{
  "best_metric": 0.770029604434967,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.12168410805548795,
  "eval_steps": 25,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006084205402774398,
      "grad_norm": 3.7732460498809814,
      "learning_rate": 2.173913043478261e-06,
      "loss": 3.2093,
      "step": 1
    },
    {
      "epoch": 0.0006084205402774398,
      "eval_loss": 1.9844963550567627,
      "eval_runtime": 0.0679,
      "eval_samples_per_second": 736.566,
      "eval_steps_per_second": 44.194,
      "step": 1
    },
    {
      "epoch": 0.0012168410805548796,
      "grad_norm": 4.146840572357178,
      "learning_rate": 4.347826086956522e-06,
      "loss": 2.2685,
      "step": 2
    },
    {
      "epoch": 0.0018252616208323193,
      "grad_norm": 3.805527448654175,
      "learning_rate": 6.521739130434783e-06,
      "loss": 2.0894,
      "step": 3
    },
    {
      "epoch": 0.002433682161109759,
      "grad_norm": 3.5490667819976807,
      "learning_rate": 8.695652173913044e-06,
      "loss": 1.9026,
      "step": 4
    },
    {
      "epoch": 0.003042102701387199,
      "grad_norm": 3.1814687252044678,
      "learning_rate": 1.0869565217391305e-05,
      "loss": 1.9351,
      "step": 5
    },
    {
      "epoch": 0.0036505232416646385,
      "grad_norm": 3.0306947231292725,
      "learning_rate": 1.3043478260869566e-05,
      "loss": 1.9283,
      "step": 6
    },
    {
      "epoch": 0.004258943781942078,
      "grad_norm": 3.2333295345306396,
      "learning_rate": 1.5217391304347828e-05,
      "loss": 1.9199,
      "step": 7
    },
    {
      "epoch": 0.004867364322219518,
      "grad_norm": 2.786118745803833,
      "learning_rate": 1.739130434782609e-05,
      "loss": 1.9464,
      "step": 8
    },
    {
      "epoch": 0.005475784862496958,
      "grad_norm": 3.1137781143188477,
      "learning_rate": 1.956521739130435e-05,
      "loss": 1.8952,
      "step": 9
    },
    {
      "epoch": 0.006084205402774398,
      "grad_norm": 3.2737996578216553,
      "learning_rate": 2.173913043478261e-05,
      "loss": 1.8745,
      "step": 10
    },
    {
      "epoch": 0.006692625943051838,
      "grad_norm": 3.218707799911499,
      "learning_rate": 2.391304347826087e-05,
      "loss": 1.9421,
      "step": 11
    },
    {
      "epoch": 0.007301046483329277,
      "grad_norm": 3.402679204940796,
      "learning_rate": 2.608695652173913e-05,
      "loss": 2.0349,
      "step": 12
    },
    {
      "epoch": 0.007909467023606717,
      "grad_norm": 2.8429970741271973,
      "learning_rate": 2.826086956521739e-05,
      "loss": 4.0381,
      "step": 13
    },
    {
      "epoch": 0.008517887563884156,
      "grad_norm": 4.92161750793457,
      "learning_rate": 3.0434782608695656e-05,
      "loss": 2.315,
      "step": 14
    },
    {
      "epoch": 0.009126308104161596,
      "grad_norm": 4.043981075286865,
      "learning_rate": 3.260869565217392e-05,
      "loss": 2.028,
      "step": 15
    },
    {
      "epoch": 0.009734728644439037,
      "grad_norm": 3.5905041694641113,
      "learning_rate": 3.478260869565218e-05,
      "loss": 2.034,
      "step": 16
    },
    {
      "epoch": 0.010343149184716476,
      "grad_norm": 3.121873378753662,
      "learning_rate": 3.695652173913043e-05,
      "loss": 1.9274,
      "step": 17
    },
    {
      "epoch": 0.010951569724993915,
      "grad_norm": 3.123685836791992,
      "learning_rate": 3.91304347826087e-05,
      "loss": 1.9217,
      "step": 18
    },
    {
      "epoch": 0.011559990265271356,
      "grad_norm": 2.93074107170105,
      "learning_rate": 4.130434782608696e-05,
      "loss": 1.6898,
      "step": 19
    },
    {
      "epoch": 0.012168410805548795,
      "grad_norm": 3.0180726051330566,
      "learning_rate": 4.347826086956522e-05,
      "loss": 1.6951,
      "step": 20
    },
    {
      "epoch": 0.012776831345826235,
      "grad_norm": 2.9282548427581787,
      "learning_rate": 4.565217391304348e-05,
      "loss": 1.7592,
      "step": 21
    },
    {
      "epoch": 0.013385251886103676,
      "grad_norm": 2.5757176876068115,
      "learning_rate": 4.782608695652174e-05,
      "loss": 1.753,
      "step": 22
    },
    {
      "epoch": 0.013993672426381115,
      "grad_norm": 2.7244386672973633,
      "learning_rate": 5e-05,
      "loss": 1.7478,
      "step": 23
    },
    {
      "epoch": 0.014602092966658554,
      "grad_norm": 2.9556708335876465,
      "learning_rate": 5.217391304347826e-05,
      "loss": 1.7354,
      "step": 24
    },
    {
      "epoch": 0.015210513506935993,
      "grad_norm": 2.826549530029297,
