{
  "best_metric": 0.5548466444015503,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.4184397163120568,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0070921985815602835,
      "grad_norm": 8.466599464416504,
      "learning_rate": 1e-05,
      "loss": 2.5463,
      "step": 1
    },
    {
      "epoch": 0.0070921985815602835,
      "eval_loss": 3.0699386596679688,
      "eval_runtime": 4.799,
      "eval_samples_per_second": 49.594,
      "eval_steps_per_second": 12.503,
      "step": 1
    },
    {
      "epoch": 0.014184397163120567,
      "grad_norm": 11.381098747253418,
      "learning_rate": 2e-05,
      "loss": 2.79,
      "step": 2
    },
    {
      "epoch": 0.02127659574468085,
      "grad_norm": 8.311277389526367,
      "learning_rate": 3e-05,
      "loss": 2.7045,
      "step": 3
    },
    {
      "epoch": 0.028368794326241134,
      "grad_norm": 4.700682163238525,
      "learning_rate": 4e-05,
      "loss": 2.6888,
      "step": 4
    },
    {
      "epoch": 0.03546099290780142,
      "grad_norm": 4.37355375289917,
      "learning_rate": 5e-05,
      "loss": 2.4132,
      "step": 5
    },
    {
      "epoch": 0.0425531914893617,
      "grad_norm": 4.892189025878906,
      "learning_rate": 6e-05,
      "loss": 2.5076,
      "step": 6
    },
    {
      "epoch": 0.04964539007092199,
      "grad_norm": 3.356898784637451,
      "learning_rate": 7e-05,
      "loss": 2.1845,
      "step": 7
    },
    {
      "epoch": 0.05673758865248227,
      "grad_norm": 2.1489040851593018,
      "learning_rate": 8e-05,
      "loss": 1.907,
      "step": 8
    },
    {
      "epoch": 0.06382978723404255,
      "grad_norm": 2.3447892665863037,
      "learning_rate": 9e-05,
      "loss": 1.8142,
      "step": 9
    },
    {
      "epoch": 0.07092198581560284,
      "grad_norm": 2.077284812927246,
      "learning_rate": 0.0001,
      "loss": 1.5445,
      "step": 10
    },
    {
      "epoch": 0.07801418439716312,
      "grad_norm": 2.0407652854919434,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.4398,
      "step": 11
    },
    {
      "epoch": 0.0851063829787234,
      "grad_norm": 1.7797677516937256,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.2779,
      "step": 12
    },
    {
      "epoch": 0.09219858156028368,
      "grad_norm": 1.876202940940857,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.1888,
      "step": 13
    },
    {
      "epoch": 0.09929078014184398,
      "grad_norm": 1.538963794708252,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.1034,
      "step": 14
    },
    {
      "epoch": 0.10638297872340426,
      "grad_norm": 1.6765902042388916,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.0398,
      "step": 15
    },
    {
      "epoch": 0.11347517730496454,
      "grad_norm": 1.3925065994262695,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.0541,
      "step": 16
    },
    {
      "epoch": 0.12056737588652482,
      "grad_norm": 1.286936640739441,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9682,
      "step": 17
    },
    {
      "epoch": 0.1276595744680851,
      "grad_norm": 1.1468030214309692,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.9219,
      "step": 18
    },
    {
      "epoch": 0.1347517730496454,
      "grad_norm": 1.3895301818847656,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.8932,
      "step": 19
    },
    {
      "epoch": 0.14184397163120568,
      "grad_norm": 1.0371119976043701,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.7789,
      "step": 20
    },
    {
      "epoch": 0.14893617021276595,
      "grad_norm": 1.1051911115646362,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.8364,
      "step": 21
    },
    {
      "epoch": 0.15602836879432624,
      "grad_norm": 1.1154706478118896,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.7336,
      "step": 22
    },
    {
      "epoch": 0.16312056737588654,
      "grad_norm": 1.1639916896820068,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.6108,
      "step": 23
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 0.8635584115982056,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.5605,
      "step": 24
    },
    {
      "epoch": 0.1773049645390071,
      "grad_norm": 0.9920921325683594,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.5958,
      "step": 25
    },
    {
      "epoch": 0.18439716312056736,
      "grad_norm": 0.983674168586731,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.5363,
      "step": 26
    },
    {
      "epoch": 0.19148936170212766,
      "grad_norm": 0.8784399032592773,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.4371,
      "step": 27
    },
    {
      "epoch": 0.19858156028368795,
      "grad_norm": 1.0307199954986572,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.4605,
