{
  "best_metric": 0.22088730335235596,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.30656039239730226,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006131207847946045,
      "eval_loss": 1.6972112655639648,
      "eval_runtime": 42.3642,
      "eval_samples_per_second": 16.217,
      "eval_steps_per_second": 4.06,
      "step": 1
    },
    {
      "epoch": 0.0061312078479460455,
      "grad_norm": 2.5399515628814697,
      "learning_rate": 4.22e-05,
      "loss": 1.0729,
      "step": 10
    },
    {
      "epoch": 0.012262415695892091,
      "grad_norm": 1.911725640296936,
      "learning_rate": 8.44e-05,
      "loss": 0.624,
      "step": 20
    },
    {
      "epoch": 0.018393623543838136,
      "grad_norm": 1.583366870880127,
      "learning_rate": 0.0001266,
      "loss": 0.5414,
      "step": 30
    },
    {
      "epoch": 0.024524831391784182,
      "grad_norm": 2.1019012928009033,
      "learning_rate": 0.0001688,
      "loss": 0.489,
      "step": 40
    },
    {
      "epoch": 0.030656039239730228,
      "grad_norm": 3.7989816665649414,
      "learning_rate": 0.000211,
      "loss": 0.6301,
      "step": 50
    },
    {
      "epoch": 0.030656039239730228,
      "eval_loss": 0.7841286063194275,
      "eval_runtime": 42.3765,
      "eval_samples_per_second": 16.212,
      "eval_steps_per_second": 4.059,
      "step": 50
    },
    {
      "epoch": 0.03678724708767627,
      "grad_norm": 2.0683157444000244,
      "learning_rate": 0.00021074300730241147,
      "loss": 0.5761,
      "step": 60
    },
    {
      "epoch": 0.04291845493562232,
      "grad_norm": 1.5029504299163818,
      "learning_rate": 0.00020997328125223568,
      "loss": 0.4392,
      "step": 70
    },
    {
      "epoch": 0.049049662783568364,
      "grad_norm": 1.8249471187591553,
      "learning_rate": 0.0002086945718774165,
      "loss": 0.4728,
      "step": 80
    },
    {
      "epoch": 0.05518087063151441,
      "grad_norm": 2.3122222423553467,
      "learning_rate": 0.00020691310892149265,
      "loss": 0.4777,
      "step": 90
    },
    {
      "epoch": 0.061312078479460456,
      "grad_norm": 3.182551145553589,
      "learning_rate": 0.00020463757149291335,
      "loss": 0.5207,
      "step": 100
    },
    {
      "epoch": 0.061312078479460456,
      "eval_loss": 0.784916877746582,
      "eval_runtime": 42.3748,
      "eval_samples_per_second": 16.212,
      "eval_steps_per_second": 4.059,
      "step": 100
    },
    {
      "epoch": 0.0674432863274065,
      "grad_norm": 1.1367835998535156,
      "learning_rate": 0.0002018790457812944,
      "loss": 0.4991,
      "step": 110
    },
    {
      "epoch": 0.07357449417535254,
      "grad_norm": 2.4769582748413086,
      "learning_rate": 0.0001986509710466168,
      "loss": 0.396,
      "step": 120
    },
    {
      "epoch": 0.07970570202329859,
      "grad_norm": 1.6102774143218994,
      "learning_rate": 0.00019496907414450293,
      "loss": 0.3531,
      "step": 130
    },
    {
      "epoch": 0.08583690987124463,
      "grad_norm": 1.7436530590057373,
      "learning_rate": 0.00019085129290655697,
      "loss": 0.4021,
      "step": 140
    },
    {
      "epoch": 0.09196811771919068,
      "grad_norm": 4.168282985687256,
      "learning_rate": 0.00018631768874905217,
      "loss": 0.4508,
      "step": 150
    },
    {
      "epoch": 0.09196811771919068,
      "eval_loss": 0.5247650146484375,
      "eval_runtime": 42.4743,
      "eval_samples_per_second": 16.175,
      "eval_steps_per_second": 4.05,
      "step": 150
    },
    {
      "epoch": 0.09809932556713673,
      "grad_norm": 1.1784135103225708,
      "learning_rate": 0.0001813903489357277,
      "loss": 0.4399,
      "step": 160
    },
    {
