{
  "best_metric": 0.015838705003261566,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.09343611305769679,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001868722261153936,
      "grad_norm": 3.2872517108917236,
      "learning_rate": 5e-05,
      "loss": 2.8184,
      "step": 1
    },
    {
      "epoch": 0.001868722261153936,
      "eval_loss": 2.0563979148864746,
      "eval_runtime": 2.4774,
      "eval_samples_per_second": 20.182,
      "eval_steps_per_second": 5.247,
      "step": 1
    },
    {
      "epoch": 0.003737444522307872,
      "grad_norm": 3.097316265106201,
      "learning_rate": 0.0001,
      "loss": 2.0664,
      "step": 2
    },
    {
      "epoch": 0.005606166783461808,
      "grad_norm": 3.1241369247436523,
      "learning_rate": 9.990365154573717e-05,
      "loss": 1.9146,
      "step": 3
    },
    {
      "epoch": 0.007474889044615744,
      "grad_norm": 2.9641897678375244,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.3542,
      "step": 4
    },
    {
      "epoch": 0.00934361130576968,
      "grad_norm": 2.4216108322143555,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.0147,
      "step": 5
    },
    {
      "epoch": 0.011212333566923615,
      "grad_norm": 2.331437587738037,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.5287,
      "step": 6
    },
    {
      "epoch": 0.013081055828077552,
      "grad_norm": 1.9484703540802002,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.3265,
      "step": 7
    },
    {
      "epoch": 0.014949778089231487,
      "grad_norm": 0.6992719173431396,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.2236,
      "step": 8
    },
    {
      "epoch": 0.016818500350385426,
      "grad_norm": 1.0140849351882935,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.2469,
      "step": 9
    },
    {
      "epoch": 0.01868722261153936,
      "grad_norm": 0.7159717082977295,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.1908,
      "step": 10
    },
    {
      "epoch": 0.020555944872693296,
      "grad_norm": 0.4799579977989197,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.1396,
      "step": 11
    },
    {
      "epoch": 0.02242466713384723,
      "grad_norm": 0.4097464680671692,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.1195,
      "step": 12
    },
    {
      "epoch": 0.02429338939500117,
      "grad_norm": 0.977213978767395,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.6143,
      "step": 13
    },
    {
      "epoch": 0.026162111656155104,
      "grad_norm": 0.513253390789032,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.2804,
      "step": 14
    },
    {
      "epoch": 0.02803083391730904,
      "grad_norm": 0.5691519975662231,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.1168,
      "step": 15
    },
    {
      "epoch": 0.029899556178462974,
      "grad_norm": 0.5832998752593994,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.1229,
      "step": 16
    },
    {
      "epoch": 0.03176827843961691,
      "grad_norm": 0.4452166259288788,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.1154,
      "step": 17
    },
    {
      "epoch": 0.03363700070077085,
      "grad_norm": 0.4491880536079407,
      "learning_rate": 7.75e-05,
      "loss": 0.0803,
      "step": 18
    },
    {
      "epoch": 0.035505722961924786,
      "grad_norm": 0.4029383957386017,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.0686,
      "step": 19
    },
    {
      "epoch": 0.03737444522307872,
      "grad_norm": 0.5263382196426392,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0714,
      "step": 20
    },
    {
      "epoch": 0.039243167484232656,
      "grad_norm": 0.5159032344818115,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0563,
      "step": 21
    },
    {
      "epoch": 0.04111188974538659,
      "grad_norm": 0.30489763617515564,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0365,
      "step": 22
    },
    {
      "epoch": 0.042980612006540526,
      "grad_norm": 0.3882354199886322,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.0408,
      "step": 23
    },
    {
      "epoch": 0.04484933426769446,
      "grad_norm": 0.37378594279289246,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0368,
      "step": 24
    },
    {
      "epoch": 0.046718056528848396,
      "grad_norm": 0.6960319876670837,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.0499,
      "step": 25
    },
    {
      "epoch": 0.046718056528848396,
      "eval_loss": 0.04135577753186226,
