{
  "best_metric": 11.062679290771484,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.5899705014749262,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0058997050147492625,
      "grad_norm": 10.886664390563965,
      "learning_rate": 1.6666666666666668e-07,
      "loss": 44.8554,
      "step": 1
    },
    {
      "epoch": 0.0058997050147492625,
      "eval_loss": 11.221614837646484,
      "eval_runtime": 1.0489,
      "eval_samples_per_second": 272.669,
      "eval_steps_per_second": 34.322,
      "step": 1
    },
    {
      "epoch": 0.011799410029498525,
      "grad_norm": 10.930596351623535,
      "learning_rate": 3.3333333333333335e-07,
      "loss": 44.876,
      "step": 2
    },
    {
      "epoch": 0.017699115044247787,
      "grad_norm": 10.833826065063477,
      "learning_rate": 5.000000000000001e-07,
      "loss": 44.8799,
      "step": 3
    },
    {
      "epoch": 0.02359882005899705,
      "grad_norm": 10.970483779907227,
      "learning_rate": 6.666666666666667e-07,
      "loss": 44.8848,
      "step": 4
    },
    {
      "epoch": 0.029498525073746312,
      "grad_norm": 11.25637435913086,
      "learning_rate": 8.333333333333333e-07,
      "loss": 44.904,
      "step": 5
    },
    {
      "epoch": 0.035398230088495575,
      "grad_norm": 11.155887603759766,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 44.8352,
      "step": 6
    },
    {
      "epoch": 0.04129793510324484,
      "grad_norm": 10.9830322265625,
      "learning_rate": 1.1666666666666668e-06,
      "loss": 44.8633,
      "step": 7
    },
    {
      "epoch": 0.0471976401179941,
      "grad_norm": 11.078715324401855,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 44.8707,
      "step": 8
    },
    {
      "epoch": 0.05309734513274336,
      "grad_norm": 11.469353675842285,
      "learning_rate": 1.5e-06,
      "loss": 44.8924,
      "step": 9
    },
    {
      "epoch": 0.058997050147492625,
      "grad_norm": 11.133667945861816,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 44.8986,
      "step": 10
    },
    {
      "epoch": 0.06489675516224189,
      "grad_norm": 11.04592227935791,
      "learning_rate": 1.8333333333333333e-06,
      "loss": 44.9135,
      "step": 11
    },
    {
      "epoch": 0.07079646017699115,
      "grad_norm": 11.071782112121582,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 44.8871,
      "step": 12
    },
    {
      "epoch": 0.07669616519174041,
      "grad_norm": 11.084949493408203,
      "learning_rate": 2.166666666666667e-06,
      "loss": 44.8941,
      "step": 13
    },
    {
      "epoch": 0.08259587020648967,
      "grad_norm": 10.90757942199707,
      "learning_rate": 2.3333333333333336e-06,
      "loss": 44.849,
      "step": 14
    },
    {
      "epoch": 0.08849557522123894,
      "grad_norm": 10.782208442687988,
      "learning_rate": 2.5e-06,
      "loss": 44.8656,
      "step": 15
    },
    {
      "epoch": 0.0943952802359882,
      "grad_norm": 10.914060592651367,
      "learning_rate": 2.666666666666667e-06,
      "loss": 44.8329,
      "step": 16
    },
    {
      "epoch": 0.10029498525073746,
      "grad_norm": 10.9237642288208,
      "learning_rate": 2.8333333333333335e-06,
      "loss": 44.8753,
      "step": 17
    },
    {
      "epoch": 0.10619469026548672,
      "grad_norm": 10.91445255279541,
      "learning_rate": 3e-06,
      "loss": 44.8781,
      "step": 18
    },
    {
      "epoch": 0.11209439528023599,
      "grad_norm": 11.406682014465332,
      "learning_rate": 3.1666666666666667e-06,
      "loss": 44.7866,
      "step": 19
    },
    {
      "epoch": 0.11799410029498525,