      "step": 28
    },
    {
      "epoch": 0.20567375886524822,
      "grad_norm": 0.9185486435890198,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.4732,
      "step": 29
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 0.9220833778381348,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.4395,
      "step": 30
    },
    {
      "epoch": 0.2198581560283688,
      "grad_norm": 0.8409585952758789,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.4078,
      "step": 31
    },
    {
      "epoch": 0.22695035460992907,
      "grad_norm": 0.9111459851264954,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.41,
      "step": 32
    },
    {
      "epoch": 0.23404255319148937,
      "grad_norm": 1.214813232421875,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.459,
      "step": 33
    },
    {
      "epoch": 0.24113475177304963,
      "grad_norm": 1.4337066411972046,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.364,
      "step": 34
    },
    {
      "epoch": 0.24822695035460993,
      "grad_norm": 6.488189697265625,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7743,
      "step": 35
    },
    {
      "epoch": 0.2553191489361702,
      "grad_norm": 1.9718403816223145,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.4387,
      "step": 36
    },
    {
      "epoch": 0.2624113475177305,
      "grad_norm": 1.7701148986816406,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.3157,
      "step": 37
    },
    {
      "epoch": 0.2695035460992908,
      "grad_norm": 1.493287205696106,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.1457,
      "step": 38
    },
    {
      "epoch": 0.2765957446808511,
      "grad_norm": 1.1461758613586426,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.1118,
      "step": 39
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 1.0173683166503906,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.0509,
      "step": 40
    },
    {
      "epoch": 0.2907801418439716,
      "grad_norm": 0.9615849256515503,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.9711,
      "step": 41
    },
    {
      "epoch": 0.2978723404255319,
      "grad_norm": 0.8943547606468201,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.9545,
      "step": 42
    },
    {
      "epoch": 0.3049645390070922,
      "grad_norm": 0.931915819644928,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.838,
      "step": 43
    },
    {
      "epoch": 0.3120567375886525,
      "grad_norm": 0.8887052536010742,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.826,
      "step": 44
    },
    {
      "epoch": 0.3191489361702128,
      "grad_norm": 0.891045093536377,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8425,
      "step": 45
    },
    {
      "epoch": 0.3262411347517731,
      "grad_norm": 0.8469178676605225,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7823,
      "step": 46
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.804279088973999,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.8002,
      "step": 47
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 0.8471317291259766,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8027,
      "step": 48
    },
    {
      "epoch": 0.3475177304964539,
      "grad_norm": 0.8144490718841553,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.7492,
      "step": 49
    },
    {
      "epoch": 0.3546099290780142,
      "grad_norm": 0.8222363591194153,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7119,
      "step": 50
    },
    {
      "epoch": 0.3546099290780142,
      "eval_loss": 0.678631603717804,
      "eval_runtime": 4.7906,
      "eval_samples_per_second": 49.681,
      "eval_steps_per_second": 12.525,
      "step": 50
    },
    {
      "epoch": 0.3617021276595745,
      "grad_norm": 0.7508844137191772,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.5916,
      "step": 51
    },
    {
      "epoch": 0.36879432624113473,
      "grad_norm": 0.8533144593238831,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.6428,
      "step": 52
    },
    {
      "epoch": 0.375886524822695,
      "grad_norm": 0.8503960371017456,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.616,
      "step": 53
    },
    {
      "epoch": 0.3829787234042553,
      "grad_norm": 0.8112523555755615,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.6629,
      "step": 54
    },
    {
      "epoch": 0.3900709219858156,
      "grad_norm": 0.798492431640625,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.5681,
      "step": 55
    },
    {
      "epoch": 0.3971631205673759,
      "grad_norm": 0.7263888716697693,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.5502,
      "step": 56
    },
    {
      "epoch": 0.40425531914893614,
