{
  "best_metric": 1.271822214126587,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.022459607799098807,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.614901949774702e-05,
      "grad_norm": 0.5340127348899841,
      "learning_rate": 1e-05,
      "loss": 1.9563,
      "step": 1
    },
    {
      "epoch": 5.614901949774702e-05,
      "eval_loss": 2.318589448928833,
      "eval_runtime": 498.916,
      "eval_samples_per_second": 60.12,
      "eval_steps_per_second": 15.031,
      "step": 1
    },
    {
      "epoch": 0.00011229803899549404,
      "grad_norm": 0.5884995460510254,
      "learning_rate": 2e-05,
      "loss": 2.0628,
      "step": 2
    },
    {
      "epoch": 0.00016844705849324105,
      "grad_norm": 0.6643912196159363,
      "learning_rate": 3e-05,
      "loss": 2.0043,
      "step": 3
    },
    {
      "epoch": 0.00022459607799098807,
      "grad_norm": 0.7389161586761475,
      "learning_rate": 4e-05,
      "loss": 2.1707,
      "step": 4
    },
    {
      "epoch": 0.0002807450974887351,
      "grad_norm": 0.6619694232940674,
      "learning_rate": 5e-05,
      "loss": 2.125,
      "step": 5
    },
    {
      "epoch": 0.0003368941169864821,
      "grad_norm": 0.6001578569412231,
      "learning_rate": 6e-05,
      "loss": 2.1454,
      "step": 6
    },
    {
      "epoch": 0.0003930431364842291,
      "grad_norm": 0.6997002959251404,
      "learning_rate": 7e-05,
      "loss": 2.0116,
      "step": 7
    },
    {
      "epoch": 0.00044919215598197615,
      "grad_norm": 0.6134568452835083,
      "learning_rate": 8e-05,
      "loss": 2.0983,
      "step": 8
    },
    {
      "epoch": 0.0005053411754797232,
      "grad_norm": 0.5624329447746277,
      "learning_rate": 9e-05,
      "loss": 2.0473,
      "step": 9
    },
    {
      "epoch": 0.0005614901949774703,
      "grad_norm": 0.48732903599739075,
      "learning_rate": 0.0001,
      "loss": 2.061,
      "step": 10
    },
    {
      "epoch": 0.0006176392144752172,
      "grad_norm": 0.47478577494621277,
      "learning_rate": 9.99983777858264e-05,
      "loss": 1.8826,
      "step": 11
    },
    {
      "epoch": 0.0006737882339729642,
      "grad_norm": 0.4254133105278015,
      "learning_rate": 9.999351124856874e-05,
      "loss": 1.8489,
      "step": 12
    },
    {
      "epoch": 0.0007299372534707113,
      "grad_norm": 0.4701955020427704,
      "learning_rate": 9.998540070400966e-05,
      "loss": 1.8981,
      "step": 13
    },
    {
      "epoch": 0.0007860862729684582,
      "grad_norm": 0.5670016407966614,
      "learning_rate": 9.997404667843075e-05,
      "loss": 1.9104,
      "step": 14
    },
    {
      "epoch": 0.0008422352924662053,
      "grad_norm": 0.4492587447166443,
      "learning_rate": 9.995944990857849e-05,
      "loss": 1.7917,
      "step": 15
    },
    {
      "epoch": 0.0008983843119639523,
      "grad_norm": 0.45886924862861633,
      "learning_rate": 9.994161134161634e-05,
      "loss": 1.7783,
      "step": 16
    },
    {
      "epoch": 0.0009545333314616994,
      "grad_norm": 0.398569792509079,
      "learning_rate": 9.992053213506334e-05,
      "loss": 1.7699,
      "step": 17
    },
    {
      "epoch": 0.0010106823509594463,
      "grad_norm": 0.3940848410129547,
      "learning_rate": 9.989621365671902e-05,
      "loss": 1.752,
      "step": 18
    },
    {
      "epoch": 0.0010668313704571934,
      "grad_norm": 0.42660221457481384,
      "learning_rate": 9.986865748457457e-05,
      "loss": 1.8189,
      "step": 19
    },
    {
      "epoch": 0.0011229803899549405,
      "grad_norm": 0.4616188704967499,
      "learning_rate": 9.983786540671051e-05,
      "loss": 1.748,
      "step": 20
    },
    {
      "epoch": 0.0011791294094526874,
      "grad_norm": 0.4288494884967804,
      "learning_rate": 9.980383942118066e-05,
      "loss": 1.7384,
      "step": 21
    },
    {
      "epoch": 0.0012352784289504344,
      "grad_norm": 0.3832777440547943,
      "learning_rate": 9.976658173588244e-05,
      "loss": 1.6527,
      "step": 22
    },
    {
      "epoch": 0.0012914274484481815,
      "grad_norm": 0.38897594809532166,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.6954,
      "step": 23
    },
    {
      "epoch": 0.0013475764679459284,
      "grad_norm": 0.397813081741333,
      "learning_rate": 9.968238114591566e-05,
      "loss": 1.7149,
      "step": 24
    },
    {
      "epoch": 0.0014037254874436755,
      "grad_norm": 0.40973904728889465,
      "learning_rate": 9.96354437049027e-05,
      "loss": 1.6836,
      "step": 25
    },
    {
      "epoch": 0.0014598745069414225,
      "grad_norm": 0.39105677604675293,
      "learning_rate": 9.95852854910781e-05,
      "loss": 1.5881,
      "step": 26
    },
    {
      "epoch": 0.0015160235264391696,
      "grad_norm": 0.44259727001190186,
      "learning_rate": 9.953190975913647e-05,
      "loss": 1.6501,
      "step": 27
    },
    {
      "epoch": 0.0015721725459369165,
      "grad_norm": 0.4385436475276947,
      "learning_rate": 9.947531997255256e-05,
      "loss": 1.6268,
      "step": 28
    },
    {
      "epoch": 0.0016283215654346636,
      "grad_norm": 0.40642112493515015,
      "learning_rate": 9.941551980335652e-05,
      "loss": 1.4861,
      "step": 29
    },
    {
      "epoch": 0.0016844705849324106,
      "grad_norm": 0.4721114933490753,
      "learning_rate": 9.935251313189564e-05,
      "loss": 1.6239,
      "step": 30
    },
    {
      "epoch": 0.0017406196044301577,
      "grad_norm": 0.3923283517360687,
      "learning_rate": 9.928630404658255e-05,
      "loss": 1.6122,
      "step": 31
    },
    {
      "epoch": 0.0017967686239279046,
      "grad_norm": 0.4088236689567566,
      "learning_rate": 9.921689684362989e-05,
      "loss": 1.551,
      "step": 32
    },
    {
      "epoch": 0.0018529176434256517,
      "grad_norm": 0.39113548398017883,
      "learning_rate": 9.914429602677162e-05,
      "loss": 1.5401,
      "step": 33
    },
    {
      "epoch": 0.0019090666629233987,
      "grad_norm": 0.4188564419746399,
      "learning_rate": 9.906850630697068e-05,
      "loss": 1.5503,
      "step": 34
    },
    {
      "epoch": 0.001965215682421146,
      "grad_norm": 0.459398478269577,
      "learning_rate": 9.898953260211338e-05,
      "loss": 1.5654,
      "step": 35
    },
    {
      "epoch": 0.0020213647019188927,
      "grad_norm": 0.4721934497356415,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.5314,
      "step": 36
    },
    {
      "epoch": 0.0020775137214166395,
      "grad_norm": 0.4360145330429077,
      "learning_rate": 9.882205394146361e-05,
      "loss": 1.4705,
      "step": 37
    },
    {
      "epoch": 0.002133662740914387,
      "grad_norm": 0.41673576831817627,
      "learning_rate": 9.87335598531214e-05,
      "loss": 1.4385,
      "step": 38
    },
    {
      "epoch": 0.0021898117604121337,
      "grad_norm": 0.4030298888683319,
      "learning_rate": 9.864190351391822e-05,
      "loss": 1.425,
      "step": 39
    },
    {
      "epoch": 0.002245960779909881,
      "grad_norm": 0.3803832232952118,
      "learning_rate": 9.85470908713026e-05,
      "loss": 1.4072,
      "step": 40
    },
    {
      "epoch": 0.002302109799407628,
      "grad_norm": 0.38645970821380615,
      "learning_rate": 9.844912807753104e-05,
      "loss": 1.3438,
      "step": 41
    },
    {
      "epoch": 0.0023582588189053747,
      "grad_norm": 0.40624821186065674,
      "learning_rate": 9.834802148926882e-05,
      "loss": 1.4071,
      "step": 42
    },
    {
      "epoch": 0.002414407838403122,
      "grad_norm": 0.386904239654541,
      "learning_rate": 9.824377766717759e-05,
      "loss": 1.3316,
      "step": 43
    },
    {
      "epoch": 0.002470556857900869,
      "grad_norm": 0.3903076648712158,
      "learning_rate": 9.813640337548954e-05,
      "loss": 1.3448,
      "step": 44
    },
    {
      "epoch": 0.0025267058773986158,
      "grad_norm": 0.40525177121162415,
      "learning_rate": 9.802590558156862e-05,
      "loss": 1.2968,
      "step": 45
    },
    {
      "epoch": 0.002582854896896363,
      "grad_norm": 0.4393541216850281,
      "learning_rate": 9.791229145545831e-05,
      "loss": 1.5067,
      "step": 46
    },
    {
      "epoch": 0.00263900391639411,
      "grad_norm": 0.4737115204334259,
      "learning_rate": 9.779556836941645e-05,
      "loss": 1.3785,
      "step": 47
    },
    {
      "epoch": 0.0026951529358918568,
      "grad_norm": 0.40890952944755554,
      "learning_rate": 9.767574389743682e-05,
      "loss": 1.3264,
      "step": 48
    },
    {
      "epoch": 0.002751301955389604,
      "grad_norm": 0.5537047982215881,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.3774,
      "step": 49
    },
    {
      "epoch": 0.002807450974887351,
      "grad_norm": 0.6409347653388977,
      "learning_rate": 9.742682209735727e-05,
      "loss": 1.331,
      "step": 50
    },
    {
      "epoch": 0.002807450974887351,
      "eval_loss": 1.4487366676330566,