      "grad_norm": 10.877439498901367,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 44.785,
      "step": 20
    },
    {
      "epoch": 0.12389380530973451,
      "grad_norm": 11.090054512023926,
      "learning_rate": 3.5e-06,
      "loss": 44.8091,
      "step": 21
    },
    {
      "epoch": 0.12979351032448377,
      "grad_norm": 10.820998191833496,
      "learning_rate": 3.6666666666666666e-06,
      "loss": 44.7878,
      "step": 22
    },
    {
      "epoch": 0.13569321533923304,
      "grad_norm": 11.049379348754883,
      "learning_rate": 3.833333333333334e-06,
      "loss": 44.7947,
      "step": 23
    },
    {
      "epoch": 0.1415929203539823,
      "grad_norm": 11.088188171386719,
      "learning_rate": 4.000000000000001e-06,
      "loss": 44.7741,
      "step": 24
    },
    {
      "epoch": 0.14749262536873156,
      "grad_norm": 11.064141273498535,
      "learning_rate": 4.166666666666667e-06,
      "loss": 44.8164,
      "step": 25
    },
    {
      "epoch": 0.15339233038348082,
      "grad_norm": 11.089920043945312,
      "learning_rate": 4.333333333333334e-06,
      "loss": 44.7799,
      "step": 26
    },
    {
      "epoch": 0.1592920353982301,
      "grad_norm": 11.03174877166748,
      "learning_rate": 4.5e-06,
      "loss": 44.7448,
      "step": 27
    },
    {
      "epoch": 0.16519174041297935,
      "grad_norm": 10.936544418334961,
      "learning_rate": 4.666666666666667e-06,
      "loss": 44.7058,
      "step": 28
    },
    {
      "epoch": 0.1710914454277286,
      "grad_norm": 11.263934135437012,
      "learning_rate": 4.833333333333333e-06,
      "loss": 44.7484,
      "step": 29
    },
    {
      "epoch": 0.17699115044247787,
      "grad_norm": 11.224115371704102,
      "learning_rate": 5e-06,
      "loss": 44.7395,
      "step": 30
    },
    {
      "epoch": 0.18289085545722714,
      "grad_norm": 11.245924949645996,
      "learning_rate": 4.997482666353287e-06,
      "loss": 44.6893,
      "step": 31
    },
    {
      "epoch": 0.1887905604719764,
      "grad_norm": 11.2431640625,
      "learning_rate": 4.989935734988098e-06,
      "loss": 44.6915,
      "step": 32
    },
    {
      "epoch": 0.19469026548672566,
      "grad_norm": 10.986893653869629,
      "learning_rate": 4.977374404419838e-06,
      "loss": 44.6643,
      "step": 33
    },
    {
      "epoch": 0.20058997050147492,
      "grad_norm": 11.198678016662598,
      "learning_rate": 4.959823971496575e-06,
      "loss": 44.7171,
      "step": 34
    },
    {
      "epoch": 0.20648967551622419,
      "grad_norm": 11.15566349029541,
      "learning_rate": 4.937319780454559e-06,
      "loss": 44.69,
      "step": 35
    },
    {
      "epoch": 0.21238938053097345,
      "grad_norm": 11.303568840026855,
      "learning_rate": 4.909907151739634e-06,
      "loss": 44.6101,
      "step": 36
    },
    {
      "epoch": 0.2182890855457227,
      "grad_norm": 11.348630905151367,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 44.6683,
      "step": 37
    },
    {
      "epoch": 0.22418879056047197,
      "grad_norm": 11.226109504699707,
      "learning_rate": 4.8405871765993435e-06,
      "loss": 44.5979,
      "step": 38
    },
    {
      "epoch": 0.23008849557522124,
      "grad_norm": 11.195021629333496,
      "learning_rate": 4.7988194313786275e-06,
      "loss": 44.6171,
      "step": 39
    },
    {
      "epoch": 0.2359882005899705,
      "grad_norm": 11.280457496643066,
      "learning_rate": 4.752422169756048e-06,
      "loss": 44.602,
      "step": 40
    },
    {
      "epoch": 0.24188790560471976,
