{
  "best_metric": 0.07540635019540787,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 1.2573221757322175,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008368200836820083,
      "grad_norm": 3.4848103523254395,
      "learning_rate": 1e-05,
      "loss": 0.7472,
      "step": 1
    },
    {
      "epoch": 0.008368200836820083,
      "eval_loss": 1.5766565799713135,
      "eval_runtime": 4.0802,
      "eval_samples_per_second": 49.507,
      "eval_steps_per_second": 12.499,
      "step": 1
    },
    {
      "epoch": 0.016736401673640166,
      "grad_norm": 3.88921856880188,
      "learning_rate": 2e-05,
      "loss": 0.863,
      "step": 2
    },
    {
      "epoch": 0.02510460251046025,
      "grad_norm": 4.598084449768066,
      "learning_rate": 3e-05,
      "loss": 1.0088,
      "step": 3
    },
    {
      "epoch": 0.03347280334728033,
      "grad_norm": 3.6586599349975586,
      "learning_rate": 4e-05,
      "loss": 0.9831,
      "step": 4
    },
    {
      "epoch": 0.04184100418410042,
      "grad_norm": 3.121110677719116,
      "learning_rate": 5e-05,
      "loss": 0.9342,
      "step": 5
    },
    {
      "epoch": 0.0502092050209205,
      "grad_norm": 2.6722185611724854,
      "learning_rate": 6e-05,
      "loss": 0.8293,
      "step": 6
    },
    {
      "epoch": 0.058577405857740586,
      "grad_norm": 2.4001119136810303,
      "learning_rate": 7e-05,
      "loss": 0.6924,
      "step": 7
    },
    {
      "epoch": 0.06694560669456066,
      "grad_norm": 3.029315710067749,
      "learning_rate": 8e-05,
      "loss": 0.5698,
      "step": 8
    },
    {
      "epoch": 0.07531380753138076,
      "grad_norm": 2.597606658935547,
      "learning_rate": 9e-05,
      "loss": 0.4675,
      "step": 9
    },
    {
      "epoch": 0.08368200836820083,
      "grad_norm": 1.8661812543869019,
      "learning_rate": 0.0001,
      "loss": 0.3722,
      "step": 10
    },
    {
      "epoch": 0.09205020920502092,
      "grad_norm": 1.7599635124206543,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.2951,
      "step": 11
    },
    {
      "epoch": 0.100418410041841,
      "grad_norm": 1.6175488233566284,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.285,
      "step": 12
    },
    {
      "epoch": 0.1087866108786611,
      "grad_norm": 1.6192901134490967,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.2916,
      "step": 13
    },
    {
      "epoch": 0.11715481171548117,
      "grad_norm": 2.2023255825042725,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.2656,
      "step": 14
    },
    {
      "epoch": 0.12552301255230125,
      "grad_norm": 1.2332242727279663,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.2047,
      "step": 15
    },
    {
      "epoch": 0.13389121338912133,
      "grad_norm": 1.2950152158737183,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.2132,
      "step": 16
    },
    {
      "epoch": 0.14225941422594143,
      "grad_norm": 1.1822935342788696,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.1827,
      "step": 17
    },
    {
      "epoch": 0.1506276150627615,
      "grad_norm": 0.8956453204154968,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.1601,
      "step": 18
    },
    {
      "epoch": 0.1589958158995816,
      "grad_norm": 1.1256321668624878,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.2129,
      "step": 19
    },
    {
      "epoch": 0.16736401673640167,
      "grad_norm": 1.0068782567977905,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.1641,
      "step": 20
    },
    {
      "epoch": 0.17573221757322174,
      "grad_norm": 1.2121520042419434,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.2133,
      "step": 21
    },
    {
      "epoch": 0.18410041841004185,
      "grad_norm": 1.0212056636810303,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.1245,
      "step": 22
    },
    {
      "epoch": 0.19246861924686193,
      "grad_norm": 1.3977688550949097,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.1618,
      "step": 23
    },
    {
      "epoch": 0.200836820083682,
      "grad_norm": 1.0460073947906494,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.1903,
      "step": 24
    },
    {
      "epoch": 0.20920502092050208,
      "grad_norm": 1.0836344957351685,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.1523,
      "step": 25
    },
    {
      "epoch": 0.2175732217573222,
      "grad_norm": 0.9304505586624146,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.1322,
      "step": 26
    },
    {
      "epoch": 0.22594142259414227,
      "grad_norm": 1.1587389707565308,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.1123,
      "step": 27
    },
    {
      "epoch": 0.23430962343096234,
      "grad_norm": 1.9223076105117798,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.1,
      "step": 28
    },
    {
      "epoch": 0.24267782426778242,
      "grad_norm": 0.7539680600166321,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0602,
      "step": 29
    },
    {
      "epoch": 0.2510460251046025,
      "grad_norm": 4.452033519744873,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.4788,
