{
  "best_metric": 0.15805459022521973,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.0835421888053467,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000835421888053467,
      "grad_norm": 7.261774063110352,
      "learning_rate": 1e-06,
      "loss": 1.5114,
      "step": 1
    },
    {
      "epoch": 0.000835421888053467,
      "eval_loss": 1.6066429615020752,
      "eval_runtime": 38.4253,
      "eval_samples_per_second": 13.116,
      "eval_steps_per_second": 3.279,
      "step": 1
    },
    {
      "epoch": 0.001670843776106934,
      "grad_norm": 17.708011627197266,
      "learning_rate": 2e-06,
      "loss": 1.5639,
      "step": 2
    },
    {
      "epoch": 0.002506265664160401,
      "grad_norm": 19.94588851928711,
      "learning_rate": 3e-06,
      "loss": 2.2871,
      "step": 3
    },
    {
      "epoch": 0.003341687552213868,
      "grad_norm": 11.027591705322266,
      "learning_rate": 4e-06,
      "loss": 1.1737,
      "step": 4
    },
    {
      "epoch": 0.004177109440267335,
      "grad_norm": 19.168018341064453,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 1.6066,
      "step": 5
    },
    {
      "epoch": 0.005012531328320802,
      "grad_norm": 11.331216812133789,
      "learning_rate": 6e-06,
      "loss": 1.7864,
      "step": 6
    },
    {
      "epoch": 0.005847953216374269,
      "grad_norm": 12.50044059753418,
      "learning_rate": 7e-06,
      "loss": 1.3554,
      "step": 7
    },
    {
      "epoch": 0.006683375104427736,
      "grad_norm": 11.597599983215332,
      "learning_rate": 8e-06,
      "loss": 1.2366,
      "step": 8
    },
    {
      "epoch": 0.007518796992481203,
      "grad_norm": 5.6630682945251465,
      "learning_rate": 9e-06,
      "loss": 0.9487,
      "step": 9
    },
    {
      "epoch": 0.00835421888053467,
      "grad_norm": 5.019942283630371,
      "learning_rate": 9.999999999999999e-06,
      "loss": 1.0092,
      "step": 10
    },
    {
      "epoch": 0.009189640768588136,
      "grad_norm": 8.010810852050781,
      "learning_rate": 1.1e-05,
      "loss": 1.4717,
      "step": 11
    },
    {
      "epoch": 0.010025062656641603,
      "grad_norm": 6.473798751831055,
      "learning_rate": 1.2e-05,
      "loss": 0.8519,
      "step": 12
    },
    {
      "epoch": 0.01086048454469507,
      "grad_norm": 4.7110595703125,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.7024,
      "step": 13
    },
    {
      "epoch": 0.011695906432748537,
      "grad_norm": 4.263626575469971,
      "learning_rate": 1.4e-05,
      "loss": 0.7116,
      "step": 14
    },
    {
      "epoch": 0.012531328320802004,
      "grad_norm": 3.472412586212158,
      "learning_rate": 1.5e-05,
      "loss": 0.5141,
      "step": 15
    },
    {
      "epoch": 0.013366750208855471,
      "grad_norm": 3.362398624420166,
      "learning_rate": 1.6e-05,
      "loss": 0.6892,
      "step": 16
    },
    {
      "epoch": 0.014202172096908938,
      "grad_norm": 2.528292179107666,
      "learning_rate": 1.7e-05,
      "loss": 0.3903,
      "step": 17
    },
    {
      "epoch": 0.015037593984962405,
      "grad_norm": 1.7493354082107544,
      "learning_rate": 1.8e-05,
      "loss": 0.2833,
      "step": 18
    },
    {
      "epoch": 0.015873015873015872,
      "grad_norm": 1.5588998794555664,
      "learning_rate": 1.9e-05,
      "loss": 0.246,
      "step": 19
    },
    {
      "epoch": 0.01670843776106934,
      "grad_norm": 1.64949369430542,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.2675,
      "step": 20
    },
    {