      "eval_runtime": 498.482,
      "eval_samples_per_second": 60.173,
      "eval_steps_per_second": 15.044,
      "step": 50
    },
    {
      "epoch": 0.0028635999943850982,
      "grad_norm": 0.6663397550582886,
      "learning_rate": 9.729774092143627e-05,
      "loss": 1.5785,
      "step": 51
    },
    {
      "epoch": 0.002919749013882845,
      "grad_norm": 0.5732940435409546,
      "learning_rate": 9.716559066288715e-05,
      "loss": 1.5659,
      "step": 52
    },
    {
      "epoch": 0.002975898033380592,
      "grad_norm": 0.562037467956543,
      "learning_rate": 9.703037989675087e-05,
      "loss": 1.6022,
      "step": 53
    },
    {
      "epoch": 0.0030320470528783392,
      "grad_norm": 0.5004995465278625,
      "learning_rate": 9.689211739666023e-05,
      "loss": 1.5031,
      "step": 54
    },
    {
      "epoch": 0.003088196072376086,
      "grad_norm": 0.4359580874443054,
      "learning_rate": 9.675081213427076e-05,
      "loss": 1.5223,
      "step": 55
    },
    {
      "epoch": 0.003144345091873833,
      "grad_norm": 0.34962624311447144,
      "learning_rate": 9.66064732786784e-05,
      "loss": 1.4151,
      "step": 56
    },
    {
      "epoch": 0.0032004941113715803,
      "grad_norm": 0.3261302709579468,
      "learning_rate": 9.645911019582467e-05,
      "loss": 1.4774,
      "step": 57
    },
    {
      "epoch": 0.003256643130869327,
      "grad_norm": 0.32419782876968384,
      "learning_rate": 9.630873244788883e-05,
      "loss": 1.3363,
      "step": 58
    },
    {
      "epoch": 0.0033127921503670744,
      "grad_norm": 0.3202192783355713,
      "learning_rate": 9.615534979266745e-05,
      "loss": 1.4802,
      "step": 59
    },
    {
      "epoch": 0.0033689411698648213,
      "grad_norm": 0.3390008807182312,
      "learning_rate": 9.599897218294122e-05,
      "loss": 1.4951,
      "step": 60
    },
    {
      "epoch": 0.003425090189362568,
      "grad_norm": 0.35550883412361145,
      "learning_rate": 9.583960976582913e-05,
      "loss": 1.3875,
      "step": 61
    },
    {
      "epoch": 0.0034812392088603154,
      "grad_norm": 0.3585120141506195,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.4687,
      "step": 62
    },
    {
      "epoch": 0.0035373882283580623,
      "grad_norm": 0.364469051361084,
      "learning_rate": 9.551197206565173e-05,
      "loss": 1.3488,
      "step": 63
    },
    {
      "epoch": 0.003593537247855809,
      "grad_norm": 0.3839256763458252,
      "learning_rate": 9.534371804252728e-05,
      "loss": 1.4195,
      "step": 64
    },
    {
      "epoch": 0.0036496862673535565,
      "grad_norm": 0.3368490934371948,
      "learning_rate": 9.517252173051911e-05,
      "loss": 1.4127,
      "step": 65
    },
    {
      "epoch": 0.0037058352868513033,
      "grad_norm": 0.3333461880683899,
      "learning_rate": 9.49983942383106e-05,
      "loss": 1.4535,
      "step": 66
    },
    {
      "epoch": 0.00376198430634905,
      "grad_norm": 0.33250004053115845,
      "learning_rate": 9.482134686478519e-05,
      "loss": 1.4062,
      "step": 67
    },
    {
      "epoch": 0.0038181333258467975,
      "grad_norm": 0.3171483278274536,
      "learning_rate": 9.464139109829321e-05,
      "loss": 1.3492,
      "step": 68
    },
    {
      "epoch": 0.0038742823453445444,
      "grad_norm": 0.3001011312007904,
      "learning_rate": 9.445853861590647e-05,
      "loss": 1.3795,
      "step": 69
    },
    {
      "epoch": 0.003930431364842292,
      "grad_norm": 0.3047218322753906,
      "learning_rate": 9.42728012826605e-05,
      "loss": 1.4481,
      "step": 70
    },
    {
      "epoch": 0.003986580384340038,
      "grad_norm": 0.30260416865348816,
      "learning_rate": 9.408419115078471e-05,
      "loss": 1.3184,
      "step": 71
    },
    {
      "epoch": 0.004042729403837785,
      "grad_norm": 0.3379102349281311,
      "learning_rate": 9.389272045892024e-05,
      "loss": 1.3685,
      "step": 72
    },
    {
      "epoch": 0.004098878423335533,
      "grad_norm": 0.3105633556842804,
      "learning_rate": 9.36984016313259e-05,
      "loss": 1.4351,
      "step": 73
    },
    {
      "epoch": 0.004155027442833279,
      "grad_norm": 0.32337304949760437,
      "learning_rate": 9.350124727707197e-05,
      "loss": 1.3573,
      "step": 74
    },
    {
      "epoch": 0.004211176462331026,
      "grad_norm": 0.34313297271728516,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.4224,
      "step": 75
    },
    {
      "epoch": 0.004267325481828774,
      "grad_norm": 0.3243308365345001,
      "learning_rate": 9.309848334400246e-05,
      "loss": 1.4161,
      "step": 76
    },
    {
      "epoch": 0.004323474501326521,
      "grad_norm": 0.32780221104621887,
      "learning_rate": 9.289289989996133e-05,
      "loss": 1.3402,
      "step": 77
    },
    {
      "epoch": 0.004379623520824267,
      "grad_norm": 0.3317124843597412,
      "learning_rate": 9.268453319711363e-05,
      "loss": 1.414,
      "step": 78
    },
    {
      "epoch": 0.004435772540322015,
      "grad_norm": 0.3497501611709595,
      "learning_rate": 9.247339675607605e-05,
      "loss": 1.3994,
      "step": 79
    },
    {
      "epoch": 0.004491921559819762,
      "grad_norm": 0.3386603593826294,
      "learning_rate": 9.225950427718975e-05,
      "loss": 1.3915,
      "step": 80
    },
    {
      "epoch": 0.0045480705793175084,
      "grad_norm": 0.3279411792755127,
      "learning_rate": 9.204286963963111e-05,
      "loss": 1.4429,
      "step": 81
    },
    {
      "epoch": 0.004604219598815256,
      "grad_norm": 0.35080745816230774,
      "learning_rate": 9.182350690051133e-05,
      "loss": 1.3705,
      "step": 82
    },
    {
      "epoch": 0.004660368618313003,
      "grad_norm": 0.35310325026512146,
      "learning_rate": 9.160143029396422e-05,
      "loss": 1.4281,
      "step": 83
    },
    {
      "epoch": 0.0047165176378107495,
      "grad_norm": 0.3270968198776245,
      "learning_rate": 9.13766542302225e-05,
      "loss": 1.375,
      "step": 84
    },
    {
      "epoch": 0.004772666657308497,
      "grad_norm": 0.4094909131526947,
      "learning_rate": 9.114919329468282e-05,
      "loss": 1.4071,
      "step": 85
    },
    {
      "epoch": 0.004828815676806244,
      "grad_norm": 0.3606330156326294,
      "learning_rate": 9.091906224695935e-05,
      "loss": 1.3264,
      "step": 86
    },
    {
      "epoch": 0.0048849646963039905,
      "grad_norm": 0.36859509348869324,
      "learning_rate": 9.068627601992598e-05,
      "loss": 1.4443,
      "step": 87
    },
    {
      "epoch": 0.004941113715801738,
      "grad_norm": 0.35740166902542114,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.3744,
      "step": 88
    },
    {
      "epoch": 0.004997262735299485,
      "grad_norm": 0.38532522320747375,
      "learning_rate": 9.021279861989885e-05,
      "loss": 1.3334,
      "step": 89
    },
    {
      "epoch": 0.0050534117547972315,
      "grad_norm": 0.3711566627025604,
      "learning_rate": 8.997213817017507e-05,
      "loss": 1.3575,
      "step": 90
    },
    {
      "epoch": 0.005109560774294979,
      "grad_norm": 0.38581743836402893,
      "learning_rate": 8.972888398568772e-05,
      "loss": 1.2886,
      "step": 91
    },
    {
      "epoch": 0.005165709793792726,
      "grad_norm": 0.3848288357257843,
      "learning_rate": 8.948305185085225e-05,
      "loss": 1.337,
      "step": 92
    },
    {
      "epoch": 0.0052218588132904725,
      "grad_norm": 0.38211366534233093,
      "learning_rate": 8.92346577173636e-05,
      "loss": 1.3127,
      "step": 93
    },
    {
      "epoch": 0.00527800783278822,
      "grad_norm": 0.36874812841415405,
      "learning_rate": 8.898371770316111e-05,
      "loss": 1.2577,
      "step": 94
    },
    {
      "epoch": 0.005334156852285967,
      "grad_norm": 0.3935130834579468,
      "learning_rate": 8.873024809138272e-05,
      "loss": 1.3627,
      "step": 95
    },
    {
      "epoch": 0.0053903058717837135,
      "grad_norm": 0.4179862439632416,
      "learning_rate": 8.847426532930831e-05,
      "loss": 1.2289,
      "step": 96
    },
    {
      "epoch": 0.005446454891281461,
      "grad_norm": 0.45972880721092224,
      "learning_rate": 8.821578602729242e-05,
      "loss": 1.433,
      "step": 97
    },
    {
      "epoch": 0.005502603910779208,
      "grad_norm": 0.4482019245624542,
      "learning_rate": 8.795482695768658e-05,
      "loss": 1.2454,
      "step": 98
    },
    {
      "epoch": 0.005558752930276955,
      "grad_norm": 0.48963579535484314,
      "learning_rate": 8.769140505375085e-05,
      "loss": 1.1945,
      "step": 99
    },
    {
      "epoch": 0.005614901949774702,
      "grad_norm": 0.5664313435554504,
      "learning_rate": 8.742553740855506e-05,
      "loss": 1.334,
      "step": 100
    },
    {
      "epoch": 0.005614901949774702,
      "eval_loss": 1.3750338554382324,
      "eval_runtime": 498.6769,
      "eval_samples_per_second": 60.149,
