{
  "best_metric": 0.1422112137079239,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.2861736334405145,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012861736334405145,
      "grad_norm": 1.0487146377563477,
      "learning_rate": 2e-05,
      "loss": 0.2797,
      "step": 1
    },
    {
      "epoch": 0.012861736334405145,
      "eval_loss": 1.4455676078796387,
      "eval_runtime": 13.2298,
      "eval_samples_per_second": 79.215,
      "eval_steps_per_second": 4.989,
      "step": 1
    },
    {
      "epoch": 0.02572347266881029,
      "grad_norm": 1.1061933040618896,
      "learning_rate": 4e-05,
      "loss": 0.2781,
      "step": 2
    },
    {
      "epoch": 0.03858520900321544,
      "grad_norm": 1.0855467319488525,
      "learning_rate": 6e-05,
      "loss": 0.3164,
      "step": 3
    },
    {
      "epoch": 0.05144694533762058,
      "grad_norm": 1.1288857460021973,
      "learning_rate": 8e-05,
      "loss": 0.4061,
      "step": 4
    },
    {
      "epoch": 0.06430868167202572,
      "grad_norm": 1.728751301765442,
      "learning_rate": 0.0001,
      "loss": 1.0447,
      "step": 5
    },
    {
      "epoch": 0.07717041800643087,
      "grad_norm": 1.8711669445037842,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.3565,
      "step": 6
    },
    {
      "epoch": 0.09003215434083602,
      "grad_norm": 1.4198046922683716,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.3228,
      "step": 7
    },
    {
      "epoch": 0.10289389067524116,
      "grad_norm": 1.639742136001587,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.3728,
      "step": 8
    },
    {
      "epoch": 0.1157556270096463,
      "grad_norm": 1.359843373298645,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.1646,
      "step": 9
    },
    {
      "epoch": 0.12861736334405144,
      "grad_norm": 1.0507453680038452,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.0657,
      "step": 10
    },
    {
      "epoch": 0.1414790996784566,
      "grad_norm": 1.6579258441925049,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8397,
      "step": 11
    },
    {
      "epoch": 0.15434083601286175,
      "grad_norm": 1.278835415840149,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7758,
      "step": 12
    },
    {
      "epoch": 0.16720257234726688,
      "grad_norm": 0.41791051626205444,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.2752,
      "step": 13
    },
    {
      "epoch": 0.18006430868167203,
      "grad_norm": 0.29641208052635193,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.2002,
      "step": 14
    },
    {
      "epoch": 0.19292604501607716,
      "grad_norm": 0.1839553564786911,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.1832,
      "step": 15
    },
    {
      "epoch": 0.2057877813504823,
      "grad_norm": 0.4557490348815918,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.171,
      "step": 16
    },
    {
      "epoch": 0.21864951768488747,
      "grad_norm": 0.48206084966659546,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.3688,
      "step": 17
    },
    {
      "epoch": 0.2315112540192926,
      "grad_norm": 1.2969698905944824,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.0203,
      "step": 18
    },
    {
      "epoch": 0.24437299035369775,
      "grad_norm": 1.250345230102539,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.0725,
      "step": 19
    },
    {
      "epoch": 0.2572347266881029,
      "grad_norm": 1.1758275032043457,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.0767,
      "step": 20
    },
    {
      "epoch": 0.27009646302250806,
      "grad_norm": 1.5035009384155273,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.9825,
      "step": 21
    },
    {
      "epoch": 0.2829581993569132,
      "grad_norm": 1.6356459856033325,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.9112,
      "step": 22
    },
    {
      "epoch": 0.2958199356913183,
      "grad_norm": 1.1673827171325684,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7037,
      "step": 23
    },
    {
      "epoch": 0.3086816720257235,
      "grad_norm": 0.9417451024055481,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.5212,
      "step": 24
    },
    {
      "epoch": 0.3215434083601286,
      "grad_norm": 1.229873538017273,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.5536,
      "step": 25
    },
    {
      "epoch": 0.3215434083601286,
      "eval_loss": 0.49254778027534485,
      "eval_runtime": 13.2514,
      "eval_samples_per_second": 79.086,
      "eval_steps_per_second": 4.981,
      "step": 25
    },
    {
      "epoch": 0.33440514469453375,
      "grad_norm": 0.5078119039535522,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.2228,
      "step": 26
    },
    {
      "epoch": 0.34726688102893893,
      "grad_norm": 0.5150062441825867,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.2157,
      "step": 27
    },
    {
      "epoch": 0.36012861736334406,
      "grad_norm": 0.4721466600894928,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.1641,
      "step": 28
    },
    {
      "epoch": 0.3729903536977492,
      "grad_norm": 0.8219810724258423,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.1476,
      "step": 29
    },
    {
      "epoch": 0.3858520900321543,
      "grad_norm": 0.7543917298316956,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.404,
      "step": 30
    },
    {
      "epoch": 0.3987138263665595,
      "grad_norm": 1.163086175918579,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.5876,
      "step": 31
    },
    {
      "epoch": 0.4115755627009646,
      "grad_norm": 1.0131382942199707,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.5902,
      "step": 32
    },
    {
      "epoch": 0.42443729903536975,
      "grad_norm": 0.9731802940368652,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.5528,
