{
  "best_metric": 0.2537326514720917,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.03614022406938923,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00024093482712926153,
      "grad_norm": 2.7897026538848877,
      "learning_rate": 1e-05,
      "loss": 5.8362,
      "step": 1
    },
    {
      "epoch": 0.00024093482712926153,
      "eval_loss": 5.242364883422852,
      "eval_runtime": 509.5798,
      "eval_samples_per_second": 13.717,
      "eval_steps_per_second": 3.43,
      "step": 1
    },
    {
      "epoch": 0.00048186965425852307,
      "grad_norm": 2.6845810413360596,
      "learning_rate": 2e-05,
      "loss": 4.8628,
      "step": 2
    },
    {
      "epoch": 0.0007228044813877846,
      "grad_norm": 2.5649805068969727,
      "learning_rate": 3e-05,
      "loss": 4.7359,
      "step": 3
    },
    {
      "epoch": 0.0009637393085170461,
      "grad_norm": 3.1907050609588623,
      "learning_rate": 4e-05,
      "loss": 5.09,
      "step": 4
    },
    {
      "epoch": 0.0012046741356463078,
      "grad_norm": 2.8700222969055176,
      "learning_rate": 5e-05,
      "loss": 4.6159,
      "step": 5
    },
    {
      "epoch": 0.0014456089627755693,
      "grad_norm": 3.2576119899749756,
      "learning_rate": 6e-05,
      "loss": 4.6056,
      "step": 6
    },
    {
      "epoch": 0.0016865437899048308,
      "grad_norm": 3.8452327251434326,
      "learning_rate": 7e-05,
      "loss": 4.3039,
      "step": 7
    },
    {
      "epoch": 0.0019274786170340923,
      "grad_norm": 3.6989893913269043,
      "learning_rate": 8e-05,
      "loss": 3.6032,
      "step": 8
    },
    {
      "epoch": 0.0021684134441633538,
      "grad_norm": 3.7668285369873047,
      "learning_rate": 9e-05,
      "loss": 2.9093,
      "step": 9
    },
    {
      "epoch": 0.0024093482712926155,
      "grad_norm": 3.5740230083465576,
      "learning_rate": 0.0001,
      "loss": 2.2147,
      "step": 10
    },
    {
      "epoch": 0.002650283098421877,
      "grad_norm": 3.976719856262207,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.7271,
      "step": 11
    },
    {
      "epoch": 0.0028912179255511385,
      "grad_norm": 2.956078290939331,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.9299,
      "step": 12
    },
    {
      "epoch": 0.0031321527526804,
      "grad_norm": 3.046994209289551,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.7804,
      "step": 13
    },
    {
      "epoch": 0.0033730875798096615,
      "grad_norm": 2.9345862865448,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.5992,
      "step": 14
    },
    {
      "epoch": 0.003614022406938923,
      "grad_norm": 2.556488037109375,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.4438,
      "step": 15
    },
    {
      "epoch": 0.0038549572340681845,
      "grad_norm": 3.2892167568206787,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.4652,
      "step": 16
    },
    {
      "epoch": 0.004095892061197446,
      "grad_norm": 2.5346927642822266,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.3075,
      "step": 17
    },
    {
      "epoch": 0.0043368268883267076,
      "grad_norm": 1.4730305671691895,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.2703,
      "step": 18
    },
    {
      "epoch": 0.004577761715455969,
      "grad_norm": 2.9341955184936523,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.3485,
      "step": 19
    },
    {
      "epoch": 0.004818696542585231,
      "grad_norm": 1.3553968667984009,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.3135,
      "step": 20
    },
    {
      "epoch": 0.005059631369714492,
      "grad_norm": 1.0334441661834717,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.2394,
      "step": 21
    },
    {
      "epoch": 0.005300566196843754,
      "grad_norm": 1.1508598327636719,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.2423,
      "step": 22
    },
    {
      "epoch": 0.005541501023973015,
      "grad_norm": 2.3248560428619385,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.3399,
      "step": 23
    },
    {
      "epoch": 0.005782435851102277,
      "grad_norm": 1.3670281171798706,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.2859,
      "step": 24
    },
    {
      "epoch": 0.006023370678231539,
      "grad_norm": 1.5140188932418823,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.2533,
      "step": 25
    },
    {
      "epoch": 0.0062643055053608,
      "grad_norm": 1.4202511310577393,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.2423,
