{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 50.63291139240506,
  "eval_steps": 25,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 0.0,
      "learning_rate": 0.00019696969696969698,
      "loss": 3.653,
      "step": 25
    },
    {
      "epoch": 1.2658227848101267,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3728,
      "eval_samples_per_second": 53.654,
      "eval_steps_per_second": 8.048,
      "step": 25
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 0.0,
      "learning_rate": 0.00019191919191919191,
      "loss": 3.661,
      "step": 50
    },
    {
      "epoch": 2.5316455696202533,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.366,
      "eval_samples_per_second": 54.652,
      "eval_steps_per_second": 8.198,
      "step": 50
    },
    {
      "epoch": 3.7974683544303796,
      "grad_norm": 0.0,
      "learning_rate": 0.00018686868686868687,
      "loss": 3.6566,
      "step": 75
    },
    {
      "epoch": 3.7974683544303796,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.36,
      "eval_samples_per_second": 55.559,
      "eval_steps_per_second": 8.334,
      "step": 75
    },
    {
      "epoch": 5.063291139240507,
      "grad_norm": 0.0,
      "learning_rate": 0.00018181818181818183,
      "loss": 3.6562,
      "step": 100
    },
    {
      "epoch": 5.063291139240507,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3575,
      "eval_samples_per_second": 55.943,
      "eval_steps_per_second": 8.391,
      "step": 100
    },
    {
      "epoch": 6.329113924050633,
      "grad_norm": 0.0,
      "learning_rate": 0.0001767676767676768,
      "loss": 3.6384,
      "step": 125
    },
    {
      "epoch": 6.329113924050633,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3524,
      "eval_samples_per_second": 56.761,
      "eval_steps_per_second": 8.514,
      "step": 125
    },
    {
      "epoch": 7.594936708860759,
      "grad_norm": 0.0,
      "learning_rate": 0.00017171717171717173,
      "loss": 3.6585,
      "step": 150
    },
    {
      "epoch": 7.594936708860759,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3546,
      "eval_samples_per_second": 56.397,
      "eval_steps_per_second": 8.459,
      "step": 150
    },
    {
      "epoch": 8.860759493670885,
      "grad_norm": 0.0,
      "learning_rate": 0.0001666666666666667,
      "loss": 3.6454,
      "step": 175
    },
    {
      "epoch": 8.860759493670885,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3607,
      "eval_samples_per_second": 55.454,
      "eval_steps_per_second": 8.318,
      "step": 175
    },
    {
      "epoch": 10.126582278481013,
      "grad_norm": 0.0,
      "learning_rate": 0.00016161616161616162,
      "loss": 3.667,
      "step": 200
    },
    {
      "epoch": 10.126582278481013,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3664,
      "eval_samples_per_second": 54.588,
      "eval_steps_per_second": 8.188,
      "step": 200
    },
    {
      "epoch": 11.39240506329114,
      "grad_norm": 0.0,
      "learning_rate": 0.00015656565656565658,
      "loss": 3.6564,
      "step": 225
    },
    {
      "epoch": 11.39240506329114,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.366,
      "eval_samples_per_second": 54.65,
      "eval_steps_per_second": 8.198,
      "step": 225
    },
    {
      "epoch": 12.658227848101266,
      "grad_norm": 0.0,
      "learning_rate": 0.00015151515151515152,
      "loss": 3.6437,
      "step": 250
    },
    {
      "epoch": 12.658227848101266,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3608,
      "eval_samples_per_second": 55.435,
      "eval_steps_per_second": 8.315,
      "step": 250
    },
    {
      "epoch": 13.924050632911392,
      "grad_norm": 0.0,
      "learning_rate": 0.00014646464646464648,
      "loss": 3.6569,
      "step": 275
    },
    {
      "epoch": 13.924050632911392,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3681,
      "eval_samples_per_second": 54.334,
      "eval_steps_per_second": 8.15,
      "step": 275
    },
    {
      "epoch": 15.189873417721518,
      "grad_norm": 0.0,
      "learning_rate": 0.0001414141414141414,
      "loss": 3.6336,
      "step": 300
    },
    {
      "epoch": 15.189873417721518,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3786,
      "eval_samples_per_second": 52.829,
      "eval_steps_per_second": 7.924,
      "step": 300
    },
    {
      "epoch": 16.455696202531644,
      "grad_norm": 0.0,
      "learning_rate": 0.00013636363636363637,
      "loss": 3.6463,
      "step": 325
    },
    {
      "epoch": 16.455696202531644,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3653,
      "eval_samples_per_second": 54.756,
      "eval_steps_per_second": 8.213,
      "step": 325
    },
    {
      "epoch": 17.72151898734177,
      "grad_norm": 0.0,
      "learning_rate": 0.00013131313131313133,
      "loss": 3.6615,