      "eval_steps_per_second": 15.038,
      "step": 100
    },
    {
      "epoch": 0.005671050969272449,
      "grad_norm": 0.5887877941131592,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.4701,
      "step": 101
    },
    {
      "epoch": 0.0057271999887701965,
      "grad_norm": 0.533300518989563,
      "learning_rate": 8.688653405904652e-05,
      "loss": 1.4185,
      "step": 102
    },
    {
      "epoch": 0.005783349008267943,
      "grad_norm": 0.47831276059150696,
      "learning_rate": 8.661343332988869e-05,
      "loss": 1.4503,
      "step": 103
    },
    {
      "epoch": 0.00583949802776569,
      "grad_norm": 0.44194933772087097,
      "learning_rate": 8.633795680751116e-05,
      "loss": 1.4504,
      "step": 104
    },
    {
      "epoch": 0.0058956470472634375,
      "grad_norm": 0.37259674072265625,
      "learning_rate": 8.606012236719073e-05,
      "loss": 1.3562,
      "step": 105
    },
    {
      "epoch": 0.005951796066761184,
      "grad_norm": 0.3651125431060791,
      "learning_rate": 8.577994803720606e-05,
      "loss": 1.363,
      "step": 106
    },
    {
      "epoch": 0.006007945086258931,
      "grad_norm": 0.3322165608406067,
      "learning_rate": 8.549745199766792e-05,
      "loss": 1.3722,
      "step": 107
    },
    {
      "epoch": 0.0060640941057566785,
      "grad_norm": 0.31796780228614807,
      "learning_rate": 8.521265257933948e-05,
      "loss": 1.3725,
      "step": 108
    },
    {
      "epoch": 0.006120243125254425,
      "grad_norm": 0.3114439845085144,
      "learning_rate": 8.492556826244687e-05,
      "loss": 1.3041,
      "step": 109
    },
    {
      "epoch": 0.006176392144752172,
      "grad_norm": 0.33855172991752625,
      "learning_rate": 8.463621767547998e-05,
      "loss": 1.3537,
      "step": 110
    },
    {
      "epoch": 0.0062325411642499195,
      "grad_norm": 0.34555360674858093,
      "learning_rate": 8.434461959398376e-05,
      "loss": 1.4027,
      "step": 111
    },
    {
      "epoch": 0.006288690183747666,
      "grad_norm": 0.3324665129184723,
      "learning_rate": 8.405079293933986e-05,
      "loss": 1.4327,
      "step": 112
    },
    {
      "epoch": 0.006344839203245413,
      "grad_norm": 0.3820353150367737,
      "learning_rate": 8.375475677753881e-05,
      "loss": 1.4021,
      "step": 113
    },
    {
      "epoch": 0.0064009882227431605,
      "grad_norm": 0.34804096817970276,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.3878,
      "step": 114
    },
    {
      "epoch": 0.006457137242240907,
      "grad_norm": 0.36230865120887756,
      "learning_rate": 8.315613291203976e-05,
      "loss": 1.4082,
      "step": 115
    },
    {
      "epoch": 0.006513286261738654,
      "grad_norm": 0.3718462884426117,
      "learning_rate": 8.285358405218655e-05,
      "loss": 1.3452,
      "step": 116
    },
    {
      "epoch": 0.0065694352812364016,
      "grad_norm": 0.33835625648498535,
      "learning_rate": 8.25489033703452e-05,
      "loss": 1.3261,
      "step": 117
    },
    {
      "epoch": 0.006625584300734149,
      "grad_norm": 0.32900914549827576,
      "learning_rate": 8.224211063680853e-05,
      "loss": 1.2985,
      "step": 118
    },
    {
      "epoch": 0.006681733320231895,
      "grad_norm": 0.33768901228904724,
      "learning_rate": 8.19332257589174e-05,
      "loss": 1.3194,
      "step": 119
    },
    {
      "epoch": 0.006737882339729643,
      "grad_norm": 0.3272550106048584,
      "learning_rate": 8.162226877976887e-05,
      "loss": 1.2992,
      "step": 120
    },
    {
      "epoch": 0.00679403135922739,
      "grad_norm": 0.3214387893676758,
      "learning_rate": 8.130925987691569e-05,
      "loss": 1.2775,
      "step": 121
    },
    {
      "epoch": 0.006850180378725136,
      "grad_norm": 0.3233121335506439,
      "learning_rate": 8.099421936105702e-05,
      "loss": 1.3604,
      "step": 122
    },
    {
      "epoch": 0.006906329398222884,
      "grad_norm": 0.3374609351158142,
      "learning_rate": 8.067716767472045e-05,
      "loss": 1.3658,
      "step": 123
    },
    {
      "epoch": 0.006962478417720631,
      "grad_norm": 0.32785022258758545,
      "learning_rate": 8.035812539093557e-05,
      "loss": 1.2985,
      "step": 124
    },
    {
      "epoch": 0.007018627437218377,
      "grad_norm": 0.3212898075580597,
      "learning_rate": 8.003711321189895e-05,
      "loss": 1.285,
      "step": 125
    },
    {
      "epoch": 0.007074776456716125,
      "grad_norm": 0.34439992904663086,
      "learning_rate": 7.971415196763088e-05,
      "loss": 1.4653,
      "step": 126
    },
    {
      "epoch": 0.007130925476213872,
      "grad_norm": 0.34514302015304565,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.3337,
      "step": 127
    },
    {
      "epoch": 0.007187074495711618,
      "grad_norm": 0.38126933574676514,
      "learning_rate": 7.906246623448183e-05,
      "loss": 1.3511,
      "step": 128
    },
    {
      "epoch": 0.007243223515209366,
      "grad_norm": 0.34479570388793945,
      "learning_rate": 7.873378403255419e-05,
      "loss": 1.329,
      "step": 129
    },
    {
      "epoch": 0.007299372534707113,
      "grad_norm": 0.34173834323883057,
      "learning_rate": 7.840323733655778e-05,
      "loss": 1.3119,
      "step": 130
    },
    {
      "epoch": 0.007355521554204859,
      "grad_norm": 0.35819727182388306,
      "learning_rate": 7.807084759519405e-05,
      "loss": 1.3358,
      "step": 131
    },
    {
      "epoch": 0.007411670573702607,
      "grad_norm": 0.35329777002334595,
      "learning_rate": 7.773663637675694e-05,
      "loss": 1.3238,
      "step": 132
    },
    {
      "epoch": 0.007467819593200354,
      "grad_norm": 0.36197683215141296,
      "learning_rate": 7.740062536773352e-05,
      "loss": 1.2516,
      "step": 133
    },
    {
      "epoch": 0.0075239686126981,
      "grad_norm": 0.36278480291366577,
      "learning_rate": 7.706283637139658e-05,
      "loss": 1.2106,
      "step": 134
    },
    {
      "epoch": 0.007580117632195848,
      "grad_norm": 0.36338376998901367,
      "learning_rate": 7.672329130639005e-05,
      "loss": 1.2502,
      "step": 135
    },
    {
      "epoch": 0.007636266651693595,
      "grad_norm": 0.369215190410614,
      "learning_rate": 7.638201220530665e-05,
      "loss": 1.3322,
      "step": 136
    },
    {
      "epoch": 0.007692415671191341,
      "grad_norm": 0.3735330104827881,
      "learning_rate": 7.603902121325813e-05,
      "loss": 1.2302,
      "step": 137
    },
    {
      "epoch": 0.007748564690689089,
      "grad_norm": 0.3798264265060425,
      "learning_rate": 7.569434058643844e-05,
      "loss": 1.4184,
      "step": 138
    },
    {
      "epoch": 0.007804713710186836,
      "grad_norm": 0.3851505517959595,
      "learning_rate": 7.534799269067953e-05,
      "loss": 1.3757,
      "step": 139
    },
    {
      "epoch": 0.007860862729684583,
      "grad_norm": 0.3895701467990875,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.2911,
      "step": 140
    },
    {
      "epoch": 0.00791701174918233,
      "grad_norm": 0.3997504711151123,
      "learning_rate": 7.465038509514688e-05,
      "loss": 1.3938,
      "step": 141
    },
    {
      "epoch": 0.007973160768680076,
      "grad_norm": 0.3898596465587616,
      "learning_rate": 7.42991706621303e-05,
      "loss": 1.2683,
      "step": 142
    },
    {
      "epoch": 0.008029309788177823,
      "grad_norm": 0.42272382974624634,
      "learning_rate": 7.394637949075154e-05,
      "loss": 1.3499,
      "step": 143
    },
    {
      "epoch": 0.00808545880767557,
      "grad_norm": 0.3854672610759735,
      "learning_rate": 7.35920344731241e-05,
      "loss": 1.2151,
      "step": 144
    },
    {
      "epoch": 0.008141607827173318,
      "grad_norm": 0.39451897144317627,
      "learning_rate": 7.323615860218843e-05,
      "loss": 1.2315,
      "step": 145
    },
    {
      "epoch": 0.008197756846671065,
      "grad_norm": 0.4249548614025116,
      "learning_rate": 7.287877497021978e-05,
      "loss": 1.1785,
      "step": 146
    },
    {
      "epoch": 0.008253905866168813,
      "grad_norm": 0.43391963839530945,
      "learning_rate": 7.251990676732984e-05,
      "loss": 1.1203,
      "step": 147
    },
    {
      "epoch": 0.008310054885666558,
      "grad_norm": 0.45870715379714966,
      "learning_rate": 7.215957727996207e-05,
      "loss": 1.1546,
      "step": 148
    },
    {
      "epoch": 0.008366203905164305,
      "grad_norm": 0.4571928083896637,
      "learning_rate": 7.179780988938051e-05,
      "loss": 1.1424,
      "step": 149
    },
    {
      "epoch": 0.008422352924662053,
      "grad_norm": 0.5306082963943481,
      "learning_rate": 7.143462807015271e-05,
      "loss": 0.979,
      "step": 150
    },
    {
      "epoch": 0.008422352924662053,
      "eval_loss": 1.3391810655593872,
      "eval_runtime": 499.3755,
      "eval_samples_per_second": 60.065,
      "eval_steps_per_second": 15.017,
