{
  "best_metric": 2.786036252975464,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.03195270998921596,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003195270998921596,
      "grad_norm": 0.4542631208896637,
      "learning_rate": 5.000000000000001e-07,
      "loss": 15.1568,
      "step": 1
    },
    {
      "epoch": 0.0003195270998921596,
      "eval_loss": 2.822023630142212,
      "eval_runtime": 886.3385,
      "eval_samples_per_second": 5.947,
      "eval_steps_per_second": 1.487,
      "step": 1
    },
    {
      "epoch": 0.0006390541997843192,
      "grad_norm": 0.4103067219257355,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 15.4511,
      "step": 2
    },
    {
      "epoch": 0.0009585812996764789,
      "grad_norm": 0.44541919231414795,
      "learning_rate": 1.5e-06,
      "loss": 12.3824,
      "step": 3
    },
    {
      "epoch": 0.0012781083995686384,
      "grad_norm": 0.6393632292747498,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 15.0988,
      "step": 4
    },
    {
      "epoch": 0.001597635499460798,
      "grad_norm": 0.6381840109825134,
      "learning_rate": 2.5e-06,
      "loss": 15.25,
      "step": 5
    },
    {
      "epoch": 0.0019171625993529577,
      "grad_norm": 0.7214181423187256,
      "learning_rate": 3e-06,
      "loss": 16.3453,
      "step": 6
    },
    {
      "epoch": 0.002236689699245117,
      "grad_norm": 0.8121290802955627,
      "learning_rate": 3.5e-06,
      "loss": 17.3123,
      "step": 7
    },
    {
      "epoch": 0.002556216799137277,
      "grad_norm": 0.7688579559326172,
      "learning_rate": 4.000000000000001e-06,
      "loss": 17.9848,
      "step": 8
    },
    {
      "epoch": 0.0028757438990294364,
      "grad_norm": 0.8018252849578857,
      "learning_rate": 4.5e-06,
      "loss": 16.204,
      "step": 9
    },
    {
      "epoch": 0.003195270998921596,
      "grad_norm": 0.8581808805465698,
      "learning_rate": 5e-06,
      "loss": 17.314,
      "step": 10
    },
    {
      "epoch": 0.0035147980988137558,
      "grad_norm": 0.8556950092315674,
      "learning_rate": 4.99847706754774e-06,
      "loss": 16.6607,
      "step": 11
    },
    {
      "epoch": 0.0038343251987059154,
      "grad_norm": 1.0415091514587402,
      "learning_rate": 4.993910125649561e-06,
      "loss": 17.439,
      "step": 12
    },
    {
      "epoch": 0.004153852298598075,
      "grad_norm": 0.9096566438674927,
      "learning_rate": 4.986304738420684e-06,
      "loss": 17.4097,
      "step": 13
    },
    {
      "epoch": 0.004473379398490234,
      "grad_norm": 1.0269314050674438,
      "learning_rate": 4.975670171853926e-06,
      "loss": 17.4317,
      "step": 14
    },
    {
      "epoch": 0.004792906498382394,
      "grad_norm": 1.1478707790374756,
      "learning_rate": 4.962019382530521e-06,
      "loss": 18.5223,
      "step": 15
    },
    {
      "epoch": 0.005112433598274554,
      "grad_norm": 1.636509895324707,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 18.0751,
      "step": 16
    },
    {
      "epoch": 0.005431960698166713,
      "grad_norm": 1.154109001159668,
      "learning_rate": 4.925739315689991e-06,
      "loss": 17.521,
      "step": 17
    },
    {
      "epoch": 0.005751487798058873,
      "grad_norm": 1.0234571695327759,
      "learning_rate": 4.903154239845798e-06,
      "loss": 18.8366,
      "step": 18
    },
    {
      "epoch": 0.0060710148979510326,
      "grad_norm": 1.3324098587036133,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 19.0732,
      "step": 19
    },
    {
      "epoch": 0.006390541997843192,
      "grad_norm": 1.424180030822754,
      "learning_rate": 4.849231551964771e-06,
      "loss": 19.0163,
      "step": 20
    },
    {
      "epoch": 0.006710069097735352,
      "grad_norm": 1.2417484521865845,
      "learning_rate": 4.817959636416969e-06,
      "loss": 19.9384,
      "step": 21
    },
    {
      "epoch": 0.0070295961976275115,
      "grad_norm": 1.5843204259872437,
      "learning_rate": 4.783863644106502e-06,
      "loss": 18.4232,
      "step": 22
    },
    {
      "epoch": 0.007349123297519671,
      "grad_norm": 1.378356695175171,
      "learning_rate": 4.746985115747918e-06,
      "loss": 19.6798,
      "step": 23
    },
    {
      "epoch": 0.007668650397411831,
      "grad_norm": 1.4657114744186401,
      "learning_rate": 4.707368982147318e-06,
      "loss": 19.7077,
      "step": 24
    },
    {
      "epoch": 0.00798817749730399,
      "grad_norm": 1.4137859344482422,