      "learning_rate": 5.4347826086956524e-05,
      "loss": 1.8359,
      "step": 25
    },
    {
      "epoch": 0.015210513506935993,
      "eval_loss": 1.7007235288619995,
      "eval_runtime": 0.0651,
      "eval_samples_per_second": 767.794,
      "eval_steps_per_second": 46.068,
      "step": 25
    },
    {
      "epoch": 0.015818934047213434,
      "grad_norm": 4.59504508972168,
      "learning_rate": 5.652173913043478e-05,
      "loss": 2.9356,
      "step": 26
    },
    {
      "epoch": 0.016427354587490874,
      "grad_norm": 4.431028842926025,
      "learning_rate": 5.869565217391305e-05,
      "loss": 1.7887,
      "step": 27
    },
    {
      "epoch": 0.017035775127768313,
      "grad_norm": 3.4355099201202393,
      "learning_rate": 6.086956521739131e-05,
      "loss": 1.6548,
      "step": 28
    },
    {
      "epoch": 0.017644195668045752,
      "grad_norm": 2.5302505493164062,
      "learning_rate": 6.304347826086957e-05,
      "loss": 1.6289,
      "step": 29
    },
    {
      "epoch": 0.01825261620832319,
      "grad_norm": 1.6945921182632446,
      "learning_rate": 6.521739130434783e-05,
      "loss": 1.4231,
      "step": 30
    },
    {
      "epoch": 0.018861036748600634,
      "grad_norm": 1.6188069581985474,
      "learning_rate": 6.73913043478261e-05,
      "loss": 1.4109,
      "step": 31
    },
    {
      "epoch": 0.019469457288878073,
      "grad_norm": 1.2194888591766357,
      "learning_rate": 6.956521739130436e-05,
      "loss": 1.4766,
      "step": 32
    },
    {
      "epoch": 0.020077877829155513,
      "grad_norm": 1.0816359519958496,
      "learning_rate": 7.17391304347826e-05,
      "loss": 1.5166,
      "step": 33
    },
    {
      "epoch": 0.020686298369432952,
      "grad_norm": 1.0028973817825317,
      "learning_rate": 7.391304347826086e-05,
      "loss": 1.5929,
      "step": 34
    },
    {
      "epoch": 0.02129471890971039,
      "grad_norm": 0.9615126848220825,
      "learning_rate": 7.608695652173914e-05,
      "loss": 1.3961,
      "step": 35
    },
    {
      "epoch": 0.02190313944998783,
      "grad_norm": 1.0823183059692383,
      "learning_rate": 7.82608695652174e-05,
      "loss": 1.4874,
      "step": 36
    },
    {
      "epoch": 0.022511559990265273,
      "grad_norm": 1.1442559957504272,
      "learning_rate": 8.043478260869566e-05,
      "loss": 1.5171,
      "step": 37
    },
    {
      "epoch": 0.023119980530542712,
      "grad_norm": 3.612239360809326,
      "learning_rate": 8.260869565217392e-05,
      "loss": 3.3537,
      "step": 38
    },
    {
      "epoch": 0.02372840107082015,
      "grad_norm": 3.0585246086120605,
      "learning_rate": 8.478260869565218e-05,
      "loss": 1.571,
      "step": 39
    },
    {
      "epoch": 0.02433682161109759,
      "grad_norm": 2.00331711769104,
      "learning_rate": 8.695652173913044e-05,
      "loss": 1.5134,
      "step": 40
    },
    {
      "epoch": 0.02494524215137503,
      "grad_norm": 1.4210355281829834,
      "learning_rate": 8.91304347826087e-05,
      "loss": 1.2967,
      "step": 41
    },
    {
      "epoch": 0.02555366269165247,
      "grad_norm": 1.2288633584976196,
      "learning_rate": 9.130434782608696e-05,
      "loss": 1.4348,
      "step": 42
    },
    {
      "epoch": 0.02616208323192991,
      "grad_norm": 1.157564640045166,
      "learning_rate": 9.347826086956522e-05,
      "loss": 1.3196,
      "step": 43
    },
    {
      "epoch": 0.02677050377220735,
      "grad_norm": 1.2825106382369995,
      "learning_rate": 9.565217391304348e-05,
      "loss": 1.349,
      "step": 44
    },
    {
      "epoch": 0.02737892431248479,
      "grad_norm": 1.2434223890304565,
      "learning_rate": 9.782608695652174e-05,
      "loss": 1.3314,
      "step": 45
    },
    {
      "epoch": 0.02798734485276223,
      "grad_norm": 1.429315447807312,
      "learning_rate": 0.0001,
      "loss": 1.3863,
      "step": 46
    },
    {
      "epoch": 0.02859576539303967,
      "grad_norm": 0.9383629560470581,
      "learning_rate": 9.999972027814122e-05,
      "loss": 1.3054,
      "step": 47
    },
    {
      "epoch": 0.029204185933317108,
      "grad_norm": 0.7935044765472412,
      "learning_rate": 9.999888111604245e-05,
      "loss": 1.298,
      "step": 48
    },
    {
      "epoch": 0.029812606473594547,
      "grad_norm": 0.859842836856842,
      "learning_rate": 9.999748252413618e-05,
      "loss": 1.3098,
      "step": 49
    },
    {
      "epoch": 0.030421027013871987,
      "grad_norm": 1.2138994932174683,
      "learning_rate": 9.999552451980984e-05,
      "loss": 1.3987,
      "step": 50
    },