      "step": 150
    },
    {
      "epoch": 0.0084785019441598,
      "grad_norm": 0.5642489790916443,
      "learning_rate": 7.107005538862646e-05,
      "loss": 1.4318,
      "step": 151
    },
    {
      "epoch": 0.008534650963657547,
      "grad_norm": 0.5044007897377014,
      "learning_rate": 7.07041155014006e-05,
      "loss": 1.4648,
      "step": 152
    },
    {
      "epoch": 0.008590799983155295,
      "grad_norm": 0.4890078008174896,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.4658,
      "step": 153
    },
    {
      "epoch": 0.008646949002653042,
      "grad_norm": 0.46746453642845154,
      "learning_rate": 6.996822917828477e-05,
      "loss": 1.5129,
      "step": 154
    },
    {
      "epoch": 0.008703098022150788,
      "grad_norm": 0.40368425846099854,
      "learning_rate": 6.959833049300377e-05,
      "loss": 1.3295,
      "step": 155
    },
    {
      "epoch": 0.008759247041648535,
      "grad_norm": 0.37394431233406067,
      "learning_rate": 6.922716010014255e-05,
      "loss": 1.3927,
      "step": 156
    },
    {
      "epoch": 0.008815396061146282,
      "grad_norm": 0.3574720323085785,
      "learning_rate": 6.885474208441603e-05,
      "loss": 1.3916,
      "step": 157
    },
    {
      "epoch": 0.00887154508064403,
      "grad_norm": 0.32283368706703186,
      "learning_rate": 6.848110061149556e-05,
      "loss": 1.3552,
      "step": 158
    },
    {
      "epoch": 0.008927694100141777,
      "grad_norm": 0.33707913756370544,
      "learning_rate": 6.810625992644085e-05,
      "loss": 1.2879,
      "step": 159
    },
    {
      "epoch": 0.008983843119639524,
      "grad_norm": 0.3094768822193146,
      "learning_rate": 6.773024435212678e-05,
      "loss": 1.4034,
      "step": 160
    },
    {
      "epoch": 0.00903999213913727,
      "grad_norm": 0.32651329040527344,
      "learning_rate": 6.735307828766515e-05,
      "loss": 1.3895,
      "step": 161
    },
    {
      "epoch": 0.009096141158635017,
      "grad_norm": 0.3196355998516083,
      "learning_rate": 6.697478620682137e-05,
      "loss": 1.2508,
      "step": 162
    },
    {
      "epoch": 0.009152290178132764,
      "grad_norm": 0.3607967793941498,
      "learning_rate": 6.659539265642643e-05,
      "loss": 1.4363,
      "step": 163
    },
    {
      "epoch": 0.009208439197630511,
      "grad_norm": 0.35106199979782104,
      "learning_rate": 6.621492225478414e-05,
      "loss": 1.2713,
      "step": 164
    },
    {
      "epoch": 0.009264588217128259,
      "grad_norm": 0.35512736439704895,
      "learning_rate": 6.583339969007363e-05,
      "loss": 1.295,
      "step": 165
    },
    {
      "epoch": 0.009320737236626006,
      "grad_norm": 0.3737083375453949,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.3323,
      "step": 166
    },
    {
      "epoch": 0.009376886256123752,
      "grad_norm": 0.4016343951225281,
      "learning_rate": 6.506729716392481e-05,
      "loss": 1.4126,
      "step": 167
    },
    {
      "epoch": 0.009433035275621499,
      "grad_norm": 0.3611617386341095,
      "learning_rate": 6.468276691378155e-05,
      "loss": 1.3274,
      "step": 168
    },
    {
      "epoch": 0.009489184295119246,
      "grad_norm": 0.3725200295448303,
      "learning_rate": 6.429728391993446e-05,
      "loss": 1.3742,
      "step": 169
    },
    {
      "epoch": 0.009545333314616994,
      "grad_norm": 0.3512539565563202,
      "learning_rate": 6.391087319582264e-05,
      "loss": 1.2968,
      "step": 170
    },
    {
      "epoch": 0.00960148233411474,
      "grad_norm": 0.36317336559295654,
      "learning_rate": 6.35235598150842e-05,
      "loss": 1.3214,
      "step": 171
    },
    {
      "epoch": 0.009657631353612488,
      "grad_norm": 0.34445124864578247,
      "learning_rate": 6.313536890992935e-05,
      "loss": 1.4116,
      "step": 172
    },
    {
      "epoch": 0.009713780373110235,
      "grad_norm": 0.3411950170993805,
      "learning_rate": 6.274632566950967e-05,
      "loss": 1.3073,
      "step": 173
    },
    {
      "epoch": 0.009769929392607981,
      "grad_norm": 0.34826982021331787,
      "learning_rate": 6.235645533828349e-05,
      "loss": 1.343,
      "step": 174
    },
    {
      "epoch": 0.009826078412105728,
      "grad_norm": 0.3545963764190674,
      "learning_rate": 6.19657832143779e-05,
      "loss": 1.242,
      "step": 175
    },
    {
      "epoch": 0.009882227431603476,
      "grad_norm": 0.3508628308773041,
      "learning_rate": 6.157433464794716e-05,
      "loss": 1.3282,
      "step": 176
    },
    {
      "epoch": 0.009938376451101223,
      "grad_norm": 0.3514939248561859,
      "learning_rate": 6.118213503952779e-05,
      "loss": 1.3372,
      "step": 177
    },
    {
      "epoch": 0.00999452547059897,
      "grad_norm": 0.3604854643344879,
      "learning_rate": 6.078920983839031e-05,
      "loss": 1.2204,
      "step": 178
    },
    {
      "epoch": 0.010050674490096717,
      "grad_norm": 0.3543670177459717,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.3297,
      "step": 179
    },
    {
      "epoch": 0.010106823509594463,
      "grad_norm": 0.3550858497619629,
      "learning_rate": 6.0001284688802226e-05,
      "loss": 1.2605,
      "step": 180
    },
    {
      "epoch": 0.01016297252909221,
      "grad_norm": 0.39260271191596985,
      "learning_rate": 5.960633586768543e-05,
      "loss": 1.3573,
      "step": 181
    },
    {
      "epoch": 0.010219121548589958,
      "grad_norm": 0.3887863755226135,
      "learning_rate": 5.921076370520058e-05,
      "loss": 1.363,
      "step": 182
    },
    {
      "epoch": 0.010275270568087705,
      "grad_norm": 0.37520524859428406,
      "learning_rate": 5.8814593869458455e-05,
      "loss": 1.3223,
      "step": 183
    },
    {
      "epoch": 0.010331419587585452,
      "grad_norm": 0.3729931712150574,
      "learning_rate": 5.841785206735192e-05,
      "loss": 1.2342,
      "step": 184
    },
    {
      "epoch": 0.0103875686070832,
      "grad_norm": 0.38081759214401245,
      "learning_rate": 5.8020564042888015e-05,
      "loss": 1.234,
      "step": 185
    },
    {
      "epoch": 0.010443717626580945,
      "grad_norm": 0.3631656765937805,
      "learning_rate": 5.762275557551727e-05,
      "loss": 1.3003,
      "step": 186
    },
    {
      "epoch": 0.010499866646078692,
      "grad_norm": 0.4031181037425995,
      "learning_rate": 5.7224452478461064e-05,
      "loss": 1.3298,
      "step": 187
    },
    {
      "epoch": 0.01055601566557644,
      "grad_norm": 0.4042447805404663,
      "learning_rate": 5.682568059703659e-05,
      "loss": 1.2979,
      "step": 188
    },
    {
      "epoch": 0.010612164685074187,
      "grad_norm": 0.40623968839645386,
      "learning_rate": 5.642646580697973e-05,
      "loss": 1.3856,
      "step": 189
    },
    {
      "epoch": 0.010668313704571934,
      "grad_norm": 0.40532568097114563,
      "learning_rate": 5.602683401276615e-05,
      "loss": 1.4164,
      "step": 190
    },
    {
      "epoch": 0.010724462724069682,
      "grad_norm": 0.39717039465904236,
      "learning_rate": 5.562681114593028e-05,
      "loss": 1.3338,
      "step": 191
    },
    {
      "epoch": 0.010780611743567427,
      "grad_norm": 0.40519657731056213,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.2581,
      "step": 192
    },
    {
      "epoch": 0.010836760763065174,
      "grad_norm": 0.39909666776657104,
      "learning_rate": 5.482569604572576e-05,
      "loss": 1.2558,
      "step": 193
    },
    {
      "epoch": 0.010892909782562922,
      "grad_norm": 0.4094207286834717,
      "learning_rate": 5.442465579556793e-05,
      "loss": 1.2703,
      "step": 194
    },
    {
      "epoch": 0.010949058802060669,
      "grad_norm": 0.4021713137626648,
      "learning_rate": 5.402332843583631e-05,
      "loss": 1.1132,
      "step": 195
    },
    {
      "epoch": 0.011005207821558416,
      "grad_norm": 0.4159744679927826,
      "learning_rate": 5.3621740008088126e-05,
      "loss": 1.2728,
      "step": 196
    },
    {
      "epoch": 0.011061356841056164,
      "grad_norm": 0.43642398715019226,
      "learning_rate": 5.321991657082097e-05,
      "loss": 1.1966,
      "step": 197
    },
    {
      "epoch": 0.01111750586055391,
      "grad_norm": 0.4745156764984131,
      "learning_rate": 5.281788419778187e-05,
      "loss": 1.1507,
      "step": 198
    },
    {
      "epoch": 0.011173654880051656,
      "grad_norm": 0.489679753780365,
      "learning_rate": 5.2415668976275355e-05,
      "loss": 1.1221,
      "step": 199
    },
    {
      "epoch": 0.011229803899549404,
      "grad_norm": 0.5562720894813538,
      "learning_rate": 5.201329700547076e-05,
      "loss": 0.987,
      "step": 200
    },
    {
      "epoch": 0.011229803899549404,
      "eval_loss": 1.3097492456436157,
      "eval_runtime": 498.6415,
      "eval_samples_per_second": 60.153,
      "eval_steps_per_second": 15.039,
      "step": 200
    },
