{
  "best_metric": 0.9707683324813843,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.014164305949008499,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028328611898016995,
      "grad_norm": 2.4459738731384277,
      "learning_rate": 5e-06,
      "loss": 1.0328,
      "step": 1
    },
    {
      "epoch": 0.00028328611898016995,
      "eval_loss": 1.364790678024292,
      "eval_runtime": 485.4956,
      "eval_samples_per_second": 12.247,
      "eval_steps_per_second": 6.124,
      "step": 1
    },
    {
      "epoch": 0.0005665722379603399,
      "grad_norm": 0.7349909543991089,
      "learning_rate": 1e-05,
      "loss": 1.044,
      "step": 2
    },
    {
      "epoch": 0.0008498583569405099,
      "grad_norm": 0.5141507387161255,
      "learning_rate": 1.5e-05,
      "loss": 1.0227,
      "step": 3
    },
    {
      "epoch": 0.0011331444759206798,
      "grad_norm": 1.156713604927063,
      "learning_rate": 2e-05,
      "loss": 1.0904,
      "step": 4
    },
    {
      "epoch": 0.00141643059490085,
      "grad_norm": 0.7857816219329834,
      "learning_rate": 2.5e-05,
      "loss": 1.1226,
      "step": 5
    },
    {
      "epoch": 0.0016997167138810198,
      "grad_norm": 0.5737718939781189,
      "learning_rate": 3e-05,
      "loss": 1.0554,
      "step": 6
    },
    {
      "epoch": 0.00198300283286119,
      "grad_norm": 0.7259950637817383,
      "learning_rate": 3.5e-05,
      "loss": 1.0777,
      "step": 7
    },
    {
      "epoch": 0.0022662889518413596,
      "grad_norm": 0.5065688490867615,
      "learning_rate": 4e-05,
      "loss": 1.0204,
      "step": 8
    },
    {
      "epoch": 0.0025495750708215297,
      "grad_norm": 0.41538459062576294,
      "learning_rate": 4.5e-05,
      "loss": 1.04,
      "step": 9
    },
    {
      "epoch": 0.0028328611898017,
      "grad_norm": 0.3766935467720032,
      "learning_rate": 5e-05,
      "loss": 0.9753,
      "step": 10
    },
    {
      "epoch": 0.0031161473087818695,
      "grad_norm": 0.40806570649147034,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.9953,
      "step": 11
    },
    {
      "epoch": 0.0033994334277620396,
      "grad_norm": 0.3899538218975067,
      "learning_rate": 6e-05,
      "loss": 1.0186,
      "step": 12
    },
    {
      "epoch": 0.0036827195467422098,
      "grad_norm": 0.43268951773643494,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.9802,
      "step": 13
    },
    {
      "epoch": 0.00396600566572238,
      "grad_norm": 0.42716556787490845,
      "learning_rate": 7e-05,
      "loss": 0.9618,
      "step": 14
    },
    {
      "epoch": 0.00424929178470255,
      "grad_norm": 0.4129604697227478,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.9033,
      "step": 15
    },
    {
      "epoch": 0.004532577903682719,
      "grad_norm": 0.40332239866256714,
      "learning_rate": 8e-05,
      "loss": 0.8851,
      "step": 16
    },
    {
      "epoch": 0.004815864022662889,
      "grad_norm": 0.42246365547180176,
      "learning_rate": 8.5e-05,
      "loss": 0.995,
      "step": 17
    },
    {
      "epoch": 0.0050991501416430595,
      "grad_norm": 0.40158501267433167,
      "learning_rate": 9e-05,
      "loss": 0.9784,
      "step": 18
    },
    {
      "epoch": 0.00538243626062323,
      "grad_norm": 0.3314235210418701,
      "learning_rate": 9.5e-05,
      "loss": 0.8783,
      "step": 19
    },
    {
      "epoch": 0.0056657223796034,
      "grad_norm": 0.30537742376327515,
      "learning_rate": 0.0001,
      "loss": 0.8774,
      "step": 20
    },
    {
      "epoch": 0.00594900849858357,
      "grad_norm": 0.3494546711444855,
      "learning_rate": 9.999238475781957e-05,
      "loss": 0.8816,
      "step": 21
    },
    {
      "epoch": 0.006232294617563739,
      "grad_norm": 0.3360932767391205,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.8611,
      "step": 22
    },
    {
      "epoch": 0.006515580736543909,
      "grad_norm": 0.3689824044704437,
      "learning_rate": 9.99314767377287e-05,
      "loss": 0.8842,
      "step": 23
    },
    {
      "epoch": 0.006798866855524079,
      "grad_norm": 0.37334781885147095,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.9124,
      "step": 24
    },
    {
      "epoch": 0.007082152974504249,
      "grad_norm": 0.38459479808807373,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.8801,
      "step": 25
    },
    {
      "epoch": 0.0073654390934844195,