    {
      "epoch": 0.030421027013871987,
      "eval_loss": 1.2663160562515259,
      "eval_runtime": 0.064,
      "eval_samples_per_second": 781.103,
      "eval_steps_per_second": 46.866,
      "step": 50
    },
    {
      "epoch": 0.03102944755414943,
      "grad_norm": 3.1896111965179443,
      "learning_rate": 9.999300712740551e-05,
      "loss": 2.1177,
      "step": 51
    },
    {
      "epoch": 0.03163786809442687,
      "grad_norm": 1.8031097650527954,
      "learning_rate": 9.998993037821958e-05,
      "loss": 1.281,
      "step": 52
    },
    {
      "epoch": 0.03224628863470431,
      "grad_norm": 1.3828022480010986,
      "learning_rate": 9.998629431050251e-05,
      "loss": 1.286,
      "step": 53
    },
    {
      "epoch": 0.03285470917498175,
      "grad_norm": 1.2959613800048828,
      "learning_rate": 9.998209896945815e-05,
      "loss": 1.3098,
      "step": 54
    },
    {
      "epoch": 0.033463129715259186,
      "grad_norm": 0.9320961236953735,
      "learning_rate": 9.997734440724333e-05,
      "loss": 1.2237,
      "step": 55
    },
    {
      "epoch": 0.034071550255536626,
      "grad_norm": 0.7311733961105347,
      "learning_rate": 9.997203068296719e-05,
      "loss": 1.1421,
      "step": 56
    },
    {
      "epoch": 0.034679970795814065,
      "grad_norm": 0.7125067710876465,
      "learning_rate": 9.996615786269035e-05,
      "loss": 1.2081,
      "step": 57
    },
    {
      "epoch": 0.035288391336091504,
      "grad_norm": 0.6830151677131653,
      "learning_rate": 9.995972601942424e-05,
      "loss": 1.2123,
      "step": 58
    },
    {
      "epoch": 0.03589681187636894,
      "grad_norm": 0.6575762629508972,
      "learning_rate": 9.995273523313003e-05,
      "loss": 1.1829,
      "step": 59
    },
    {
      "epoch": 0.03650523241664638,
      "grad_norm": 0.8578693866729736,
      "learning_rate": 9.994518559071775e-05,
      "loss": 1.1763,
      "step": 60
    },
    {
      "epoch": 0.03711365295692383,
      "grad_norm": 0.8111445307731628,
      "learning_rate": 9.993707718604522e-05,
      "loss": 1.1614,
      "step": 61
    },
    {
      "epoch": 0.03772207349720127,
      "grad_norm": 0.9371657967567444,
      "learning_rate": 9.992841011991676e-05,
      "loss": 1.2245,
      "step": 62
    },
    {
      "epoch": 0.03833049403747871,
      "grad_norm": 2.6930816173553467,
      "learning_rate": 9.991918450008206e-05,
      "loss": 2.285,
      "step": 63
    },
    {
      "epoch": 0.03893891457775615,
      "grad_norm": 1.746653437614441,
      "learning_rate": 9.99094004412348e-05,
      "loss": 1.301,
      "step": 64
    },
    {
      "epoch": 0.039547335118033586,
      "grad_norm": 1.1019763946533203,
      "learning_rate": 9.98990580650112e-05,
      "loss": 1.1406,
      "step": 65
    },
    {
      "epoch": 0.040155755658311025,
      "grad_norm": 1.0221314430236816,
      "learning_rate": 9.988815749998852e-05,
      "loss": 1.0963,
      "step": 66
    },
    {
      "epoch": 0.040764176198588464,
      "grad_norm": 0.7163240313529968,
      "learning_rate": 9.987669888168351e-05,
      "loss": 1.0621,
      "step": 67
    },
    {
      "epoch": 0.041372596738865904,
      "grad_norm": 1.0129799842834473,
      "learning_rate": 9.986468235255065e-05,
      "loss": 1.0655,
      "step": 68
    },
    {
      "epoch": 0.04198101727914334,
      "grad_norm": 1.0162873268127441,
      "learning_rate": 9.985210806198042e-05,
      "loss": 1.1478,
      "step": 69
    },
    {
      "epoch": 0.04258943781942078,
      "grad_norm": 0.6798834204673767,
      "learning_rate": 9.983897616629744e-05,
      "loss": 1.0584,
      "step": 70
    },
    {
      "epoch": 0.04319785835969822,
      "grad_norm": 0.82222980260849,
      "learning_rate": 9.982528682875851e-05,
      "loss": 1.0776,
      "step": 71
    },
    {
      "epoch": 0.04380627889997566,
      "grad_norm": 0.8663562536239624,
      "learning_rate": 9.981104021955063e-05,
      "loss": 1.073,
      "step": 72
    },
    {
      "epoch": 0.0444146994402531,
      "grad_norm": 1.122699499130249,
      "learning_rate": 9.979623651578881e-05,
      "loss": 1.0509,
      "step": 73
    },
    {
      "epoch": 0.045023119980530546,
      "grad_norm": 1.1595953702926636,
      "learning_rate": 9.978087590151393e-05,
      "loss": 1.1094,
      "step": 74
    },
    {
      "epoch": 0.045631540520807985,
      "grad_norm": 1.62815523147583,
      "learning_rate": 9.976495856769038e-05,
      "loss": 1.1211,
      "step": 75
    },
    {
      "epoch": 0.045631540520807985,
      "eval_loss": 1.0243722200393677,
