{
  "best_metric": 0.7105076909065247,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.2170138888888889,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00043402777777777775,
      "eval_loss": 1.0486223697662354,
      "eval_runtime": 49.5892,
      "eval_samples_per_second": 9.78,
      "eval_steps_per_second": 2.46,
      "step": 1
    },
    {
      "epoch": 0.004340277777777778,
      "grad_norm": 1.30818772315979,
      "learning_rate": 4.2600000000000005e-05,
      "loss": 0.912,
      "step": 10
    },
    {
      "epoch": 0.008680555555555556,
      "grad_norm": 0.8930862545967102,
      "learning_rate": 8.520000000000001e-05,
      "loss": 0.8451,
      "step": 20
    },
    {
      "epoch": 0.013020833333333334,
      "grad_norm": 1.0381461381912231,
      "learning_rate": 0.0001278,
      "loss": 0.5786,
      "step": 30
    },
    {
      "epoch": 0.017361111111111112,
      "grad_norm": 1.2415528297424316,
      "learning_rate": 0.00017040000000000002,
      "loss": 0.6245,
      "step": 40
    },
    {
      "epoch": 0.021701388888888888,
      "grad_norm": 0.8442565202713013,
      "learning_rate": 0.000213,
      "loss": 0.4496,
      "step": 50
    },
    {
      "epoch": 0.021701388888888888,
      "eval_loss": 0.7272957563400269,
      "eval_runtime": 49.5625,
      "eval_samples_per_second": 9.786,
      "eval_steps_per_second": 2.462,
      "step": 50
    },
    {
      "epoch": 0.026041666666666668,
      "grad_norm": 1.2658860683441162,
      "learning_rate": 0.00021274057135267128,
      "loss": 0.8503,
      "step": 60
    },
    {
      "epoch": 0.030381944444444444,
      "grad_norm": 1.3917545080184937,
      "learning_rate": 0.00021196354932097723,
      "loss": 0.6671,
      "step": 70
    },
    {
      "epoch": 0.034722222222222224,
      "grad_norm": 1.3726558685302734,
      "learning_rate": 0.0002106727194781503,
      "loss": 0.7479,
      "step": 80
    },
    {
      "epoch": 0.0390625,
      "grad_norm": 1.26426100730896,
      "learning_rate": 0.00020887437061743096,
      "loss": 0.8955,
      "step": 90
    },
    {
      "epoch": 0.043402777777777776,
      "grad_norm": 0.8687089085578918,
      "learning_rate": 0.00020657726411369925,
      "loss": 0.8438,
      "step": 100
    },
    {
      "epoch": 0.043402777777777776,
      "eval_loss": 0.7392935752868652,
      "eval_runtime": 49.5607,
      "eval_samples_per_second": 9.786,
      "eval_steps_per_second": 2.462,
      "step": 100
    },
    {
      "epoch": 0.04774305555555555,
      "grad_norm": 0.9549110531806946,
      "learning_rate": 0.000203792591238937,
      "loss": 0.7712,
      "step": 110
    },
    {
      "epoch": 0.052083333333333336,
      "grad_norm": 1.3070204257965088,
      "learning_rate": 0.0002005339186394757,
      "loss": 0.669,
      "step": 120
    },
    {
      "epoch": 0.05642361111111111,
      "grad_norm": 1.2052979469299316,
      "learning_rate": 0.00019681712224065936,
      "loss": 0.616,
      "step": 130
    },
    {
      "epoch": 0.06076388888888889,
      "grad_norm": 0.6207852363586426,
      "learning_rate": 0.0001926603099009319,
      "loss": 0.7878,
      "step": 140
    },
    {
      "epoch": 0.06510416666666667,
      "grad_norm": 0.7814576029777527,
      "learning_rate": 0.00018808373319217114,
      "loss": 0.4888,
      "step": 150
    },
    {
      "epoch": 0.06510416666666667,
      "eval_loss": 0.7211872339248657,
      "eval_runtime": 49.5742,
      "eval_samples_per_second": 9.783,
      "eval_steps_per_second": 2.461,
      "step": 150
    },
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 0.8724411129951477,
      "learning_rate": 0.00018310968873606635,
      "loss": 0.7598,