      "grad_norm": 0.8264017701148987,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.5399,
      "step": 57
    },
    {
      "epoch": 0.41134751773049644,
      "grad_norm": 0.8400811553001404,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.5601,
      "step": 58
    },
    {
      "epoch": 0.41843971631205673,
      "grad_norm": 0.6590602993965149,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.4145,
      "step": 59
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 0.6831833124160767,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.4572,
      "step": 60
    },
    {
      "epoch": 0.4326241134751773,
      "grad_norm": 0.7180217504501343,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.4557,
      "step": 61
    },
    {
      "epoch": 0.4397163120567376,
      "grad_norm": 0.7752038240432739,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.4242,
      "step": 62
    },
    {
      "epoch": 0.44680851063829785,
      "grad_norm": 0.7440842986106873,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.3796,
      "step": 63
    },
    {
      "epoch": 0.45390070921985815,
      "grad_norm": 0.6200229525566101,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.3455,
      "step": 64
    },
    {
      "epoch": 0.46099290780141844,
      "grad_norm": 0.7641000747680664,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.4208,
      "step": 65
    },
    {
      "epoch": 0.46808510638297873,
      "grad_norm": 0.6254017353057861,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.3165,
      "step": 66
    },
    {
      "epoch": 0.475177304964539,
      "grad_norm": 0.7451967597007751,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.3721,
      "step": 67
    },
    {
      "epoch": 0.48226950354609927,
      "grad_norm": 0.8342266082763672,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.3302,
      "step": 68
    },
    {
      "epoch": 0.48936170212765956,
      "grad_norm": 1.0637445449829102,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.3497,
      "step": 69
    },
    {
      "epoch": 0.49645390070921985,
      "grad_norm": 4.373008728027344,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.5389,
      "step": 70
    },
    {
      "epoch": 0.5035460992907801,
      "grad_norm": 1.1846193075180054,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.2084,
      "step": 71
    },
    {
      "epoch": 0.5106382978723404,
      "grad_norm": 1.0939291715621948,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.0292,
      "step": 72
    },
    {
      "epoch": 0.5177304964539007,
      "grad_norm": 1.0259311199188232,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.0296,
      "step": 73
    },
    {
      "epoch": 0.524822695035461,
      "grad_norm": 0.9105002880096436,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.9741,
      "step": 74
    },
    {
      "epoch": 0.5319148936170213,
      "grad_norm": 0.7753514051437378,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.8692,
      "step": 75
    },
    {
      "epoch": 0.5390070921985816,
      "grad_norm": 0.7796815037727356,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.9347,
      "step": 76
    },
    {
      "epoch": 0.5460992907801419,
      "grad_norm": 0.7500946521759033,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.8826,
      "step": 77
    },
    {
      "epoch": 0.5531914893617021,
      "grad_norm": 0.7475610375404358,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.8292,
      "step": 78
    },
    {
      "epoch": 0.5602836879432624,
      "grad_norm": 0.647667646408081,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7195,
      "step": 79
    },
    {
      "epoch": 0.5673758865248227,
      "grad_norm": 0.7568182945251465,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7319,
      "step": 80
    },
    {
      "epoch": 0.574468085106383,
      "grad_norm": 0.7180904150009155,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7153,
      "step": 81
    },
    {
      "epoch": 0.5815602836879432,
      "grad_norm": 0.7035728096961975,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7557,
      "step": 82
    },
    {
      "epoch": 0.5886524822695035,
      "grad_norm": 0.7218835353851318,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6606,
      "step": 83
    },
    {
      "epoch": 0.5957446808510638,
      "grad_norm": 0.7264882326126099,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.6508,
      "step": 84
    },
    {
      "epoch": 0.6028368794326241,
      "grad_norm": 0.6674414873123169,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.621,
      "step": 85
    },
    {
      "epoch": 0.6099290780141844,
      "grad_norm": 0.6697022318840027,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5768,
      "step": 86
    },
    {
      "epoch": 0.6170212765957447,