      "eval_runtime": 0.0649,
      "eval_samples_per_second": 770.624,
      "eval_steps_per_second": 46.237,
      "step": 75
    },
    {
      "epoch": 0.046239961061085424,
      "grad_norm": 2.726969003677368,
      "learning_rate": 9.97484847122038e-05,
      "loss": 2.205,
      "step": 76
    },
    {
      "epoch": 0.046848381601362864,
      "grad_norm": 2.2901804447174072,
      "learning_rate": 9.973145453985854e-05,
      "loss": 1.1102,
      "step": 77
    },
    {
      "epoch": 0.0474568021416403,
      "grad_norm": 2.2033584117889404,
      "learning_rate": 9.971386826237507e-05,
      "loss": 1.0353,
      "step": 78
    },
    {
      "epoch": 0.04806522268191774,
      "grad_norm": 2.2385048866271973,
      "learning_rate": 9.969572609838744e-05,
      "loss": 1.0281,
      "step": 79
    },
    {
      "epoch": 0.04867364322219518,
      "grad_norm": 1.700537919998169,
      "learning_rate": 9.967702827344057e-05,
      "loss": 1.0513,
      "step": 80
    },
    {
      "epoch": 0.04928206376247262,
      "grad_norm": 1.1010593175888062,
      "learning_rate": 9.965777501998734e-05,
      "loss": 1.0073,
      "step": 81
    },
    {
      "epoch": 0.04989048430275006,
      "grad_norm": 0.7716583609580994,
      "learning_rate": 9.963796657738579e-05,
      "loss": 1.0205,
      "step": 82
    },
    {
      "epoch": 0.0504989048430275,
      "grad_norm": 0.7150983810424805,
      "learning_rate": 9.961760319189612e-05,
      "loss": 0.924,
      "step": 83
    },
    {
      "epoch": 0.05110732538330494,
      "grad_norm": 0.9970099925994873,
      "learning_rate": 9.959668511667762e-05,
      "loss": 1.0786,
      "step": 84
    },
    {
      "epoch": 0.05171574592358238,
      "grad_norm": 1.10440194606781,
      "learning_rate": 9.957521261178554e-05,
      "loss": 1.0916,
      "step": 85
    },
    {
      "epoch": 0.05232416646385982,
      "grad_norm": 1.2334967851638794,
      "learning_rate": 9.95531859441678e-05,
      "loss": 1.0281,
      "step": 86
    },
    {
      "epoch": 0.05293258700413726,
      "grad_norm": 1.5450046062469482,
      "learning_rate": 9.953060538766178e-05,
      "loss": 0.9459,
      "step": 87
    },
    {
      "epoch": 0.0535410075444147,
      "grad_norm": 2.800281524658203,
      "learning_rate": 9.950747122299084e-05,
      "loss": 2.3543,
      "step": 88
    },
    {
      "epoch": 0.05414942808469214,
      "grad_norm": 1.7520790100097656,
      "learning_rate": 9.948378373776079e-05,
      "loss": 1.0488,
      "step": 89
    },
    {
      "epoch": 0.05475784862496958,
      "grad_norm": 1.148888111114502,
      "learning_rate": 9.945954322645642e-05,
      "loss": 0.8649,
      "step": 90
    },
    {
      "epoch": 0.05536626916524702,
      "grad_norm": 0.883175253868103,
      "learning_rate": 9.943474999043775e-05,
      "loss": 0.9496,
      "step": 91
    },
    {
      "epoch": 0.05597468970552446,
      "grad_norm": 1.041022539138794,
      "learning_rate": 9.940940433793637e-05,
      "loss": 0.9575,
      "step": 92
    },
    {
      "epoch": 0.0565831102458019,
      "grad_norm": 0.8950981497764587,
      "learning_rate": 9.938350658405152e-05,
      "loss": 0.8507,
      "step": 93
    },
    {
      "epoch": 0.05719153078607934,
      "grad_norm": 0.8415868282318115,
      "learning_rate": 9.935705705074617e-05,
      "loss": 0.9419,
      "step": 94
    },
    {
      "epoch": 0.05779995132635678,
      "grad_norm": 0.8708381652832031,
      "learning_rate": 9.933005606684317e-05,
      "loss": 1.0413,
      "step": 95
    },
    {
      "epoch": 0.058408371866634216,
      "grad_norm": 1.0290625095367432,
      "learning_rate": 9.930250396802094e-05,
      "loss": 0.9954,
      "step": 96
    },
    {
      "epoch": 0.059016792406911656,
      "grad_norm": 0.8220187425613403,
      "learning_rate": 9.927440109680946e-05,
      "loss": 0.987,
      "step": 97
    },
    {
      "epoch": 0.059625212947189095,
      "grad_norm": 0.8632601499557495,
      "learning_rate": 9.924574780258596e-05,
      "loss": 0.9248,
      "step": 98
    },
    {
      "epoch": 0.060233633487466534,
      "grad_norm": 1.202643632888794,
      "learning_rate": 9.921654444157054e-05,
      "loss": 0.9264,
      "step": 99
    },
    {
      "epoch": 0.06084205402774397,
      "grad_norm": 1.6064764261245728,
      "learning_rate": 9.91867913768218e-05,
      "loss": 1.032,
      "step": 100
    },
    {
      "epoch": 0.06084205402774397,
      "eval_loss": 0.901063084602356,
      "eval_runtime": 0.0644,
      "eval_samples_per_second": 776.142,