      "step": 26
    },
    {
      "epoch": 0.006505240332490061,
      "grad_norm": 1.0033921003341675,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.2302,
      "step": 27
    },
    {
      "epoch": 0.006746175159619323,
      "grad_norm": 1.338563323020935,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.2563,
      "step": 28
    },
    {
      "epoch": 0.006987109986748585,
      "grad_norm": 1.742248296737671,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.356,
      "step": 29
    },
    {
      "epoch": 0.007228044813877846,
      "grad_norm": 1.6856114864349365,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.3796,
      "step": 30
    },
    {
      "epoch": 0.007468979641007107,
      "grad_norm": 1.2257651090621948,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.3383,
      "step": 31
    },
    {
      "epoch": 0.007709914468136369,
      "grad_norm": 1.0800436735153198,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.2814,
      "step": 32
    },
    {
      "epoch": 0.00795084929526563,
      "grad_norm": 1.1578192710876465,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.2607,
      "step": 33
    },
    {
      "epoch": 0.008191784122394892,
      "grad_norm": 0.7927069067955017,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.2871,
      "step": 34
    },
    {
      "epoch": 0.008432718949524154,
      "grad_norm": 0.7488431930541992,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.2815,
      "step": 35
    },
    {
      "epoch": 0.008673653776653415,
      "grad_norm": 0.8880829811096191,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.2472,
      "step": 36
    },
    {
      "epoch": 0.008914588603782676,
      "grad_norm": 0.785861611366272,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.254,
      "step": 37
    },
    {
      "epoch": 0.009155523430911939,
      "grad_norm": 0.9267710447311401,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.31,
      "step": 38
    },
    {
      "epoch": 0.0093964582580412,
      "grad_norm": 0.9613037109375,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.2692,
      "step": 39
    },
    {
      "epoch": 0.009637393085170462,
      "grad_norm": 0.7821824550628662,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.2649,
      "step": 40
    },
    {
      "epoch": 0.009878327912299723,
      "grad_norm": 0.34622684121131897,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.2259,
      "step": 41
    },
    {
      "epoch": 0.010119262739428984,
      "grad_norm": 0.9428150057792664,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.3055,
      "step": 42
    },
    {
      "epoch": 0.010360197566558246,
      "grad_norm": 0.6529460549354553,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.2491,
      "step": 43
    },
    {
      "epoch": 0.010601132393687507,
      "grad_norm": 0.959650456905365,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.2854,
      "step": 44
    },
    {
      "epoch": 0.01084206722081677,
      "grad_norm": 0.9203677773475647,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.2827,
      "step": 45
    },
    {
      "epoch": 0.01108300204794603,
      "grad_norm": 0.6406137943267822,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.2689,
      "step": 46
    },
    {
      "epoch": 0.011323936875075291,
      "grad_norm": 0.6154417395591736,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.28,
      "step": 47
    },
    {
      "epoch": 0.011564871702204554,
      "grad_norm": 0.6750221848487854,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.255,
      "step": 48
    },
    {
      "epoch": 0.011805806529333815,
      "grad_norm": 0.8649730682373047,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.3184,
      "step": 49
    },
    {
      "epoch": 0.012046741356463078,
      "grad_norm": 0.9113279581069946,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.3207,
      "step": 50
    },
    {
      "epoch": 0.012046741356463078,
      "eval_loss": 0.2953316271305084,
      "eval_runtime": 511.8644,
      "eval_samples_per_second": 13.656,
      "eval_steps_per_second": 3.415,
      "step": 50
    },
    {
      "epoch": 0.012287676183592338,
      "grad_norm": 1.0552361011505127,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.7515,
      "step": 51
    },
    {
      "epoch": 0.0125286110107216,
      "grad_norm": 0.5925299525260925,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.2375,
      "step": 52
    },
    {
      "epoch": 0.012769545837850862,