      "step": 350
    },
    {
      "epoch": 17.72151898734177,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3677,
      "eval_samples_per_second": 54.397,
      "eval_steps_per_second": 8.16,
      "step": 350
    },
    {
      "epoch": 18.9873417721519,
      "grad_norm": 0.0,
      "learning_rate": 0.00012626262626262626,
      "loss": 3.6409,
      "step": 375
    },
    {
      "epoch": 18.9873417721519,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.365,
      "eval_samples_per_second": 54.799,
      "eval_steps_per_second": 8.22,
      "step": 375
    },
    {
      "epoch": 20.253164556962027,
      "grad_norm": 0.0,
      "learning_rate": 0.00012121212121212122,
      "loss": 3.647,
      "step": 400
    },
    {
      "epoch": 20.253164556962027,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3733,
      "eval_samples_per_second": 53.579,
      "eval_steps_per_second": 8.037,
      "step": 400
    },
    {
      "epoch": 21.518987341772153,
      "grad_norm": 0.0,
      "learning_rate": 0.00011616161616161616,
      "loss": 3.6702,
      "step": 425
    },
    {
      "epoch": 21.518987341772153,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3653,
      "eval_samples_per_second": 54.748,
      "eval_steps_per_second": 8.212,
      "step": 425
    },
    {
      "epoch": 22.78481012658228,
      "grad_norm": 0.0,
      "learning_rate": 0.00011111111111111112,
      "loss": 3.6336,
      "step": 450
    },
    {
      "epoch": 22.78481012658228,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3648,
      "eval_samples_per_second": 54.832,
      "eval_steps_per_second": 8.225,
      "step": 450
    },
    {
      "epoch": 24.050632911392405,
      "grad_norm": 0.0,
      "learning_rate": 0.00010606060606060606,
      "loss": 3.6546,
      "step": 475
    },
    {
      "epoch": 24.050632911392405,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3614,
      "eval_samples_per_second": 55.34,
      "eval_steps_per_second": 8.301,
      "step": 475
    },
    {
      "epoch": 25.31645569620253,
      "grad_norm": 0.0,
      "learning_rate": 0.00010101010101010102,
      "loss": 3.6487,
      "step": 500
    },
    {
      "epoch": 25.31645569620253,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3549,
      "eval_samples_per_second": 56.359,
      "eval_steps_per_second": 8.454,
      "step": 500
    },
    {
      "epoch": 26.582278481012658,
      "grad_norm": 0.0,
      "learning_rate": 9.595959595959596e-05,
      "loss": 3.6221,
      "step": 525
    },
    {
      "epoch": 26.582278481012658,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3694,
      "eval_samples_per_second": 54.137,
      "eval_steps_per_second": 8.121,
      "step": 525
    },
    {
      "epoch": 27.848101265822784,
      "grad_norm": 0.0,
      "learning_rate": 9.090909090909092e-05,
      "loss": 3.644,
      "step": 550
    },
    {
      "epoch": 27.848101265822784,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3655,
      "eval_samples_per_second": 54.72,
      "eval_steps_per_second": 8.208,
      "step": 550
    },
    {
      "epoch": 29.11392405063291,
      "grad_norm": 0.0,
      "learning_rate": 8.585858585858586e-05,
      "loss": 3.6389,
      "step": 575
    },
    {
      "epoch": 29.11392405063291,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3643,
      "eval_samples_per_second": 54.896,
      "eval_steps_per_second": 8.234,
      "step": 575
    },
    {
      "epoch": 30.379746835443036,
      "grad_norm": 0.0,
      "learning_rate": 8.080808080808081e-05,
      "loss": 3.656,
      "step": 600
    },
    {
      "epoch": 30.379746835443036,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3693,
      "eval_samples_per_second": 54.156,
      "eval_steps_per_second": 8.123,
      "step": 600
    },
    {
      "epoch": 31.645569620253166,
      "grad_norm": 0.0,
      "learning_rate": 7.575757575757576e-05,
      "loss": 3.6414,
      "step": 625
    },
    {
      "epoch": 31.645569620253166,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3634,
      "eval_samples_per_second": 55.039,
      "eval_steps_per_second": 8.256,
      "step": 625
    },
    {
      "epoch": 32.91139240506329,
      "grad_norm": 0.0,
      "learning_rate": 7.07070707070707e-05,
      "loss": 3.6422,
      "step": 650
    },
    {
      "epoch": 32.91139240506329,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3731,
      "eval_samples_per_second": 53.611,
      "eval_steps_per_second": 8.042,
      "step": 650
    },
    {
      "epoch": 34.177215189873415,
      "grad_norm": 0.0,
      "learning_rate": 6.565656565656566e-05,
      "loss": 3.6396,
      "step": 675
    },
    {
      "epoch": 34.177215189873415,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3707,
      "eval_samples_per_second": 53.955,
      "eval_steps_per_second": 8.093,
