{
  "best_metric": 11.01180648803711,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.0066445182724253,
  "eval_steps": 100,
  "global_step": 113,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008859357696566999,
      "grad_norm": 1.7000117301940918,
      "learning_rate": 2e-05,
      "loss": 88.7471,
      "step": 1
    },
    {
      "epoch": 0.008859357696566999,
      "eval_loss": 11.089943885803223,
      "eval_runtime": 1.0596,
      "eval_samples_per_second": 179.311,
      "eval_steps_per_second": 45.3,
      "step": 1
    },
    {
      "epoch": 0.017718715393133997,
      "grad_norm": 1.9952071905136108,
      "learning_rate": 4e-05,
      "loss": 88.7374,
      "step": 2
    },
    {
      "epoch": 0.026578073089700997,
      "grad_norm": 1.8046919107437134,
      "learning_rate": 6e-05,
      "loss": 88.7934,
      "step": 3
    },
    {
      "epoch": 0.035437430786267994,
      "grad_norm": 1.8296611309051514,
      "learning_rate": 8e-05,
      "loss": 88.7156,
      "step": 4
    },
    {
      "epoch": 0.044296788482835,
      "grad_norm": 1.87436044216156,
      "learning_rate": 0.0001,
      "loss": 88.7446,
      "step": 5
    },
    {
      "epoch": 0.053156146179401995,
      "grad_norm": 1.8545674085617065,
      "learning_rate": 0.00012,
      "loss": 88.8033,
      "step": 6
    },
    {
      "epoch": 0.06201550387596899,
      "grad_norm": 1.7815138101577759,
      "learning_rate": 0.00014,
      "loss": 88.7283,
      "step": 7
    },
    {
      "epoch": 0.07087486157253599,
      "grad_norm": 2.0521814823150635,
      "learning_rate": 0.00016,
      "loss": 88.7129,
      "step": 8
    },
    {
      "epoch": 0.07973421926910298,
      "grad_norm": 1.9217674732208252,
      "learning_rate": 0.00018,
      "loss": 88.659,
      "step": 9
    },
    {
      "epoch": 0.08859357696567,
      "grad_norm": 1.9446423053741455,
      "learning_rate": 0.0002,
      "loss": 88.6336,
      "step": 10
    },
    {
      "epoch": 0.09745293466223699,
      "grad_norm": 1.8381359577178955,
      "learning_rate": 0.00019995348836233516,
      "loss": 88.7198,
      "step": 11
    },
    {
      "epoch": 0.10631229235880399,
      "grad_norm": 1.9090080261230469,
      "learning_rate": 0.00019981399671598939,
      "loss": 88.6303,
      "step": 12
    },
    {
      "epoch": 0.11517165005537099,
      "grad_norm": 1.8912723064422607,
      "learning_rate": 0.00019958165482066094,
      "loss": 88.6177,
      "step": 13
    },
    {
      "epoch": 0.12403100775193798,
      "grad_norm": 1.9282634258270264,
      "learning_rate": 0.0001992566788083908,
      "loss": 88.5971,
      "step": 14
    },
    {
      "epoch": 0.132890365448505,
      "grad_norm": 1.6373441219329834,
      "learning_rate": 0.00019883937098250963,
      "loss": 88.6673,
      "step": 15
    },
    {
      "epoch": 0.14174972314507198,
      "grad_norm": 1.9328405857086182,
      "learning_rate": 0.00019833011953642525,
      "loss": 88.632,
      "step": 16
    },
    {
      "epoch": 0.150609080841639,
      "grad_norm": 2.005837917327881,
      "learning_rate": 0.0001977293981925125,
      "loss": 88.6044,
      "step": 17
    },
    {
      "epoch": 0.15946843853820597,
      "grad_norm": 1.9346294403076172,
      "learning_rate": 0.00019703776576144105,
      "loss": 88.6249,
      "step": 18
    },
    {
      "epoch": 0.16832779623477298,
      "grad_norm": 1.9649502038955688,
      "learning_rate": 0.0001962558656223516,
      "loss": 88.5367,
      "step": 19
    },
    {
      "epoch": 0.17718715393134,
      "grad_norm": 1.8136121034622192,
      "learning_rate": 0.00019538442512436328,
      "loss": 88.5989,
      "step": 20
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 2.0163049697875977,
      "learning_rate": 0.00019442425490996988,
      "loss": 88.6022,
      "step": 21
    },
    {
      "epoch": 0.19490586932447398,
      "grad_norm": 1.772336483001709,
      "learning_rate": 0.00019337624816095358,
      "loss": 88.5585,