      "grad_norm": 0.6013833284378052,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.5086,
      "step": 87
    },
    {
      "epoch": 0.624113475177305,
      "grad_norm": 0.7232674360275269,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.601,
      "step": 88
    },
    {
      "epoch": 0.6312056737588653,
      "grad_norm": 0.6740778088569641,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.5408,
      "step": 89
    },
    {
      "epoch": 0.6382978723404256,
      "grad_norm": 0.707331657409668,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.4931,
      "step": 90
    },
    {
      "epoch": 0.6453900709219859,
      "grad_norm": 0.6922100186347961,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.5058,
      "step": 91
    },
    {
      "epoch": 0.6524822695035462,
      "grad_norm": 0.7236265540122986,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.4645,
      "step": 92
    },
    {
      "epoch": 0.6595744680851063,
      "grad_norm": 0.6964171528816223,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.4154,
      "step": 93
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.7128075361251831,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.4834,
      "step": 94
    },
    {
      "epoch": 0.6737588652482269,
      "grad_norm": 0.6621071696281433,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.4125,
      "step": 95
    },
    {
      "epoch": 0.6808510638297872,
      "grad_norm": 0.7316243052482605,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.3689,
      "step": 96
    },
    {
      "epoch": 0.6879432624113475,
      "grad_norm": 0.754240870475769,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.4185,
      "step": 97
    },
    {
      "epoch": 0.6950354609929078,
      "grad_norm": 0.5534430146217346,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.3116,
      "step": 98
    },
    {
      "epoch": 0.7021276595744681,
      "grad_norm": 0.6348011493682861,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.3867,
      "step": 99
    },
    {
      "epoch": 0.7092198581560284,
      "grad_norm": 0.6221848726272583,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.3144,
      "step": 100
    },
    {
      "epoch": 0.7092198581560284,
      "eval_loss": 0.6137951016426086,
      "eval_runtime": 4.7903,
      "eval_samples_per_second": 49.683,
      "eval_steps_per_second": 12.525,
      "step": 100
    },
    {
      "epoch": 0.7163120567375887,
      "grad_norm": 0.7364077568054199,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.3699,
      "step": 101
    },
    {
      "epoch": 0.723404255319149,
      "grad_norm": 0.7822397947311401,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.3408,
      "step": 102
    },
    {
      "epoch": 0.7304964539007093,
      "grad_norm": 0.7377681136131287,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.2187,
      "step": 103
    },
    {
      "epoch": 0.7375886524822695,
      "grad_norm": 1.005196213722229,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.2648,
      "step": 104
    },
    {
      "epoch": 0.7446808510638298,
      "grad_norm": 3.281944513320923,
      "learning_rate": 5e-05,
      "loss": 0.478,
      "step": 105
    },
    {
      "epoch": 0.75177304964539,
      "grad_norm": 1.1480039358139038,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.1023,
      "step": 106
    },
    {
      "epoch": 0.7588652482269503,
      "grad_norm": 1.0301520824432373,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.0126,
      "step": 107
    },
    {
      "epoch": 0.7659574468085106,
      "grad_norm": 0.9889645576477051,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.0137,
      "step": 108
    },
    {
      "epoch": 0.7730496453900709,
      "grad_norm": 0.8208257555961609,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.8266,
      "step": 109
    },
    {
      "epoch": 0.7801418439716312,
      "grad_norm": 0.8290475010871887,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8726,
      "step": 110
    },
    {
      "epoch": 0.7872340425531915,
      "grad_norm": 0.7626585960388184,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.8406,
      "step": 111
    },
    {
      "epoch": 0.7943262411347518,
      "grad_norm": 0.7503089308738708,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.7593,
      "step": 112
    },
    {
      "epoch": 0.8014184397163121,
      "grad_norm": 0.6868686676025391,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.7269,
      "step": 113
    },
    {
      "epoch": 0.8085106382978723,
      "grad_norm": 0.6195743680000305,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.6782,
      "step": 114
    },
    {
      "epoch": 0.8156028368794326,
