{
  "best_metric": 1.971840500831604,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.03352891869237217,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033528918692372173,
      "grad_norm": 3.0645880699157715,
      "learning_rate": 5e-06,
      "loss": 2.5227,
      "step": 1
    },
    {
      "epoch": 0.00033528918692372173,
      "eval_loss": 4.411320209503174,
      "eval_runtime": 413.4616,
      "eval_samples_per_second": 12.149,
      "eval_steps_per_second": 6.076,
      "step": 1
    },
    {
      "epoch": 0.0006705783738474435,
      "grad_norm": 4.630534648895264,
      "learning_rate": 1e-05,
      "loss": 3.4584,
      "step": 2
    },
    {
      "epoch": 0.001005867560771165,
      "grad_norm": 4.6843414306640625,
      "learning_rate": 1.5e-05,
      "loss": 3.2337,
      "step": 3
    },
    {
      "epoch": 0.001341156747694887,
      "grad_norm": 5.27373743057251,
      "learning_rate": 2e-05,
      "loss": 3.4903,
      "step": 4
    },
    {
      "epoch": 0.0016764459346186086,
      "grad_norm": 4.094366073608398,
      "learning_rate": 2.5e-05,
      "loss": 3.4112,
      "step": 5
    },
    {
      "epoch": 0.00201173512154233,
      "grad_norm": 4.469041347503662,
      "learning_rate": 3e-05,
      "loss": 3.9968,
      "step": 6
    },
    {
      "epoch": 0.002347024308466052,
      "grad_norm": 3.391988754272461,
      "learning_rate": 3.5e-05,
      "loss": 2.8687,
      "step": 7
    },
    {
      "epoch": 0.002682313495389774,
      "grad_norm": 4.106904029846191,
      "learning_rate": 4e-05,
      "loss": 3.1234,
      "step": 8
    },
    {
      "epoch": 0.0030176026823134955,
      "grad_norm": 4.628849029541016,
      "learning_rate": 4.5e-05,
      "loss": 2.5943,
      "step": 9
    },
    {
      "epoch": 0.003352891869237217,
      "grad_norm": 4.383242130279541,
      "learning_rate": 5e-05,
      "loss": 3.0693,
      "step": 10
    },
    {
      "epoch": 0.0036881810561609388,
      "grad_norm": 5.0880446434021,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.3701,
      "step": 11
    },
    {
      "epoch": 0.00402347024308466,
      "grad_norm": 4.474156856536865,
      "learning_rate": 6e-05,
      "loss": 2.3279,
      "step": 12
    },
    {
      "epoch": 0.0043587594300083824,
      "grad_norm": 3.052427053451538,
      "learning_rate": 6.500000000000001e-05,
      "loss": 2.382,
      "step": 13
    },
    {
      "epoch": 0.004694048616932104,
      "grad_norm": 3.632539749145508,
      "learning_rate": 7e-05,
      "loss": 2.3547,
      "step": 14
    },
    {
      "epoch": 0.005029337803855826,
      "grad_norm": 3.813579559326172,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.0444,
      "step": 15
    },
    {
      "epoch": 0.005364626990779548,
      "grad_norm": 3.673614025115967,
      "learning_rate": 8e-05,
      "loss": 2.4787,
      "step": 16
    },
    {
      "epoch": 0.005699916177703269,
      "grad_norm": 3.4429280757904053,
      "learning_rate": 8.5e-05,
      "loss": 2.0714,
      "step": 17
    },
    {
      "epoch": 0.006035205364626991,
      "grad_norm": 6.227026462554932,
      "learning_rate": 9e-05,
      "loss": 2.6872,
      "step": 18
    },
    {
      "epoch": 0.006370494551550712,
      "grad_norm": 2.7409024238586426,
      "learning_rate": 9.5e-05,
      "loss": 2.2862,
      "step": 19
    },
    {
      "epoch": 0.006705783738474434,
      "grad_norm": 3.4296722412109375,
      "learning_rate": 0.0001,
      "loss": 2.4185,
      "step": 20
    },
    {
      "epoch": 0.007041072925398156,
      "grad_norm": 3.6439619064331055,
      "learning_rate": 9.999238475781957e-05,
      "loss": 2.4921,
      "step": 21
    },
    {
      "epoch": 0.0073763621123218775,
      "grad_norm": 2.5447402000427246,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.1374,
      "step": 22
    },
    {
      "epoch": 0.0077116512992456,
      "grad_norm": 3.3165926933288574,
      "learning_rate": 9.99314767377287e-05,
      "loss": 2.3914,
      "step": 23
    },
    {
      "epoch": 0.00804694048616932,
      "grad_norm": 2.4111523628234863,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.1302,
      "step": 24
    },
    {
      "epoch": 0.008382229673093043,
      "grad_norm": 2.1574089527130127,
      "learning_rate": 9.980973490458728e-05,
      "loss": 2.1361,
      "step": 25
    },
    {
