{
  "best_metric": 5.546361923217773,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.013568060784912316,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013568060784912317,
      "grad_norm": 15.762146949768066,
      "learning_rate": 5.000000000000001e-07,
      "loss": 17.5251,
      "step": 1
    },
    {
      "epoch": 0.00013568060784912317,
      "eval_loss": 17.97577667236328,
      "eval_runtime": 988.5204,
      "eval_samples_per_second": 12.557,
      "eval_steps_per_second": 3.14,
      "step": 1
    },
    {
      "epoch": 0.00027136121569824634,
      "grad_norm": 15.15388298034668,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 17.0609,
      "step": 2
    },
    {
      "epoch": 0.0004070418235473695,
      "grad_norm": 17.901601791381836,
      "learning_rate": 1.5e-06,
      "loss": 18.277,
      "step": 3
    },
    {
      "epoch": 0.0005427224313964927,
      "grad_norm": 16.00199317932129,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 18.4372,
      "step": 4
    },
    {
      "epoch": 0.0006784030392456158,
      "grad_norm": 16.555130004882812,
      "learning_rate": 2.5e-06,
      "loss": 17.4032,
      "step": 5
    },
    {
      "epoch": 0.000814083647094739,
      "grad_norm": 16.318920135498047,
      "learning_rate": 3e-06,
      "loss": 17.5668,
      "step": 6
    },
    {
      "epoch": 0.0009497642549438621,
      "grad_norm": 17.335289001464844,
      "learning_rate": 3.5e-06,
      "loss": 18.4793,
      "step": 7
    },
    {
      "epoch": 0.0010854448627929854,
      "grad_norm": 17.1308536529541,
      "learning_rate": 4.000000000000001e-06,
      "loss": 18.0238,
      "step": 8
    },
    {
      "epoch": 0.0012211254706421084,
      "grad_norm": 16.88369369506836,
      "learning_rate": 4.5e-06,
      "loss": 18.038,
      "step": 9
    },
    {
      "epoch": 0.0013568060784912316,
      "grad_norm": 18.023923873901367,
      "learning_rate": 5e-06,
      "loss": 17.9376,
      "step": 10
    },
    {
      "epoch": 0.001492486686340355,
      "grad_norm": 16.119089126586914,
      "learning_rate": 4.99847706754774e-06,
      "loss": 17.228,
      "step": 11
    },
    {
      "epoch": 0.001628167294189478,
      "grad_norm": 19.076875686645508,
      "learning_rate": 4.993910125649561e-06,
      "loss": 18.2888,
      "step": 12
    },
    {
      "epoch": 0.0017638479020386012,
      "grad_norm": 17.7404727935791,
      "learning_rate": 4.986304738420684e-06,
      "loss": 17.6689,
      "step": 13
    },
    {
      "epoch": 0.0018995285098877242,
      "grad_norm": 19.57935905456543,
      "learning_rate": 4.975670171853926e-06,
      "loss": 18.0748,
      "step": 14
    },
    {
      "epoch": 0.0020352091177368472,
      "grad_norm": 19.126384735107422,
      "learning_rate": 4.962019382530521e-06,
      "loss": 17.7308,
      "step": 15
    },
    {
      "epoch": 0.0021708897255859707,
      "grad_norm": 19.213788986206055,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 17.6152,
      "step": 16
    },
    {
      "epoch": 0.0023065703334350937,
      "grad_norm": 19.342151641845703,
      "learning_rate": 4.925739315689991e-06,
      "loss": 17.7039,
      "step": 17
    },
    {
      "epoch": 0.0024422509412842168,
      "grad_norm": 17.80344581604004,
      "learning_rate": 4.903154239845798e-06,
      "loss": 15.9165,
      "step": 18
    },
    {
      "epoch": 0.0025779315491333402,
      "grad_norm": 20.63853645324707,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 17.62,
      "step": 19
    },
    {
      "epoch": 0.0027136121569824633,
      "grad_norm": 22.237533569335938,
      "learning_rate": 4.849231551964771e-06,
      "loss": 17.8717,
      "step": 20
    },
    {
      "epoch": 0.0028492927648315863,
      "grad_norm": 21.161718368530273,
      "learning_rate": 4.817959636416969e-06,
      "loss": 16.7998,
      "step": 21
    },
    {
      "epoch": 0.00298497337268071,
      "grad_norm": 22.185317993164062,
      "learning_rate": 4.783863644106502e-06,
      "loss": 17.1446,
      "step": 22
    },
    {
      "epoch": 0.003120653980529833,
      "grad_norm": 23.86289405822754,
      "learning_rate": 4.746985115747918e-06,
      "loss": 16.7542,
      "step": 23
    },
    {
      "epoch": 0.003256334588378956,
      "grad_norm": 21.632293701171875,
      "learning_rate": 4.707368982147318e-06,
      "loss": 16.4251,
      "step": 24
    },
    {
      "epoch": 0.003392015196228079,