    {
      "epoch": 0.011285952919047151,
      "grad_norm": 0.46652019023895264,
      "learning_rate": 5.161079439470866e-05,
      "loss": 1.4637,
      "step": 201
    },
    {
      "epoch": 0.011342101938544898,
      "grad_norm": 0.4668552279472351,
      "learning_rate": 5.1208187261806615e-05,
      "loss": 1.387,
      "step": 202
    },
    {
      "epoch": 0.011398250958042646,
      "grad_norm": 0.41647565364837646,
      "learning_rate": 5.080550173136457e-05,
      "loss": 1.3549,
      "step": 203
    },
    {
      "epoch": 0.011454399977540393,
      "grad_norm": 0.42582443356513977,
      "learning_rate": 5.0402763933069496e-05,
      "loss": 1.4554,
      "step": 204
    },
    {
      "epoch": 0.011510548997038138,
      "grad_norm": 0.4078443944454193,
      "learning_rate": 5e-05,
      "loss": 1.3543,
      "step": 205
    },
    {
      "epoch": 0.011566698016535886,
      "grad_norm": 0.40546315908432007,
      "learning_rate": 4.9597236066930516e-05,
      "loss": 1.3727,
      "step": 206
    },
    {
      "epoch": 0.011622847036033633,
      "grad_norm": 0.3524981141090393,
      "learning_rate": 4.919449826863544e-05,
      "loss": 1.344,
      "step": 207
    },
    {
      "epoch": 0.01167899605553138,
      "grad_norm": 0.35291409492492676,
      "learning_rate": 4.87918127381934e-05,
      "loss": 1.4609,
      "step": 208
    },
    {
      "epoch": 0.011735145075029128,
      "grad_norm": 0.3335376977920532,
      "learning_rate": 4.8389205605291365e-05,
      "loss": 1.2127,
      "step": 209
    },
    {
      "epoch": 0.011791294094526875,
      "grad_norm": 0.33301424980163574,
      "learning_rate": 4.798670299452926e-05,
      "loss": 1.2796,
      "step": 210
    },
    {
      "epoch": 0.01184744311402462,
      "grad_norm": 0.3301815390586853,
      "learning_rate": 4.758433102372466e-05,
      "loss": 1.2696,
      "step": 211
    },
    {
      "epoch": 0.011903592133522368,
      "grad_norm": 0.3339588940143585,
      "learning_rate": 4.7182115802218126e-05,
      "loss": 1.2953,
      "step": 212
    },
    {
      "epoch": 0.011959741153020115,
      "grad_norm": 0.3536163568496704,
      "learning_rate": 4.678008342917903e-05,
      "loss": 1.3142,
      "step": 213
    },
    {
      "epoch": 0.012015890172517862,
      "grad_norm": 0.35881930589675903,
      "learning_rate": 4.6378259991911886e-05,
      "loss": 1.2631,
      "step": 214
    },
    {
      "epoch": 0.01207203919201561,
      "grad_norm": 0.34832143783569336,
      "learning_rate": 4.597667156416371e-05,
      "loss": 1.3148,
      "step": 215
    },
    {
      "epoch": 0.012128188211513357,
      "grad_norm": 0.3691975772380829,
      "learning_rate": 4.5575344204432084e-05,
      "loss": 1.3122,
      "step": 216
    },
    {
      "epoch": 0.012184337231011104,
      "grad_norm": 0.3549201488494873,
      "learning_rate": 4.5174303954274244e-05,
      "loss": 1.3102,
      "step": 217
    },
    {
      "epoch": 0.01224048625050885,
      "grad_norm": 0.36213812232017517,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.3093,
      "step": 218
    },
    {
      "epoch": 0.012296635270006597,
      "grad_norm": 0.3908132016658783,
      "learning_rate": 4.437318885406973e-05,
      "loss": 1.3132,
      "step": 219
    },
    {
      "epoch": 0.012352784289504344,
      "grad_norm": 0.3759017586708069,
      "learning_rate": 4.397316598723385e-05,
      "loss": 1.2697,
      "step": 220
    },
    {
      "epoch": 0.012408933309002092,
      "grad_norm": 0.35085058212280273,
      "learning_rate": 4.3573534193020274e-05,
      "loss": 1.3245,
      "step": 221
    },
    {
      "epoch": 0.012465082328499839,
      "grad_norm": 0.3695438802242279,
      "learning_rate": 4.317431940296343e-05,
      "loss": 1.2508,
      "step": 222
    },
    {
      "epoch": 0.012521231347997586,
      "grad_norm": 0.34485650062561035,
      "learning_rate": 4.277554752153895e-05,
      "loss": 1.2654,
      "step": 223
    },
    {
      "epoch": 0.012577380367495332,
      "grad_norm": 0.3876595199108124,
      "learning_rate": 4.237724442448273e-05,
      "loss": 1.2942,
      "step": 224
    },
    {
      "epoch": 0.01263352938699308,
      "grad_norm": 0.355491042137146,
      "learning_rate": 4.197943595711198e-05,
      "loss": 1.2436,
      "step": 225
    },
    {
      "epoch": 0.012689678406490826,
      "grad_norm": 0.3636676073074341,
      "learning_rate": 4.1582147932648074e-05,
      "loss": 1.2598,
      "step": 226
    },
    {
      "epoch": 0.012745827425988574,
      "grad_norm": 0.36330193281173706,
      "learning_rate": 4.118540613054156e-05,
      "loss": 1.3101,
      "step": 227
    },
    {
      "epoch": 0.012801976445486321,
      "grad_norm": 0.3567420542240143,
      "learning_rate": 4.078923629479943e-05,
      "loss": 1.2313,
      "step": 228
    },
    {
      "epoch": 0.012858125464984068,
      "grad_norm": 0.3769914209842682,
      "learning_rate": 4.039366413231458e-05,
      "loss": 1.3703,
      "step": 229
    },
    {
      "epoch": 0.012914274484481814,
      "grad_norm": 0.36686626076698303,
      "learning_rate": 3.9998715311197785e-05,
      "loss": 1.2676,
      "step": 230
    },
    {
      "epoch": 0.012970423503979561,
      "grad_norm": 0.36683401465415955,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.3576,
      "step": 231
    },
    {
      "epoch": 0.013026572523477309,
      "grad_norm": 0.38010573387145996,
      "learning_rate": 3.92107901616097e-05,
      "loss": 1.318,
      "step": 232
    },
    {
      "epoch": 0.013082721542975056,
      "grad_norm": 0.387713760137558,
      "learning_rate": 3.8817864960472236e-05,
      "loss": 1.2782,
      "step": 233
    },
    {
      "epoch": 0.013138870562472803,
      "grad_norm": 0.38116419315338135,
      "learning_rate": 3.842566535205286e-05,
      "loss": 1.2469,
      "step": 234
    },
    {
      "epoch": 0.01319501958197055,
      "grad_norm": 0.4058433175086975,
      "learning_rate": 3.803421678562213e-05,
      "loss": 1.1416,
      "step": 235
    },
    {
      "epoch": 0.013251168601468298,
      "grad_norm": 0.3921027183532715,
      "learning_rate": 3.764354466171652e-05,
      "loss": 1.2828,
      "step": 236
    },
    {
      "epoch": 0.013307317620966043,
      "grad_norm": 0.40361857414245605,
      "learning_rate": 3.725367433049033e-05,
      "loss": 1.3705,
      "step": 237
    },
    {
      "epoch": 0.01336346664046379,
      "grad_norm": 0.41897809505462646,
      "learning_rate": 3.6864631090070655e-05,
      "loss": 1.3478,
      "step": 238
    },
    {
      "epoch": 0.013419615659961538,
      "grad_norm": 0.3961997628211975,
      "learning_rate": 3.6476440184915815e-05,
      "loss": 1.1923,
      "step": 239
    },
    {
      "epoch": 0.013475764679459285,
      "grad_norm": 0.3889695107936859,
      "learning_rate": 3.608912680417737e-05,
      "loss": 1.2304,
      "step": 240
    },
    {
      "epoch": 0.013531913698957032,
      "grad_norm": 0.42765000462532043,
      "learning_rate": 3.570271608006555e-05,
      "loss": 1.3064,
      "step": 241
    },
    {
      "epoch": 0.01358806271845478,
      "grad_norm": 0.4513327479362488,
      "learning_rate": 3.531723308621847e-05,
      "loss": 1.3254,
      "step": 242
    },
    {
      "epoch": 0.013644211737952525,
      "grad_norm": 0.43143191933631897,
      "learning_rate": 3.493270283607522e-05,
      "loss": 1.2714,
      "step": 243
    },
    {
      "epoch": 0.013700360757450273,
      "grad_norm": 0.4802146255970001,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.2424,
      "step": 244
    },
    {
      "epoch": 0.01375650977694802,
      "grad_norm": 0.4541313052177429,
      "learning_rate": 3.4166600309926387e-05,
      "loss": 1.1924,
      "step": 245
    },
    {
      "epoch": 0.013812658796445767,
      "grad_norm": 0.44022858142852783,
      "learning_rate": 3.3785077745215873e-05,
      "loss": 1.1144,
      "step": 246
    },
    {
      "epoch": 0.013868807815943514,
      "grad_norm": 0.46132948994636536,
      "learning_rate": 3.340460734357359e-05,
      "loss": 1.0814,
      "step": 247
    },
    {
      "epoch": 0.013924956835441262,
      "grad_norm": 0.5146449208259583,
      "learning_rate": 3.3025213793178646e-05,
      "loss": 1.2631,
      "step": 248
    },
    {
      "epoch": 0.013981105854939007,
      "grad_norm": 0.5137025117874146,
      "learning_rate": 3.264692171233485e-05,
      "loss": 1.1387,
      "step": 249
    },
    {
      "epoch": 0.014037254874436755,
      "grad_norm": 0.6411381959915161,
      "learning_rate": 3.226975564787322e-05,
      "loss": 1.0166,
      "step": 250
    },
    {
      "epoch": 0.014037254874436755,
      "eval_loss": 1.296608567237854,
      "eval_runtime": 499.0876,
      "eval_samples_per_second": 60.1,
      "eval_steps_per_second": 15.025,
      "step": 250
    },
    {
      "epoch": 0.014093403893934502,