      "eval_steps_per_second": 46.569,
      "step": 100
    },
    {
      "epoch": 0.06145047456802142,
      "grad_norm": 2.1135504245758057,
      "learning_rate": 9.915648897823232e-05,
      "loss": 1.8061,
      "step": 101
    },
    {
      "epoch": 0.06205889510829886,
      "grad_norm": 1.5115822553634644,
      "learning_rate": 9.912563762252399e-05,
      "loss": 0.9178,
      "step": 102
    },
    {
      "epoch": 0.06266731564857629,
      "grad_norm": 1.3775817155838013,
      "learning_rate": 9.909423769324343e-05,
      "loss": 0.8464,
      "step": 103
    },
    {
      "epoch": 0.06327573618885374,
      "grad_norm": 1.1930534839630127,
      "learning_rate": 9.906228958075717e-05,
      "loss": 0.9817,
      "step": 104
    },
    {
      "epoch": 0.06388415672913117,
      "grad_norm": 1.158815622329712,
      "learning_rate": 9.902979368224675e-05,
      "loss": 0.9052,
      "step": 105
    },
    {
      "epoch": 0.06449257726940862,
      "grad_norm": 0.8110672831535339,
      "learning_rate": 9.899675040170388e-05,
      "loss": 0.8699,
      "step": 106
    },
    {
      "epoch": 0.06510099780968605,
      "grad_norm": 0.6599923372268677,
      "learning_rate": 9.896316014992537e-05,
      "loss": 0.8528,
      "step": 107
    },
    {
      "epoch": 0.0657094183499635,
      "grad_norm": 0.7083361744880676,
      "learning_rate": 9.892902334450798e-05,
      "loss": 0.9154,
      "step": 108
    },
    {
      "epoch": 0.06631783889024094,
      "grad_norm": 1.0131536722183228,
      "learning_rate": 9.889434040984332e-05,
      "loss": 0.9124,
      "step": 109
    },
    {
      "epoch": 0.06692625943051837,
      "grad_norm": 1.1790049076080322,
      "learning_rate": 9.885911177711248e-05,
      "loss": 0.8958,
      "step": 110
    },
    {
      "epoch": 0.06753467997079582,
      "grad_norm": 1.2120789289474487,
      "learning_rate": 9.882333788428073e-05,
      "loss": 0.8547,
      "step": 111
    },
    {
      "epoch": 0.06814310051107325,
      "grad_norm": 1.194826364517212,
      "learning_rate": 9.878701917609207e-05,
      "loss": 0.9218,
      "step": 112
    },
    {
      "epoch": 0.0687515210513507,
      "grad_norm": 2.966965913772583,
      "learning_rate": 9.875015610406369e-05,
      "loss": 2.5956,
      "step": 113
    },
    {
      "epoch": 0.06935994159162813,
      "grad_norm": 1.3608638048171997,
      "learning_rate": 9.871274912648033e-05,
      "loss": 0.9144,
      "step": 114
    },
    {
      "epoch": 0.06996836213190558,
      "grad_norm": 1.4627468585968018,
      "learning_rate": 9.867479870838862e-05,
      "loss": 0.9815,
      "step": 115
    },
    {
      "epoch": 0.07057678267218301,
      "grad_norm": 1.1806144714355469,
      "learning_rate": 9.863630532159132e-05,
      "loss": 0.7937,
      "step": 116
    },
    {
      "epoch": 0.07118520321246045,
      "grad_norm": 1.0851095914840698,
      "learning_rate": 9.859726944464137e-05,
      "loss": 0.8003,
      "step": 117
    },
    {
      "epoch": 0.07179362375273789,
      "grad_norm": 1.126287579536438,
      "learning_rate": 9.855769156283603e-05,
      "loss": 0.9241,
      "step": 118
    },
    {
      "epoch": 0.07240204429301533,
      "grad_norm": 0.6791806817054749,
      "learning_rate": 9.851757216821079e-05,
      "loss": 0.9201,
      "step": 119
    },
    {
      "epoch": 0.07301046483329277,
      "grad_norm": 0.7268375158309937,
      "learning_rate": 9.847691175953328e-05,
      "loss": 0.8126,
      "step": 120
    },
    {
      "epoch": 0.07361888537357021,
      "grad_norm": 0.8680149912834167,
      "learning_rate": 9.843571084229707e-05,
      "loss": 0.8912,
      "step": 121
    },
    {
      "epoch": 0.07422730591384766,
      "grad_norm": 1.042919397354126,
      "learning_rate": 9.839396992871535e-05,
      "loss": 0.9064,
      "step": 122
    },
    {
      "epoch": 0.07483572645412509,
      "grad_norm": 1.2081691026687622,
      "learning_rate": 9.835168953771461e-05,
      "loss": 0.9376,
      "step": 123
    },
    {
      "epoch": 0.07544414699440254,
      "grad_norm": 1.1437644958496094,
      "learning_rate": 9.830887019492818e-05,
      "loss": 0.9418,
      "step": 124
    },
    {
      "epoch": 0.07605256753467997,
      "grad_norm": 1.2367491722106934,
      "learning_rate": 9.826551243268966e-05,
      "loss": 1.015,
      "step": 125
    },
    {
      "epoch": 0.07605256753467997,
      "eval_loss": 0.8607701063156128,
      "eval_runtime": 0.0636,
      "eval_samples_per_second": 785.848,
      "eval_steps_per_second": 47.151,