      "grad_norm": 21.998170852661133,
      "learning_rate": 4.665063509461098e-06,
      "loss": 15.8686,
      "step": 25
    },
    {
      "epoch": 0.0035276958040772024,
      "grad_norm": 22.968353271484375,
      "learning_rate": 4.620120240391065e-06,
      "loss": 15.1071,
      "step": 26
    },
    {
      "epoch": 0.0036633764119263254,
      "grad_norm": 27.793222427368164,
      "learning_rate": 4.572593931387604e-06,
      "loss": 16.0389,
      "step": 27
    },
    {
      "epoch": 0.0037990570197754484,
      "grad_norm": 25.256834030151367,
      "learning_rate": 4.522542485937369e-06,
      "loss": 14.966,
      "step": 28
    },
    {
      "epoch": 0.003934737627624572,
      "grad_norm": 27.452804565429688,
      "learning_rate": 4.470026884016805e-06,
      "loss": 15.3857,
      "step": 29
    },
    {
      "epoch": 0.0040704182354736945,
      "grad_norm": 28.503049850463867,
      "learning_rate": 4.415111107797445e-06,
      "loss": 14.2744,
      "step": 30
    },
    {
      "epoch": 0.004206098843322818,
      "grad_norm": 26.86528205871582,
      "learning_rate": 4.357862063693486e-06,
      "loss": 14.3296,
      "step": 31
    },
    {
      "epoch": 0.004341779451171941,
      "grad_norm": 28.72145652770996,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 14.8378,
      "step": 32
    },
    {
      "epoch": 0.004477460059021064,
      "grad_norm": 28.283493041992188,
      "learning_rate": 4.236645926147493e-06,
      "loss": 14.1692,
      "step": 33
    },
    {
      "epoch": 0.0046131406668701875,
      "grad_norm": 30.041580200195312,
      "learning_rate": 4.172826515897146e-06,
      "loss": 13.4264,
      "step": 34
    },
    {
      "epoch": 0.004748821274719311,
      "grad_norm": 33.323081970214844,
      "learning_rate": 4.106969024216348e-06,
      "loss": 13.2793,
      "step": 35
    },
    {
      "epoch": 0.0048845018825684336,
      "grad_norm": 25.383710861206055,
      "learning_rate": 4.039153688314146e-06,
      "loss": 13.0025,
      "step": 36
    },
    {
      "epoch": 0.005020182490417557,
      "grad_norm": 34.86724090576172,
      "learning_rate": 3.969463130731183e-06,
      "loss": 12.8519,
      "step": 37
    },
    {
      "epoch": 0.0051558630982666805,
      "grad_norm": 28.57182502746582,
      "learning_rate": 3.897982258676867e-06,
      "loss": 12.3253,
      "step": 38
    },
    {
      "epoch": 0.005291543706115803,
      "grad_norm": 27.965444564819336,
      "learning_rate": 3.824798160583012e-06,
      "loss": 11.9458,
      "step": 39
    },
    {
      "epoch": 0.0054272243139649266,
      "grad_norm": 30.288328170776367,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 11.5927,
      "step": 40
    },
    {
      "epoch": 0.00556290492181405,
      "grad_norm": 29.882335662841797,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 11.8575,
      "step": 41
    },
    {
      "epoch": 0.005698585529663173,
      "grad_norm": 27.096267700195312,
      "learning_rate": 3.595927866972694e-06,
      "loss": 11.5122,
      "step": 42
    },
    {
      "epoch": 0.005834266137512296,
      "grad_norm": 27.859052658081055,
      "learning_rate": 3.516841607689501e-06,
      "loss": 11.2235,
      "step": 43
    },
    {
      "epoch": 0.00596994674536142,
      "grad_norm": 27.79047203063965,
      "learning_rate": 3.436516483539781e-06,
      "loss": 10.7358,
      "step": 44
    },
    {
      "epoch": 0.006105627353210542,
      "grad_norm": 27.116655349731445,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 10.6031,
      "step": 45
    },
    {
      "epoch": 0.006241307961059666,
      "grad_norm": 29.671985626220703,
      "learning_rate": 3.272542485937369e-06,
      "loss": 10.5947,
      "step": 46
    },
    {
      "epoch": 0.006376988568908789,
      "grad_norm": 24.509077072143555,
      "learning_rate": 3.189093389542498e-06,
      "loss": 10.671,
      "step": 47
    },
    {
      "epoch": 0.006512669176757912,
      "grad_norm": 30.852890014648438,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 10.7918,
      "step": 48
    },
    {
      "epoch": 0.006648349784607035,
      "grad_norm": 29.77279281616211,
      "learning_rate": 3.019779227044398e-06,
      "loss": 11.0377,
      "step": 49
    },
    {
      "epoch": 0.006784030392456158,
      "grad_norm": 32.51844787597656,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 11.3717,
      "step": 50
    },
    {
      "epoch": 0.006784030392456158,
