{
  "best_metric": 1.7232028245925903,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.44543429844098,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008908685968819599,
      "grad_norm": 0.19165605306625366,
      "learning_rate": 5e-05,
      "loss": 1.7415,
      "step": 1
    },
    {
      "epoch": 0.008908685968819599,
      "eval_loss": 3.07926607131958,
      "eval_runtime": 2.5471,
      "eval_samples_per_second": 19.63,
      "eval_steps_per_second": 5.104,
      "step": 1
    },
    {
      "epoch": 0.017817371937639197,
      "grad_norm": 0.30985021591186523,
      "learning_rate": 0.0001,
      "loss": 1.9616,
      "step": 2
    },
    {
      "epoch": 0.026726057906458798,
      "grad_norm": 0.3591505289077759,
      "learning_rate": 9.990365154573717e-05,
      "loss": 1.9983,
      "step": 3
    },
    {
      "epoch": 0.035634743875278395,
      "grad_norm": 0.5411798357963562,
      "learning_rate": 9.961501876182148e-05,
      "loss": 2.1615,
      "step": 4
    },
    {
      "epoch": 0.044543429844097995,
      "grad_norm": 0.9157348871231079,
      "learning_rate": 9.913533761814537e-05,
      "loss": 2.184,
      "step": 5
    },
    {
      "epoch": 0.053452115812917596,
      "grad_norm": 0.8482625484466553,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.191,
      "step": 6
    },
    {
      "epoch": 0.062360801781737196,
      "grad_norm": 0.8526954054832458,
      "learning_rate": 9.761185582727977e-05,
      "loss": 2.239,
      "step": 7
    },
    {
      "epoch": 0.07126948775055679,
      "grad_norm": 1.0108094215393066,
      "learning_rate": 9.657457896300791e-05,
      "loss": 2.044,
      "step": 8
    },
    {
      "epoch": 0.0801781737193764,
      "grad_norm": 1.543118953704834,
      "learning_rate": 9.535927336897098e-05,
      "loss": 2.0646,
      "step": 9
    },
    {
      "epoch": 0.08908685968819599,
      "grad_norm": 1.9588677883148193,
      "learning_rate": 9.397114317029975e-05,
      "loss": 2.0951,
      "step": 10
    },
    {
      "epoch": 0.09799554565701558,
      "grad_norm": 3.5548055171966553,
      "learning_rate": 9.241613255361455e-05,
      "loss": 2.1184,
      "step": 11
    },
    {
      "epoch": 0.10690423162583519,
      "grad_norm": 5.5011420249938965,
      "learning_rate": 9.070090031310558e-05,
      "loss": 2.4666,
      "step": 12
    },
    {
      "epoch": 0.11581291759465479,
      "grad_norm": 1.8376637697219849,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.8736,
      "step": 13
    },
    {
      "epoch": 0.12472160356347439,
      "grad_norm": 2.4126038551330566,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.8446,
      "step": 14
    },
    {
      "epoch": 0.133630289532294,
      "grad_norm": 2.8026652336120605,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.9524,
      "step": 15
    },
    {
      "epoch": 0.14253897550111358,
      "grad_norm": 1.930046558380127,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.9445,
      "step": 16
    },
    {
      "epoch": 0.1514476614699332,
      "grad_norm": 0.7267770171165466,
      "learning_rate": 8.000066048588211e-05,
      "loss": 2.0923,
      "step": 17
    },
    {
      "epoch": 0.1603563474387528,
      "grad_norm": 0.7256228923797607,
      "learning_rate": 7.75e-05,
      "loss": 1.9739,
      "step": 18
    },
    {
      "epoch": 0.16926503340757237,
      "grad_norm": 1.3526475429534912,
      "learning_rate": 7.490299105985507e-05,
      "loss": 2.0263,
      "step": 19
    },
    {
      "epoch": 0.17817371937639198,
      "grad_norm": 1.6756101846694946,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.9611,
      "step": 20
    },
    {
      "epoch": 0.1870824053452116,
      "grad_norm": 1.841839075088501,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.8476,
      "step": 21
    },
    {
      "epoch": 0.19599109131403117,
      "grad_norm": 2.0583412647247314,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.711,
      "step": 22
    },
    {
      "epoch": 0.20489977728285078,
      "grad_norm": 3.033216714859009,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.8935,
      "step": 23
    },
    {
      "epoch": 0.21380846325167038,
      "grad_norm": 2.919166088104248,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.4921,
      "step": 24
    },
    {
      "epoch": 0.22271714922049,
      "grad_norm": 12.295625686645508,
      "learning_rate": 5.794314081535644e-05,
      "loss": 2.6217,
      "step": 25
    },
    {
      "epoch": 0.22271714922049,
      "eval_loss": 1.8678327798843384,
      "eval_runtime": 1.3382,