      "grad_norm": 0.6514648795127869,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.7044,
      "step": 115
    },
    {
      "epoch": 0.8226950354609929,
      "grad_norm": 0.6324070692062378,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.7258,
      "step": 116
    },
    {
      "epoch": 0.8297872340425532,
      "grad_norm": 0.6351830363273621,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.6291,
      "step": 117
    },
    {
      "epoch": 0.8368794326241135,
      "grad_norm": 0.6871326565742493,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.6441,
      "step": 118
    },
    {
      "epoch": 0.8439716312056738,
      "grad_norm": 0.620800256729126,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.6262,
      "step": 119
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 0.680656909942627,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.6229,
      "step": 120
    },
    {
      "epoch": 0.8581560283687943,
      "grad_norm": 0.6494395136833191,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.5342,
      "step": 121
    },
    {
      "epoch": 0.8652482269503546,
      "grad_norm": 0.6457289457321167,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.5708,
      "step": 122
    },
    {
      "epoch": 0.8723404255319149,
      "grad_norm": 0.6741331219673157,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.5889,
      "step": 123
    },
    {
      "epoch": 0.8794326241134752,
      "grad_norm": 0.6758741140365601,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.5569,
      "step": 124
    },
    {
      "epoch": 0.8865248226950354,
      "grad_norm": 0.6911808848381042,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.5204,
      "step": 125
    },
    {
      "epoch": 0.8936170212765957,
      "grad_norm": 0.6139733195304871,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.5116,
      "step": 126
    },
    {
      "epoch": 0.900709219858156,
      "grad_norm": 0.6231783032417297,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.4477,
      "step": 127
    },
    {
      "epoch": 0.9078014184397163,
      "grad_norm": 0.6089223027229309,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.4558,
      "step": 128
    },
    {
      "epoch": 0.9148936170212766,
      "grad_norm": 0.6706297993659973,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.4384,
      "step": 129
    },
    {
      "epoch": 0.9219858156028369,
      "grad_norm": 0.6966522336006165,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.4937,
      "step": 130
    },
    {
      "epoch": 0.9290780141843972,
      "grad_norm": 0.5600222945213318,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.3526,
      "step": 131
    },
    {
      "epoch": 0.9361702127659575,
      "grad_norm": 0.651127278804779,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.3998,
      "step": 132
    },
    {
      "epoch": 0.9432624113475178,
      "grad_norm": 0.6429144740104675,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.365,
      "step": 133
    },
    {
      "epoch": 0.950354609929078,
      "grad_norm": 0.6141672134399414,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.3848,
      "step": 134
    },
    {
      "epoch": 0.9574468085106383,
      "grad_norm": 0.6924313306808472,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.406,
      "step": 135
    },
    {
      "epoch": 0.9645390070921985,
      "grad_norm": 0.7273817658424377,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.3722,
      "step": 136
    },
    {
      "epoch": 0.9716312056737588,
      "grad_norm": 0.7967301607131958,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.3919,
      "step": 137
    },
    {
      "epoch": 0.9787234042553191,
      "grad_norm": 0.6811634302139282,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.2536,
      "step": 138
    },
    {
      "epoch": 0.9858156028368794,
      "grad_norm": 1.3567222356796265,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.3179,
      "step": 139
    },
    {
      "epoch": 0.9929078014184397,
      "grad_norm": 3.067021608352661,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.446,
      "step": 140
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.8055833578109741,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.6873,
      "step": 141
    },
    {
      "epoch": 1.0070921985815602,
      "grad_norm": 0.7620219588279724,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.97,
      "step": 142
    },
    {
      "epoch": 1.0141843971631206,
      "grad_norm": 0.7523685097694397,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.8848,
      "step": 143
    },
    {
      "epoch": 1.0212765957446808,
      "grad_norm": 0.7327337265014648,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.8298,
      "step": 144
    },
    {
      "epoch": 1.0283687943262412,