      "eval_loss": 9.308085441589355,
      "eval_runtime": 992.1874,
      "eval_samples_per_second": 12.511,
      "eval_steps_per_second": 3.128,
      "step": 50
    },
    {
      "epoch": 0.006919711000305281,
      "grad_norm": 26.32299041748047,
      "learning_rate": 2.847932752400164e-06,
      "loss": 8.778,
      "step": 51
    },
    {
      "epoch": 0.007055391608154405,
      "grad_norm": 27.48458480834961,
      "learning_rate": 2.761321158169134e-06,
      "loss": 8.6638,
      "step": 52
    },
    {
      "epoch": 0.007191072216003527,
      "grad_norm": 28.693199157714844,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 8.4307,
      "step": 53
    },
    {
      "epoch": 0.007326752823852651,
      "grad_norm": 25.406177520751953,
      "learning_rate": 2.587248741756253e-06,
      "loss": 8.0378,
      "step": 54
    },
    {
      "epoch": 0.007462433431701774,
      "grad_norm": 28.44993019104004,
      "learning_rate": 2.5e-06,
      "loss": 8.276,
      "step": 55
    },
    {
      "epoch": 0.007598114039550897,
      "grad_norm": 24.69778823852539,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 8.2592,
      "step": 56
    },
    {
      "epoch": 0.00773379464740002,
      "grad_norm": 25.933664321899414,
      "learning_rate": 2.325608815639687e-06,
      "loss": 8.3317,
      "step": 57
    },
    {
      "epoch": 0.007869475255249144,
      "grad_norm": 27.458454132080078,
      "learning_rate": 2.238678841830867e-06,
      "loss": 7.7944,
      "step": 58
    },
    {
      "epoch": 0.008005155863098266,
      "grad_norm": 25.28622817993164,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 7.7405,
      "step": 59
    },
    {
      "epoch": 0.008140836470947389,
      "grad_norm": 29.014318466186523,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 7.3388,
      "step": 60
    },
    {
      "epoch": 0.008276517078796513,
      "grad_norm": 27.211328506469727,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 7.5491,
      "step": 61
    },
    {
      "epoch": 0.008412197686645636,
      "grad_norm": 28.228635787963867,
      "learning_rate": 1.895195261000831e-06,
      "loss": 6.9176,
      "step": 62
    },
    {
      "epoch": 0.008547878294494759,
      "grad_norm": 28.854480743408203,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 6.9789,
      "step": 63
    },
    {
      "epoch": 0.008683558902343883,
      "grad_norm": 30.74064064025879,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 6.791,
      "step": 64
    },
    {
      "epoch": 0.008819239510193005,
      "grad_norm": 30.067106246948242,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 7.27,
      "step": 65
    },
    {
      "epoch": 0.008954920118042128,
      "grad_norm": 28.86882209777832,
      "learning_rate": 1.56348351646022e-06,
      "loss": 6.8992,
      "step": 66
    },
    {
      "epoch": 0.009090600725891252,
      "grad_norm": 29.37924575805664,
      "learning_rate": 1.4831583923105e-06,
      "loss": 7.1342,
      "step": 67
    },
    {
      "epoch": 0.009226281333740375,
      "grad_norm": 28.117305755615234,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 6.8556,
      "step": 68
    },
    {
      "epoch": 0.009361961941589498,
      "grad_norm": 31.97182846069336,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 7.6376,
      "step": 69
    },
    {
      "epoch": 0.009497642549438622,
      "grad_norm": 30.822277069091797,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 7.0273,
      "step": 70
    },
    {
      "epoch": 0.009633323157287745,
      "grad_norm": 36.39443588256836,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 6.5916,
      "step": 71
    },
    {
      "epoch": 0.009769003765136867,
      "grad_norm": 31.061527252197266,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 6.3773,
      "step": 72
    },
    {
      "epoch": 0.009904684372985991,
      "grad_norm": 36.107337951660156,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 5.9991,
      "step": 73
    },
    {
      "epoch": 0.010040364980835114,
      "grad_norm": 33.352020263671875,
      "learning_rate": 9.608463116858544e-07,
      "loss": 6.0698,
      "step": 74
    },
    {
      "epoch": 0.010176045588684237,
      "grad_norm": 30.981962203979492,
      "learning_rate": 8.930309757836517e-07,
      "loss": 6.5031,
      "step": 75
    },
    {
      "epoch": 0.010311726196533361,
      "grad_norm": 31.83991050720215,