      "step": 160
    },
    {
      "epoch": 0.07378472222222222,
      "grad_norm": 1.6653738021850586,
      "learning_rate": 0.0001777624095772184,
      "loss": 0.8254,
      "step": 170
    },
    {
      "epoch": 0.078125,
      "grad_norm": 1.2747048139572144,
      "learning_rate": 0.0001720679471221826,
      "loss": 0.8594,
      "step": 180
    },
    {
      "epoch": 0.08246527777777778,
      "grad_norm": 1.4110088348388672,
      "learning_rate": 0.00016605404421963453,
      "loss": 0.7506,
      "step": 190
    },
    {
      "epoch": 0.08680555555555555,
      "grad_norm": 2.366544485092163,
      "learning_rate": 0.00015975,
      "loss": 0.9703,
      "step": 200
    },
    {
      "epoch": 0.08680555555555555,
      "eval_loss": 0.7333279252052307,
      "eval_runtime": 49.6093,
      "eval_samples_per_second": 9.776,
      "eval_steps_per_second": 2.459,
      "step": 200
    },
    {
      "epoch": 0.09114583333333333,
      "grad_norm": 1.0888848304748535,
      "learning_rate": 0.00015318652713303674,
      "loss": 0.5779,
      "step": 210
    },
    {
      "epoch": 0.0954861111111111,
      "grad_norm": 0.9510017037391663,
      "learning_rate": 0.00014639560219879464,
      "loss": 0.7727,
      "step": 220
    },
    {
      "epoch": 0.0998263888888889,
      "grad_norm": 0.347385048866272,
      "learning_rate": 0.0001394103099009319,
      "loss": 0.6551,
      "step": 230
    },
    {
      "epoch": 0.10416666666666667,
      "grad_norm": 1.4552265405654907,
      "learning_rate": 0.0001322646818813646,
      "loss": 0.6279,
      "step": 240
    },
    {
      "epoch": 0.10850694444444445,
      "grad_norm": 1.388659119606018,
      "learning_rate": 0.0001249935309215281,
      "loss": 0.7938,
      "step": 250
    },
    {
      "epoch": 0.10850694444444445,
      "eval_loss": 0.7187796831130981,
      "eval_runtime": 49.5717,
      "eval_samples_per_second": 9.784,
      "eval_steps_per_second": 2.461,
      "step": 250
    },
    {
      "epoch": 0.11284722222222222,
      "grad_norm": 0.9789396524429321,
      "learning_rate": 0.0001176322813380051,
      "loss": 0.8391,
      "step": 260
    },
    {
      "epoch": 0.1171875,
      "grad_norm": 1.4175513982772827,
      "learning_rate": 0.00011021679639881638,
      "loss": 0.8921,
      "step": 270
    },
    {
      "epoch": 0.12152777777777778,
      "grad_norm": 1.268831729888916,
      "learning_rate": 0.00010278320360118368,
      "loss": 0.5002,
      "step": 280
    },
    {
      "epoch": 0.12586805555555555,
      "grad_norm": 0.8849596977233887,
      "learning_rate": 9.536771866199493e-05,
      "loss": 0.602,
      "step": 290
    },
    {
      "epoch": 0.13020833333333334,
      "grad_norm": 1.0034514665603638,
      "learning_rate": 8.800646907847192e-05,
      "loss": 0.8343,
      "step": 300
    },
    {
      "epoch": 0.13020833333333334,
      "eval_loss": 0.7189058065414429,
      "eval_runtime": 49.5602,
      "eval_samples_per_second": 9.786,
      "eval_steps_per_second": 2.462,
      "step": 300
    },
    {
      "epoch": 0.1345486111111111,
      "grad_norm": 0.5106523036956787,
      "learning_rate": 8.07353181186354e-05,
      "loss": 0.715,
      "step": 310
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 0.9988264441490173,
      "learning_rate": 7.35896900990681e-05,
      "loss": 0.8572,
      "step": 320
    },
    {
      "epoch": 0.14322916666666666,
      "grad_norm": 1.3042094707489014,
      "learning_rate": 6.660439780120536e-05,
      "loss": 0.7248,
      "step": 330
    },
    {
      "epoch": 0.14756944444444445,
      "grad_norm": 0.9319302439689636,
      "learning_rate": 5.981347286696324e-05,