      "grad_norm": 0.7034635543823242,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.8475,
      "step": 145
    },
    {
      "epoch": 1.0354609929078014,
      "grad_norm": 0.7120792269706726,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.762,
      "step": 146
    },
    {
      "epoch": 1.0425531914893618,
      "grad_norm": 0.6720845699310303,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.7217,
      "step": 147
    },
    {
      "epoch": 1.049645390070922,
      "grad_norm": 0.6797341108322144,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.6815,
      "step": 148
    },
    {
      "epoch": 1.0567375886524824,
      "grad_norm": 0.6580546498298645,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.6314,
      "step": 149
    },
    {
      "epoch": 1.0638297872340425,
      "grad_norm": 0.6475302577018738,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.581,
      "step": 150
    },
    {
      "epoch": 1.0638297872340425,
      "eval_loss": 0.572862982749939,
      "eval_runtime": 4.7895,
      "eval_samples_per_second": 49.692,
      "eval_steps_per_second": 12.527,
      "step": 150
    },
    {
      "epoch": 1.070921985815603,
      "grad_norm": 0.6567291021347046,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.6218,
      "step": 151
    },
    {
      "epoch": 1.0780141843971631,
      "grad_norm": 0.6199505925178528,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.6388,
      "step": 152
    },
    {
      "epoch": 1.0851063829787233,
      "grad_norm": 0.680757999420166,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.6442,
      "step": 153
    },
    {
      "epoch": 1.0921985815602837,
      "grad_norm": 0.6183621287345886,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.5102,
      "step": 154
    },
    {
      "epoch": 1.099290780141844,
      "grad_norm": 0.6224300265312195,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.5639,
      "step": 155
    },
    {
      "epoch": 1.1063829787234043,
      "grad_norm": 0.6107857823371887,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.5675,
      "step": 156
    },
    {
      "epoch": 1.1134751773049645,
      "grad_norm": 0.6195837259292603,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.4551,
      "step": 157
    },
    {
      "epoch": 1.1205673758865249,
      "grad_norm": 0.6741180419921875,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.5074,
      "step": 158
    },
    {
      "epoch": 1.127659574468085,
      "grad_norm": 0.6889761686325073,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.5106,
      "step": 159
    },
    {
      "epoch": 1.1347517730496455,
      "grad_norm": 0.7215981483459473,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.5301,
      "step": 160
    },
    {
      "epoch": 1.1418439716312057,
      "grad_norm": 0.6086937189102173,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.5091,
      "step": 161
    },
    {
      "epoch": 1.148936170212766,
      "grad_norm": 0.6391672492027283,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.4777,
      "step": 162
    },
    {
      "epoch": 1.1560283687943262,
      "grad_norm": 0.6463271975517273,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.4645,
      "step": 163
    },
    {
      "epoch": 1.1631205673758864,
      "grad_norm": 0.5843028426170349,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.3409,
      "step": 164
    },
    {
      "epoch": 1.1702127659574468,
      "grad_norm": 0.5878259539604187,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.3214,
      "step": 165
    },
    {
      "epoch": 1.177304964539007,
      "grad_norm": 0.6149991154670715,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.3949,
      "step": 166
    },
    {
      "epoch": 1.1843971631205674,
      "grad_norm": 0.6172844767570496,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.3944,
      "step": 167
    },
    {
      "epoch": 1.1914893617021276,
      "grad_norm": 0.590404748916626,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.3293,
      "step": 168
    },
    {
      "epoch": 1.198581560283688,
      "grad_norm": 0.593180775642395,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.3232,
      "step": 169
    },
    {
      "epoch": 1.2056737588652482,
      "grad_norm": 0.6218432784080505,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.2893,
      "step": 170
    },
    {
      "epoch": 1.2127659574468086,
      "grad_norm": 0.6478301286697388,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.3506,
      "step": 171
    },
    {
      "epoch": 1.2198581560283688,
      "grad_norm": 0.6458804607391357,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.2752,
      "step": 172
    },
    {
      "epoch": 1.226950354609929,