      "learning_rate": 8.271734841028553e-07,
      "loss": 6.594,
      "step": 76
    },
    {
      "epoch": 0.010447406804382484,
      "grad_norm": 33.01601791381836,
      "learning_rate": 7.633540738525066e-07,
      "loss": 6.1583,
      "step": 77
    },
    {
      "epoch": 0.010583087412231606,
      "grad_norm": 34.49018859863281,
      "learning_rate": 7.016504991533727e-07,
      "loss": 6.3534,
      "step": 78
    },
    {
      "epoch": 0.01071876802008073,
      "grad_norm": 35.218048095703125,
      "learning_rate": 6.421379363065142e-07,
      "loss": 5.9496,
      "step": 79
    },
    {
      "epoch": 0.010854448627929853,
      "grad_norm": 34.13999557495117,
      "learning_rate": 5.848888922025553e-07,
      "loss": 5.9489,
      "step": 80
    },
    {
      "epoch": 0.010990129235778976,
      "grad_norm": 33.84051513671875,
      "learning_rate": 5.299731159831953e-07,
      "loss": 5.8639,
      "step": 81
    },
    {
      "epoch": 0.0111258098436281,
      "grad_norm": 36.259944915771484,
      "learning_rate": 4.774575140626317e-07,
      "loss": 6.283,
      "step": 82
    },
    {
      "epoch": 0.011261490451477223,
      "grad_norm": 32.591651916503906,
      "learning_rate": 4.27406068612396e-07,
      "loss": 6.2367,
      "step": 83
    },
    {
      "epoch": 0.011397171059326345,
      "grad_norm": 35.87070083618164,
      "learning_rate": 3.798797596089351e-07,
      "loss": 6.3597,
      "step": 84
    },
    {
      "epoch": 0.01153285166717547,
      "grad_norm": 35.934539794921875,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 5.7746,
      "step": 85
    },
    {
      "epoch": 0.011668532275024592,
      "grad_norm": 35.99143981933594,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 6.9046,
      "step": 86
    },
    {
      "epoch": 0.011804212882873715,
      "grad_norm": 32.2277946472168,
      "learning_rate": 2.53014884252083e-07,
      "loss": 6.1874,
      "step": 87
    },
    {
      "epoch": 0.01193989349072284,
      "grad_norm": 38.41813659667969,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 6.0549,
      "step": 88
    },
    {
      "epoch": 0.012075574098571962,
      "grad_norm": 35.493804931640625,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 6.046,
      "step": 89
    },
    {
      "epoch": 0.012211254706421084,
      "grad_norm": 34.95344543457031,
      "learning_rate": 1.507684480352292e-07,
      "loss": 5.976,
      "step": 90
    },
    {
      "epoch": 0.012346935314270209,
      "grad_norm": 32.631591796875,
      "learning_rate": 1.223587092621162e-07,
      "loss": 5.7902,
      "step": 91
    },
    {
      "epoch": 0.012482615922119331,
      "grad_norm": 35.305580139160156,
      "learning_rate": 9.684576015420277e-08,
      "loss": 6.4926,
      "step": 92
    },
    {
      "epoch": 0.012618296529968454,
      "grad_norm": 35.67231369018555,
      "learning_rate": 7.426068431000883e-08,
      "loss": 5.8871,
      "step": 93
    },
    {
      "epoch": 0.012753977137817578,
      "grad_norm": 38.47718811035156,
      "learning_rate": 5.463099816548578e-08,
      "loss": 5.4537,
      "step": 94
    },
    {
      "epoch": 0.0128896577456667,
      "grad_norm": 39.857582092285156,
      "learning_rate": 3.798061746947995e-08,
      "loss": 5.6496,
      "step": 95
    },
    {
      "epoch": 0.013025338353515823,
      "grad_norm": 35.418609619140625,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 6.1474,
      "step": 96
    },
    {
      "epoch": 0.013161018961364948,
      "grad_norm": 32.19925308227539,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 6.7492,
      "step": 97
    },
    {
      "epoch": 0.01329669956921407,
      "grad_norm": 39.599151611328125,
      "learning_rate": 6.089874350439507e-09,
      "loss": 5.7039,
      "step": 98
    },
    {
      "epoch": 0.013432380177063193,
      "grad_norm": 38.118282318115234,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 5.5559,
      "step": 99
    },
    {
      "epoch": 0.013568060784912316,
      "grad_norm": 35.434478759765625,
      "learning_rate": 0.0,
      "loss": 8.8397,
      "step": 100
    },
    {
      "epoch": 0.013568060784912316,
      "eval_loss": 5.546361923217773,
      "eval_runtime": 993.065,
      "eval_samples_per_second": 12.5,
      "eval_steps_per_second": 3.126,
      "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": 1.483800336924672e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}