      "epoch": 0.017543859649122806,
      "grad_norm": 0.8435382843017578,
      "learning_rate": 2.1e-05,
      "loss": 0.1553,
      "step": 21
    },
    {
      "epoch": 0.018379281537176273,
      "grad_norm": 0.6495569348335266,
      "learning_rate": 2.2e-05,
      "loss": 0.1196,
      "step": 22
    },
    {
      "epoch": 0.01921470342522974,
      "grad_norm": 1.0182844400405884,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.1567,
      "step": 23
    },
    {
      "epoch": 0.020050125313283207,
      "grad_norm": 2.8188316822052,
      "learning_rate": 2.4e-05,
      "loss": 0.2064,
      "step": 24
    },
    {
      "epoch": 0.020885547201336674,
      "grad_norm": 1.613542914390564,
      "learning_rate": 2.5e-05,
      "loss": 0.173,
      "step": 25
    },
    {
      "epoch": 0.02172096908939014,
      "grad_norm": 1.5958133935928345,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.184,
      "step": 26
    },
    {
      "epoch": 0.022556390977443608,
      "grad_norm": 0.7841217517852783,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.1614,
      "step": 27
    },
    {
      "epoch": 0.023391812865497075,
      "grad_norm": 1.057112455368042,
      "learning_rate": 2.8e-05,
      "loss": 0.1174,
      "step": 28
    },
    {
      "epoch": 0.02422723475355054,
      "grad_norm": 2.9374876022338867,
      "learning_rate": 2.9e-05,
      "loss": 0.4939,
      "step": 29
    },
    {
      "epoch": 0.02506265664160401,
      "grad_norm": 0.8594872355461121,
      "learning_rate": 3e-05,
      "loss": 0.1437,
      "step": 30
    },
    {
      "epoch": 0.025898078529657476,
      "grad_norm": 0.6192961931228638,
      "learning_rate": 2.9984895998119723e-05,
      "loss": 0.1466,
      "step": 31
    },
    {
      "epoch": 0.026733500417710943,
      "grad_norm": 1.5436159372329712,
      "learning_rate": 2.993961440992859e-05,
      "loss": 0.2683,
      "step": 32
    },
    {
      "epoch": 0.02756892230576441,
      "grad_norm": 0.42387092113494873,
      "learning_rate": 2.9864246426519023e-05,
      "loss": 0.1387,
      "step": 33
    },
    {
      "epoch": 0.028404344193817876,
      "grad_norm": 3.636671304702759,
      "learning_rate": 2.9758943828979444e-05,
      "loss": 0.2699,
      "step": 34
    },
    {
      "epoch": 0.029239766081871343,
      "grad_norm": 0.8583257794380188,
      "learning_rate": 2.9623918682727355e-05,
      "loss": 0.1803,
      "step": 35
    },
    {
      "epoch": 0.03007518796992481,
      "grad_norm": 1.826141595840454,
      "learning_rate": 2.9459442910437798e-05,
      "loss": 0.3046,
      "step": 36
    },
    {
      "epoch": 0.030910609857978277,
      "grad_norm": 0.7456461787223816,
      "learning_rate": 2.9265847744427305e-05,
      "loss": 0.1901,
      "step": 37
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 0.8312434554100037,
      "learning_rate": 2.904352305959606e-05,
      "loss": 0.2098,
      "step": 38
    },
    {
      "epoch": 0.03258145363408521,
      "grad_norm": 0.42538195848464966,
      "learning_rate": 2.8792916588271762e-05,
      "loss": 0.1526,
      "step": 39
    },
    {
      "epoch": 0.03341687552213868,
      "grad_norm": 0.3908769488334656,
      "learning_rate": 2.8514533018536286e-05,
      "loss": 0.1633,
      "step": 40
    },
    {
      "epoch": 0.034252297410192145,
      "grad_norm": 0.3974226713180542,
      "learning_rate": 2.820893297785107e-05,
      "loss": 0.1491,
      "step": 41
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 0.36495357751846313,