      "step": 30
    },
    {
      "epoch": 0.2594142259414226,
      "grad_norm": 3.088981866836548,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.4023,
      "step": 31
    },
    {
      "epoch": 0.26778242677824265,
      "grad_norm": 2.3259027004241943,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.3357,
      "step": 32
    },
    {
      "epoch": 0.27615062761506276,
      "grad_norm": 1.3535948991775513,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.2125,
      "step": 33
    },
    {
      "epoch": 0.28451882845188287,
      "grad_norm": 0.6757339239120483,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.1745,
      "step": 34
    },
    {
      "epoch": 0.2928870292887029,
      "grad_norm": 0.997547447681427,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.1698,
      "step": 35
    },
    {
      "epoch": 0.301255230125523,
      "grad_norm": 1.2034856081008911,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.1886,
      "step": 36
    },
    {
      "epoch": 0.30962343096234307,
      "grad_norm": 1.122100591659546,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.1912,
      "step": 37
    },
    {
      "epoch": 0.3179916317991632,
      "grad_norm": 0.8844034075737,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.1782,
      "step": 38
    },
    {
      "epoch": 0.3263598326359833,
      "grad_norm": 0.4449402093887329,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.1225,
      "step": 39
    },
    {
      "epoch": 0.33472803347280333,
      "grad_norm": 0.5567941069602966,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.1362,
      "step": 40
    },
    {
      "epoch": 0.34309623430962344,
      "grad_norm": 0.6472607254981995,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.1481,
      "step": 41
    },
    {
      "epoch": 0.3514644351464435,
      "grad_norm": 0.5753950476646423,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.1365,
      "step": 42
    },
    {
      "epoch": 0.3598326359832636,
      "grad_norm": 0.5642210841178894,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.1053,
      "step": 43
    },
    {
      "epoch": 0.3682008368200837,
      "grad_norm": 0.4673701524734497,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.1113,
      "step": 44
    },
    {
      "epoch": 0.37656903765690375,
      "grad_norm": 0.8079649806022644,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.1491,
      "step": 45
    },
    {
      "epoch": 0.38493723849372385,
      "grad_norm": 0.8153290152549744,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.1367,
      "step": 46
    },
    {
      "epoch": 0.39330543933054396,
      "grad_norm": 0.6437317728996277,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.0991,
      "step": 47
    },
    {
      "epoch": 0.401673640167364,
      "grad_norm": 0.6529302000999451,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1035,
      "step": 48
    },
    {
      "epoch": 0.4100418410041841,
      "grad_norm": 0.5692593455314636,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.0992,
      "step": 49
    },
    {
      "epoch": 0.41841004184100417,
      "grad_norm": 0.5359004735946655,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.1008,
      "step": 50
    },
    {
      "epoch": 0.41841004184100417,
      "eval_loss": 0.15166662633419037,
      "eval_runtime": 4.0723,
      "eval_samples_per_second": 49.604,
      "eval_steps_per_second": 12.524,
      "step": 50
    },
    {
      "epoch": 0.42677824267782427,
      "grad_norm": 0.5589534640312195,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.11,
      "step": 51
    },
    {
      "epoch": 0.4351464435146444,
      "grad_norm": 0.5620235204696655,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.0946,
      "step": 52
    },
    {
      "epoch": 0.4435146443514644,
      "grad_norm": 0.8351897597312927,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.1539,
      "step": 53
    },
    {
      "epoch": 0.45188284518828453,
      "grad_norm": 0.6207558512687683,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.1107,
      "step": 54
    },
    {
      "epoch": 0.4602510460251046,
      "grad_norm": 0.7445648312568665,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.1152,
      "step": 55
    },
    {
      "epoch": 0.4686192468619247,
      "grad_norm": 0.628424346446991,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.0807,
      "step": 56
    },
    {
      "epoch": 0.4769874476987448,
      "grad_norm": 0.5635355114936829,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.0555,
      "step": 57
    },
    {
      "epoch": 0.48535564853556484,
      "grad_norm": 1.0648820400238037,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.0634,
      "step": 58
    },
    {
      "epoch": 0.49372384937238495,
      "grad_norm": 1.8602968454360962,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.2547,
      "step": 59
    },
    {
      "epoch": 0.502092050209205,
      "grad_norm": 1.5479875802993774,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.3128,