      "learning_rate": 4.665063509461098e-06,
      "loss": 19.1794,
      "step": 25
    },
    {
      "epoch": 0.00830770459719615,
      "grad_norm": 1.708204746246338,
      "learning_rate": 4.620120240391065e-06,
      "loss": 20.172,
      "step": 26
    },
    {
      "epoch": 0.00862723169708831,
      "grad_norm": 1.3741956949234009,
      "learning_rate": 4.572593931387604e-06,
      "loss": 19.5121,
      "step": 27
    },
    {
      "epoch": 0.008946758796980469,
      "grad_norm": 1.672687292098999,
      "learning_rate": 4.522542485937369e-06,
      "loss": 19.3691,
      "step": 28
    },
    {
      "epoch": 0.009266285896872629,
      "grad_norm": 1.9943945407867432,
      "learning_rate": 4.470026884016805e-06,
      "loss": 17.0405,
      "step": 29
    },
    {
      "epoch": 0.009585812996764788,
      "grad_norm": 2.3718981742858887,
      "learning_rate": 4.415111107797445e-06,
      "loss": 17.6282,
      "step": 30
    },
    {
      "epoch": 0.009905340096656948,
      "grad_norm": 2.2666637897491455,
      "learning_rate": 4.357862063693486e-06,
      "loss": 17.6547,
      "step": 31
    },
    {
      "epoch": 0.010224867196549107,
      "grad_norm": 2.4329729080200195,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 18.943,
      "step": 32
    },
    {
      "epoch": 0.010544394296441268,
      "grad_norm": 2.7743804454803467,
      "learning_rate": 4.236645926147493e-06,
      "loss": 19.7421,
      "step": 33
    },
    {
      "epoch": 0.010863921396333426,
      "grad_norm": 2.731886148452759,
      "learning_rate": 4.172826515897146e-06,
      "loss": 24.2004,
      "step": 34
    },
    {
      "epoch": 0.011183448496225585,
      "grad_norm": 2.7625598907470703,
      "learning_rate": 4.106969024216348e-06,
      "loss": 26.9592,
      "step": 35
    },
    {
      "epoch": 0.011502975596117746,
      "grad_norm": 3.5860679149627686,
      "learning_rate": 4.039153688314146e-06,
      "loss": 28.8936,
      "step": 36
    },
    {
      "epoch": 0.011822502696009905,
      "grad_norm": 2.9752390384674072,
      "learning_rate": 3.969463130731183e-06,
      "loss": 28.598,
      "step": 37
    },
    {
      "epoch": 0.012142029795902065,
      "grad_norm": 3.910142183303833,
      "learning_rate": 3.897982258676867e-06,
      "loss": 29.005,
      "step": 38
    },
    {
      "epoch": 0.012461556895794224,
      "grad_norm": 3.509363889694214,
      "learning_rate": 3.824798160583012e-06,
      "loss": 29.2251,
      "step": 39
    },
    {
      "epoch": 0.012781083995686384,
      "grad_norm": 4.890401840209961,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 29.8219,
      "step": 40
    },
    {
      "epoch": 0.013100611095578543,
      "grad_norm": 4.316377639770508,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 29.8349,
      "step": 41
    },
    {
      "epoch": 0.013420138195470704,
      "grad_norm": 5.008350372314453,
      "learning_rate": 3.595927866972694e-06,
      "loss": 31.3168,
      "step": 42
    },
    {
      "epoch": 0.013739665295362863,
      "grad_norm": 4.941371440887451,
      "learning_rate": 3.516841607689501e-06,
      "loss": 31.449,
      "step": 43
    },
    {
      "epoch": 0.014059192395255023,
      "grad_norm": 6.248507022857666,
      "learning_rate": 3.436516483539781e-06,
      "loss": 32.5496,
      "step": 44
    },
    {
      "epoch": 0.014378719495147182,
      "grad_norm": 5.927119255065918,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 33.2277,
      "step": 45
    },
    {
      "epoch": 0.014698246595039342,
      "grad_norm": 6.774079322814941,
      "learning_rate": 3.272542485937369e-06,
      "loss": 33.6978,
      "step": 46
    },
    {
      "epoch": 0.015017773694931501,
      "grad_norm": 7.833065986633301,
      "learning_rate": 3.189093389542498e-06,
      "loss": 34.0778,
      "step": 47
    },
    {
      "epoch": 0.015337300794823662,
      "grad_norm": 8.638693809509277,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 35.4129,
      "step": 48
    },
    {
      "epoch": 0.01565682789471582,
      "grad_norm": 10.667224884033203,
      "learning_rate": 3.019779227044398e-06,
      "loss": 38.1759,
      "step": 49
    },
    {
      "epoch": 0.01597635499460798,
      "grad_norm": 14.18898868560791,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 42.3519,
      "step": 50
    },
    {
      "epoch": 0.01597635499460798,
      "eval_loss": 2.800990581512451,