      "eval_runtime": 1.8396,
      "eval_samples_per_second": 27.18,
      "eval_steps_per_second": 7.067,
      "step": 25
    },
    {
      "epoch": 0.04858677879000234,
      "grad_norm": 0.5107179284095764,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.4535,
      "step": 26
    },
    {
      "epoch": 0.050455501051156273,
      "grad_norm": 0.4900267422199249,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.0796,
      "step": 27
    },
    {
      "epoch": 0.05232422331231021,
      "grad_norm": 0.3207160234451294,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.043,
      "step": 28
    },
    {
      "epoch": 0.054192945573464144,
      "grad_norm": 0.5145649313926697,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.0424,
      "step": 29
    },
    {
      "epoch": 0.05606166783461808,
      "grad_norm": 0.22890864312648773,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.0244,
      "step": 30
    },
    {
      "epoch": 0.057930390095772014,
      "grad_norm": 0.23109875619411469,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.0231,
      "step": 31
    },
    {
      "epoch": 0.05979911235692595,
      "grad_norm": 0.11645814031362534,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.0134,
      "step": 32
    },
    {
      "epoch": 0.06166783461807989,
      "grad_norm": 0.18600647151470184,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.0153,
      "step": 33
    },
    {
      "epoch": 0.06353655687923382,
      "grad_norm": 0.2838912904262543,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.0163,
      "step": 34
    },
    {
      "epoch": 0.06540527914038775,
      "grad_norm": 0.24853822588920593,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.0185,
      "step": 35
    },
    {
      "epoch": 0.0672740014015417,
      "grad_norm": 0.20572882890701294,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.0135,
      "step": 36
    },
    {
      "epoch": 0.06914272366269564,
      "grad_norm": 0.22797401249408722,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.0179,
      "step": 37
    },
    {
      "epoch": 0.07101144592384957,
      "grad_norm": 0.6385992765426636,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.3246,
      "step": 38
    },
    {
      "epoch": 0.07288016818500351,
      "grad_norm": 0.25923556089401245,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.0883,
      "step": 39
    },
    {
      "epoch": 0.07474889044615744,
      "grad_norm": 0.1639515459537506,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.0275,
      "step": 40
    },
    {
      "epoch": 0.07661761270731138,
      "grad_norm": 0.1730871945619583,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.0234,
      "step": 41
    },
    {
      "epoch": 0.07848633496846531,
      "grad_norm": 0.23780955374240875,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.0164,
      "step": 42
    },
    {
      "epoch": 0.08035505722961925,
      "grad_norm": 0.14500492811203003,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.013,
      "step": 43
    },
    {
      "epoch": 0.08222377949077318,
      "grad_norm": 0.18985842168331146,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.0164,
      "step": 44
    },
    {
      "epoch": 0.08409250175192712,
      "grad_norm": 0.11164896190166473,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.01,
      "step": 45
    },
    {
      "epoch": 0.08596122401308105,
      "grad_norm": 0.11438169330358505,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.0078,
      "step": 46
    },
    {
      "epoch": 0.08782994627423499,
      "grad_norm": 0.17679692804813385,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.0074,
      "step": 47
    },
    {
      "epoch": 0.08969866853538892,
      "grad_norm": 0.12496514618396759,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.0074,
      "step": 48
    },
    {
      "epoch": 0.09156739079654286,
      "grad_norm": 0.1692323088645935,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.009,
      "step": 49
    },
    {
      "epoch": 0.09343611305769679,
      "grad_norm": 0.1172904223203659,
      "learning_rate": 1e-05,
      "loss": 0.0082,
      "step": 50
    },
    {
      "epoch": 0.09343611305769679,
      "eval_loss": 0.015838705003261566,
      "eval_runtime": 1.8329,
      "eval_samples_per_second": 27.28,
      "eval_steps_per_second": 7.093,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 5.6943585332822016e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}