      "grad_norm": 0.4505254328250885,
      "learning_rate": 3.189374007355917e-05,
      "loss": 1.4111,
      "step": 251
    },
    {
      "epoch": 0.01414955291343225,
      "grad_norm": 0.4572156071662903,
      "learning_rate": 3.151889938850445e-05,
      "loss": 1.3163,
      "step": 252
    },
    {
      "epoch": 0.014205701932929997,
      "grad_norm": 0.4478249251842499,
      "learning_rate": 3.114525791558398e-05,
      "loss": 1.4217,
      "step": 253
    },
    {
      "epoch": 0.014261850952427744,
      "grad_norm": 0.4304685890674591,
      "learning_rate": 3.0772839899857464e-05,
      "loss": 1.3542,
      "step": 254
    },
    {
      "epoch": 0.01431799997192549,
      "grad_norm": 0.4152209162712097,
      "learning_rate": 3.0401669506996256e-05,
      "loss": 1.2942,
      "step": 255
    },
    {
      "epoch": 0.014374148991423237,
      "grad_norm": 0.3953701853752136,
      "learning_rate": 3.003177082171523e-05,
      "loss": 1.3711,
      "step": 256
    },
    {
      "epoch": 0.014430298010920984,
      "grad_norm": 0.4507032632827759,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.4114,
      "step": 257
    },
    {
      "epoch": 0.014486447030418731,
      "grad_norm": 0.4072997272014618,
      "learning_rate": 2.9295884498599414e-05,
      "loss": 1.3021,
      "step": 258
    },
    {
      "epoch": 0.014542596049916479,
      "grad_norm": 0.40184441208839417,
      "learning_rate": 2.8929944611373554e-05,
      "loss": 1.2979,
      "step": 259
    },
    {
      "epoch": 0.014598745069414226,
      "grad_norm": 0.37164926528930664,
      "learning_rate": 2.8565371929847284e-05,
      "loss": 1.348,
      "step": 260
    },
    {
      "epoch": 0.014654894088911973,
      "grad_norm": 0.35735926032066345,
      "learning_rate": 2.8202190110619493e-05,
      "loss": 1.3025,
      "step": 261
    },
    {
      "epoch": 0.014711043108409719,
      "grad_norm": 0.3573881983757019,
      "learning_rate": 2.784042272003794e-05,
      "loss": 1.343,
      "step": 262
    },
    {
      "epoch": 0.014767192127907466,
      "grad_norm": 0.35015079379081726,
      "learning_rate": 2.7480093232670158e-05,
      "loss": 1.3121,
      "step": 263
    },
    {
      "epoch": 0.014823341147405213,
      "grad_norm": 0.3534146249294281,
      "learning_rate": 2.712122502978024e-05,
      "loss": 1.2726,
      "step": 264
    },
    {
      "epoch": 0.01487949016690296,
      "grad_norm": 0.3313038945198059,
      "learning_rate": 2.6763841397811573e-05,
      "loss": 1.348,
      "step": 265
    },
    {
      "epoch": 0.014935639186400708,
      "grad_norm": 0.3493979275226593,
      "learning_rate": 2.64079655268759e-05,
      "loss": 1.3328,
      "step": 266
    },
    {
      "epoch": 0.014991788205898455,
      "grad_norm": 0.3691670298576355,
      "learning_rate": 2.605362050924848e-05,
      "loss": 1.336,
      "step": 267
    },
    {
      "epoch": 0.0150479372253962,
      "grad_norm": 0.35904359817504883,
      "learning_rate": 2.57008293378697e-05,
      "loss": 1.3473,
      "step": 268
    },
    {
      "epoch": 0.015104086244893948,
      "grad_norm": 0.3535221219062805,
      "learning_rate": 2.534961490485313e-05,
      "loss": 1.2746,
      "step": 269
    },
    {
      "epoch": 0.015160235264391695,
      "grad_norm": 0.34725767374038696,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.1893,
      "step": 270
    },
    {
      "epoch": 0.015216384283889443,
      "grad_norm": 0.35040995478630066,
      "learning_rate": 2.4652007309320498e-05,
      "loss": 1.2737,
      "step": 271
    },
    {
      "epoch": 0.01527253330338719,
      "grad_norm": 0.34966787695884705,
      "learning_rate": 2.430565941356157e-05,
      "loss": 1.2286,
      "step": 272
    },
    {
      "epoch": 0.015328682322884937,
      "grad_norm": 0.37002241611480713,
      "learning_rate": 2.3960978786741877e-05,
      "loss": 1.215,
      "step": 273
    },
    {
      "epoch": 0.015384831342382683,
      "grad_norm": 0.39117783308029175,
      "learning_rate": 2.361798779469336e-05,
      "loss": 1.2223,
      "step": 274
    },
    {
      "epoch": 0.01544098036188043,
      "grad_norm": 0.36275404691696167,
      "learning_rate": 2.3276708693609943e-05,
      "loss": 1.2425,
      "step": 275
    },
    {
      "epoch": 0.015497129381378177,
      "grad_norm": 0.3890242874622345,
      "learning_rate": 2.2937163628603435e-05,
      "loss": 1.3307,
      "step": 276
    },
    {
      "epoch": 0.015553278400875925,
      "grad_norm": 0.3915593922138214,
      "learning_rate": 2.259937463226651e-05,
      "loss": 1.3258,
      "step": 277
    },
    {
      "epoch": 0.015609427420373672,
      "grad_norm": 0.38208678364753723,
      "learning_rate": 2.2263363623243054e-05,
      "loss": 1.2349,
      "step": 278
    },
    {
      "epoch": 0.015665576439871418,
      "grad_norm": 0.3824746012687683,
      "learning_rate": 2.192915240480596e-05,
      "loss": 1.2961,
      "step": 279
    },
    {
      "epoch": 0.015721725459369167,
      "grad_norm": 0.39434826374053955,
      "learning_rate": 2.1596762663442218e-05,
      "loss": 1.2594,
      "step": 280
    },
    {
      "epoch": 0.015777874478866912,
      "grad_norm": 0.37662407755851746,
      "learning_rate": 2.1266215967445824e-05,
      "loss": 1.3304,
      "step": 281
    },
    {
      "epoch": 0.01583402349836466,
      "grad_norm": 0.37989699840545654,
      "learning_rate": 2.0937533765518187e-05,
      "loss": 1.3393,
      "step": 282
    },
    {
      "epoch": 0.015890172517862407,
      "grad_norm": 0.36484554409980774,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.2497,
      "step": 283
    },
    {
      "epoch": 0.015946321537360152,
      "grad_norm": 0.40005627274513245,
      "learning_rate": 2.0285848032369137e-05,
      "loss": 1.3388,
      "step": 284
    },
    {
      "epoch": 0.0160024705568579,
      "grad_norm": 0.40992552042007446,
      "learning_rate": 1.996288678810105e-05,
      "loss": 1.2011,
      "step": 285
    },
    {
      "epoch": 0.016058619576355647,
      "grad_norm": 0.382816880941391,
      "learning_rate": 1.9641874609064443e-05,
      "loss": 1.232,
      "step": 286
    },
    {
      "epoch": 0.016114768595853396,
      "grad_norm": 0.4048992097377777,
      "learning_rate": 1.932283232527956e-05,
      "loss": 1.3749,
      "step": 287
    },
    {
      "epoch": 0.01617091761535114,
      "grad_norm": 0.4019702076911926,
      "learning_rate": 1.9005780638942982e-05,
      "loss": 1.3299,
      "step": 288
    },
    {
      "epoch": 0.01622706663484889,
      "grad_norm": 0.4380313456058502,
      "learning_rate": 1.8690740123084316e-05,
      "loss": 1.233,
      "step": 289
    },
    {
      "epoch": 0.016283215654346636,
      "grad_norm": 0.39561840891838074,
      "learning_rate": 1.837773122023114e-05,
      "loss": 1.2887,
      "step": 290
    },
    {
      "epoch": 0.01633936467384438,
      "grad_norm": 0.4392796754837036,
      "learning_rate": 1.8066774241082612e-05,
      "loss": 1.4252,
      "step": 291
    },
    {
      "epoch": 0.01639551369334213,
      "grad_norm": 0.40080904960632324,
      "learning_rate": 1.7757889363191483e-05,
      "loss": 1.2624,
      "step": 292
    },
    {
      "epoch": 0.016451662712839876,
      "grad_norm": 0.45219239592552185,
      "learning_rate": 1.745109662965481e-05,
      "loss": 1.2129,
      "step": 293
    },
    {
      "epoch": 0.016507811732337625,
      "grad_norm": 0.43907997012138367,
      "learning_rate": 1.714641594781347e-05,
      "loss": 1.3124,
      "step": 294
    },
    {
      "epoch": 0.01656396075183537,
      "grad_norm": 0.41240158677101135,
      "learning_rate": 1.684386708796025e-05,
      "loss": 1.1324,
      "step": 295
    },
    {
      "epoch": 0.016620109771333116,
      "grad_norm": 0.44435441493988037,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.2009,
      "step": 296
    },
    {
      "epoch": 0.016676258790830865,
      "grad_norm": 0.4538898169994354,
      "learning_rate": 1.62452432224612e-05,
      "loss": 1.1685,
      "step": 297
    },
    {
      "epoch": 0.01673240781032861,
      "grad_norm": 0.4689037501811981,
      "learning_rate": 1.5949207060660138e-05,
      "loss": 1.1904,
      "step": 298
    },
    {
      "epoch": 0.01678855682982636,
      "grad_norm": 0.4631802439689636,
      "learning_rate": 1.5655380406016235e-05,
      "loss": 1.0483,
      "step": 299
    },
    {
      "epoch": 0.016844705849324106,
      "grad_norm": 0.6165627837181091,
      "learning_rate": 1.536378232452003e-05,
      "loss": 0.9398,
      "step": 300
    },
    {
      "epoch": 0.016844705849324106,
      "eval_loss": 1.279380202293396,
      "eval_runtime": 499.0134,
      "eval_samples_per_second": 60.109,
      "eval_steps_per_second": 15.028,
      "step": 300
    },
    {
      "epoch": 0.016900854868821855,
      "grad_norm": 0.39996984601020813,