      "epoch": 0.008717518860016765,
      "grad_norm": 2.2673230171203613,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.9017,
      "step": 26
    },
    {
      "epoch": 0.009052808046940487,
      "grad_norm": 2.552058219909668,
      "learning_rate": 9.962730758206611e-05,
      "loss": 2.1296,
      "step": 27
    },
    {
      "epoch": 0.009388097233864207,
      "grad_norm": 2.4075942039489746,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.1832,
      "step": 28
    },
    {
      "epoch": 0.00972338642078793,
      "grad_norm": 2.210503101348877,
      "learning_rate": 9.938441702975689e-05,
      "loss": 2.1556,
      "step": 29
    },
    {
      "epoch": 0.010058675607711651,
      "grad_norm": 2.603090286254883,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.9968,
      "step": 30
    },
    {
      "epoch": 0.010393964794635373,
      "grad_norm": 2.427295446395874,
      "learning_rate": 9.908135917238321e-05,
      "loss": 2.0991,
      "step": 31
    },
    {
      "epoch": 0.010729253981559096,
      "grad_norm": 2.822526216506958,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.1003,
      "step": 32
    },
    {
      "epoch": 0.011064543168482816,
      "grad_norm": 2.231940269470215,
      "learning_rate": 9.871850323926177e-05,
      "loss": 2.2889,
      "step": 33
    },
    {
      "epoch": 0.011399832355406538,
      "grad_norm": 2.446948766708374,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.3449,
      "step": 34
    },
    {
      "epoch": 0.01173512154233026,
      "grad_norm": 2.6945621967315674,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.1744,
      "step": 35
    },
    {
      "epoch": 0.012070410729253982,
      "grad_norm": 2.202670097351074,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.4228,
      "step": 36
    },
    {
      "epoch": 0.012405699916177704,
      "grad_norm": 2.983804225921631,
      "learning_rate": 9.781523779815179e-05,
      "loss": 2.2251,
      "step": 37
    },
    {
      "epoch": 0.012740989103101424,
      "grad_norm": 3.077720880508423,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.274,
      "step": 38
    },
    {
      "epoch": 0.013076278290025146,
      "grad_norm": 1.9877910614013672,
      "learning_rate": 9.727592877996585e-05,
      "loss": 1.9802,
      "step": 39
    },
    {
      "epoch": 0.013411567476948869,
      "grad_norm": 2.4598207473754883,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.2072,
      "step": 40
    },
    {
      "epoch": 0.01374685666387259,
      "grad_norm": 2.6784284114837646,
      "learning_rate": 9.667902132486009e-05,
      "loss": 2.0905,
      "step": 41
    },
    {
      "epoch": 0.014082145850796313,
      "grad_norm": 2.057436943054199,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.9063,
      "step": 42
    },
    {
      "epoch": 0.014417435037720033,
      "grad_norm": 2.43062686920166,
      "learning_rate": 9.602524267262203e-05,
      "loss": 2.3002,
      "step": 43
    },
    {
      "epoch": 0.014752724224643755,
      "grad_norm": 2.5436949729919434,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.5027,
      "step": 44
    },
    {
      "epoch": 0.015088013411567477,
      "grad_norm": 2.3301496505737305,
      "learning_rate": 9.53153893518325e-05,
      "loss": 2.2546,
      "step": 45
    },
    {
      "epoch": 0.0154233025984912,
      "grad_norm": 2.0488905906677246,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.2543,
      "step": 46
    },
    {
      "epoch": 0.01575859178541492,
      "grad_norm": 1.8271653652191162,
      "learning_rate": 9.45503262094184e-05,
      "loss": 2.0725,
      "step": 47
    },
    {
      "epoch": 0.01609388097233864,
      "grad_norm": 1.8139671087265015,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.9978,
      "step": 48
    },
    {
      "epoch": 0.016429170159262364,
      "grad_norm": 3.030299186706543,
      "learning_rate": 9.373098535696979e-05,
      "loss": 2.083,
      "step": 49
    },
    {
      "epoch": 0.016764459346186086,
      "grad_norm": 2.121826410293579,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.1672,
      "step": 50
    },
    {
      "epoch": 0.016764459346186086,
      "eval_loss": 2.070281505584717,
      "eval_runtime": 415.3934,
      "eval_samples_per_second": 12.092,
      "eval_steps_per_second": 6.047,