      "step": 22
    },
    {
      "epoch": 0.20376522702104097,
      "grad_norm": 1.5951476097106934,
      "learning_rate": 0.00019224137976751795,
      "loss": 88.5738,
      "step": 23
    },
    {
      "epoch": 0.21262458471760798,
      "grad_norm": 1.623684287071228,
      "learning_rate": 0.00019102070542141328,
      "loss": 88.5241,
      "step": 24
    },
    {
      "epoch": 0.22148394241417496,
      "grad_norm": 1.7089464664459229,
      "learning_rate": 0.00018971536063389744,
      "loss": 88.5202,
      "step": 25
    },
    {
      "epoch": 0.23034330011074197,
      "grad_norm": 1.8459341526031494,
      "learning_rate": 0.00018832655967944607,
      "loss": 88.4915,
      "step": 26
    },
    {
      "epoch": 0.23920265780730898,
      "grad_norm": 1.7073566913604736,
      "learning_rate": 0.0001868555944661949,
      "loss": 88.4679,
      "step": 27
    },
    {
      "epoch": 0.24806201550387597,
      "grad_norm": 1.6638760566711426,
      "learning_rate": 0.00018530383333416418,
      "loss": 88.5159,
      "step": 28
    },
    {
      "epoch": 0.25692137320044295,
      "grad_norm": 1.7694356441497803,
      "learning_rate": 0.0001836727197823842,
      "loss": 88.4419,
      "step": 29
    },
    {
      "epoch": 0.26578073089701,
      "grad_norm": 1.5755650997161865,
      "learning_rate": 0.00018196377112610526,
      "loss": 88.5145,
      "step": 30
    },
    {
      "epoch": 0.27464008859357697,
      "grad_norm": 1.6858540773391724,
      "learning_rate": 0.00018017857708534107,
      "loss": 88.4256,
      "step": 31
    },
    {
      "epoch": 0.28349944629014395,
      "grad_norm": 1.6921030282974243,
      "learning_rate": 0.00017831879830605937,
      "loss": 88.4547,
      "step": 32
    },
    {
      "epoch": 0.292358803986711,
      "grad_norm": 1.6553444862365723,
      "learning_rate": 0.0001763861648153945,
      "loss": 88.444,
      "step": 33
    },
    {
      "epoch": 0.301218161683278,
      "grad_norm": 1.6478825807571411,
      "learning_rate": 0.0001743824744123196,
      "loss": 88.4493,
      "step": 34
    },
    {
      "epoch": 0.31007751937984496,
      "grad_norm": 1.6460453271865845,
      "learning_rate": 0.00017230959099527512,
      "loss": 88.4299,
      "step": 35
    },
    {
      "epoch": 0.31893687707641194,
      "grad_norm": 1.63612699508667,
      "learning_rate": 0.00017016944282830933,
      "loss": 88.3685,
      "step": 36
    },
    {
      "epoch": 0.327796234772979,
      "grad_norm": 1.7421164512634277,
      "learning_rate": 0.00016796402074734402,
      "loss": 88.4323,
      "step": 37
    },
    {
      "epoch": 0.33665559246954596,
      "grad_norm": 1.6525160074234009,
      "learning_rate": 0.00016569537630823383,
      "loss": 88.4168,
      "step": 38
    },
    {
      "epoch": 0.34551495016611294,
      "grad_norm": 1.7259595394134521,
      "learning_rate": 0.00016336561987834153,
      "loss": 88.3543,
      "step": 39
    },
    {
      "epoch": 0.35437430786268,
      "grad_norm": 1.5089702606201172,
      "learning_rate": 0.00016097691867340545,
      "loss": 88.3855,
      "step": 40
    },
    {
      "epoch": 0.36323366555924697,
      "grad_norm": 1.7765790224075317,
      "learning_rate": 0.00015853149474152423,
      "loss": 88.4514,
      "step": 41
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 1.8243776559829712,
      "learning_rate": 0.00015603162289613503,
      "loss": 88.4046,
      "step": 42
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 1.8020275831222534,
      "learning_rate": 0.00015347962859990744,
      "loss": 88.3666,
      "step": 43
    },
    {
      "epoch": 0.38981173864894797,
      "grad_norm": 1.634013295173645,
      "learning_rate": 0.00015087788580152206,
      "loss": 88.4025,
      "step": 44
    },
    {
      "epoch": 0.39867109634551495,
      "grad_norm": 1.8167768716812134,
      "learning_rate": 0.00014822881472734562,
      "loss": 88.3001,
      "step": 45
    },
    {