      "step": 33
    },
    {
      "epoch": 0.43729903536977494,
      "grad_norm": 0.9890906810760498,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.5109,
      "step": 34
    },
    {
      "epoch": 0.45016077170418006,
      "grad_norm": 1.0157954692840576,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.4497,
      "step": 35
    },
    {
      "epoch": 0.4630225080385852,
      "grad_norm": 0.781050980091095,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.3504,
      "step": 36
    },
    {
      "epoch": 0.4758842443729904,
      "grad_norm": 0.604677140712738,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.2506,
      "step": 37
    },
    {
      "epoch": 0.4887459807073955,
      "grad_norm": 0.38148045539855957,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.2123,
      "step": 38
    },
    {
      "epoch": 0.5016077170418006,
      "grad_norm": 0.3363175690174103,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.1864,
      "step": 39
    },
    {
      "epoch": 0.5144694533762058,
      "grad_norm": 0.3012297749519348,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.1605,
      "step": 40
    },
    {
      "epoch": 0.5273311897106109,
      "grad_norm": 0.21193085610866547,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.107,
      "step": 41
    },
    {
      "epoch": 0.5401929260450161,
      "grad_norm": 0.4295702576637268,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.1823,
      "step": 42
    },
    {
      "epoch": 0.5530546623794212,
      "grad_norm": 1.3062560558319092,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3417,
      "step": 43
    },
    {
      "epoch": 0.5659163987138264,
      "grad_norm": 0.8124111890792847,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.2701,
      "step": 44
    },
    {
      "epoch": 0.5787781350482315,
      "grad_norm": 0.7088838815689087,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.2764,
      "step": 45
    },
    {
      "epoch": 0.5916398713826366,
      "grad_norm": 0.7764143943786621,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.3054,
      "step": 46
    },
    {
      "epoch": 0.6045016077170418,
      "grad_norm": 0.6154634356498718,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.2202,
      "step": 47
    },
    {
      "epoch": 0.617363344051447,
      "grad_norm": 0.6224243640899658,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.2393,
      "step": 48
    },
    {
      "epoch": 0.6302250803858521,
      "grad_norm": 0.5424495339393616,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.2231,
      "step": 49
    },
    {
      "epoch": 0.6430868167202572,
      "grad_norm": 0.6866870522499084,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.1925,
      "step": 50
    },
    {
      "epoch": 0.6430868167202572,
      "eval_loss": 0.19903014600276947,
      "eval_runtime": 13.2667,
      "eval_samples_per_second": 78.995,
      "eval_steps_per_second": 4.975,
      "step": 50
    },
    {
      "epoch": 0.6559485530546624,
      "grad_norm": 0.30935201048851013,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.1668,
      "step": 51
    },
    {
      "epoch": 0.6688102893890675,
      "grad_norm": 0.29703548550605774,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.1548,
      "step": 52
    },
    {
      "epoch": 0.6816720257234726,
      "grad_norm": 0.2632124125957489,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.1155,
      "step": 53
    },
    {
      "epoch": 0.6945337620578779,
      "grad_norm": 0.3463415801525116,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.1157,
      "step": 54
    },
    {
      "epoch": 0.707395498392283,
      "grad_norm": 0.4073414206504822,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.1667,
      "step": 55
    },
    {
      "epoch": 0.7202572347266881,
      "grad_norm": 0.6212286353111267,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.2416,
      "step": 56
    },
    {
      "epoch": 0.7331189710610932,
      "grad_norm": 0.5285773277282715,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.2056,
      "step": 57
    },
    {
      "epoch": 0.7459807073954984,
      "grad_norm": 0.4094732403755188,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.1692,
      "step": 58
    },
    {
      "epoch": 0.7588424437299035,
      "grad_norm": 0.4649737775325775,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.1719,
      "step": 59
    },
    {
      "epoch": 0.7717041800643086,
      "grad_norm": 0.49657511711120605,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.2085,
      "step": 60
    },
    {
      "epoch": 0.7845659163987139,
      "grad_norm": 0.5126468539237976,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.1658,
      "step": 61
    },
    {
      "epoch": 0.797427652733119,
      "grad_norm": 0.503258228302002,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.123,
      "step": 62
    },
    {
      "epoch": 0.8102893890675241,
      "grad_norm": 0.29781374335289,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.1707,
      "step": 63
    },
    {
      "epoch": 0.8231511254019293,
      "grad_norm": 0.24223004281520844,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.1478,
      "step": 64
    },
    {
      "epoch": 0.8360128617363344,
      "grad_norm": 0.2178749293088913,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.1198,
      "step": 65
    },
    {
      "epoch": 0.8488745980707395,
      "grad_norm": 0.32112425565719604,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.0997,
      "step": 66
    },
    {
      "epoch": 0.8617363344051447,
      "grad_norm": 0.4156148135662079,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.1173,
      "step": 67
    },
    {
      "epoch": 0.8745980707395499,