      "step": 50
    },
    {
      "epoch": 0.017099748533109808,
      "grad_norm": 2.837768077850342,
      "learning_rate": 9.285836503510562e-05,
      "loss": 1.3665,
      "step": 51
    },
    {
      "epoch": 0.01743503772003353,
      "grad_norm": 2.6767208576202393,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.97,
      "step": 52
    },
    {
      "epoch": 0.017770326906957252,
      "grad_norm": 1.704293966293335,
      "learning_rate": 9.193352839727121e-05,
      "loss": 1.6777,
      "step": 53
    },
    {
      "epoch": 0.018105616093880974,
      "grad_norm": 1.6387865543365479,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.6942,
      "step": 54
    },
    {
      "epoch": 0.018440905280804692,
      "grad_norm": 1.7911442518234253,
      "learning_rate": 9.09576022144496e-05,
      "loss": 1.6699,
      "step": 55
    },
    {
      "epoch": 0.018776194467728415,
      "grad_norm": 1.837194800376892,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.002,
      "step": 56
    },
    {
      "epoch": 0.019111483654652137,
      "grad_norm": 2.0472233295440674,
      "learning_rate": 8.993177550236464e-05,
      "loss": 1.9996,
      "step": 57
    },
    {
      "epoch": 0.01944677284157586,
      "grad_norm": 1.6679171323776245,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.6527,
      "step": 58
    },
    {
      "epoch": 0.01978206202849958,
      "grad_norm": 1.514108419418335,
      "learning_rate": 8.885729807284856e-05,
      "loss": 1.6827,
      "step": 59
    },
    {
      "epoch": 0.020117351215423303,
      "grad_norm": 2.0194151401519775,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.168,
      "step": 60
    },
    {
      "epoch": 0.020452640402347025,
      "grad_norm": 1.5403530597686768,
      "learning_rate": 8.773547901113862e-05,
      "loss": 1.6586,
      "step": 61
    },
    {
      "epoch": 0.020787929589270747,
      "grad_norm": 1.7011923789978027,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.7703,
      "step": 62
    },
    {
      "epoch": 0.02112321877619447,
      "grad_norm": 1.5274035930633545,
      "learning_rate": 8.656768508095853e-05,
      "loss": 1.7972,
      "step": 63
    },
    {
      "epoch": 0.02145850796311819,
      "grad_norm": 1.4921406507492065,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.5572,
      "step": 64
    },
    {
      "epoch": 0.02179379715004191,
      "grad_norm": 1.6368732452392578,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.8478,
      "step": 65
    },
    {
      "epoch": 0.02212908633696563,
      "grad_norm": 2.0866599082946777,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.0398,
      "step": 66
    },
    {
      "epoch": 0.022464375523889354,
      "grad_norm": 1.8268249034881592,
      "learning_rate": 8.409991800312493e-05,
      "loss": 1.9158,
      "step": 67
    },
    {
      "epoch": 0.022799664710813076,
      "grad_norm": 1.592197060585022,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.8296,
      "step": 68
    },
    {
      "epoch": 0.023134953897736798,
      "grad_norm": 1.9506229162216187,
      "learning_rate": 8.280295144952536e-05,
      "loss": 2.001,
      "step": 69
    },
    {
      "epoch": 0.02347024308466052,
      "grad_norm": 1.7068800926208496,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.5299,
      "step": 70
    },
    {
      "epoch": 0.023805532271584242,
      "grad_norm": 1.5702540874481201,
      "learning_rate": 8.146601955249188e-05,
      "loss": 1.935,
      "step": 71
    },
    {
      "epoch": 0.024140821458507964,
      "grad_norm": 2.0129430294036865,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.0506,
      "step": 72
    },
    {
      "epoch": 0.024476110645431686,
      "grad_norm": 1.8408924341201782,
      "learning_rate": 8.009075115760243e-05,
      "loss": 2.2472,
      "step": 73
    },
    {
      "epoch": 0.024811399832355408,
      "grad_norm": 1.6532615423202515,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.7969,
      "step": 74
    },
    {
      "epoch": 0.025146689019279127,
      "grad_norm": 1.6880450248718262,
      "learning_rate": 7.86788218175523e-05,
      "loss": 1.9276,
      "step": 75
    },
    {
      "epoch": 0.02548197820620285,
      "grad_norm": 1.74911367893219,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.9406,
      "step": 76
    },