      "grad_norm": 11.282366752624512,
      "learning_rate": 4.701488829641845e-06,
      "loss": 44.5678,
      "step": 41
    },
    {
      "epoch": 0.24778761061946902,
      "grad_norm": 11.656867027282715,
      "learning_rate": 4.646121984004666e-06,
      "loss": 44.5781,
      "step": 42
    },
    {
      "epoch": 0.2536873156342183,
      "grad_norm": 10.911307334899902,
      "learning_rate": 4.586433134303257e-06,
      "loss": 44.5528,
      "step": 43
    },
    {
      "epoch": 0.25958702064896755,
      "grad_norm": 11.045024871826172,
      "learning_rate": 4.522542485937369e-06,
      "loss": 44.5775,
      "step": 44
    },
    {
      "epoch": 0.26548672566371684,
      "grad_norm": 10.932096481323242,
      "learning_rate": 4.454578706170075e-06,
      "loss": 44.5573,
      "step": 45
    },
    {
      "epoch": 0.2713864306784661,
      "grad_norm": 11.110983848571777,
      "learning_rate": 4.382678665009028e-06,
      "loss": 44.5243,
      "step": 46
    },
    {
      "epoch": 0.27728613569321536,
      "grad_norm": 11.290690422058105,
      "learning_rate": 4.3069871595684795e-06,
      "loss": 44.4917,
      "step": 47
    },
    {
      "epoch": 0.2831858407079646,
      "grad_norm": 11.164863586425781,
      "learning_rate": 4.227656622467162e-06,
      "loss": 44.4501,
      "step": 48
    },
    {
      "epoch": 0.2890855457227139,
      "grad_norm": 11.13447380065918,
      "learning_rate": 4.144846814849282e-06,
      "loss": 44.4477,
      "step": 49
    },
    {
      "epoch": 0.2949852507374631,
      "grad_norm": 11.295125007629395,
      "learning_rate": 4.058724504646834e-06,
      "loss": 44.4398,
      "step": 50
    },
    {
      "epoch": 0.2949852507374631,
      "eval_loss": 11.117125511169434,
      "eval_runtime": 0.6596,
      "eval_samples_per_second": 433.596,
      "eval_steps_per_second": 54.579,
      "step": 50
    },
    {
      "epoch": 0.3008849557522124,
      "grad_norm": 11.262834548950195,
      "learning_rate": 3.969463130731183e-06,
      "loss": 44.5064,
      "step": 51
    },
    {
      "epoch": 0.30678466076696165,
      "grad_norm": 11.28780460357666,
      "learning_rate": 3.8772424536302565e-06,
      "loss": 44.4551,
      "step": 52
    },
    {
      "epoch": 0.31268436578171094,
      "grad_norm": 11.082712173461914,
      "learning_rate": 3.782248193514766e-06,
      "loss": 44.4367,
      "step": 53
    },
    {
      "epoch": 0.3185840707964602,
      "grad_norm": 11.272944450378418,
      "learning_rate": 3.684671656182497e-06,
      "loss": 44.495,
      "step": 54
    },
    {
      "epoch": 0.32448377581120946,
      "grad_norm": 11.367984771728516,
      "learning_rate": 3.5847093477938955e-06,
      "loss": 44.4521,
      "step": 55
    },
    {
      "epoch": 0.3303834808259587,
      "grad_norm": 11.50567626953125,
      "learning_rate": 3.4825625791348093e-06,
      "loss": 44.4069,
      "step": 56
    },
    {
      "epoch": 0.336283185840708,
      "grad_norm": 11.37206745147705,
      "learning_rate": 3.3784370602033572e-06,
      "loss": 44.4106,
      "step": 57
    },
    {
      "epoch": 0.3421828908554572,
      "grad_norm": 11.600016593933105,
      "learning_rate": 3.272542485937369e-06,
      "loss": 44.3691,
      "step": 58
    },
    {
      "epoch": 0.3480825958702065,
      "grad_norm": 11.29223918914795,
      "learning_rate": 3.165092113916688e-06,
      "loss": 44.3776,
      "step": 59
    },
    {
      "epoch": 0.35398230088495575,
      "grad_norm": 11.168807983398438,
      "learning_rate": 3.056302334890786e-06,
      "loss": 44.3662,