      "grad_norm": 0.611186146736145,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.2472,
      "step": 53
    },
    {
      "epoch": 0.013010480664980123,
      "grad_norm": 0.613996684551239,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.2734,
      "step": 54
    },
    {
      "epoch": 0.013251415492109385,
      "grad_norm": 0.6335679292678833,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.2563,
      "step": 55
    },
    {
      "epoch": 0.013492350319238646,
      "grad_norm": 0.3528399169445038,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.1847,
      "step": 56
    },
    {
      "epoch": 0.013733285146367907,
      "grad_norm": 0.971021831035614,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.3174,
      "step": 57
    },
    {
      "epoch": 0.01397421997349717,
      "grad_norm": 0.7653561234474182,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.2841,
      "step": 58
    },
    {
      "epoch": 0.01421515480062643,
      "grad_norm": 0.5496749877929688,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.2655,
      "step": 59
    },
    {
      "epoch": 0.014456089627755691,
      "grad_norm": 0.5923565030097961,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.2768,
      "step": 60
    },
    {
      "epoch": 0.014697024454884954,
      "grad_norm": 0.6262228488922119,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.2214,
      "step": 61
    },
    {
      "epoch": 0.014937959282014215,
      "grad_norm": 0.45588913559913635,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.2558,
      "step": 62
    },
    {
      "epoch": 0.015178894109143477,
      "grad_norm": 0.2943878173828125,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.2471,
      "step": 63
    },
    {
      "epoch": 0.015419828936272738,
      "grad_norm": 0.39070063829421997,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.2447,
      "step": 64
    },
    {
      "epoch": 0.015660763763402,
      "grad_norm": 0.5298280119895935,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.2571,
      "step": 65
    },
    {
      "epoch": 0.01590169859053126,
      "grad_norm": 0.6332111954689026,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.2839,
      "step": 66
    },
    {
      "epoch": 0.016142633417660524,
      "grad_norm": 0.3768083453178406,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.2159,
      "step": 67
    },
    {
      "epoch": 0.016383568244789783,
      "grad_norm": 0.4113668203353882,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.231,
      "step": 68
    },
    {
      "epoch": 0.016624503071919046,
      "grad_norm": 0.596541702747345,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.2575,
      "step": 69
    },
    {
      "epoch": 0.01686543789904831,
      "grad_norm": 0.6093540787696838,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.2782,
      "step": 70
    },
    {
      "epoch": 0.017106372726177568,
      "grad_norm": 0.3764282763004303,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.2746,
      "step": 71
    },
    {
      "epoch": 0.01734730755330683,
      "grad_norm": 0.4304805397987366,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.221,
      "step": 72
    },
    {
      "epoch": 0.017588242380436093,
      "grad_norm": 0.4044836163520813,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.2574,
      "step": 73
    },
    {
      "epoch": 0.017829177207565352,
      "grad_norm": 0.5122354030609131,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.2165,
      "step": 74
    },
    {
      "epoch": 0.018070112034694615,
      "grad_norm": 0.5512914657592773,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.2753,
      "step": 75
    },
    {
      "epoch": 0.018311046861823877,
      "grad_norm": 0.30249151587486267,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.2452,
      "step": 76
    },
    {
      "epoch": 0.01855198168895314,
      "grad_norm": 0.4858316481113434,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.24,
      "step": 77
    },
    {
      "epoch": 0.0187929165160824,
      "grad_norm": 0.5286673307418823,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.2612,
      "step": 78
    },
    {
      "epoch": 0.01903385134321166,
      "grad_norm": 0.45666831731796265,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.2665,
      "step": 79
    },
    {
      "epoch": 0.019274786170340924,
      "grad_norm": 0.3813072741031647,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.2395,
      "step": 80