      "learning_rate": 1.5074431737553157e-05,
      "loss": 1.3848,
      "step": 301
    },
    {
      "epoch": 0.0169570038883196,
      "grad_norm": 0.38276180624961853,
      "learning_rate": 1.4787347420660541e-05,
      "loss": 1.3349,
      "step": 302
    },
    {
      "epoch": 0.017013152907817346,
      "grad_norm": 0.39884066581726074,
      "learning_rate": 1.4502548002332088e-05,
      "loss": 1.3812,
      "step": 303
    },
    {
      "epoch": 0.017069301927315095,
      "grad_norm": 0.3843788206577301,
      "learning_rate": 1.422005196279395e-05,
      "loss": 1.2971,
      "step": 304
    },
    {
      "epoch": 0.01712545094681284,
      "grad_norm": 0.41161036491394043,
      "learning_rate": 1.3939877632809278e-05,
      "loss": 1.3222,
      "step": 305
    },
    {
      "epoch": 0.01718159996631059,
      "grad_norm": 0.3806777596473694,
      "learning_rate": 1.3662043192488849e-05,
      "loss": 1.4334,
      "step": 306
    },
    {
      "epoch": 0.017237748985808335,
      "grad_norm": 0.41733574867248535,
      "learning_rate": 1.338656667011134e-05,
      "loss": 1.3468,
      "step": 307
    },
    {
      "epoch": 0.017293898005306084,
      "grad_norm": 0.36818546056747437,
      "learning_rate": 1.3113465940953495e-05,
      "loss": 1.2919,
      "step": 308
    },
    {
      "epoch": 0.01735004702480383,
      "grad_norm": 0.36422911286354065,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.3379,
      "step": 309
    },
    {
      "epoch": 0.017406196044301575,
      "grad_norm": 0.3661137819290161,
      "learning_rate": 1.257446259144494e-05,
      "loss": 1.2738,
      "step": 310
    },
    {
      "epoch": 0.017462345063799324,
      "grad_norm": 0.38392874598503113,
      "learning_rate": 1.2308594946249163e-05,
      "loss": 1.3739,
      "step": 311
    },
    {
      "epoch": 0.01751849408329707,
      "grad_norm": 0.3421986997127533,
      "learning_rate": 1.204517304231343e-05,
      "loss": 1.2518,
      "step": 312
    },
    {
      "epoch": 0.01757464310279482,
      "grad_norm": 0.36683598160743713,
      "learning_rate": 1.178421397270758e-05,
      "loss": 1.2443,
      "step": 313
    },
    {
      "epoch": 0.017630792122292564,
      "grad_norm": 0.35750842094421387,
      "learning_rate": 1.1525734670691701e-05,
      "loss": 1.3185,
      "step": 314
    },
    {
      "epoch": 0.01768694114179031,
      "grad_norm": 0.3540304899215698,
      "learning_rate": 1.1269751908617277e-05,
      "loss": 1.2935,
      "step": 315
    },
    {
      "epoch": 0.01774309016128806,
      "grad_norm": 0.3719668984413147,
      "learning_rate": 1.1016282296838887e-05,
      "loss": 1.3725,
      "step": 316
    },
    {
      "epoch": 0.017799239180785804,
      "grad_norm": 0.36506494879722595,
      "learning_rate": 1.0765342282636416e-05,
      "loss": 1.3109,
      "step": 317
    },
    {
      "epoch": 0.017855388200283553,
      "grad_norm": 0.364102840423584,
      "learning_rate": 1.0516948149147754e-05,
      "loss": 1.3361,
      "step": 318
    },
    {
      "epoch": 0.0179115372197813,
      "grad_norm": 0.37906649708747864,
      "learning_rate": 1.0271116014312293e-05,
      "loss": 1.2841,
      "step": 319
    },
    {
      "epoch": 0.017967686239279048,
      "grad_norm": 0.3620559871196747,
      "learning_rate": 1.0027861829824952e-05,
      "loss": 1.3347,
      "step": 320
    },
    {
      "epoch": 0.018023835258776794,
      "grad_norm": 0.39068368077278137,
      "learning_rate": 9.787201380101157e-06,
      "loss": 1.4736,
      "step": 321
    },
    {
      "epoch": 0.01807998427827454,
      "grad_norm": 0.3771114945411682,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.2449,
      "step": 322
    },
    {
      "epoch": 0.018136133297772288,
      "grad_norm": 0.3521263599395752,
      "learning_rate": 9.313723980074018e-06,
      "loss": 1.2032,
      "step": 323
    },
    {
      "epoch": 0.018192282317270034,
      "grad_norm": 0.36386626958847046,
      "learning_rate": 9.080937753040646e-06,
      "loss": 1.2131,
      "step": 324
    },
    {
      "epoch": 0.018248431336767783,
      "grad_norm": 0.36094191670417786,
      "learning_rate": 8.850806705317183e-06,
      "loss": 1.2094,
      "step": 325
    },
    {
      "epoch": 0.01830458035626553,
      "grad_norm": 0.3768877685070038,
      "learning_rate": 8.623345769777514e-06,
      "loss": 1.2808,
      "step": 326
    },
    {
      "epoch": 0.018360729375763277,
      "grad_norm": 0.3609795570373535,
      "learning_rate": 8.398569706035792e-06,
      "loss": 1.2626,
      "step": 327
    },
    {
      "epoch": 0.018416878395261023,
      "grad_norm": 0.39607855677604675,
      "learning_rate": 8.176493099488663e-06,
      "loss": 1.183,
      "step": 328
    },
    {
      "epoch": 0.01847302741475877,
      "grad_norm": 0.3754710853099823,
      "learning_rate": 7.957130360368898e-06,
      "loss": 1.2081,
      "step": 329
    },
    {
      "epoch": 0.018529176434256518,
      "grad_norm": 0.376335084438324,
      "learning_rate": 7.740495722810271e-06,
      "loss": 1.3336,
      "step": 330
    },
    {
      "epoch": 0.018585325453754263,
      "grad_norm": 0.3971085846424103,
      "learning_rate": 7.526603243923957e-06,
      "loss": 1.4144,
      "step": 331
    },
    {
      "epoch": 0.018641474473252012,
      "grad_norm": 0.4067937731742859,
      "learning_rate": 7.315466802886401e-06,
      "loss": 1.2518,
      "step": 332
    },
    {
      "epoch": 0.018697623492749758,
      "grad_norm": 0.39756736159324646,
      "learning_rate": 7.107100100038671e-06,
      "loss": 1.2623,
      "step": 333
    },
    {
      "epoch": 0.018753772512247503,
      "grad_norm": 0.4126104712486267,
      "learning_rate": 6.901516655997536e-06,
      "loss": 1.3702,
      "step": 334
    },
    {
      "epoch": 0.018809921531745252,
      "grad_norm": 0.3861372470855713,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.1146,
      "step": 335
    },
    {
      "epoch": 0.018866070551242998,
      "grad_norm": 0.37583255767822266,
      "learning_rate": 6.498752722928042e-06,
      "loss": 1.2149,
      "step": 336
    },
    {
      "epoch": 0.018922219570740747,
      "grad_norm": 0.40195921063423157,
      "learning_rate": 6.301598368674105e-06,
      "loss": 1.3847,
      "step": 337
    },
    {
      "epoch": 0.018978368590238492,
      "grad_norm": 0.41740453243255615,
      "learning_rate": 6.107279541079769e-06,
      "loss": 1.2578,
      "step": 338
    },
    {
      "epoch": 0.01903451760973624,
      "grad_norm": 0.43475598096847534,
      "learning_rate": 5.915808849215304e-06,
      "loss": 1.221,
      "step": 339
    },
    {
      "epoch": 0.019090666629233987,
      "grad_norm": 0.44030851125717163,
      "learning_rate": 5.727198717339511e-06,
      "loss": 1.333,
      "step": 340
    },
    {
      "epoch": 0.019146815648731733,
      "grad_norm": 0.41893166303634644,
      "learning_rate": 5.54146138409355e-06,
      "loss": 1.1942,
      "step": 341
    },
    {
      "epoch": 0.01920296466822948,
      "grad_norm": 0.4973892867565155,
      "learning_rate": 5.358608901706802e-06,
      "loss": 1.3368,
      "step": 342
    },
    {
      "epoch": 0.019259113687727227,
      "grad_norm": 0.46447569131851196,
      "learning_rate": 5.178653135214812e-06,
      "loss": 1.1584,
      "step": 343
    },
    {
      "epoch": 0.019315262707224976,
      "grad_norm": 0.4224729537963867,
      "learning_rate": 5.001605761689398e-06,
      "loss": 1.2833,
      "step": 344
    },
    {
      "epoch": 0.019371411726722722,
      "grad_norm": 0.43293389678001404,
      "learning_rate": 4.827478269480895e-06,
      "loss": 1.1903,
      "step": 345
    },
    {
      "epoch": 0.01942756074622047,
      "grad_norm": 0.46209219098091125,
      "learning_rate": 4.65628195747273e-06,
      "loss": 1.19,
      "step": 346
    },
    {
      "epoch": 0.019483709765718216,
      "grad_norm": 0.49419763684272766,
      "learning_rate": 4.488027934348271e-06,
      "loss": 1.2566,
      "step": 347
    },
    {
      "epoch": 0.019539858785215962,
      "grad_norm": 0.5506183505058289,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.2258,
      "step": 348
    },
    {
      "epoch": 0.01959600780471371,
      "grad_norm": 0.5689681172370911,
      "learning_rate": 4.16039023417088e-06,
      "loss": 1.0813,
      "step": 349
    },
    {
      "epoch": 0.019652156824211457,
      "grad_norm": 0.743087649345398,
      "learning_rate": 4.001027817058789e-06,
      "loss": 1.0321,
      "step": 350
    },
    {
      "epoch": 0.019652156824211457,
      "eval_loss": 1.2723369598388672,
      "eval_runtime": 499.2128,
      "eval_samples_per_second": 60.085,
      "eval_steps_per_second": 15.022,
      "step": 350
    },
    {
      "epoch": 0.019708305843709206,
      "grad_norm": 0.36800873279571533,