      "step": 60
    },
    {
      "epoch": 0.5104602510460251,
      "grad_norm": 1.3398643732070923,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.2635,
      "step": 61
    },
    {
      "epoch": 0.5188284518828452,
      "grad_norm": 0.9705513119697571,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.2057,
      "step": 62
    },
    {
      "epoch": 0.5271966527196653,
      "grad_norm": 0.7675544619560242,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.178,
      "step": 63
    },
    {
      "epoch": 0.5355648535564853,
      "grad_norm": 0.7129813432693481,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.1655,
      "step": 64
    },
    {
      "epoch": 0.5439330543933054,
      "grad_norm": 0.7832943201065063,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.1606,
      "step": 65
    },
    {
      "epoch": 0.5523012552301255,
      "grad_norm": 0.7569060325622559,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.143,
      "step": 66
    },
    {
      "epoch": 0.5606694560669456,
      "grad_norm": 0.7445584535598755,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.128,
      "step": 67
    },
    {
      "epoch": 0.5690376569037657,
      "grad_norm": 0.5912233591079712,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.1289,
      "step": 68
    },
    {
      "epoch": 0.5774058577405857,
      "grad_norm": 0.5939972996711731,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.1251,
      "step": 69
    },
    {
      "epoch": 0.5857740585774058,
      "grad_norm": 0.5252910852432251,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.1211,
      "step": 70
    },
    {
      "epoch": 0.5941422594142259,
      "grad_norm": 0.5812236666679382,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.1478,
      "step": 71
    },
    {
      "epoch": 0.602510460251046,
      "grad_norm": 0.46988946199417114,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.1213,
      "step": 72
    },
    {
      "epoch": 0.6108786610878661,
      "grad_norm": 0.4680638611316681,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.1172,
      "step": 73
    },
    {
      "epoch": 0.6192468619246861,
      "grad_norm": 0.4192774295806885,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.1102,
      "step": 74
    },
    {
      "epoch": 0.6276150627615062,
      "grad_norm": 0.4939725995063782,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.112,
      "step": 75
    },
    {
      "epoch": 0.6359832635983264,
      "grad_norm": 0.3755834102630615,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.0967,
      "step": 76
    },
    {
      "epoch": 0.6443514644351465,
      "grad_norm": 0.4578147530555725,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.092,
      "step": 77
    },
    {
      "epoch": 0.6527196652719666,
      "grad_norm": 0.34847137331962585,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.0872,
      "step": 78
    },
    {
      "epoch": 0.6610878661087866,
      "grad_norm": 0.6222680807113647,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.1088,
      "step": 79
    },
    {
      "epoch": 0.6694560669456067,
      "grad_norm": 0.3839572072029114,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.0883,
      "step": 80
    },
    {
      "epoch": 0.6778242677824268,
      "grad_norm": 0.6254891157150269,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.0723,
      "step": 81
    },
    {
      "epoch": 0.6861924686192469,
      "grad_norm": 0.4347880780696869,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.0798,
      "step": 82
    },
    {
      "epoch": 0.694560669456067,
      "grad_norm": 0.5865311622619629,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.0801,
      "step": 83
    },
    {
      "epoch": 0.702928870292887,
      "grad_norm": 0.3609165549278259,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.056,
      "step": 84
    },
    {
      "epoch": 0.7112970711297071,
      "grad_norm": 0.5713534951210022,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.0781,
      "step": 85
    },
    {
      "epoch": 0.7196652719665272,
      "grad_norm": 0.8238276243209839,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0878,
      "step": 86
    },
    {
      "epoch": 0.7280334728033473,
      "grad_norm": 0.7100816369056702,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.0299,
      "step": 87
    },
    {
      "epoch": 0.7364016736401674,
      "grad_norm": 1.6119959354400635,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.1945,
      "step": 88
    },
    {
      "epoch": 0.7447698744769874,
      "grad_norm": 1.3309483528137207,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.2027,
      "step": 89
    },
    {
      "epoch": 0.7531380753138075,
      "grad_norm": 1.1444945335388184,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.1986,
      "step": 90
    },
    {
      "epoch": 0.7615062761506276,
      "grad_norm": 0.9420828223228455,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.1783,
      "step": 91