      "eval_runtime": 885.3579,
      "eval_samples_per_second": 5.954,
      "eval_steps_per_second": 1.489,
      "step": 50
    },
    {
      "epoch": 0.01629588209450014,
      "grad_norm": 0.4598936140537262,
      "learning_rate": 2.847932752400164e-06,
      "loss": 14.898,
      "step": 51
    },
    {
      "epoch": 0.0166154091943923,
      "grad_norm": 0.5623840689659119,
      "learning_rate": 2.761321158169134e-06,
      "loss": 14.9036,
      "step": 52
    },
    {
      "epoch": 0.01693493629428446,
      "grad_norm": 0.5559747815132141,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 13.1005,
      "step": 53
    },
    {
      "epoch": 0.01725446339417662,
      "grad_norm": 0.7431466579437256,
      "learning_rate": 2.587248741756253e-06,
      "loss": 16.5878,
      "step": 54
    },
    {
      "epoch": 0.017573990494068777,
      "grad_norm": 0.8783532977104187,
      "learning_rate": 2.5e-06,
      "loss": 17.6206,
      "step": 55
    },
    {
      "epoch": 0.017893517593960937,
      "grad_norm": 0.8926708698272705,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 16.7598,
      "step": 56
    },
    {
      "epoch": 0.018213044693853098,
      "grad_norm": 0.993622899055481,
      "learning_rate": 2.325608815639687e-06,
      "loss": 18.1749,
      "step": 57
    },
    {
      "epoch": 0.018532571793745258,
      "grad_norm": 1.064647912979126,
      "learning_rate": 2.238678841830867e-06,
      "loss": 16.2944,
      "step": 58
    },
    {
      "epoch": 0.018852098893637415,
      "grad_norm": 1.0806492567062378,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 15.8283,
      "step": 59
    },
    {
      "epoch": 0.019171625993529576,
      "grad_norm": 1.020936369895935,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 17.8089,
      "step": 60
    },
    {
      "epoch": 0.019491153093421736,
      "grad_norm": 1.0202960968017578,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 16.9171,
      "step": 61
    },
    {
      "epoch": 0.019810680193313897,
      "grad_norm": 1.1508572101593018,
      "learning_rate": 1.895195261000831e-06,
      "loss": 17.2636,
      "step": 62
    },
    {
      "epoch": 0.020130207293206054,
      "grad_norm": 1.0971193313598633,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 17.0854,
      "step": 63
    },
    {
      "epoch": 0.020449734393098214,
      "grad_norm": 1.3636854887008667,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 17.5989,
      "step": 64
    },
    {
      "epoch": 0.020769261492990375,
      "grad_norm": 1.2558183670043945,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 17.343,
      "step": 65
    },
    {
      "epoch": 0.021088788592882535,
      "grad_norm": 1.7393505573272705,
      "learning_rate": 1.56348351646022e-06,
      "loss": 18.1173,
      "step": 66
    },
    {
      "epoch": 0.021408315692774692,
      "grad_norm": 1.3264778852462769,
      "learning_rate": 1.4831583923105e-06,
      "loss": 17.7952,
      "step": 67
    },
    {
      "epoch": 0.021727842792666853,
      "grad_norm": 1.246366024017334,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 18.808,
      "step": 68
    },
    {
      "epoch": 0.022047369892559013,
      "grad_norm": 1.3943363428115845,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 19.9147,
      "step": 69
    },
    {
      "epoch": 0.02236689699245117,
      "grad_norm": 1.5551766157150269,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 18.7218,
      "step": 70
    },
    {
      "epoch": 0.02268642409234333,
      "grad_norm": 1.5984143018722534,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 19.9538,
      "step": 71
    },
    {
      "epoch": 0.02300595119223549,
      "grad_norm": 1.7078524827957153,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 19.0477,
      "step": 72
    },
    {
      "epoch": 0.023325478292127652,
      "grad_norm": 1.86801278591156,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 19.7327,
      "step": 73
    },
    {
      "epoch": 0.02364500539201981,
      "grad_norm": 1.7517181634902954,
      "learning_rate": 9.608463116858544e-07,
      "loss": 19.406,
      "step": 74
    },
    {
      "epoch": 0.02396453249191197,
      "grad_norm": 1.7723991870880127,
      "learning_rate": 8.930309757836517e-07,
      "loss": 19.6767,
      "step": 75
    },
    {
      "epoch": 0.02428405959180413,
      "grad_norm": 1.7405762672424316,
      "learning_rate": 8.271734841028553e-07,