      "epoch": 0.10423053341508277,
      "grad_norm": 1.4040613174438477,
      "learning_rate": 0.00017609327897085954,
      "loss": 0.3591,
      "step": 170
    },
    {
      "epoch": 0.11036174126302882,
      "grad_norm": 1.1797558069229126,
      "learning_rate": 0.00017045228564685694,
      "loss": 0.3523,
      "step": 180
    },
    {
      "epoch": 0.11649294911097487,
      "grad_norm": 1.590161681175232,
      "learning_rate": 0.0001644948513161638,
      "loss": 0.3406,
      "step": 190
    },
    {
      "epoch": 0.12262415695892091,
      "grad_norm": 3.65169358253479,
      "learning_rate": 0.00015825,
      "loss": 0.3927,
      "step": 200
    },
    {
      "epoch": 0.12262415695892091,
      "eval_loss": 0.5356494784355164,
      "eval_runtime": 42.3757,
      "eval_samples_per_second": 16.212,
      "eval_steps_per_second": 4.059,
      "step": 200
    },
    {
      "epoch": 0.12875536480686695,
      "grad_norm": 1.1879467964172363,
      "learning_rate": 0.00015174815598624768,
      "loss": 0.4153,
      "step": 210
    },
    {
      "epoch": 0.134886572654813,
      "grad_norm": 2.3014867305755615,
      "learning_rate": 0.00014502099560537873,
      "loss": 0.3318,
      "step": 220
    },
    {
      "epoch": 0.14101778050275904,
      "grad_norm": 1.5435618162155151,
      "learning_rate": 0.00013810129290655696,
      "loss": 0.3028,
      "step": 230
    },
    {
      "epoch": 0.14714898835070508,
      "grad_norm": 2.062577486038208,
      "learning_rate": 0.00013102275998576495,
      "loss": 0.3095,
      "step": 240
    },
    {
      "epoch": 0.15328019619865113,
      "grad_norm": 3.058638095855713,
      "learning_rate": 0.00012381988274386116,
      "loss": 0.3716,
      "step": 250
    },
    {
      "epoch": 0.15328019619865113,
      "eval_loss": 0.38261598348617554,
      "eval_runtime": 42.4189,
      "eval_samples_per_second": 16.196,
      "eval_steps_per_second": 4.055,
      "step": 250
    },
    {
      "epoch": 0.15941140404659718,
      "grad_norm": 1.1857730150222778,
      "learning_rate": 0.00011652775287473745,
      "loss": 0.3379,
      "step": 260
    },
    {
      "epoch": 0.16554261189454322,
      "grad_norm": 1.465416431427002,
      "learning_rate": 0.00010918189690211387,
      "loss": 0.2494,
      "step": 270
    },
    {
      "epoch": 0.17167381974248927,
      "grad_norm": 1.1710807085037231,
      "learning_rate": 0.00010181810309788618,
      "loss": 0.2669,
      "step": 280
    },
    {
      "epoch": 0.17780502759043532,
      "grad_norm": 1.733910083770752,
      "learning_rate": 9.447224712526258e-05,
      "loss": 0.2858,
      "step": 290
    },
    {
      "epoch": 0.18393623543838136,
      "grad_norm": 1.8814456462860107,
      "learning_rate": 8.718011725613886e-05,
      "loss": 0.3506,
      "step": 300
    },
    {
      "epoch": 0.18393623543838136,
      "eval_loss": 0.35164520144462585,
      "eval_runtime": 42.4421,
      "eval_samples_per_second": 16.187,
      "eval_steps_per_second": 4.053,
      "step": 300
    },
    {
      "epoch": 0.1900674432863274,
      "grad_norm": 0.981971800327301,
      "learning_rate": 7.997724001423507e-05,
      "loss": 0.3302,
      "step": 310
    },
    {
      "epoch": 0.19619865113427346,
      "grad_norm": 1.1474406719207764,
      "learning_rate": 7.289870709344306e-05,
      "loss": 0.2733,
      "step": 320
    },
    {
      "epoch": 0.2023298589822195,
      "grad_norm": 1.0042413473129272,
      "learning_rate": 6.597900439462128e-05,
      "loss": 0.2392,
      "step": 330
    },
    {
      "epoch": 0.20846106683016555,
      "grad_norm": 1.0399328470230103,
      "learning_rate": 5.9251844013752326e-05,
      "loss": 0.2247,
      "step": 340