      "epoch": 0.40753045404208194,
      "grad_norm": 1.8726773262023926,
      "learning_rate": 0.0001455348796300571,
      "loss": 88.2561,
      "step": 46
    },
    {
      "epoch": 0.416389811738649,
      "grad_norm": 1.6560800075531006,
      "learning_rate": 0.0001427985864963193,
      "loss": 88.3241,
      "step": 47
    },
    {
      "epoch": 0.42524916943521596,
      "grad_norm": 1.8344228267669678,
      "learning_rate": 0.0001400224807156278,
      "loss": 88.3057,
      "step": 48
    },
    {
      "epoch": 0.43410852713178294,
      "grad_norm": 1.7484591007232666,
      "learning_rate": 0.00013720914471250644,
      "loss": 88.3512,
      "step": 49
    },
    {
      "epoch": 0.4429678848283499,
      "grad_norm": 1.8629359006881714,
      "learning_rate": 0.00013436119554425133,
      "loss": 88.2738,
      "step": 50
    },
    {
      "epoch": 0.45182724252491696,
      "grad_norm": 1.7476680278778076,
      "learning_rate": 0.0001314812824664585,
      "loss": 88.2808,
      "step": 51
    },
    {
      "epoch": 0.46068660022148394,
      "grad_norm": 1.9814788103103638,
      "learning_rate": 0.0001285720844685996,
      "loss": 88.268,
      "step": 52
    },
    {
      "epoch": 0.4695459579180509,
      "grad_norm": 1.8949189186096191,
      "learning_rate": 0.00012563630778193805,
      "loss": 88.2733,
      "step": 53
    },
    {
      "epoch": 0.47840531561461797,
      "grad_norm": 1.5467251539230347,
      "learning_rate": 0.00012267668336210413,
      "loss": 88.3703,
      "step": 54
    },
    {
      "epoch": 0.48726467331118495,
      "grad_norm": 1.8193094730377197,
      "learning_rate": 0.00011969596434867063,
      "loss": 88.2722,
      "step": 55
    },
    {
      "epoch": 0.49612403100775193,
      "grad_norm": 1.8863904476165771,
      "learning_rate": 0.00011669692350409223,
      "loss": 88.2492,
      "step": 56
    },
    {
      "epoch": 0.5049833887043189,
      "grad_norm": 1.7994129657745361,
      "learning_rate": 0.00011368235063439103,
      "loss": 88.1733,
      "step": 57
    },
    {
      "epoch": 0.5138427464008859,
      "grad_norm": 1.7645139694213867,
      "learning_rate": 0.00011065504999398762,
      "loss": 88.2902,
      "step": 58
    },
    {
      "epoch": 0.5227021040974529,
      "grad_norm": 1.7159887552261353,
      "learning_rate": 0.00010761783767709182,
      "loss": 88.2566,
      "step": 59
    },
    {
      "epoch": 0.53156146179402,
      "grad_norm": 1.5432287454605103,
      "learning_rate": 0.00010457353899807946,
      "loss": 88.2397,
      "step": 60
    },
    {
      "epoch": 0.540420819490587,
      "grad_norm": 1.6790579557418823,
      "learning_rate": 0.0001015249858632926,
      "loss": 88.2717,
      "step": 61
    },
    {
      "epoch": 0.5492801771871539,
      "grad_norm": 1.6221708059310913,
      "learning_rate": 9.847501413670742e-05,
      "loss": 88.1482,
      "step": 62
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 1.6908060312271118,
      "learning_rate": 9.542646100192056e-05,
      "loss": 88.1413,
      "step": 63
    },
    {
      "epoch": 0.5669988925802879,
      "grad_norm": 1.5770460367202759,
      "learning_rate": 9.238216232290822e-05,
      "loss": 88.2858,
      "step": 64
    },
    {
      "epoch": 0.5758582502768549,
      "grad_norm": 1.6058683395385742,
      "learning_rate": 8.93449500060124e-05,
      "loss": 88.2268,
      "step": 65
    },
    {
      "epoch": 0.584717607973422,
      "grad_norm": 1.5394655466079712,
      "learning_rate": 8.6317649365609e-05,
      "loss": 88.2221,
      "step": 66
    },
    {
      "epoch": 0.593576965669989,
      "grad_norm": 1.5921432971954346,
      "learning_rate": 8.33030764959078e-05,
      "loss": 88.1241,
      "step": 67
    },
    {
      "epoch": 0.602436323366556,
      "grad_norm": 1.553252935409546,
      "learning_rate": 8.030403565132942e-05,
      "loss": 88.1573,
      "step": 68
    },
    {
      "epoch": 0.6112956810631229,
      "grad_norm": 1.7506428956985474,