      "loss": 18.9852,
      "step": 76
    },
    {
      "epoch": 0.02460358669169629,
      "grad_norm": 2.2709810733795166,
      "learning_rate": 7.633540738525066e-07,
      "loss": 16.1077,
      "step": 77
    },
    {
      "epoch": 0.024923113791588448,
      "grad_norm": 2.5845401287078857,
      "learning_rate": 7.016504991533727e-07,
      "loss": 16.7456,
      "step": 78
    },
    {
      "epoch": 0.02524264089148061,
      "grad_norm": 2.6944775581359863,
      "learning_rate": 6.421379363065142e-07,
      "loss": 17.1069,
      "step": 79
    },
    {
      "epoch": 0.02556216799137277,
      "grad_norm": 2.878634214401245,
      "learning_rate": 5.848888922025553e-07,
      "loss": 18.3942,
      "step": 80
    },
    {
      "epoch": 0.02588169509126493,
      "grad_norm": 3.0304110050201416,
      "learning_rate": 5.299731159831953e-07,
      "loss": 17.8819,
      "step": 81
    },
    {
      "epoch": 0.026201222191157086,
      "grad_norm": 3.3057451248168945,
      "learning_rate": 4.774575140626317e-07,
      "loss": 18.5736,
      "step": 82
    },
    {
      "epoch": 0.026520749291049247,
      "grad_norm": 3.3953466415405273,
      "learning_rate": 4.27406068612396e-07,
      "loss": 23.0032,
      "step": 83
    },
    {
      "epoch": 0.026840276390941407,
      "grad_norm": 4.374539375305176,
      "learning_rate": 3.798797596089351e-07,
      "loss": 25.4286,
      "step": 84
    },
    {
      "epoch": 0.027159803490833568,
      "grad_norm": 3.490527391433716,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 26.9727,
      "step": 85
    },
    {
      "epoch": 0.027479330590725725,
      "grad_norm": 4.934103488922119,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 28.1652,
      "step": 86
    },
    {
      "epoch": 0.027798857690617886,
      "grad_norm": 4.795266151428223,
      "learning_rate": 2.53014884252083e-07,
      "loss": 30.8333,
      "step": 87
    },
    {
      "epoch": 0.028118384790510046,
      "grad_norm": 4.224905490875244,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 27.3162,
      "step": 88
    },
    {
      "epoch": 0.028437911890402203,
      "grad_norm": 4.559455394744873,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 29.1512,
      "step": 89
    },
    {
      "epoch": 0.028757438990294364,
      "grad_norm": 4.907705307006836,
      "learning_rate": 1.507684480352292e-07,
      "loss": 29.6763,
      "step": 90
    },
    {
      "epoch": 0.029076966090186524,
      "grad_norm": 5.672667026519775,
      "learning_rate": 1.223587092621162e-07,
      "loss": 30.8263,
      "step": 91
    },
    {
      "epoch": 0.029396493190078685,
      "grad_norm": 8.072755813598633,
      "learning_rate": 9.684576015420277e-08,
      "loss": 30.6112,
      "step": 92
    },
    {
      "epoch": 0.02971602028997084,
      "grad_norm": 6.152291774749756,
      "learning_rate": 7.426068431000883e-08,
      "loss": 31.3257,
      "step": 93
    },
    {
      "epoch": 0.030035547389863002,
      "grad_norm": 7.361919403076172,
      "learning_rate": 5.463099816548578e-08,
      "loss": 31.6235,
      "step": 94
    },
    {
      "epoch": 0.030355074489755163,
      "grad_norm": 6.712725639343262,
      "learning_rate": 3.798061746947995e-08,
      "loss": 33.694,
      "step": 95
    },
    {
      "epoch": 0.030674601589647323,
      "grad_norm": 8.276151657104492,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 34.3615,
      "step": 96
    },
    {
      "epoch": 0.03099412868953948,
      "grad_norm": 7.104736804962158,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 34.9578,
      "step": 97
    },
    {
      "epoch": 0.03131365578943164,
      "grad_norm": 9.987726211547852,
      "learning_rate": 6.089874350439507e-09,
      "loss": 34.2474,
      "step": 98
    },
    {
      "epoch": 0.0316331828893238,
      "grad_norm": 10.876480102539062,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 38.6954,
      "step": 99
    },
    {
      "epoch": 0.03195270998921596,
      "grad_norm": 15.421370506286621,
      "learning_rate": 0.0,
      "loss": 41.5902,
      "step": 100
    },
    {
      "epoch": 0.03195270998921596,
      "eval_loss": 2.786036252975464,
      "eval_runtime": 886.1971,
      "eval_samples_per_second": 5.948,
      "eval_steps_per_second": 1.487,
      "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": 2.6533929242591232e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}