{
  "best_metric": 1.38231360912323,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.02160818950382195,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010804094751910974,
      "eval_loss": 1.7889565229415894,
      "eval_runtime": 537.8419,
      "eval_samples_per_second": 28.984,
      "eval_steps_per_second": 7.247,
      "step": 1
    },
    {
      "epoch": 0.00032412284255732923,
      "grad_norm": 0.8091393709182739,
      "learning_rate": 3e-05,
      "loss": 1.5699,
      "step": 3
    },
    {
      "epoch": 0.0006482456851146585,
      "grad_norm": 0.8223854303359985,
      "learning_rate": 6e-05,
      "loss": 1.7854,
      "step": 6
    },
    {
      "epoch": 0.0009723685276719876,
      "grad_norm": 0.8447192311286926,
      "learning_rate": 9e-05,
      "loss": 1.8246,
      "step": 9
    },
    {
      "epoch": 0.001296491370229317,
      "grad_norm": 0.8499614000320435,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.8264,
      "step": 12
    },
    {
      "epoch": 0.0016206142127866462,
      "grad_norm": 0.8196111917495728,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.7786,
      "step": 15
    },
    {
      "epoch": 0.0019447370553439753,
      "grad_norm": 0.7101804614067078,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.7327,
      "step": 18
    },
    {
      "epoch": 0.0022688598979013048,
      "grad_norm": 0.7729286551475525,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.7386,
      "step": 21
    },
    {
      "epoch": 0.002592982740458634,
      "grad_norm": 0.6755093336105347,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.4494,
      "step": 24
    },
    {
      "epoch": 0.002917105583015963,
      "grad_norm": 0.7253813743591309,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.4436,
      "step": 27
    },
    {
      "epoch": 0.0032412284255732924,
      "grad_norm": 0.5313703417778015,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.3522,
      "step": 30
    },
    {
      "epoch": 0.0035653512681306215,
      "grad_norm": 0.5184443593025208,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.2604,
      "step": 33
    },
    {
      "epoch": 0.0038894741106879505,
      "grad_norm": 0.6221433281898499,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.354,
      "step": 36
    },
    {
      "epoch": 0.00421359695324528,
      "grad_norm": 0.5940028429031372,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.3683,
      "step": 39
    },
    {
      "epoch": 0.0045377197958026095,
      "grad_norm": 0.5949783325195312,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.3312,
      "step": 42
    },
    {
      "epoch": 0.004861842638359939,
      "grad_norm": 0.5560756325721741,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.3331,
      "step": 45
    },
    {
      "epoch": 0.005185965480917268,
      "grad_norm": 0.5510199666023254,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.2569,
      "step": 48
    },
    {
      "epoch": 0.005402047375955487,
      "eval_loss": 1.4472901821136475,
      "eval_runtime": 542.7445,
      "eval_samples_per_second": 28.723,
      "eval_steps_per_second": 7.182,
      "step": 50
    },
    {
      "epoch": 0.005510088323474597,
      "grad_norm": 0.560280978679657,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.3376,
      "step": 51
    },
    {
      "epoch": 0.005834211166031926,
      "grad_norm": 0.4924287497997284,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.4859,
      "step": 54
    },
    {
      "epoch": 0.006158334008589256,
      "grad_norm": 0.5823892951011658,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.6142,
      "step": 57
    },
    {
      "epoch": 0.006482456851146585,
      "grad_norm": 0.4990837275981903,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.6329,
      "step": 60
    },
    {
      "epoch": 0.006806579693703914,
      "grad_norm": 0.5565041899681091,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.6867,
      "step": 63
    },
    {
      "epoch": 0.007130702536261243,
      "grad_norm": 0.5534407496452332,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.6361,
      "step": 66
    },
    {
      "epoch": 0.007454825378818572,
      "grad_norm": 0.6305408477783203,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.5459,
      "step": 69
    },
    {
      "epoch": 0.007778948221375901,
      "grad_norm": 0.6603249311447144,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.6251,
      "step": 72
    },
    {
      "epoch": 0.00810307106393323,
      "grad_norm": 0.6320300698280334,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.3576,
      "step": 75
    },
    {
      "epoch": 0.00842719390649056,
      "grad_norm": 0.5601158142089844,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.3429,
      "step": 78
    },
    {
      "epoch": 0.00875131674904789,
      "grad_norm": 0.5731490850448608,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.3739,
      "step": 81
    },
    {
      "epoch": 0.009075439591605219,
      "grad_norm": 0.5410912036895752,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.2813,
      "step": 84
    },
    {
      "epoch": 0.009399562434162548,
      "grad_norm": 0.5254283547401428,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.2508,
      "step": 87
    },
    {
      "epoch": 0.009723685276719877,
      "grad_norm": 0.5095140933990479,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.204,
      "step": 90
    },
    {
      "epoch": 0.010047808119277206,
      "grad_norm": 0.49006080627441406,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.2471,
      "step": 93
    },
    {
      "epoch": 0.010371930961834535,
      "grad_norm": 0.5014355778694153,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.2864,
      "step": 96
    },
    {
      "epoch": 0.010696053804391864,
      "grad_norm": 0.53614342212677,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.2349,
      "step": 99
    },
    {
      "epoch": 0.010804094751910975,
      "eval_loss": 1.4096521139144897,
      "eval_runtime": 542.4184,