      "learning_rate": 7.732331663789592e-05,
      "loss": 88.2591,
      "step": 69
    },
    {
      "epoch": 0.6201550387596899,
      "grad_norm": 1.4636502265930176,
      "learning_rate": 7.436369221806201e-05,
      "loss": 88.2353,
      "step": 70
    },
    {
      "epoch": 0.6290143964562569,
      "grad_norm": 1.5952634811401367,
      "learning_rate": 7.142791553140045e-05,
      "loss": 88.1222,
      "step": 71
    },
    {
      "epoch": 0.6378737541528239,
      "grad_norm": 1.4096498489379883,
      "learning_rate": 6.851871753354153e-05,
      "loss": 88.1584,
      "step": 72
    },
    {
      "epoch": 0.646733111849391,
      "grad_norm": 1.4336620569229126,
      "learning_rate": 6.563880445574873e-05,
      "loss": 88.2297,
      "step": 73
    },
    {
      "epoch": 0.655592469545958,
      "grad_norm": 1.530969500541687,
      "learning_rate": 6.279085528749359e-05,
      "loss": 88.0665,
      "step": 74
    },
    {
      "epoch": 0.6644518272425249,
      "grad_norm": 1.375839114189148,
      "learning_rate": 5.9977519284372194e-05,
      "loss": 88.1804,
      "step": 75
    },
    {
      "epoch": 0.6733111849390919,
      "grad_norm": 1.5607173442840576,
      "learning_rate": 5.720141350368072e-05,
      "loss": 88.1716,
      "step": 76
    },
    {
      "epoch": 0.6821705426356589,
      "grad_norm": 1.380002498626709,
      "learning_rate": 5.446512036994287e-05,
      "loss": 88.2189,
      "step": 77
    },
    {
      "epoch": 0.6910299003322259,
      "grad_norm": 1.3200513124465942,
      "learning_rate": 5.177118527265438e-05,
      "loss": 88.1267,
      "step": 78
    },
    {
      "epoch": 0.6998892580287929,
      "grad_norm": 1.3193778991699219,
      "learning_rate": 4.912211419847794e-05,
      "loss": 88.1561,
      "step": 79
    },
    {
      "epoch": 0.70874861572536,
      "grad_norm": 1.5167840719223022,
      "learning_rate": 4.652037140009259e-05,
      "loss": 88.1425,
      "step": 80
    },
    {
      "epoch": 0.717607973421927,
      "grad_norm": 1.4421601295471191,
      "learning_rate": 4.3968377103865024e-05,
      "loss": 88.1163,
      "step": 81
    },
    {
      "epoch": 0.7264673311184939,
      "grad_norm": 1.406391978263855,
      "learning_rate": 4.146850525847579e-05,
      "loss": 88.1702,
      "step": 82
    },
    {
      "epoch": 0.7353266888150609,
      "grad_norm": 1.4038128852844238,
      "learning_rate": 3.902308132659457e-05,
      "loss": 88.0944,
      "step": 83
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 1.3674670457839966,
      "learning_rate": 3.663438012165848e-05,
      "loss": 88.1737,
      "step": 84
    },
    {
      "epoch": 0.7530454042081949,
      "grad_norm": 1.3968989849090576,
      "learning_rate": 3.430462369176619e-05,
      "loss": 88.1595,
      "step": 85
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 1.4933903217315674,
      "learning_rate": 3.203597925265598e-05,
      "loss": 88.2609,
      "step": 86
    },
    {
      "epoch": 0.770764119601329,
      "grad_norm": 1.5437737703323364,
      "learning_rate": 2.98305571716907e-05,
      "loss": 88.1411,
      "step": 87
    },
    {
      "epoch": 0.7796234772978959,
      "grad_norm": 1.2470422983169556,
      "learning_rate": 2.769040900472488e-05,
      "loss": 88.1128,
      "step": 88
    },
    {
      "epoch": 0.7884828349944629,
      "grad_norm": 1.2969799041748047,
      "learning_rate": 2.5617525587680402e-05,
      "loss": 88.2228,
      "step": 89
    },
    {
      "epoch": 0.7973421926910299,
      "grad_norm": 1.4092624187469482,
      "learning_rate": 2.3613835184605525e-05,
      "loss": 88.2412,
      "step": 90
    },
    {
      "epoch": 0.8062015503875969,
      "grad_norm": 1.2208858728408813,
      "learning_rate": 2.1681201693940668e-05,
      "loss": 88.0666,
      "step": 91
    },
    {
      "epoch": 0.8150609080841639,
      "grad_norm": 1.3910318613052368,
      "learning_rate": 1.982142291465896e-05,
      "loss": 88.1084,