      "grad_norm": 0.6425474882125854,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.2805,
      "step": 173
    },
    {
      "epoch": 1.2340425531914894,
      "grad_norm": 0.86031574010849,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.2867,
      "step": 174
    },
    {
      "epoch": 1.2411347517730495,
      "grad_norm": 0.9669718146324158,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.2346,
      "step": 175
    },
    {
      "epoch": 1.24822695035461,
      "grad_norm": 2.3252344131469727,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.3444,
      "step": 176
    },
    {
      "epoch": 1.2553191489361701,
      "grad_norm": 0.6892974376678467,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.972,
      "step": 177
    },
    {
      "epoch": 1.2624113475177305,
      "grad_norm": 0.6964266300201416,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.8448,
      "step": 178
    },
    {
      "epoch": 1.2695035460992907,
      "grad_norm": 0.6308414340019226,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.8024,
      "step": 179
    },
    {
      "epoch": 1.2765957446808511,
      "grad_norm": 0.6421607136726379,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.7139,
      "step": 180
    },
    {
      "epoch": 1.2836879432624113,
      "grad_norm": 0.6400377750396729,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7137,
      "step": 181
    },
    {
      "epoch": 1.2907801418439715,
      "grad_norm": 0.6507327556610107,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.7303,
      "step": 182
    },
    {
      "epoch": 1.297872340425532,
      "grad_norm": 0.6380562782287598,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.6967,
      "step": 183
    },
    {
      "epoch": 1.3049645390070923,
      "grad_norm": 0.663581907749176,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.6911,
      "step": 184
    },
    {
      "epoch": 1.3120567375886525,
      "grad_norm": 0.6940181851387024,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.6766,
      "step": 185
    },
    {
      "epoch": 1.3191489361702127,
      "grad_norm": 0.6271922588348389,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.6185,
      "step": 186
    },
    {
      "epoch": 1.326241134751773,
      "grad_norm": 0.6617581248283386,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.6131,
      "step": 187
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.6716302037239075,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.6003,
      "step": 188
    },
    {
      "epoch": 1.3404255319148937,
      "grad_norm": 0.6330739855766296,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.6246,
      "step": 189
    },
    {
      "epoch": 1.3475177304964538,
      "grad_norm": 0.6464995741844177,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.5481,
      "step": 190
    },
    {
      "epoch": 1.3546099290780143,
      "grad_norm": 0.595725417137146,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.516,
      "step": 191
    },
    {
      "epoch": 1.3617021276595744,
      "grad_norm": 0.5912885665893555,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.4816,
      "step": 192
    },
    {
      "epoch": 1.3687943262411348,
      "grad_norm": 0.6033816337585449,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.4885,
      "step": 193
    },
    {
      "epoch": 1.375886524822695,
      "grad_norm": 0.6120988130569458,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.5061,
      "step": 194
    },
    {
      "epoch": 1.3829787234042552,
      "grad_norm": 0.6251870393753052,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.4762,
      "step": 195
    },
    {
      "epoch": 1.3900709219858156,
      "grad_norm": 0.585071861743927,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.4354,
      "step": 196
    },
    {
      "epoch": 1.397163120567376,
      "grad_norm": 0.6192173361778259,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.398,
      "step": 197
    },
    {
      "epoch": 1.4042553191489362,
      "grad_norm": 0.5994616150856018,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.3988,
      "step": 198
    },
    {
      "epoch": 1.4113475177304964,
      "grad_norm": 0.6203757524490356,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.4086,
      "step": 199
    },
    {
      "epoch": 1.4184397163120568,
      "grad_norm": 0.5554829835891724,
      "learning_rate": 0.0,
      "loss": 0.3529,
      "step": 200
    },
    {
      "epoch": 1.4184397163120568,
      "eval_loss": 0.5548466444015503,
      "eval_runtime": 4.7922,
      "eval_samples_per_second": 49.664,
      "eval_steps_per_second": 12.52,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 4.264962487536845e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}