      "loss": 0.873,
      "step": 340
    },
    {
      "epoch": 0.1519097222222222,
      "grad_norm": 1.1595097780227661,
      "learning_rate": 5.325000000000002e-05,
      "loss": 0.5117,
      "step": 350
    },
    {
      "epoch": 0.1519097222222222,
      "eval_loss": 0.7169974446296692,
      "eval_runtime": 49.5441,
      "eval_samples_per_second": 9.789,
      "eval_steps_per_second": 2.462,
      "step": 350
    },
    {
      "epoch": 0.15625,
      "grad_norm": 1.3601690530776978,
      "learning_rate": 4.6945955780365475e-05,
      "loss": 0.8535,
      "step": 360
    },
    {
      "epoch": 0.1605902777777778,
      "grad_norm": 0.8528502583503723,
      "learning_rate": 4.0932052877817393e-05,
      "loss": 0.7758,
      "step": 370
    },
    {
      "epoch": 0.16493055555555555,
      "grad_norm": 0.9841234683990479,
      "learning_rate": 3.523759042278163e-05,
      "loss": 0.6716,
      "step": 380
    },
    {
      "epoch": 0.16927083333333334,
      "grad_norm": 0.7331548929214478,
      "learning_rate": 2.989031126393367e-05,
      "loss": 0.9835,
      "step": 390
    },
    {
      "epoch": 0.1736111111111111,
      "grad_norm": 1.9498828649520874,
      "learning_rate": 2.4916266807828855e-05,
      "loss": 0.9712,
      "step": 400
    },
    {
      "epoch": 0.1736111111111111,
      "eval_loss": 0.7105076909065247,
      "eval_runtime": 49.5867,
      "eval_samples_per_second": 9.781,
      "eval_steps_per_second": 2.46,
      "step": 400
    },
    {
      "epoch": 0.1779513888888889,
      "grad_norm": 1.3422185182571411,
      "learning_rate": 2.033969009906811e-05,
      "loss": 0.8554,
      "step": 410
    },
    {
      "epoch": 0.18229166666666666,
      "grad_norm": 1.4816110134124756,
      "learning_rate": 1.6182877759340637e-05,
      "loss": 0.6037,
      "step": 420
    },
    {
      "epoch": 0.18663194444444445,
      "grad_norm": 0.8355005383491516,
      "learning_rate": 1.2466081360524275e-05,
      "loss": 0.6468,
      "step": 430
    },
    {
      "epoch": 0.1909722222222222,
      "grad_norm": 0.657798171043396,
      "learning_rate": 9.207408761062996e-06,
      "loss": 0.48,
      "step": 440
    },
    {
      "epoch": 0.1953125,
      "grad_norm": 1.6586601734161377,
      "learning_rate": 6.422735886300764e-06,
      "loss": 0.6231,
      "step": 450
    },
    {
      "epoch": 0.1953125,
      "eval_loss": 0.712680459022522,
      "eval_runtime": 49.6689,
      "eval_samples_per_second": 9.765,
      "eval_steps_per_second": 2.456,
      "step": 450
    },
    {
      "epoch": 0.1996527777777778,
      "grad_norm": 0.8355949521064758,
      "learning_rate": 4.125629382569038e-06,
      "loss": 0.6722,
      "step": 460
    },
    {
      "epoch": 0.20399305555555555,
      "grad_norm": 1.7075914144515991,
      "learning_rate": 2.327280521849694e-06,
      "loss": 0.66,
      "step": 470
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 0.7151721119880676,
      "learning_rate": 1.0364506790227565e-06,
      "loss": 0.6677,
      "step": 480
    },
    {
      "epoch": 0.2126736111111111,
      "grad_norm": 0.9590463042259216,
      "learning_rate": 2.5942864732872295e-07,
      "loss": 0.9534,
      "step": 490
    },
    {
      "epoch": 0.2170138888888889,
      "grad_norm": 2.80539870262146,
      "learning_rate": 0.0,
      "loss": 0.8418,
      "step": 500
    },
    {
      "epoch": 0.2170138888888889,
      "eval_loss": 0.7122297286987305,
      "eval_runtime": 49.691,
      "eval_samples_per_second": 9.76,
      "eval_steps_per_second": 2.455,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.64727392017449e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}