    },
    {
      "epoch": 0.7698744769874477,
      "grad_norm": 0.7960387468338013,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.1642,
      "step": 92
    },
    {
      "epoch": 0.7782426778242678,
      "grad_norm": 0.6485269069671631,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.1292,
      "step": 93
    },
    {
      "epoch": 0.7866108786610879,
      "grad_norm": 0.7513681650161743,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.1737,
      "step": 94
    },
    {
      "epoch": 0.7949790794979079,
      "grad_norm": 0.6703801155090332,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.1357,
      "step": 95
    },
    {
      "epoch": 0.803347280334728,
      "grad_norm": 0.7546550035476685,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.1346,
      "step": 96
    },
    {
      "epoch": 0.8117154811715481,
      "grad_norm": 0.5935238003730774,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.1048,
      "step": 97
    },
    {
      "epoch": 0.8200836820083682,
      "grad_norm": 0.4116928279399872,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0998,
      "step": 98
    },
    {
      "epoch": 0.8284518828451883,
      "grad_norm": 0.5409568548202515,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.1126,
      "step": 99
    },
    {
      "epoch": 0.8368200836820083,
      "grad_norm": 0.5066820979118347,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.1014,
      "step": 100
    },
    {
      "epoch": 0.8368200836820083,
      "eval_loss": 0.10415530204772949,
      "eval_runtime": 4.076,
      "eval_samples_per_second": 49.558,
      "eval_steps_per_second": 12.512,
      "step": 100
    },
    {
      "epoch": 0.8451882845188284,
      "grad_norm": 0.40647611021995544,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.1071,
      "step": 101
    },
    {
      "epoch": 0.8535564853556485,
      "grad_norm": 0.3912857472896576,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.0873,
      "step": 102
    },
    {
      "epoch": 0.8619246861924686,
      "grad_norm": 0.4201953411102295,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.0937,
      "step": 103
    },
    {
      "epoch": 0.8702928870292888,
      "grad_norm": 0.45583081245422363,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.0906,
      "step": 104
    },
    {
      "epoch": 0.8786610878661087,
      "grad_norm": 0.39570245146751404,
      "learning_rate": 5e-05,
      "loss": 0.0873,
      "step": 105
    },
    {
      "epoch": 0.8870292887029289,
      "grad_norm": 0.45384737849235535,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.1021,
      "step": 106
    },
    {
      "epoch": 0.895397489539749,
      "grad_norm": 0.40736356377601624,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.0887,
      "step": 107
    },
    {
      "epoch": 0.9037656903765691,
      "grad_norm": 0.42815500497817993,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.0755,
      "step": 108
    },
    {
      "epoch": 0.9121338912133892,
      "grad_norm": 0.3796560764312744,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.0783,
      "step": 109
    },
    {
      "epoch": 0.9205020920502092,
      "grad_norm": 0.43120044469833374,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.079,
      "step": 110
    },
    {
      "epoch": 0.9288702928870293,
      "grad_norm": 0.4474979341030121,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.0907,
      "step": 111
    },
    {
      "epoch": 0.9372384937238494,
      "grad_norm": 0.3411693274974823,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.0518,
      "step": 112
    },
    {
      "epoch": 0.9456066945606695,
      "grad_norm": 0.430654913187027,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.0606,
      "step": 113
    },
    {
      "epoch": 0.9539748953974896,
      "grad_norm": 0.4269810616970062,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.0623,
      "step": 114
    },
    {
      "epoch": 0.9623430962343096,
      "grad_norm": 0.4438549876213074,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.0568,
      "step": 115
    },
    {
      "epoch": 0.9707112970711297,
      "grad_norm": 0.9744530916213989,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.0582,
      "step": 116
    },
    {
      "epoch": 0.9790794979079498,
      "grad_norm": 0.8297134041786194,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.1539,
      "step": 117
    },
    {
      "epoch": 0.9874476987447699,
      "grad_norm": 0.795654833316803,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.1596,
      "step": 118
    },
    {
      "epoch": 0.99581589958159,
      "grad_norm": 0.4995171129703522,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.0761,
      "step": 119
    },
    {
      "epoch": 1.006276150627615,
      "grad_norm": 0.9617952704429626,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.138,
      "step": 120
    },
    {
      "epoch": 1.0146443514644352,
      "grad_norm": 0.5126711130142212,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.1132,