      "eval_samples_per_second": 28.74,
      "eval_steps_per_second": 7.186,
      "step": 100
    },
    {
      "epoch": 0.011020176646949193,
      "grad_norm": 0.49735087156295776,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.3988,
      "step": 102
    },
    {
      "epoch": 0.011344299489506523,
      "grad_norm": 0.4606347382068634,
      "learning_rate": 5e-05,
      "loss": 1.5228,
      "step": 105
    },
    {
      "epoch": 0.011668422332063852,
      "grad_norm": 0.5091155171394348,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.4814,
      "step": 108
    },
    {
      "epoch": 0.01199254517462118,
      "grad_norm": 0.5642185211181641,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.6132,
      "step": 111
    },
    {
      "epoch": 0.012316668017178511,
      "grad_norm": 0.5649376511573792,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.5986,
      "step": 114
    },
    {
      "epoch": 0.01264079085973584,
      "grad_norm": 0.5556029081344604,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.606,
      "step": 117
    },
    {
      "epoch": 0.01296491370229317,
      "grad_norm": 0.6111022233963013,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.5919,
      "step": 120
    },
    {
      "epoch": 0.013289036544850499,
      "grad_norm": 0.7231109142303467,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.45,
      "step": 123
    },
    {
      "epoch": 0.013613159387407828,
      "grad_norm": 0.570808470249176,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.3601,
      "step": 126
    },
    {
      "epoch": 0.013937282229965157,
      "grad_norm": 0.5434361696243286,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.3497,
      "step": 129
    },
    {
      "epoch": 0.014261405072522486,
      "grad_norm": 0.4750564992427826,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.2799,
      "step": 132
    },
    {
      "epoch": 0.014585527915079815,
      "grad_norm": 0.5212507843971252,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.2695,
      "step": 135
    },
    {
      "epoch": 0.014909650757637144,
      "grad_norm": 0.5255863070487976,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.2256,
      "step": 138
    },
    {
      "epoch": 0.015233773600194473,
      "grad_norm": 0.5165453553199768,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.2671,
      "step": 141
    },
    {
      "epoch": 0.015557896442751802,
      "grad_norm": 0.5220006704330444,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.2104,
      "step": 144
    },
    {
      "epoch": 0.01588201928530913,
      "grad_norm": 0.48809775710105896,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.206,
      "step": 147
    },
    {
      "epoch": 0.01620614212786646,
      "grad_norm": 0.6223570108413696,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.1717,
      "step": 150
    },
    {
      "epoch": 0.01620614212786646,
      "eval_loss": 1.3886877298355103,
      "eval_runtime": 541.2859,
      "eval_samples_per_second": 28.8,
      "eval_steps_per_second": 7.201,
      "step": 150
    },
    {
      "epoch": 0.01653026497042379,
      "grad_norm": 0.5191346406936646,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.5168,
      "step": 153
    },
    {
      "epoch": 0.01685438781298112,
      "grad_norm": 0.5353146195411682,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.4967,
      "step": 156
    },
    {
      "epoch": 0.017178510655538447,
      "grad_norm": 0.5311741828918457,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.5718,
      "step": 159
    },
    {
      "epoch": 0.01750263349809578,
      "grad_norm": 0.5845088362693787,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.5607,
      "step": 162
    },
    {
      "epoch": 0.01782675634065311,
      "grad_norm": 0.5743259191513062,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.581,
      "step": 165
    },
    {
      "epoch": 0.018150879183210438,
      "grad_norm": 0.6573442220687866,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.6465,
      "step": 168
    },
    {
      "epoch": 0.018475002025767767,
      "grad_norm": 0.6954129934310913,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.5841,
      "step": 171
    },
    {
      "epoch": 0.018799124868325096,
      "grad_norm": 0.5963082909584045,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.4765,
      "step": 174
    },
    {
      "epoch": 0.019123247710882425,
      "grad_norm": 0.44104716181755066,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.2437,
      "step": 177
    },
    {
      "epoch": 0.019447370553439754,
      "grad_norm": 0.5068080425262451,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.2188,
      "step": 180
    },
    {
      "epoch": 0.019771493395997083,
      "grad_norm": 0.4765148460865021,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.2455,
      "step": 183
    },
    {
      "epoch": 0.020095616238554413,
      "grad_norm": 0.5346724390983582,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.3474,
      "step": 186
    },
    {
      "epoch": 0.02041973908111174,
      "grad_norm": 0.5100587606430054,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.262,
      "step": 189
    },
    {
      "epoch": 0.02074386192366907,
      "grad_norm": 0.48295655846595764,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.3058,
      "step": 192
    },
    {
      "epoch": 0.0210679847662264,
      "grad_norm": 0.5347855687141418,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.2393,
      "step": 195
    },
    {
      "epoch": 0.02139210760878373,
      "grad_norm": 0.5421356558799744,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.2671,
      "step": 198
    },
    {
      "epoch": 0.02160818950382195,
      "eval_loss": 1.38231360912323,
      "eval_runtime": 542.45,
      "eval_samples_per_second": 28.738,
      "eval_steps_per_second": 7.186,
      "step": 200
    }
  ],
  "logging_steps": 3,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 7.8039887118336e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}