      "step": 60
    },
    {
      "epoch": 0.35988200589970504,
      "grad_norm": 11.356904029846191,
      "learning_rate": 2.946392236996592e-06,
      "loss": 44.3792,
      "step": 61
    },
    {
      "epoch": 0.36578171091445427,
      "grad_norm": 11.171018600463867,
      "learning_rate": 2.835583164544139e-06,
      "loss": 44.3577,
      "step": 62
    },
    {
      "epoch": 0.37168141592920356,
      "grad_norm": 11.397581100463867,
      "learning_rate": 2.724098272258584e-06,
      "loss": 44.3313,
      "step": 63
    },
    {
      "epoch": 0.3775811209439528,
      "grad_norm": 11.264802932739258,
      "learning_rate": 2.6121620758762877e-06,
      "loss": 44.33,
      "step": 64
    },
    {
      "epoch": 0.3834808259587021,
      "grad_norm": 11.5596923828125,
      "learning_rate": 2.5e-06,
      "loss": 44.3594,
      "step": 65
    },
    {
      "epoch": 0.3893805309734513,
      "grad_norm": 11.320469856262207,
      "learning_rate": 2.3878379241237136e-06,
      "loss": 44.3022,
      "step": 66
    },
    {
      "epoch": 0.3952802359882006,
      "grad_norm": 11.212388038635254,
      "learning_rate": 2.2759017277414165e-06,
      "loss": 44.3685,
      "step": 67
    },
    {
      "epoch": 0.40117994100294985,
      "grad_norm": 11.267321586608887,
      "learning_rate": 2.1644168354558623e-06,
      "loss": 44.3347,
      "step": 68
    },
    {
      "epoch": 0.40707964601769914,
      "grad_norm": 11.387954711914062,
      "learning_rate": 2.053607763003409e-06,
      "loss": 44.2862,
      "step": 69
    },
    {
      "epoch": 0.41297935103244837,
      "grad_norm": 11.291707992553711,
      "learning_rate": 1.9436976651092143e-06,
      "loss": 44.3167,
      "step": 70
    },
    {
      "epoch": 0.41887905604719766,
      "grad_norm": 11.472674369812012,
      "learning_rate": 1.8349078860833125e-06,
      "loss": 44.3085,
      "step": 71
    },
    {
      "epoch": 0.4247787610619469,
      "grad_norm": 11.46934700012207,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 44.3146,
      "step": 72
    },
    {
      "epoch": 0.4306784660766962,
      "grad_norm": 11.346488952636719,
      "learning_rate": 1.6215629397966432e-06,
      "loss": 44.2872,
      "step": 73
    },
    {
      "epoch": 0.4365781710914454,
      "grad_norm": 11.554361343383789,
      "learning_rate": 1.5174374208651913e-06,
      "loss": 44.2945,
      "step": 74
    },
    {
      "epoch": 0.4424778761061947,
      "grad_norm": 11.511228561401367,
      "learning_rate": 1.415290652206105e-06,
      "loss": 44.3073,
      "step": 75
    },
    {
      "epoch": 0.44837758112094395,
      "grad_norm": 11.469541549682617,
      "learning_rate": 1.3153283438175036e-06,
      "loss": 44.3281,
      "step": 76
    },
    {
      "epoch": 0.45427728613569324,
      "grad_norm": 11.547125816345215,
      "learning_rate": 1.217751806485235e-06,
      "loss": 44.3098,
      "step": 77
    },
    {
      "epoch": 0.46017699115044247,
      "grad_norm": 11.442727088928223,
      "learning_rate": 1.122757546369744e-06,
      "loss": 44.2586,
      "step": 78
    },
    {
      "epoch": 0.46607669616519176,
      "grad_norm": 11.528830528259277,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 44.2821,
      "step": 79
    },
    {
      "epoch": 0.471976401179941,
      "grad_norm": 11.535983085632324,
      "learning_rate": 9.412754953531664e-07,
      "loss": 44.3261,
      "step": 80
    },
    {
      "epoch": 0.4778761061946903,
      "grad_norm": 11.634220123291016,
      "learning_rate": 8.551531851507186e-07,
      "loss": 44.275,