      "step": 125
    },
    {
      "epoch": 0.07666098807495741,
      "grad_norm": 2.4859538078308105,
      "learning_rate": 9.82216167900263e-05,
      "loss": 1.8291,
      "step": 126
    },
    {
      "epoch": 0.07726940861523485,
      "grad_norm": 1.4214491844177246,
      "learning_rate": 9.81771838126524e-05,
      "loss": 1.0467,
      "step": 127
    },
    {
      "epoch": 0.0778778291555123,
      "grad_norm": 1.3560972213745117,
      "learning_rate": 9.813221405296237e-05,
      "loss": 1.0159,
      "step": 128
    },
    {
      "epoch": 0.07848624969578973,
      "grad_norm": 1.501007080078125,
      "learning_rate": 9.8086708070024e-05,
      "loss": 0.8479,
      "step": 129
    },
    {
      "epoch": 0.07909467023606717,
      "grad_norm": 1.5460386276245117,
      "learning_rate": 9.804066642957143e-05,
      "loss": 0.9617,
      "step": 130
    },
    {
      "epoch": 0.0797030907763446,
      "grad_norm": 1.2963954210281372,
      "learning_rate": 9.799408970399813e-05,
      "loss": 0.8346,
      "step": 131
    },
    {
      "epoch": 0.08031151131662205,
      "grad_norm": 0.8653491139411926,
      "learning_rate": 9.79469784723498e-05,
      "loss": 0.8009,
      "step": 132
    },
    {
      "epoch": 0.08091993185689948,
      "grad_norm": 1.0787755250930786,
      "learning_rate": 9.789933332031717e-05,
      "loss": 0.9501,
      "step": 133
    },
    {
      "epoch": 0.08152835239717693,
      "grad_norm": 1.0019638538360596,
      "learning_rate": 9.78511548402287e-05,
      "loss": 0.841,
      "step": 134
    },
    {
      "epoch": 0.08213677293745437,
      "grad_norm": 1.1226329803466797,
      "learning_rate": 9.780244363104323e-05,
      "loss": 0.8492,
      "step": 135
    },
    {
      "epoch": 0.08274519347773181,
      "grad_norm": 1.269909381866455,
      "learning_rate": 9.775320029834254e-05,
      "loss": 0.854,
      "step": 136
    },
    {
      "epoch": 0.08335361401800925,
      "grad_norm": 1.76808762550354,
      "learning_rate": 9.770342545432383e-05,
      "loss": 0.8746,
      "step": 137
    },
    {
      "epoch": 0.08396203455828669,
      "grad_norm": 3.7219080924987793,
      "learning_rate": 9.765311971779204e-05,
      "loss": 2.2368,
      "step": 138
    },
    {
      "epoch": 0.08457045509856413,
      "grad_norm": 1.7717487812042236,
      "learning_rate": 9.760228371415227e-05,
      "loss": 1.0042,
      "step": 139
    },
    {
      "epoch": 0.08517887563884156,
      "grad_norm": 1.4473094940185547,
      "learning_rate": 9.75509180754019e-05,
      "loss": 0.8678,
      "step": 140
    },
    {
      "epoch": 0.08578729617911901,
      "grad_norm": 1.3099236488342285,
      "learning_rate": 9.749902344012279e-05,
      "loss": 0.7265,
      "step": 141
    },
    {
      "epoch": 0.08639571671939644,
      "grad_norm": 1.1434625387191772,
      "learning_rate": 9.744660045347336e-05,
      "loss": 0.7999,
      "step": 142
    },
    {
      "epoch": 0.08700413725967389,
      "grad_norm": 1.1469634771347046,
      "learning_rate": 9.73936497671805e-05,
      "loss": 0.8769,
      "step": 143
    },
    {
      "epoch": 0.08761255779995132,
      "grad_norm": 1.1170365810394287,
      "learning_rate": 9.734017203953149e-05,
      "loss": 0.8353,
      "step": 144
    },
    {
      "epoch": 0.08822097834022877,
      "grad_norm": 0.7087867259979248,
      "learning_rate": 9.728616793536588e-05,
      "loss": 0.8558,
      "step": 145
    },
    {
      "epoch": 0.0888293988805062,
      "grad_norm": 0.7099660634994507,
      "learning_rate": 9.723163812606716e-05,
      "loss": 0.7829,
      "step": 146
    },
    {
      "epoch": 0.08943781942078365,
      "grad_norm": 1.0997332334518433,
      "learning_rate": 9.71765832895544e-05,
      "loss": 0.8654,
      "step": 147
    },
    {
      "epoch": 0.09004623996106109,
      "grad_norm": 1.0360599756240845,
      "learning_rate": 9.712100411027391e-05,
      "loss": 0.8817,
      "step": 148
    },
    {
      "epoch": 0.09065466050133852,
      "grad_norm": 1.460658311843872,
      "learning_rate": 9.70649012791906e-05,
      "loss": 0.8495,
      "step": 149
    },
    {
      "epoch": 0.09126308104161597,
      "grad_norm": 1.6194958686828613,
      "learning_rate": 9.700827549377955e-05,
      "loss": 0.929,
      "step": 150
    },
    {
      "epoch": 0.09126308104161597,
      "eval_loss": 0.8000746369361877,
      "eval_runtime": 0.0648,
      "eval_samples_per_second": 771.193,
      "eval_steps_per_second": 46.272,
      "step": 150
    },
    {
      "epoch": 0.0918715015818934,