    },
    {
      "epoch": 0.2145922746781116,
      "grad_norm": 2.1786627769470215,
      "learning_rate": 5.275000000000002e-05,
      "loss": 0.326,
      "step": 350
    },
    {
      "epoch": 0.2145922746781116,
      "eval_loss": 0.2690972089767456,
      "eval_runtime": 42.4522,
      "eval_samples_per_second": 16.183,
      "eval_steps_per_second": 4.052,
      "step": 350
    },
    {
      "epoch": 0.22072348252605764,
      "grad_norm": 0.7868878245353699,
      "learning_rate": 4.650514868383623e-05,
      "loss": 0.2916,
      "step": 360
    },
    {
      "epoch": 0.2268546903740037,
      "grad_norm": 0.9699639081954956,
      "learning_rate": 4.054771435314305e-05,
      "loss": 0.2132,
      "step": 370
    },
    {
      "epoch": 0.23298589822194973,
      "grad_norm": 0.8491773009300232,
      "learning_rate": 3.4906721029140495e-05,
      "loss": 0.1864,
      "step": 380
    },
    {
      "epoch": 0.23911710606989578,
      "grad_norm": 0.9103133678436279,
      "learning_rate": 2.9609651064272323e-05,
      "loss": 0.2154,
      "step": 390
    },
    {
      "epoch": 0.24524831391784183,
      "grad_norm": 2.587815999984741,
      "learning_rate": 2.468231125094783e-05,
      "loss": 0.2517,
      "step": 400
    },
    {
      "epoch": 0.24524831391784183,
      "eval_loss": 0.2357824444770813,
      "eval_runtime": 42.4802,
      "eval_samples_per_second": 16.172,
      "eval_steps_per_second": 4.049,
      "step": 400
    },
    {
      "epoch": 0.25137952176578787,
      "grad_norm": 0.9035682082176208,
      "learning_rate": 2.0148707093443057e-05,
      "loss": 0.2775,
      "step": 410
    },
    {
      "epoch": 0.2575107296137339,
      "grad_norm": 0.6796780228614807,
      "learning_rate": 1.603092585549706e-05,
      "loss": 0.2234,
      "step": 420
    },
    {
      "epoch": 0.26364193746167996,
      "grad_norm": 1.1364048719406128,
      "learning_rate": 1.2349028953383204e-05,
      "loss": 0.1956,
      "step": 430
    },
    {
      "epoch": 0.269773145309626,
      "grad_norm": 0.9247281551361084,
      "learning_rate": 9.120954218705596e-06,
      "loss": 0.1868,
      "step": 440
    },
    {
      "epoch": 0.27590435315757206,
      "grad_norm": 1.8796603679656982,
      "learning_rate": 6.362428507086673e-06,
      "loss": 0.2535,
      "step": 450
    },
    {
      "epoch": 0.27590435315757206,
      "eval_loss": 0.22399407625198364,
      "eval_runtime": 42.4648,
      "eval_samples_per_second": 16.178,
      "eval_steps_per_second": 4.05,
      "step": 450
    },
    {
      "epoch": 0.2820355610055181,
      "grad_norm": 0.8298888802528381,
      "learning_rate": 4.0868910785073565e-06,
      "loss": 0.2218,
      "step": 460
    },
    {
      "epoch": 0.28816676885346415,
      "grad_norm": 0.9988222122192383,
      "learning_rate": 2.3054281225835e-06,
      "loss": 0.2328,
      "step": 470
    },
    {
      "epoch": 0.29429797670141017,
      "grad_norm": 0.8386346101760864,
      "learning_rate": 1.026718747764327e-06,
      "loss": 0.217,
      "step": 480
    },
    {
      "epoch": 0.30042918454935624,
      "grad_norm": 0.7417736053466797,
      "learning_rate": 2.5699269758854715e-07,
      "loss": 0.1874,
      "step": 490
    },
    {
      "epoch": 0.30656039239730226,
      "grad_norm": 2.6463584899902344,
      "learning_rate": 0.0,
      "loss": 0.3353,
      "step": 500
    },
    {
      "epoch": 0.30656039239730226,
      "eval_loss": 0.22088730335235596,
      "eval_runtime": 42.3398,
      "eval_samples_per_second": 16.226,
      "eval_steps_per_second": 4.062,
      "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.437638077028762e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}