      "step": 81
    },
    {
      "epoch": 0.4837758112094395,
      "grad_norm": 11.648545265197754,
      "learning_rate": 7.723433775328385e-07,
      "loss": 44.2439,
      "step": 82
    },
    {
      "epoch": 0.4896755162241888,
      "grad_norm": 11.617422103881836,
      "learning_rate": 6.930128404315214e-07,
      "loss": 44.3185,
      "step": 83
    },
    {
      "epoch": 0.49557522123893805,
      "grad_norm": 11.682761192321777,
      "learning_rate": 6.17321334990973e-07,
      "loss": 44.2801,
      "step": 84
    },
    {
      "epoch": 0.5014749262536873,
      "grad_norm": 11.089653968811035,
      "learning_rate": 5.454212938299256e-07,
      "loss": 44.2543,
      "step": 85
    },
    {
      "epoch": 0.5073746312684366,
      "grad_norm": 11.051488876342773,
      "learning_rate": 4.774575140626317e-07,
      "loss": 44.2673,
      "step": 86
    },
    {
      "epoch": 0.5132743362831859,
      "grad_norm": 11.184460639953613,
      "learning_rate": 4.1356686569674344e-07,
      "loss": 44.2306,
      "step": 87
    },
    {
      "epoch": 0.5191740412979351,
      "grad_norm": 11.230326652526855,
      "learning_rate": 3.538780159953348e-07,
      "loss": 44.2451,
      "step": 88
    },
    {
      "epoch": 0.5250737463126843,
      "grad_norm": 11.29784107208252,
      "learning_rate": 2.98511170358155e-07,
      "loss": 44.2646,
      "step": 89
    },
    {
      "epoch": 0.5309734513274337,
      "grad_norm": 11.078227996826172,
      "learning_rate": 2.4757783024395244e-07,
      "loss": 44.2559,
      "step": 90
    },
    {
      "epoch": 0.5368731563421829,
      "grad_norm": 11.108466148376465,
      "learning_rate": 2.0118056862137358e-07,
      "loss": 44.2589,
      "step": 91
    },
    {
      "epoch": 0.5427728613569321,
      "grad_norm": 11.564451217651367,
      "learning_rate": 1.59412823400657e-07,
      "loss": 44.2609,
      "step": 92
    },
    {
      "epoch": 0.5486725663716814,
      "grad_norm": 11.223318099975586,
      "learning_rate": 1.223587092621162e-07,
      "loss": 44.2762,
      "step": 93
    },
    {
      "epoch": 0.5545722713864307,
      "grad_norm": 11.573466300964355,
      "learning_rate": 9.00928482603669e-08,
      "loss": 44.2708,
      "step": 94
    },
    {
      "epoch": 0.56047197640118,
      "grad_norm": 11.500224113464355,
      "learning_rate": 6.268021954544095e-08,
      "loss": 44.2757,
      "step": 95
    },
    {
      "epoch": 0.5663716814159292,
      "grad_norm": 11.30689525604248,
      "learning_rate": 4.017602850342584e-08,
      "loss": 44.224,
      "step": 96
    },
    {
      "epoch": 0.5722713864306784,
      "grad_norm": 11.348673820495605,
      "learning_rate": 2.262559558016325e-08,
      "loss": 44.2502,
      "step": 97
    },
    {
      "epoch": 0.5781710914454278,
      "grad_norm": 11.519439697265625,
      "learning_rate": 1.006426501190233e-08,
      "loss": 44.2666,
      "step": 98
    },
    {
      "epoch": 0.584070796460177,
      "grad_norm": 11.413444519042969,
      "learning_rate": 2.5173336467135266e-09,
      "loss": 44.3009,
      "step": 99
    },
    {
      "epoch": 0.5899705014749262,
      "grad_norm": 11.36845588684082,
      "learning_rate": 0.0,
      "loss": 44.1867,
      "step": 100
    },
    {
      "epoch": 0.5899705014749262,
      "eval_loss": 11.062679290771484,
      "eval_runtime": 0.6567,
      "eval_samples_per_second": 435.541,
      "eval_steps_per_second": 54.823,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": 11943700070400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}