      "grad_norm": 2.0881123542785645,
      "learning_rate": 9.695112745801716e-05,
      "loss": 1.903,
      "step": 151
    },
    {
      "epoch": 0.09247992212217085,
      "grad_norm": 1.1570873260498047,
      "learning_rate": 9.689345788237256e-05,
      "loss": 0.9427,
      "step": 152
    },
    {
      "epoch": 0.09308834266244828,
      "grad_norm": 0.8610666990280151,
      "learning_rate": 9.683526748379864e-05,
      "loss": 0.8573,
      "step": 153
    },
    {
      "epoch": 0.09369676320272573,
      "grad_norm": 0.8190277218818665,
      "learning_rate": 9.677655698572326e-05,
      "loss": 0.6991,
      "step": 154
    },
    {
      "epoch": 0.09430518374300316,
      "grad_norm": 0.8921626210212708,
      "learning_rate": 9.671732711804022e-05,
      "loss": 0.7823,
      "step": 155
    },
    {
      "epoch": 0.0949136042832806,
      "grad_norm": 0.6367238759994507,
      "learning_rate": 9.665757861710008e-05,
      "loss": 0.8343,
      "step": 156
    },
    {
      "epoch": 0.09552202482355804,
      "grad_norm": 0.533492922782898,
      "learning_rate": 9.659731222570114e-05,
      "loss": 0.8161,
      "step": 157
    },
    {
      "epoch": 0.09613044536383548,
      "grad_norm": 0.7728853821754456,
      "learning_rate": 9.653652869308019e-05,
      "loss": 0.925,
      "step": 158
    },
    {
      "epoch": 0.09673886590411292,
      "grad_norm": 0.7567634582519531,
      "learning_rate": 9.647522877490312e-05,
      "loss": 0.8247,
      "step": 159
    },
    {
      "epoch": 0.09734728644439036,
      "grad_norm": 0.6781755685806274,
      "learning_rate": 9.641341323325554e-05,
      "loss": 0.8119,
      "step": 160
    },
    {
      "epoch": 0.09795570698466781,
      "grad_norm": 0.9459850788116455,
      "learning_rate": 9.635108283663343e-05,
      "loss": 0.7861,
      "step": 161
    },
    {
      "epoch": 0.09856412752494524,
      "grad_norm": 0.8214953541755676,
      "learning_rate": 9.628823835993338e-05,
      "loss": 0.8647,
      "step": 162
    },
    {
      "epoch": 0.09917254806522269,
      "grad_norm": 2.5658833980560303,
      "learning_rate": 9.622488058444314e-05,
      "loss": 2.3544,
      "step": 163
    },
    {
      "epoch": 0.09978096860550012,
      "grad_norm": 1.3964160680770874,
      "learning_rate": 9.61610102978318e-05,
      "loss": 0.8933,
      "step": 164
    },
    {
      "epoch": 0.10038938914577757,
      "grad_norm": 1.2962576150894165,
      "learning_rate": 9.609662829414005e-05,
      "loss": 0.7469,
      "step": 165
    },
    {
      "epoch": 0.100997809686055,
      "grad_norm": 1.0267356634140015,
      "learning_rate": 9.603173537377026e-05,
      "loss": 0.8354,
      "step": 166
    },
    {
      "epoch": 0.10160623022633244,
      "grad_norm": 0.7708994150161743,
      "learning_rate": 9.59663323434766e-05,
      "loss": 0.9245,
      "step": 167
    },
    {
      "epoch": 0.10221465076660988,
      "grad_norm": 0.5819109678268433,
      "learning_rate": 9.590042001635495e-05,
      "loss": 0.8,
      "step": 168
    },
    {
      "epoch": 0.10282307130688732,
      "grad_norm": 0.5333255529403687,
      "learning_rate": 9.583399921183276e-05,
      "loss": 0.798,
      "step": 169
    },
    {
      "epoch": 0.10343149184716476,
      "grad_norm": 0.9702023267745972,
      "learning_rate": 9.5767070755659e-05,
      "loss": 0.9434,
      "step": 170
    },
    {
      "epoch": 0.1040399123874422,
      "grad_norm": 0.9722750186920166,
      "learning_rate": 9.569963547989376e-05,
      "loss": 0.8818,
      "step": 171
    },
    {
      "epoch": 0.10464833292771963,
      "grad_norm": 1.0027716159820557,
      "learning_rate": 9.563169422289797e-05,
      "loss": 0.7531,
      "step": 172
    },
    {
      "epoch": 0.10525675346799708,
      "grad_norm": 0.7870794534683228,
      "learning_rate": 9.556324782932292e-05,
      "loss": 0.8253,
      "step": 173
    },
    {
      "epoch": 0.10586517400827453,
      "grad_norm": 0.7732038497924805,
      "learning_rate": 9.549429715009983e-05,
      "loss": 0.8425,
      "step": 174
    },
    {
      "epoch": 0.10647359454855196,
      "grad_norm": 1.3445314168930054,
      "learning_rate": 9.542484304242927e-05,
      "loss": 0.8793,
      "step": 175
    },
    {
      "epoch": 0.10647359454855196,
      "eval_loss": 0.7928541302680969,
      "eval_runtime": 0.0638,
      "eval_samples_per_second": 783.396,
      "eval_steps_per_second": 47.004,
      "step": 175
    },
    {
      "epoch": 0.1070820150888294,
      "grad_norm": 3.020885705947876,
