{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.17953321364452424,
  "eval_steps": 5,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003590664272890485,
      "eval_loss": 11.042671203613281,
      "eval_runtime": 0.2536,
      "eval_samples_per_second": 465.332,
      "eval_steps_per_second": 232.666,
      "step": 1
    },
    {
      "epoch": 0.010771992818671455,
      "grad_norm": 3.922430992126465,
      "learning_rate": 3e-05,
      "loss": 44.1523,
      "step": 3
    },
    {
      "epoch": 0.017953321364452424,
      "eval_loss": 11.039698600769043,
      "eval_runtime": 0.247,
      "eval_samples_per_second": 477.641,
      "eval_steps_per_second": 238.82,
      "step": 5
    },
    {
      "epoch": 0.02154398563734291,
      "grad_norm": 3.7408604621887207,
      "learning_rate": 6e-05,
      "loss": 44.1838,
      "step": 6
    },
    {
      "epoch": 0.03231597845601436,
      "grad_norm": 3.6904845237731934,
      "learning_rate": 9e-05,
      "loss": 44.1623,
      "step": 9
    },
    {
      "epoch": 0.03590664272890485,
      "eval_loss": 11.029208183288574,
      "eval_runtime": 0.2744,
      "eval_samples_per_second": 429.955,
      "eval_steps_per_second": 214.977,
      "step": 10
    },
    {
      "epoch": 0.04308797127468582,
      "grad_norm": 3.711442470550537,
      "learning_rate": 9.938441702975689e-05,
      "loss": 44.1317,
      "step": 12
    },
    {
      "epoch": 0.05385996409335727,
      "grad_norm": 3.626725196838379,
      "learning_rate": 9.619397662556435e-05,
      "loss": 44.0647,
      "step": 15
    },
    {
      "epoch": 0.05385996409335727,
      "eval_loss": 11.008035659790039,
      "eval_runtime": 0.2443,
      "eval_samples_per_second": 482.954,
      "eval_steps_per_second": 241.477,
      "step": 15
    },
    {
      "epoch": 0.06463195691202872,
      "grad_norm": 3.3971025943756104,
      "learning_rate": 9.045084971874738e-05,
      "loss": 43.9962,
      "step": 18
    },
    {
      "epoch": 0.0718132854578097,
      "eval_loss": 10.996824264526367,
      "eval_runtime": 0.2446,
      "eval_samples_per_second": 482.454,
      "eval_steps_per_second": 241.227,
      "step": 20
    },
    {
      "epoch": 0.07540394973070018,
      "grad_norm": 3.6952595710754395,
      "learning_rate": 8.247240241650918e-05,
      "loss": 43.9724,
      "step": 21
    },
    {
      "epoch": 0.08617594254937164,
      "grad_norm": 3.675994396209717,
      "learning_rate": 7.269952498697734e-05,
      "loss": 43.9475,
      "step": 24
    },
    {
      "epoch": 0.08976660682226212,
      "eval_loss": 10.981802940368652,
      "eval_runtime": 0.2466,
      "eval_samples_per_second": 478.457,
      "eval_steps_per_second": 239.228,
      "step": 25
    },
    {
      "epoch": 0.09694793536804308,
      "grad_norm": 3.6856377124786377,
      "learning_rate": 6.167226819279528e-05,
      "loss": 43.9206,
      "step": 27
    },
    {
      "epoch": 0.10771992818671454,
      "grad_norm": 3.877152919769287,
      "learning_rate": 5e-05,
      "loss": 43.9313,
      "step": 30
    },
    {
      "epoch": 0.10771992818671454,
      "eval_loss": 10.966498374938965,
      "eval_runtime": 0.256,
      "eval_samples_per_second": 460.954,
      "eval_steps_per_second": 230.477,
      "step": 30
    },
    {
      "epoch": 0.118491921005386,
      "grad_norm": 3.32474684715271,
      "learning_rate": 3.832773180720475e-05,
      "loss": 43.8417,
      "step": 33
    },
    {
      "epoch": 0.12567324955116696,
      "eval_loss": 10.952359199523926,
      "eval_runtime": 0.2511,
      "eval_samples_per_second": 469.903,
      "eval_steps_per_second": 234.952,
      "step": 35
    },
    {
      "epoch": 0.12926391382405744,
      "grad_norm": 3.8607993125915527,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 43.7851,
      "step": 36
    },
    {
      "epoch": 0.1400359066427289,
      "grad_norm": 3.5752923488616943,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 43.7701,
      "step": 39
    },
    {
      "epoch": 0.1436265709156194,
      "eval_loss": 10.948221206665039,
      "eval_runtime": 0.2411,
      "eval_samples_per_second": 489.506,
      "eval_steps_per_second": 244.753,
      "step": 40
    },
    {
      "epoch": 0.15080789946140036,
      "grad_norm": 3.8073651790618896,
      "learning_rate": 9.549150281252633e-06,
      "loss": 43.8047,
      "step": 42
    },
    {
      "epoch": 0.1615798922800718,
      "grad_norm": 3.3860981464385986,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 43.8426,
      "step": 45
    },
    {
      "epoch": 0.1615798922800718,
      "eval_loss": 10.947005271911621,
      "eval_runtime": 0.2768,
      "eval_samples_per_second": 426.339,
      "eval_steps_per_second": 213.17,
      "step": 45
    },
    {
      "epoch": 0.17235188509874327,
      "grad_norm": 3.8361706733703613,
      "learning_rate": 6.15582970243117e-07,
      "loss": 43.7625,
      "step": 48
    },
    {
      "epoch": 0.17953321364452424,
      "eval_loss": 10.946943283081055,
      "eval_runtime": 0.2515,
      "eval_samples_per_second": 469.196,
      "eval_steps_per_second": 234.598,
      "step": 50
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 37355520000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}