      "learning_rate": 2.7876731904027994e-05,
      "loss": 0.1951,
      "step": 42
    },
    {
      "epoch": 0.03592314118629908,
      "grad_norm": 0.560374915599823,
      "learning_rate": 2.7518598805819542e-05,
      "loss": 0.1859,
      "step": 43
    },
    {
      "epoch": 0.036758563074352546,
      "grad_norm": 0.3539278209209442,
      "learning_rate": 2.7135254915624213e-05,
      "loss": 0.15,
      "step": 44
    },
    {
      "epoch": 0.03759398496240601,
      "grad_norm": 1.142353892326355,
      "learning_rate": 2.672747223702045e-05,
      "loss": 0.174,
      "step": 45
    },
    {
      "epoch": 0.03842940685045948,
      "grad_norm": 0.7058913111686707,
      "learning_rate": 2.6296071990054167e-05,
      "loss": 0.1992,
      "step": 46
    },
    {
      "epoch": 0.03926482873851295,
      "grad_norm": 0.38486120104789734,
      "learning_rate": 2.5841922957410875e-05,
      "loss": 0.1652,
      "step": 47
    },
    {
      "epoch": 0.040100250626566414,
      "grad_norm": 3.6414639949798584,
      "learning_rate": 2.5365939734802973e-05,
      "loss": 0.4362,
      "step": 48
    },
    {
      "epoch": 0.04093567251461988,
      "grad_norm": 0.3310062885284424,
      "learning_rate": 2.4869080889095693e-05,
      "loss": 0.2132,
      "step": 49
    },
    {
      "epoch": 0.04177109440267335,
      "grad_norm": 0.39665135741233826,
      "learning_rate": 2.4352347027881003e-05,
      "loss": 0.2063,
      "step": 50
    },
    {
      "epoch": 0.04177109440267335,
      "eval_loss": 0.1654907464981079,
      "eval_runtime": 39.1179,
      "eval_samples_per_second": 12.884,
      "eval_steps_per_second": 3.221,
      "step": 50
    },
    {
      "epoch": 0.042606516290726815,
      "grad_norm": 0.3080545663833618,
      "learning_rate": 2.3816778784387097e-05,
      "loss": 0.1177,
      "step": 51
    },
    {
      "epoch": 0.04344193817878028,
      "grad_norm": 0.40985429286956787,
      "learning_rate": 2.3263454721781537e-05,
      "loss": 0.1433,
      "step": 52
    },
    {
      "epoch": 0.04427736006683375,
      "grad_norm": 0.15664848685264587,
      "learning_rate": 2.2693489161088592e-05,
      "loss": 0.0884,
      "step": 53
    },
    {
      "epoch": 0.045112781954887216,
      "grad_norm": 0.15345360338687897,
      "learning_rate": 2.210802993709498e-05,
      "loss": 0.1044,
      "step": 54
    },
    {
      "epoch": 0.04594820384294068,
      "grad_norm": 0.20342934131622314,
      "learning_rate": 2.1508256086763372e-05,
      "loss": 0.1088,
      "step": 55
    },
    {
      "epoch": 0.04678362573099415,
      "grad_norm": 0.16992981731891632,
      "learning_rate": 2.0895375474808857e-05,
      "loss": 0.1459,
      "step": 56
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 0.17031916975975037,
      "learning_rate": 2.0270622361220143e-05,
      "loss": 0.1282,
      "step": 57
    },
    {
      "epoch": 0.04845446950710108,
      "grad_norm": 0.2852511703968048,
      "learning_rate": 1.963525491562421e-05,
      "loss": 0.1329,
      "step": 58
    },
    {
      "epoch": 0.04928989139515455,
      "grad_norm": 0.4877017140388489,
      "learning_rate": 1.8990552683500128e-05,
      "loss": 0.1365,
      "step": 59
    },
    {
      "epoch": 0.05012531328320802,
      "grad_norm": 0.3902769684791565,
      "learning_rate": 1.8337814009344716e-05,
      "loss": 0.1584,
      "step": 60
    },
    {
      "epoch": 0.050960735171261484,
      "grad_norm": 0.2292199432849884,