      "learning_rate": 9.535488636977042e-05,
      "loss": 1.6845,
      "step": 176
    },
    {
      "epoch": 0.10769043562910684,
      "grad_norm": 2.2240676879882812,
      "learning_rate": 9.528442800183043e-05,
      "loss": 0.8827,
      "step": 177
    },
    {
      "epoch": 0.10829885616938428,
      "grad_norm": 1.7883273363113403,
      "learning_rate": 9.521346881455356e-05,
      "loss": 0.7705,
      "step": 178
    },
    {
      "epoch": 0.10890727670966172,
      "grad_norm": 1.2515283823013306,
      "learning_rate": 9.514200969011025e-05,
      "loss": 0.7441,
      "step": 179
    },
    {
      "epoch": 0.10951569724993916,
      "grad_norm": 0.8652520179748535,
      "learning_rate": 9.507005151688627e-05,
      "loss": 0.725,
      "step": 180
    },
    {
      "epoch": 0.1101241177902166,
      "grad_norm": 0.6205310225486755,
      "learning_rate": 9.499759518947156e-05,
      "loss": 0.7823,
      "step": 181
    },
    {
      "epoch": 0.11073253833049404,
      "grad_norm": 0.6425133943557739,
      "learning_rate": 9.492464160864917e-05,
      "loss": 0.7767,
      "step": 182
    },
    {
      "epoch": 0.11134095887077147,
      "grad_norm": 1.1534785032272339,
      "learning_rate": 9.485119168138405e-05,
      "loss": 0.8115,
      "step": 183
    },
    {
      "epoch": 0.11194937941104892,
      "grad_norm": 1.0528301000595093,
      "learning_rate": 9.477724632081176e-05,
      "loss": 0.7672,
      "step": 184
    },
    {
      "epoch": 0.11255779995132635,
      "grad_norm": 1.1875839233398438,
      "learning_rate": 9.470280644622713e-05,
      "loss": 0.8329,
      "step": 185
    },
    {
      "epoch": 0.1131662204916038,
      "grad_norm": 1.0731632709503174,
      "learning_rate": 9.462787298307285e-05,
      "loss": 0.8891,
      "step": 186
    },
    {
      "epoch": 0.11377464103188123,
      "grad_norm": 1.1598612070083618,
      "learning_rate": 9.455244686292789e-05,
      "loss": 0.7696,
      "step": 187
    },
    {
      "epoch": 0.11438306157215868,
      "grad_norm": 3.4111616611480713,
      "learning_rate": 9.447652902349602e-05,
      "loss": 1.4939,
      "step": 188
    },
    {
      "epoch": 0.11499148211243612,
      "grad_norm": 1.8949023485183716,
      "learning_rate": 9.44001204085941e-05,
      "loss": 0.8453,
      "step": 189
    },
    {
      "epoch": 0.11559990265271355,
      "grad_norm": 1.656935214996338,
      "learning_rate": 9.432322196814033e-05,
      "loss": 0.7722,
      "step": 190
    },
    {
      "epoch": 0.116208323192991,
      "grad_norm": 1.8966083526611328,
      "learning_rate": 9.424583465814249e-05,
      "loss": 0.7714,
      "step": 191
    },
    {
      "epoch": 0.11681674373326843,
      "grad_norm": 1.4729326963424683,
      "learning_rate": 9.4167959440686e-05,
      "loss": 0.8103,
      "step": 192
    },
    {
      "epoch": 0.11742516427354588,
      "grad_norm": 1.2855483293533325,
      "learning_rate": 9.408959728392199e-05,
      "loss": 0.751,
      "step": 193
    },
    {
      "epoch": 0.11803358481382331,
      "grad_norm": 0.6022900938987732,
      "learning_rate": 9.401074916205528e-05,
      "loss": 0.7532,
      "step": 194
    },
    {
      "epoch": 0.11864200535410076,
      "grad_norm": 0.6037607789039612,
      "learning_rate": 9.393141605533224e-05,
      "loss": 0.683,
      "step": 195
    },
    {
      "epoch": 0.11925042589437819,
      "grad_norm": 1.0040525197982788,
      "learning_rate": 9.385159895002859e-05,
      "loss": 0.7185,
      "step": 196
    },
    {
      "epoch": 0.11985884643465564,
      "grad_norm": 1.1619277000427246,
      "learning_rate": 9.37712988384372e-05,
      "loss": 0.934,
      "step": 197
    },
    {
      "epoch": 0.12046726697493307,
      "grad_norm": 1.2666449546813965,
      "learning_rate": 9.369051671885566e-05,
      "loss": 0.8437,
      "step": 198
    },
    {
      "epoch": 0.12107568751521051,
      "grad_norm": 1.3021451234817505,
      "learning_rate": 9.360925359557397e-05,
      "loss": 0.7939,
      "step": 199
    },
    {
      "epoch": 0.12168410805548795,
      "grad_norm": 1.3136470317840576,
      "learning_rate": 9.3527510478862e-05,
      "loss": 0.8785,
      "step": 200
    },
    {
      "epoch": 0.12168410805548795,
      "eval_loss": 0.770029604434967,
      "eval_runtime": 0.0645,
      "eval_samples_per_second": 775.029,
      "eval_steps_per_second": 46.502,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 937,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3040284166258688e+16,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}