    {
      "epoch": 0.02581726739312657,
      "grad_norm": 1.6293855905532837,
      "learning_rate": 7.723195175075136e-05,
      "loss": 1.8643,
      "step": 77
    },
    {
      "epoch": 0.026152556580050293,
      "grad_norm": 1.846153974533081,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.9918,
      "step": 78
    },
    {
      "epoch": 0.026487845766974015,
      "grad_norm": 1.8405578136444092,
      "learning_rate": 7.575190374550272e-05,
      "loss": 2.0667,
      "step": 79
    },
    {
      "epoch": 0.026823134953897737,
      "grad_norm": 1.7012615203857422,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.2575,
      "step": 80
    },
    {
      "epoch": 0.02715842414082146,
      "grad_norm": 1.868895173072815,
      "learning_rate": 7.424048101231686e-05,
      "loss": 2.0323,
      "step": 81
    },
    {
      "epoch": 0.02749371332774518,
      "grad_norm": 1.862149953842163,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.1767,
      "step": 82
    },
    {
      "epoch": 0.027829002514668903,
      "grad_norm": 1.9703943729400635,
      "learning_rate": 7.269952498697734e-05,
      "loss": 2.0881,
      "step": 83
    },
    {
      "epoch": 0.028164291701592625,
      "grad_norm": 1.7949926853179932,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.2016,
      "step": 84
    },
    {
      "epoch": 0.028499580888516344,
      "grad_norm": 1.8068915605545044,
      "learning_rate": 7.113091308703498e-05,
      "loss": 2.2612,
      "step": 85
    },
    {
      "epoch": 0.028834870075440066,
      "grad_norm": 2.0017426013946533,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.0378,
      "step": 86
    },
    {
      "epoch": 0.029170159262363788,
      "grad_norm": 1.7997188568115234,
      "learning_rate": 6.953655642446368e-05,
      "loss": 1.8471,
      "step": 87
    },
    {
      "epoch": 0.02950544844928751,
      "grad_norm": 2.1644763946533203,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.0321,
      "step": 88
    },
    {
      "epoch": 0.029840737636211232,
      "grad_norm": 1.910346269607544,
      "learning_rate": 6.7918397477265e-05,
      "loss": 2.0989,
      "step": 89
    },
    {
      "epoch": 0.030176026823134954,
      "grad_norm": 1.8434735536575317,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.9885,
      "step": 90
    },
    {
      "epoch": 0.030511316010058676,
      "grad_norm": 2.194366216659546,
      "learning_rate": 6.627840772285784e-05,
      "loss": 2.1688,
      "step": 91
    },
    {
      "epoch": 0.0308466051969824,
      "grad_norm": 1.953049659729004,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.1352,
      "step": 92
    },
    {
      "epoch": 0.03118189438390612,
      "grad_norm": 2.183722734451294,
      "learning_rate": 6.461858523613684e-05,
      "loss": 2.3673,
      "step": 93
    },
    {
      "epoch": 0.03151718357082984,
      "grad_norm": 1.875823736190796,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.045,
      "step": 94
    },
    {
      "epoch": 0.03185247275775356,
      "grad_norm": 1.9691027402877808,
      "learning_rate": 6.294095225512603e-05,
      "loss": 2.3289,
      "step": 95
    },
    {
      "epoch": 0.03218776194467728,
      "grad_norm": 1.7443435192108154,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.033,
      "step": 96
    },
    {
      "epoch": 0.032523051131601005,
      "grad_norm": 1.6460736989974976,
      "learning_rate": 6.124755271719325e-05,
      "loss": 1.9156,
      "step": 97
    },
    {
      "epoch": 0.03285834031852473,
      "grad_norm": 1.6413999795913696,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.1261,
      "step": 98
    },
    {
      "epoch": 0.03319362950544845,
      "grad_norm": 1.6792007684707642,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 2.001,
      "step": 99
    },
    {
      "epoch": 0.03352891869237217,
      "grad_norm": 2.3478386402130127,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.215,
      "step": 100
    },
    {
      "epoch": 0.03352891869237217,
      "eval_loss": 1.971840500831604,
      "eval_runtime": 415.4443,
      "eval_samples_per_second": 12.091,
      "eval_steps_per_second": 6.047,
      "step": 100
    }
  ],
  "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": 1.508513578745856e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}