      "learning_rate": 3.844650207332562e-06,
      "loss": 1.3682,
      "step": 351
    },
    {
      "epoch": 0.01976445486320695,
      "grad_norm": 0.3377681076526642,
      "learning_rate": 3.691267552111183e-06,
      "loss": 1.3038,
      "step": 352
    },
    {
      "epoch": 0.019820603882704697,
      "grad_norm": 0.34921079874038696,
      "learning_rate": 3.54088980417534e-06,
      "loss": 1.2905,
      "step": 353
    },
    {
      "epoch": 0.019876752902202446,
      "grad_norm": 0.3415435552597046,
      "learning_rate": 3.393526721321616e-06,
      "loss": 1.3048,
      "step": 354
    },
    {
      "epoch": 0.01993290192170019,
      "grad_norm": 0.385629802942276,
      "learning_rate": 3.249187865729264e-06,
      "loss": 1.2855,
      "step": 355
    },
    {
      "epoch": 0.01998905094119794,
      "grad_norm": 0.33783087134361267,
      "learning_rate": 3.1078826033397843e-06,
      "loss": 1.2968,
      "step": 356
    },
    {
      "epoch": 0.020045199960695686,
      "grad_norm": 0.37677091360092163,
      "learning_rate": 2.9696201032491434e-06,
      "loss": 1.3106,
      "step": 357
    },
    {
      "epoch": 0.020101348980193435,
      "grad_norm": 0.3581361770629883,
      "learning_rate": 2.8344093371128424e-06,
      "loss": 1.343,
      "step": 358
    },
    {
      "epoch": 0.02015749799969118,
      "grad_norm": 0.34285494685173035,
      "learning_rate": 2.70225907856374e-06,
      "loss": 1.3371,
      "step": 359
    },
    {
      "epoch": 0.020213647019188926,
      "grad_norm": 0.35909414291381836,
      "learning_rate": 2.573177902642726e-06,
      "loss": 1.3167,
      "step": 360
    },
    {
      "epoch": 0.020269796038686675,
      "grad_norm": 0.3384222388267517,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.2706,
      "step": 361
    },
    {
      "epoch": 0.02032594505818442,
      "grad_norm": 0.3651668131351471,
      "learning_rate": 2.324256102563188e-06,
      "loss": 1.3289,
      "step": 362
    },
    {
      "epoch": 0.02038209407768217,
      "grad_norm": 0.34311142563819885,
      "learning_rate": 2.204431630583548e-06,
      "loss": 1.2932,
      "step": 363
    },
    {
      "epoch": 0.020438243097179915,
      "grad_norm": 0.3421182632446289,
      "learning_rate": 2.087708544541689e-06,
      "loss": 1.2895,
      "step": 364
    },
    {
      "epoch": 0.020494392116677664,
      "grad_norm": 0.364944726228714,
      "learning_rate": 1.974094418431388e-06,
      "loss": 1.3483,
      "step": 365
    },
    {
      "epoch": 0.02055054113617541,
      "grad_norm": 0.3558295667171478,
      "learning_rate": 1.8635966245104664e-06,
      "loss": 1.3057,
      "step": 366
    },
    {
      "epoch": 0.020606690155673155,
      "grad_norm": 0.35519397258758545,
      "learning_rate": 1.7562223328224325e-06,
      "loss": 1.3091,
      "step": 367
    },
    {
      "epoch": 0.020662839175170904,
      "grad_norm": 0.3448637127876282,
      "learning_rate": 1.6519785107311891e-06,
      "loss": 1.2512,
      "step": 368
    },
    {
      "epoch": 0.02071898819466865,
      "grad_norm": 0.3545093238353729,
      "learning_rate": 1.5508719224689717e-06,
      "loss": 1.3812,
      "step": 369
    },
    {
      "epoch": 0.0207751372141664,
      "grad_norm": 0.35398516058921814,
      "learning_rate": 1.4529091286973995e-06,
      "loss": 1.3211,
      "step": 370
    },
    {
      "epoch": 0.020831286233664145,
      "grad_norm": 0.3714781403541565,
      "learning_rate": 1.358096486081778e-06,
      "loss": 1.333,
      "step": 371
    },
    {
      "epoch": 0.02088743525316189,
      "grad_norm": 0.35507217049598694,
      "learning_rate": 1.2664401468786114e-06,
      "loss": 1.3185,
      "step": 372
    },
    {
      "epoch": 0.02094358427265964,
      "grad_norm": 0.3716376721858978,
      "learning_rate": 1.1779460585363944e-06,
      "loss": 1.2996,
      "step": 373
    },
    {
      "epoch": 0.020999733292157385,
      "grad_norm": 0.36729657649993896,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.2479,
      "step": 374
    },
    {
      "epoch": 0.021055882311655134,
      "grad_norm": 0.35884541273117065,
      "learning_rate": 1.0104673978866164e-06,
      "loss": 1.3301,
      "step": 375
    },
    {
      "epoch": 0.02111203133115288,
      "grad_norm": 0.3605683445930481,
      "learning_rate": 9.314936930293283e-07,
      "loss": 1.2289,
      "step": 376
    },
    {
      "epoch": 0.02116818035065063,
      "grad_norm": 0.3460223078727722,
      "learning_rate": 8.557039732283944e-07,
      "loss": 1.237,
      "step": 377
    },
    {
      "epoch": 0.021224329370148374,
      "grad_norm": 0.3702046275138855,
      "learning_rate": 7.83103156370113e-07,
      "loss": 1.2009,
      "step": 378
    },
    {
      "epoch": 0.02128047838964612,
      "grad_norm": 0.36723971366882324,
      "learning_rate": 7.136959534174592e-07,
      "loss": 1.2211,
      "step": 379
    },
    {
      "epoch": 0.02133662740914387,
      "grad_norm": 0.37710997462272644,
      "learning_rate": 6.474868681043578e-07,
      "loss": 1.2392,
      "step": 380
    },
    {
      "epoch": 0.021392776428641614,
      "grad_norm": 0.3700467348098755,
      "learning_rate": 5.844801966434832e-07,
      "loss": 1.2476,
      "step": 381
    },
    {
      "epoch": 0.021448925448139363,
      "grad_norm": 0.3700866997241974,
      "learning_rate": 5.246800274474439e-07,
      "loss": 1.2151,
      "step": 382
    },
    {
      "epoch": 0.02150507446763711,
      "grad_norm": 0.4157610237598419,
      "learning_rate": 4.680902408635335e-07,
      "loss": 1.4174,
      "step": 383
    },
    {
      "epoch": 0.021561223487134854,
      "grad_norm": 0.39180654287338257,
      "learning_rate": 4.1471450892189846e-07,
      "loss": 1.3271,
      "step": 384
    },
    {
      "epoch": 0.021617372506632603,
      "grad_norm": 0.3855951130390167,
      "learning_rate": 3.6455629509730136e-07,
      "loss": 1.2205,
      "step": 385
    },
    {
      "epoch": 0.02167352152613035,
      "grad_norm": 0.3870358169078827,
      "learning_rate": 3.1761885408435054e-07,
      "loss": 1.2145,
      "step": 386
    },
    {
      "epoch": 0.021729670545628098,
      "grad_norm": 0.40940991044044495,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.3489,
      "step": 387
    },
    {
      "epoch": 0.021785819565125843,
      "grad_norm": 0.380584180355072,
      "learning_rate": 2.334182641175686e-07,
      "loss": 1.2265,
      "step": 388
    },
    {
      "epoch": 0.021841968584623592,
      "grad_norm": 0.41339078545570374,
      "learning_rate": 1.9616057881935436e-07,
      "loss": 1.2366,
      "step": 389
    },
    {
      "epoch": 0.021898117604121338,
      "grad_norm": 0.39812958240509033,
      "learning_rate": 1.6213459328950352e-07,
      "loss": 1.2635,
      "step": 390
    },
    {
      "epoch": 0.021954266623619084,
      "grad_norm": 0.42198699712753296,
      "learning_rate": 1.3134251542544774e-07,
      "loss": 1.2593,
      "step": 391
    },
    {
      "epoch": 0.022010415643116833,
      "grad_norm": 0.4326508641242981,
      "learning_rate": 1.0378634328099269e-07,
      "loss": 1.1585,
      "step": 392
    },
    {
      "epoch": 0.022066564662614578,
      "grad_norm": 0.4443672001361847,
      "learning_rate": 7.946786493666647e-08,
      "loss": 1.184,
      "step": 393
    },
    {
      "epoch": 0.022122713682112327,
      "grad_norm": 0.41310712695121765,
      "learning_rate": 5.838865838366792e-08,
      "loss": 1.1833,
      "step": 394
    },
    {
      "epoch": 0.022178862701610073,
      "grad_norm": 0.4295123219490051,
      "learning_rate": 4.055009142152067e-08,
      "loss": 1.2364,
      "step": 395
    },
    {
      "epoch": 0.02223501172110782,
      "grad_norm": 0.45007407665252686,
      "learning_rate": 2.595332156925534e-08,
      "loss": 1.226,
      "step": 396
    },
    {
      "epoch": 0.022291160740605567,
      "grad_norm": 0.48439890146255493,
      "learning_rate": 1.4599295990352924e-08,
      "loss": 1.1626,
      "step": 397
    },
    {
      "epoch": 0.022347309760103313,
      "grad_norm": 0.4942685067653656,
      "learning_rate": 6.488751431266149e-09,
      "loss": 1.1715,
      "step": 398
    },
    {
      "epoch": 0.022403458779601062,
      "grad_norm": 0.45637187361717224,
      "learning_rate": 1.622214173602199e-09,
      "loss": 1.1143,
      "step": 399
    },
    {
      "epoch": 0.022459607799098807,
      "grad_norm": 0.6239014267921448,
      "learning_rate": 0.0,
      "loss": 0.9608,
      "step": 400
    },
    {
      "epoch": 0.022459607799098807,
      "eval_loss": 1.271822214126587,
      "eval_runtime": 498.9496,
      "eval_samples_per_second": 60.116,
      "eval_steps_per_second": 15.03,
      "step": 400
    }
  ],
  "logging_steps": 1,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2.7475518160896e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}