      "eval_samples_per_second": 37.365,
      "eval_steps_per_second": 9.715,
      "step": 25
    },
    {
      "epoch": 0.23162583518930957,
      "grad_norm": 0.4222097396850586,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.6003,
      "step": 26
    },
    {
      "epoch": 0.24053452115812918,
      "grad_norm": 0.80172199010849,
      "learning_rate": 5.205685918464356e-05,
      "loss": 1.6958,
      "step": 27
    },
    {
      "epoch": 0.24944320712694878,
      "grad_norm": 0.8624845743179321,
      "learning_rate": 4.912632135009769e-05,
      "loss": 2.0,
      "step": 28
    },
    {
      "epoch": 0.2583518930957684,
      "grad_norm": 1.0457912683486938,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 1.8821,
      "step": 29
    },
    {
      "epoch": 0.267260579064588,
      "grad_norm": 0.801153838634491,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 1.9877,
      "step": 30
    },
    {
      "epoch": 0.27616926503340755,
      "grad_norm": 0.6440266966819763,
      "learning_rate": 4.053522406135775e-05,
      "loss": 2.0081,
      "step": 31
    },
    {
      "epoch": 0.28507795100222716,
      "grad_norm": 0.48909497261047363,
      "learning_rate": 3.777924554357096e-05,
      "loss": 1.9782,
      "step": 32
    },
    {
      "epoch": 0.29398663697104677,
      "grad_norm": 0.4719208776950836,
      "learning_rate": 3.509700894014496e-05,
      "loss": 1.7975,
      "step": 33
    },
    {
      "epoch": 0.3028953229398664,
      "grad_norm": 0.6802312135696411,
      "learning_rate": 3.250000000000001e-05,
      "loss": 1.8392,
      "step": 34
    },
    {
      "epoch": 0.311804008908686,
      "grad_norm": 1.0054951906204224,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 1.7632,
      "step": 35
    },
    {
      "epoch": 0.3207126948775056,
      "grad_norm": 1.5242421627044678,
      "learning_rate": 2.760573569460757e-05,
      "loss": 1.6814,
      "step": 36
    },
    {
      "epoch": 0.32962138084632514,
      "grad_norm": 3.246612071990967,
      "learning_rate": 2.53294383204969e-05,
      "loss": 1.6508,
      "step": 37
    },
    {
      "epoch": 0.33853006681514475,
      "grad_norm": 0.32325273752212524,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 1.6682,
      "step": 38
    },
    {
      "epoch": 0.34743875278396436,
      "grad_norm": 0.2519363760948181,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 1.4816,
      "step": 39
    },
    {
      "epoch": 0.35634743875278396,
      "grad_norm": 0.3244990110397339,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 1.7353,
      "step": 40
    },
    {
      "epoch": 0.36525612472160357,
      "grad_norm": 0.3196703791618347,
      "learning_rate": 1.758386744638546e-05,
      "loss": 1.7866,
      "step": 41
    },
    {
      "epoch": 0.3741648106904232,
      "grad_norm": 0.2564365565776825,
      "learning_rate": 1.602885682970026e-05,
      "loss": 1.9444,
      "step": 42
    },
    {
      "epoch": 0.3830734966592428,
      "grad_norm": 0.2975054979324341,
      "learning_rate": 1.464072663102903e-05,
      "loss": 1.88,
      "step": 43
    },
    {
      "epoch": 0.39198218262806234,
      "grad_norm": 0.35675594210624695,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 1.929,
      "step": 44
    },
    {
      "epoch": 0.40089086859688194,
      "grad_norm": 0.32580721378326416,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 1.8816,
      "step": 45
    },
    {
      "epoch": 0.40979955456570155,
      "grad_norm": 0.4181939959526062,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 1.8151,
      "step": 46
    },
    {
      "epoch": 0.41870824053452116,
      "grad_norm": 0.5043487548828125,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 1.7663,
      "step": 47
    },
    {
      "epoch": 0.42761692650334077,
      "grad_norm": 0.7439761757850647,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 1.8092,
      "step": 48
    },
    {
      "epoch": 0.4365256124721604,
      "grad_norm": 1.6642370223999023,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 1.5948,
      "step": 49
    },
    {
      "epoch": 0.44543429844098,
      "grad_norm": 4.350525379180908,
      "learning_rate": 1e-05,
      "loss": 2.0755,
      "step": 50
    },
    {
      "epoch": 0.44543429844098,
      "eval_loss": 1.7232028245925903,
      "eval_runtime": 1.3416,
      "eval_samples_per_second": 37.27,
      "eval_steps_per_second": 9.69,
      "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": 1.0621851957775565e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}