      "grad_norm": 0.608623206615448,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.1976,
      "step": 68
    },
    {
      "epoch": 0.887459807073955,
      "grad_norm": 0.5557019114494324,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.2075,
      "step": 69
    },
    {
      "epoch": 0.9003215434083601,
      "grad_norm": 0.5011090040206909,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.183,
      "step": 70
    },
    {
      "epoch": 0.9131832797427653,
      "grad_norm": 0.43509817123413086,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.1857,
      "step": 71
    },
    {
      "epoch": 0.9260450160771704,
      "grad_norm": 0.4756283462047577,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.187,
      "step": 72
    },
    {
      "epoch": 0.9389067524115756,
      "grad_norm": 0.46354904770851135,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.1792,
      "step": 73
    },
    {
      "epoch": 0.9517684887459807,
      "grad_norm": 0.347188800573349,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.137,
      "step": 74
    },
    {
      "epoch": 0.9646302250803859,
      "grad_norm": 0.4456610083580017,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.1723,
      "step": 75
    },
    {
      "epoch": 0.9646302250803859,
      "eval_loss": 0.1474793553352356,
      "eval_runtime": 13.2804,
      "eval_samples_per_second": 78.913,
      "eval_steps_per_second": 4.97,
      "step": 75
    },
    {
      "epoch": 0.977491961414791,
      "grad_norm": 0.2270452380180359,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.1252,
      "step": 76
    },
    {
      "epoch": 0.9903536977491961,
      "grad_norm": 0.2915286123752594,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.1449,
      "step": 77
    },
    {
      "epoch": 1.0032154340836013,
      "grad_norm": 0.5222342014312744,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.233,
      "step": 78
    },
    {
      "epoch": 1.0160771704180065,
      "grad_norm": 0.25487202405929565,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.1399,
      "step": 79
    },
    {
      "epoch": 1.0289389067524115,
      "grad_norm": 0.2985232472419739,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.145,
      "step": 80
    },
    {
      "epoch": 1.0418006430868167,
      "grad_norm": 0.2104199081659317,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0817,
      "step": 81
    },
    {
      "epoch": 1.0546623794212218,
      "grad_norm": 0.2394314408302307,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.1194,
      "step": 82
    },
    {
      "epoch": 1.067524115755627,
      "grad_norm": 0.43497416377067566,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.1466,
      "step": 83
    },
    {
      "epoch": 1.0803858520900322,
      "grad_norm": 0.6538999676704407,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.1417,
      "step": 84
    },
    {
      "epoch": 1.0932475884244373,
      "grad_norm": 0.6253057718276978,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.1486,
      "step": 85
    },
    {
      "epoch": 1.1061093247588425,
      "grad_norm": 0.3550533354282379,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.1428,
      "step": 86
    },
    {
      "epoch": 1.1189710610932475,
      "grad_norm": 0.5495473742485046,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.1549,
      "step": 87
    },
    {
      "epoch": 1.1318327974276527,
      "grad_norm": 0.5441097617149353,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.1766,
      "step": 88
    },
    {
      "epoch": 1.144694533762058,
      "grad_norm": 0.5258228778839111,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.1593,
      "step": 89
    },
    {
      "epoch": 1.157556270096463,
      "grad_norm": 0.24209189414978027,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0892,
      "step": 90
    },
    {
      "epoch": 1.1704180064308682,
      "grad_norm": 0.3027883470058441,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.1809,
      "step": 91
    },
    {
      "epoch": 1.1832797427652733,
      "grad_norm": 0.25001150369644165,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.1422,
      "step": 92
    },
    {
      "epoch": 1.1961414790996785,
      "grad_norm": 0.19552123546600342,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.1008,
      "step": 93
    },
    {
      "epoch": 1.2090032154340835,
      "grad_norm": 0.26038041710853577,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.1037,
      "step": 94
    },
    {
      "epoch": 1.2218649517684887,
      "grad_norm": 0.4653327465057373,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.1306,
      "step": 95
    },
    {
      "epoch": 1.234726688102894,
      "grad_norm": 0.4531954824924469,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.1631,
      "step": 96
    },
    {
      "epoch": 1.247588424437299,
      "grad_norm": 0.37266069650650024,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.1288,
      "step": 97
    },
    {
      "epoch": 1.2604501607717042,
      "grad_norm": 0.6075907349586487,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.1764,
      "step": 98
    },
    {
      "epoch": 1.2733118971061093,
      "grad_norm": 0.3153791129589081,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.1421,
      "step": 99
    },
    {
      "epoch": 1.2861736334405145,
      "grad_norm": 0.6054843664169312,
      "learning_rate": 0.0,
      "loss": 0.1747,
      "step": 100
    },
    {
      "epoch": 1.2861736334405145,
      "eval_loss": 0.1422112137079239,
      "eval_runtime": 13.267,
      "eval_samples_per_second": 78.993,
      "eval_steps_per_second": 4.975,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 6.357855120654336e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}