      "learning_rate": 1.767835342197955e-05,
      "loss": 0.1402,
      "step": 61
    },
    {
      "epoch": 0.05179615705931495,
      "grad_norm": 0.2017497420310974,
      "learning_rate": 1.7013498987264832e-05,
      "loss": 0.1482,
      "step": 62
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 0.2939629852771759,
      "learning_rate": 1.6344589633551502e-05,
      "loss": 0.1461,
      "step": 63
    },
    {
      "epoch": 0.053467000835421885,
      "grad_norm": 0.1926645189523697,
      "learning_rate": 1.5672972455257726e-05,
      "loss": 0.1044,
      "step": 64
    },
    {
      "epoch": 0.05430242272347535,
      "grad_norm": 0.3081521987915039,
      "learning_rate": 1.5e-05,
      "loss": 0.1596,
      "step": 65
    },
    {
      "epoch": 0.05513784461152882,
      "grad_norm": 0.4025512933731079,
      "learning_rate": 1.4327027544742281e-05,
      "loss": 0.1735,
      "step": 66
    },
    {
      "epoch": 0.055973266499582286,
      "grad_norm": 0.20314837992191315,
      "learning_rate": 1.36554103664485e-05,
      "loss": 0.125,
      "step": 67
    },
    {
      "epoch": 0.05680868838763575,
      "grad_norm": 0.20744721591472626,
      "learning_rate": 1.2986501012735174e-05,
      "loss": 0.1095,
      "step": 68
    },
    {
      "epoch": 0.05764411027568922,
      "grad_norm": 0.2043089121580124,
      "learning_rate": 1.2321646578020452e-05,
      "loss": 0.1544,
      "step": 69
    },
    {
      "epoch": 0.05847953216374269,
      "grad_norm": 0.2829361855983734,
      "learning_rate": 1.1662185990655285e-05,
      "loss": 0.1347,
      "step": 70
    },
    {
      "epoch": 0.059314954051796154,
      "grad_norm": 0.2790044844150543,
      "learning_rate": 1.1009447316499875e-05,
      "loss": 0.1564,
      "step": 71
    },
    {
      "epoch": 0.06015037593984962,
      "grad_norm": 2.54337739944458,
      "learning_rate": 1.036474508437579e-05,
      "loss": 0.1629,
      "step": 72
    },
    {
      "epoch": 0.06098579782790309,
      "grad_norm": 0.279619425535202,
      "learning_rate": 9.729377638779859e-06,
      "loss": 0.1506,
      "step": 73
    },
    {
      "epoch": 0.061821219715956555,
      "grad_norm": 0.2148342877626419,
      "learning_rate": 9.104624525191147e-06,
      "loss": 0.1222,
      "step": 74
    },
    {
      "epoch": 0.06265664160401002,
      "grad_norm": 3.0420451164245605,
      "learning_rate": 8.491743913236629e-06,
      "loss": 0.1404,
      "step": 75
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 0.2432384490966797,
      "learning_rate": 7.89197006290502e-06,
      "loss": 0.1076,
      "step": 76
    },
    {
      "epoch": 0.06432748538011696,
      "grad_norm": 3.1877377033233643,
      "learning_rate": 7.30651083891141e-06,
      "loss": 0.152,
      "step": 77
    },
    {
      "epoch": 0.06516290726817042,
      "grad_norm": 0.4180755019187927,
      "learning_rate": 6.736545278218464e-06,
      "loss": 0.1127,
      "step": 78
    },
    {
      "epoch": 0.06599832915622389,
      "grad_norm": 0.25477147102355957,
      "learning_rate": 6.1832212156129045e-06,
      "loss": 0.1277,
      "step": 79
    },
    {
      "epoch": 0.06683375104427736,
      "grad_norm": 0.399618536233902,
      "learning_rate": 5.647652972118998e-06,
      "loss": 0.1418,
      "step": 80
    },
    {
      "epoch": 0.06766917293233082,
      "grad_norm": 0.27185890078544617,
      "learning_rate": 5.130919110904311e-06,
      "loss": 0.155,
      "step": 81
    },
    {
      "epoch": 0.06850459482038429,