      "step": 92
    },
    {
      "epoch": 0.8239202657807309,
      "grad_norm": 1.4518864154815674,
      "learning_rate": 1.8036228873894746e-05,
      "loss": 88.1844,
      "step": 93
    },
    {
      "epoch": 0.832779623477298,
      "grad_norm": 1.4225211143493652,
      "learning_rate": 1.6327280217615792e-05,
      "loss": 88.1233,
      "step": 94
    },
    {
      "epoch": 0.8416389811738649,
      "grad_norm": 1.3186362981796265,
      "learning_rate": 1.4696166665835853e-05,
      "loss": 88.1479,
      "step": 95
    },
    {
      "epoch": 0.8504983388704319,
      "grad_norm": 1.3430944681167603,
      "learning_rate": 1.3144405533805138e-05,
      "loss": 88.077,
      "step": 96
    },
    {
      "epoch": 0.8593576965669989,
      "grad_norm": 1.212870478630066,
      "learning_rate": 1.167344032055394e-05,
      "loss": 88.107,
      "step": 97
    },
    {
      "epoch": 0.8682170542635659,
      "grad_norm": 1.360379934310913,
      "learning_rate": 1.02846393661026e-05,
      "loss": 88.0353,
      "step": 98
    },
    {
      "epoch": 0.8770764119601329,
      "grad_norm": 1.258919596672058,
      "learning_rate": 8.979294578586738e-06,
      "loss": 88.0631,
      "step": 99
    },
    {
      "epoch": 0.8859357696566998,
      "grad_norm": 1.4021327495574951,
      "learning_rate": 7.758620232482084e-06,
      "loss": 88.0937,
      "step": 100
    },
    {
      "epoch": 0.8859357696566998,
      "eval_loss": 11.01180648803711,
      "eval_runtime": 0.6808,
      "eval_samples_per_second": 279.069,
      "eval_steps_per_second": 70.502,
      "step": 100
    },
    {
      "epoch": 0.8947951273532669,
      "grad_norm": 1.4452682733535767,
      "learning_rate": 6.623751839046455e-06,
      "loss": 88.1532,
      "step": 101
    },
    {
      "epoch": 0.9036544850498339,
      "grad_norm": 1.3395559787750244,
      "learning_rate": 5.575745090030138e-06,
      "loss": 88.1788,
      "step": 102
    },
    {
      "epoch": 0.9125138427464009,
      "grad_norm": 1.4853826761245728,
      "learning_rate": 4.61557487563673e-06,
      "loss": 88.1785,
      "step": 103
    },
    {
      "epoch": 0.9213732004429679,
      "grad_norm": 1.385549545288086,
      "learning_rate": 3.7441343776484117e-06,
      "loss": 88.1602,
      "step": 104
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 1.4303137063980103,
      "learning_rate": 2.9622342385589254e-06,
      "loss": 88.0615,
      "step": 105
    },
    {
      "epoch": 0.9390919158361019,
      "grad_norm": 1.3606700897216797,
      "learning_rate": 2.2706018074875045e-06,
      "loss": 88.1822,
      "step": 106
    },
    {
      "epoch": 0.9479512735326688,
      "grad_norm": 1.3698482513427734,
      "learning_rate": 1.6698804635747579e-06,
      "loss": 88.1556,
      "step": 107
    },
    {
      "epoch": 0.9568106312292359,
      "grad_norm": 1.4697903394699097,
      "learning_rate": 1.160629017490389e-06,
      "loss": 88.1125,
      "step": 108
    },
    {
      "epoch": 0.9656699889258029,
      "grad_norm": 1.2570511102676392,
      "learning_rate": 7.433211916092142e-07,
      "loss": 88.0736,
      "step": 109
    },
    {
      "epoch": 0.9745293466223699,
      "grad_norm": 1.4869191646575928,
      "learning_rate": 4.1834517933907467e-07,
      "loss": 88.137,
      "step": 110
    },
    {
      "epoch": 0.9833887043189369,
      "grad_norm": 1.265148401260376,
      "learning_rate": 1.8600328401061629e-07,
      "loss": 88.1054,
      "step": 111
    },
    {
      "epoch": 0.9922480620155039,
      "grad_norm": 1.3339345455169678,
      "learning_rate": 4.651163766484779e-08,
      "loss": 88.0929,
      "step": 112
    },
    {
      "epoch": 1.0066445182724253,
      "grad_norm": 1.3491634130477905,
      "learning_rate": 0.0,
      "loss": 88.1079,
      "step": 113
    }
  ],
  "logging_steps": 1,
  "max_steps": 113,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 1692024176640.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}