      "step": 121
    },
    {
      "epoch": 1.0230125523012552,
      "grad_norm": 0.4848877191543579,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.1071,
      "step": 122
    },
    {
      "epoch": 1.0313807531380754,
      "grad_norm": 0.44112974405288696,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.1004,
      "step": 123
    },
    {
      "epoch": 1.0397489539748954,
      "grad_norm": 0.5203883647918701,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.1179,
      "step": 124
    },
    {
      "epoch": 1.0481171548117154,
      "grad_norm": 0.4299384653568268,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.1128,
      "step": 125
    },
    {
      "epoch": 1.0564853556485356,
      "grad_norm": 0.36720457673072815,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.0803,
      "step": 126
    },
    {
      "epoch": 1.0648535564853556,
      "grad_norm": 0.38658344745635986,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.0782,
      "step": 127
    },
    {
      "epoch": 1.0732217573221758,
      "grad_norm": 0.42113763093948364,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.0871,
      "step": 128
    },
    {
      "epoch": 1.0815899581589958,
      "grad_norm": 0.31596583127975464,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.0754,
      "step": 129
    },
    {
      "epoch": 1.0899581589958158,
      "grad_norm": 0.4931642711162567,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.083,
      "step": 130
    },
    {
      "epoch": 1.098326359832636,
      "grad_norm": 0.5247243046760559,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.0955,
      "step": 131
    },
    {
      "epoch": 1.106694560669456,
      "grad_norm": 0.5747186541557312,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.1038,
      "step": 132
    },
    {
      "epoch": 1.1150627615062763,
      "grad_norm": 0.48280155658721924,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.0817,
      "step": 133
    },
    {
      "epoch": 1.1234309623430963,
      "grad_norm": 0.40240225195884705,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.0714,
      "step": 134
    },
    {
      "epoch": 1.1317991631799162,
      "grad_norm": 0.5216189026832581,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.0755,
      "step": 135
    },
    {
      "epoch": 1.1401673640167365,
      "grad_norm": 0.4143962860107422,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.0726,
      "step": 136
    },
    {
      "epoch": 1.1485355648535565,
      "grad_norm": 0.33933359384536743,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.057,
      "step": 137
    },
    {
      "epoch": 1.1569037656903767,
      "grad_norm": 0.44673094153404236,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.0569,
      "step": 138
    },
    {
      "epoch": 1.1652719665271967,
      "grad_norm": 0.5124291181564331,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.0813,
      "step": 139
    },
    {
      "epoch": 1.1736401673640167,
      "grad_norm": 0.5399123430252075,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.0778,
      "step": 140
    },
    {
      "epoch": 1.1820083682008369,
      "grad_norm": 0.3727053999900818,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.0579,
      "step": 141
    },
    {
      "epoch": 1.1903765690376569,
      "grad_norm": 0.4652441740036011,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.0662,
      "step": 142
    },
    {
      "epoch": 1.198744769874477,
      "grad_norm": 0.47085118293762207,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0554,
      "step": 143
    },
    {
      "epoch": 1.207112970711297,
      "grad_norm": 0.5209120512008667,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.0774,
      "step": 144
    },
    {
      "epoch": 1.215481171548117,
      "grad_norm": 0.4766678214073181,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.0639,
      "step": 145
    },
    {
      "epoch": 1.2238493723849373,
      "grad_norm": 0.4801768362522125,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.0537,
      "step": 146
    },
    {
      "epoch": 1.2322175732217573,
      "grad_norm": 0.5006198883056641,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.0554,
      "step": 147
    },
    {
      "epoch": 1.2405857740585775,
      "grad_norm": 0.25908923149108887,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.0186,
      "step": 148
    },
    {
      "epoch": 1.2489539748953975,
      "grad_norm": 0.3488486409187317,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.0464,
      "step": 149
    },
    {
      "epoch": 1.2573221757322175,
      "grad_norm": 0.339759886264801,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0755,
      "step": 150
    },
    {
      "epoch": 1.2573221757322175,
      "eval_loss": 0.07540635019540787,
      "eval_runtime": 4.0734,
      "eval_samples_per_second": 49.59,
      "eval_steps_per_second": 12.52,
      "step": 150
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.19972177870848e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}