      "grad_norm": 0.3251090943813324,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.8642,
      "step": 26
    },
    {
      "epoch": 0.00764872521246459,
      "grad_norm": 0.3844033479690552,
      "learning_rate": 9.962730758206611e-05,
      "loss": 0.9023,
      "step": 27
    },
    {
      "epoch": 0.00793201133144476,
      "grad_norm": 0.40686604380607605,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.9195,
      "step": 28
    },
    {
      "epoch": 0.00821529745042493,
      "grad_norm": 0.30939722061157227,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.8657,
      "step": 29
    },
    {
      "epoch": 0.0084985835694051,
      "grad_norm": 0.4041453003883362,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.9044,
      "step": 30
    },
    {
      "epoch": 0.008781869688385268,
      "grad_norm": 0.4817129373550415,
      "learning_rate": 9.908135917238321e-05,
      "loss": 0.9488,
      "step": 31
    },
    {
      "epoch": 0.009065155807365438,
      "grad_norm": 0.4093549847602844,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.9094,
      "step": 32
    },
    {
      "epoch": 0.009348441926345609,
      "grad_norm": 0.43957093358039856,
      "learning_rate": 9.871850323926177e-05,
      "loss": 0.9521,
      "step": 33
    },
    {
      "epoch": 0.009631728045325779,
      "grad_norm": 0.517327070236206,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.8606,
      "step": 34
    },
    {
      "epoch": 0.009915014164305949,
      "grad_norm": 0.6792945861816406,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.0191,
      "step": 35
    },
    {
      "epoch": 0.010198300283286119,
      "grad_norm": 0.5788185000419617,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.9683,
      "step": 36
    },
    {
      "epoch": 0.010481586402266289,
      "grad_norm": 0.63746178150177,
      "learning_rate": 9.781523779815179e-05,
      "loss": 1.0815,
      "step": 37
    },
    {
      "epoch": 0.01076487252124646,
      "grad_norm": 0.5034915208816528,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9157,
      "step": 38
    },
    {
      "epoch": 0.01104815864022663,
      "grad_norm": 0.568718433380127,
      "learning_rate": 9.727592877996585e-05,
      "loss": 1.0136,
      "step": 39
    },
    {
      "epoch": 0.0113314447592068,
      "grad_norm": 0.7134827971458435,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.9963,
      "step": 40
    },
    {
      "epoch": 0.01161473087818697,
      "grad_norm": 0.6913411617279053,
      "learning_rate": 9.667902132486009e-05,
      "loss": 1.0246,
      "step": 41
    },
    {
      "epoch": 0.01189801699716714,
      "grad_norm": 0.7879395484924316,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.1409,
      "step": 42
    },
    {
      "epoch": 0.012181303116147308,
      "grad_norm": 0.6506746411323547,
      "learning_rate": 9.602524267262203e-05,
      "loss": 1.0367,
      "step": 43
    },
    {
      "epoch": 0.012464589235127478,
      "grad_norm": 0.7825458645820618,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.0962,
      "step": 44
    },
    {
      "epoch": 0.012747875354107648,
      "grad_norm": 0.8112017512321472,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.9379,
      "step": 45
    },
    {
      "epoch": 0.013031161473087818,
      "grad_norm": 0.9518360495567322,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.2331,
      "step": 46
    },
    {
      "epoch": 0.013314447592067988,
      "grad_norm": 1.0096303224563599,
      "learning_rate": 9.45503262094184e-05,
      "loss": 1.0212,
      "step": 47
    },
    {
      "epoch": 0.013597733711048159,
      "grad_norm": 1.4635624885559082,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.18,
      "step": 48
    },
    {
      "epoch": 0.013881019830028329,
      "grad_norm": 1.5704519748687744,
      "learning_rate": 9.373098535696979e-05,
      "loss": 1.0703,
      "step": 49
    },
    {
      "epoch": 0.014164305949008499,
      "grad_norm": 2.2931337356567383,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.0591,
      "step": 50
    },
    {
      "epoch": 0.014164305949008499,
      "eval_loss": 0.9707683324813843,
      "eval_runtime": 488.0589,
      "eval_samples_per_second": 12.183,
      "eval_steps_per_second": 6.091,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.8634147815424e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}