      "step": 675
    },
    {
      "epoch": 35.44303797468354,
      "grad_norm": 0.0,
      "learning_rate": 6.060606060606061e-05,
      "loss": 3.6658,
      "step": 700
    },
    {
      "epoch": 35.44303797468354,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3884,
      "eval_samples_per_second": 51.489,
      "eval_steps_per_second": 7.723,
      "step": 700
    },
    {
      "epoch": 36.70886075949367,
      "grad_norm": 0.0,
      "learning_rate": 5.555555555555556e-05,
      "loss": 3.6473,
      "step": 725
    },
    {
      "epoch": 36.70886075949367,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3649,
      "eval_samples_per_second": 54.809,
      "eval_steps_per_second": 8.221,
      "step": 725
    },
    {
      "epoch": 37.9746835443038,
      "grad_norm": 0.0,
      "learning_rate": 5.050505050505051e-05,
      "loss": 3.6263,
      "step": 750
    },
    {
      "epoch": 37.9746835443038,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3636,
      "eval_samples_per_second": 55.009,
      "eval_steps_per_second": 8.251,
      "step": 750
    },
    {
      "epoch": 39.24050632911393,
      "grad_norm": 0.0,
      "learning_rate": 4.545454545454546e-05,
      "loss": 3.6617,
      "step": 775
    },
    {
      "epoch": 39.24050632911393,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3597,
      "eval_samples_per_second": 55.595,
      "eval_steps_per_second": 8.339,
      "step": 775
    },
    {
      "epoch": 40.50632911392405,
      "grad_norm": 0.0,
      "learning_rate": 4.0404040404040405e-05,
      "loss": 3.6533,
      "step": 800
    },
    {
      "epoch": 40.50632911392405,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3586,
      "eval_samples_per_second": 55.77,
      "eval_steps_per_second": 8.366,
      "step": 800
    },
    {
      "epoch": 41.77215189873418,
      "grad_norm": 0.0,
      "learning_rate": 3.535353535353535e-05,
      "loss": 3.6451,
      "step": 825
    },
    {
      "epoch": 41.77215189873418,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.365,
      "eval_samples_per_second": 54.797,
      "eval_steps_per_second": 8.22,
      "step": 825
    },
    {
      "epoch": 43.037974683544306,
      "grad_norm": 0.0,
      "learning_rate": 3.0303030303030306e-05,
      "loss": 3.6378,
      "step": 850
    },
    {
      "epoch": 43.037974683544306,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3685,
      "eval_samples_per_second": 54.277,
      "eval_steps_per_second": 8.142,
      "step": 850
    },
    {
      "epoch": 44.30379746835443,
      "grad_norm": 0.0,
      "learning_rate": 2.5252525252525256e-05,
      "loss": 3.6434,
      "step": 875
    },
    {
      "epoch": 44.30379746835443,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3608,
      "eval_samples_per_second": 55.439,
      "eval_steps_per_second": 8.316,
      "step": 875
    },
    {
      "epoch": 45.56962025316456,
      "grad_norm": 0.0,
      "learning_rate": 2.0202020202020203e-05,
      "loss": 3.6663,
      "step": 900
    },
    {
      "epoch": 45.56962025316456,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3668,
      "eval_samples_per_second": 54.52,
      "eval_steps_per_second": 8.178,
      "step": 900
    },
    {
      "epoch": 46.835443037974684,
      "grad_norm": 0.0,
      "learning_rate": 1.5151515151515153e-05,
      "loss": 3.6625,
      "step": 925
    },
    {
      "epoch": 46.835443037974684,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3641,
      "eval_samples_per_second": 54.926,
      "eval_steps_per_second": 8.239,
      "step": 925
    },
    {
      "epoch": 48.10126582278481,
      "grad_norm": 0.0,
      "learning_rate": 1.0101010101010101e-05,
      "loss": 3.6488,
      "step": 950
    },
    {
      "epoch": 48.10126582278481,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3619,
      "eval_samples_per_second": 55.257,
      "eval_steps_per_second": 8.289,
      "step": 950
    },
    {
      "epoch": 49.36708860759494,
      "grad_norm": 0.0,
      "learning_rate": 5.050505050505051e-06,
      "loss": 3.6441,
      "step": 975
    },
    {
      "epoch": 49.36708860759494,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3685,
      "eval_samples_per_second": 54.269,
      "eval_steps_per_second": 8.14,
      "step": 975
    },
    {
      "epoch": 50.63291139240506,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 3.6187,
      "step": 1000
    },
    {
      "epoch": 50.63291139240506,
      "eval_loss": 3.791062116622925,
      "eval_runtime": 0.3719,
      "eval_samples_per_second": 53.775,
      "eval_steps_per_second": 8.066,
      "step": 1000
    }
  ],
  "logging_steps": 25,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 53,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2138672638863360.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}