      "grad_norm": 1.3203309774398804,
      "learning_rate": 4.6340602651970304e-06,
      "loss": 0.3033,
      "step": 82
    },
    {
      "epoch": 0.06934001670843776,
      "grad_norm": 0.3346821367740631,
      "learning_rate": 4.158077042589129e-06,
      "loss": 0.1639,
      "step": 83
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 0.3132845163345337,
      "learning_rate": 3.7039280099458373e-06,
      "loss": 0.1417,
      "step": 84
    },
    {
      "epoch": 0.07101086048454469,
      "grad_norm": 0.30599430203437805,
      "learning_rate": 3.272527762979553e-06,
      "loss": 0.1666,
      "step": 85
    },
    {
      "epoch": 0.07184628237259816,
      "grad_norm": 0.5425288677215576,
      "learning_rate": 2.86474508437579e-06,
      "loss": 0.1837,
      "step": 86
    },
    {
      "epoch": 0.07268170426065163,
      "grad_norm": 0.2609088122844696,
      "learning_rate": 2.4814011941804603e-06,
      "loss": 0.1981,
      "step": 87
    },
    {
      "epoch": 0.07351712614870509,
      "grad_norm": 0.2561860680580139,
      "learning_rate": 2.1232680959720085e-06,
      "loss": 0.1169,
      "step": 88
    },
    {
      "epoch": 0.07435254803675856,
      "grad_norm": 0.26870644092559814,
      "learning_rate": 1.79106702214893e-06,
      "loss": 0.162,
      "step": 89
    },
    {
      "epoch": 0.07518796992481203,
      "grad_norm": 0.35758742690086365,
      "learning_rate": 1.4854669814637145e-06,
      "loss": 0.1946,
      "step": 90
    },
    {
      "epoch": 0.07602339181286549,
      "grad_norm": 0.40720826387405396,
      "learning_rate": 1.2070834117282414e-06,
      "loss": 0.1676,
      "step": 91
    },
    {
      "epoch": 0.07685881370091896,
      "grad_norm": 0.2641846835613251,
      "learning_rate": 9.56476940403942e-07,
      "loss": 0.1419,
      "step": 92
    },
    {
      "epoch": 0.07769423558897243,
      "grad_norm": 0.32390695810317993,
      "learning_rate": 7.341522555726971e-07,
      "loss": 0.1727,
      "step": 93
    },
    {
      "epoch": 0.0785296574770259,
      "grad_norm": 0.17990685999393463,
      "learning_rate": 5.405570895622014e-07,
      "loss": 0.1278,
      "step": 94
    },
    {
      "epoch": 0.07936507936507936,
      "grad_norm": 0.5421126484870911,
      "learning_rate": 3.760813172726457e-07,
      "loss": 0.1988,
      "step": 95
    },
    {
      "epoch": 0.08020050125313283,
      "grad_norm": 0.22047364711761475,
      "learning_rate": 2.41056171020555e-07,
      "loss": 0.1636,
      "step": 96
    },
    {
      "epoch": 0.0810359231411863,
      "grad_norm": 0.2979952096939087,
      "learning_rate": 1.357535734809795e-07,
      "loss": 0.1766,
      "step": 97
    },
    {
      "epoch": 0.08187134502923976,
      "grad_norm": 0.4420830309391022,
      "learning_rate": 6.038559007141397e-08,
      "loss": 0.2073,
      "step": 98
    },
    {
      "epoch": 0.08270676691729323,
      "grad_norm": 0.8136470913887024,
      "learning_rate": 1.510400188028116e-08,
      "loss": 0.2351,
      "step": 99
    },
    {
      "epoch": 0.0835421888053467,
      "grad_norm": 0.37833961844444275,
      "learning_rate": 0.0,
      "loss": 0.1832,
      "step": 100
    },
    {
      "epoch": 0.0835421888053467,
      "eval_loss": 0.15805459022521973,
      "eval_runtime": 39.1836,
      "eval_samples_per_second": 12.863,
      "eval_steps_per_second": 3.216,
      "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": 3.3812411056128e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}