
    {
      "epoch": 0.010289494099873423,
      "eval_loss": 10.737412452697754,
      "eval_runtime": 7.1792,
      "eval_samples_per_second": 359.091,
      "eval_steps_per_second": 179.545,
      "step": 126
    },
    {
      "epoch": 0.01061614470621861,
      "grad_norm": 0.310713529586792,
      "learning_rate": 9.679484224283449e-05,
      "loss": 10.7422,
      "step": 130
    },
    {
      "epoch": 0.011432771222081582,
      "grad_norm": 0.2092239260673523,
      "learning_rate": 8.404001049666211e-05,
      "loss": 10.7337,
      "step": 140
    },
    {
      "epoch": 0.012249397737944551,
      "grad_norm": 0.19805459678173065,
      "learning_rate": 7.154724133689677e-05,
      "loss": 10.7418,
      "step": 150
    },
    {
      "epoch": 0.013066024253807521,
      "grad_norm": 0.179554283618927,
      "learning_rate": 5.952166568776062e-05,
      "loss": 10.7348,
      "step": 160
    },
    {
      "epoch": 0.01388265076967049,
      "grad_norm": 0.22178767621517181,
      "learning_rate": 4.8160743168947496e-05,
      "loss": 10.7329,
      "step": 170
    },
    {
      "epoch": 0.014699277285533462,
      "grad_norm": 0.23290759325027466,
      "learning_rate": 3.7651019814126654e-05,
      "loss": 10.7324,
      "step": 180
    },
    {
      "epoch": 0.015434241149810134,
      "eval_loss": 10.731443405151367,
      "eval_runtime": 7.1741,
      "eval_samples_per_second": 359.346,
      "eval_steps_per_second": 179.673,
      "step": 189
    },
    {
      "epoch": 0.015515903801396431,
      "grad_norm": 0.2047327607870102,
      "learning_rate": 2.8165064990227252e-05,
      "loss": 10.7352,
      "step": 190
    },
    {
      "epoch": 0.0163325303172594,
      "grad_norm": 0.20196911692619324,
      "learning_rate": 1.985863781320435e-05,
      "loss": 10.7285,
      "step": 200
    },
    {
      "epoch": 0.017149156833122372,
      "grad_norm": 0.21181835234165192,
      "learning_rate": 1.286812958766106e-05,
      "loss": 10.7256,
      "step": 210
    },
    {
      "epoch": 0.017965783348985343,
      "grad_norm": 0.23975443840026855,
      "learning_rate": 7.308324265397836e-06,
      "loss": 10.7394,
      "step": 220
    },
    {
      "epoch": 0.01878240986484831,
      "grad_norm": 0.21740056574344635,
      "learning_rate": 3.270513696097055e-06,
      "loss": 10.7338,
      "step": 230
    },
    {
      "epoch": 0.019599036380711282,
      "grad_norm": 0.2698234021663666,
      "learning_rate": 8.209986176753948e-07,
      "loss": 10.7245,
      "step": 240
    },
    {
      "epoch": 0.020415662896574253,
      "grad_norm": 0.2873691916465759,
      "learning_rate": 0.0,
      "loss": 10.729,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 63,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 16031529566208.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}