    },
    {
      "epoch": 0.019515720997470183,
      "grad_norm": 0.48633506894111633,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.2829,
      "step": 81
    },
    {
      "epoch": 0.019756655824599446,
      "grad_norm": 0.5978692770004272,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.2392,
      "step": 82
    },
    {
      "epoch": 0.01999759065172871,
      "grad_norm": 0.3837064206600189,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.2315,
      "step": 83
    },
    {
      "epoch": 0.020238525478857967,
      "grad_norm": 0.5809662938117981,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.2415,
      "step": 84
    },
    {
      "epoch": 0.02047946030598723,
      "grad_norm": 0.5919232964515686,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.2374,
      "step": 85
    },
    {
      "epoch": 0.020720395133116493,
      "grad_norm": 0.47563308477401733,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2224,
      "step": 86
    },
    {
      "epoch": 0.020961329960245755,
      "grad_norm": 0.3658895790576935,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.2474,
      "step": 87
    },
    {
      "epoch": 0.021202264787375014,
      "grad_norm": 0.5233673453330994,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.2577,
      "step": 88
    },
    {
      "epoch": 0.021443199614504277,
      "grad_norm": 0.7580683827400208,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.3074,
      "step": 89
    },
    {
      "epoch": 0.02168413444163354,
      "grad_norm": 0.3404545783996582,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.2327,
      "step": 90
    },
    {
      "epoch": 0.0219250692687628,
      "grad_norm": 0.42800337076187134,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.2559,
      "step": 91
    },
    {
      "epoch": 0.02216600409589206,
      "grad_norm": 0.4471622407436371,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.2464,
      "step": 92
    },
    {
      "epoch": 0.022406938923021324,
      "grad_norm": 0.5359969735145569,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.2855,
      "step": 93
    },
    {
      "epoch": 0.022647873750150583,
      "grad_norm": 0.43152597546577454,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.2572,
      "step": 94
    },
    {
      "epoch": 0.022888808577279846,
      "grad_norm": 0.5459998846054077,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.2744,
      "step": 95
    },
    {
      "epoch": 0.023129743404409108,
      "grad_norm": 0.7160676121711731,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.3009,
      "step": 96
    },
    {
      "epoch": 0.023370678231538367,
      "grad_norm": 0.4426705241203308,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.2747,
      "step": 97
    },
    {
      "epoch": 0.02361161305866763,
      "grad_norm": 0.45476841926574707,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.2913,
      "step": 98
    },
    {
      "epoch": 0.023852547885796892,
      "grad_norm": 0.669862687587738,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.2896,
      "step": 99
    },
    {
      "epoch": 0.024093482712926155,
      "grad_norm": 0.21566569805145264,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.2563,
      "step": 100
    },
    {
      "epoch": 0.024093482712926155,
      "eval_loss": 0.26430198550224304,
      "eval_runtime": 510.5793,
      "eval_samples_per_second": 13.69,
      "eval_steps_per_second": 3.424,
      "step": 100
    },
    {
      "epoch": 0.024334417540055414,
      "grad_norm": 1.290234923362732,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.5726,
      "step": 101
    },
    {
      "epoch": 0.024575352367184677,
      "grad_norm": 0.45329946279525757,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.2452,
      "step": 102
    },
    {
      "epoch": 0.02481628719431394,
      "grad_norm": 0.24364599585533142,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.2485,
      "step": 103
    },
    {
      "epoch": 0.0250572220214432,
      "grad_norm": 0.327094167470932,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.2375,
      "step": 104
    },
    {
      "epoch": 0.02529815684857246,
      "grad_norm": 0.3715580701828003,
      "learning_rate": 5e-05,
      "loss": 0.2613,
      "step": 105
    },
    {
      "epoch": 0.025539091675701724,
      "grad_norm": 0.28282630443573,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.2301,
      "step": 106
    },
    {
      "epoch": 0.025780026502830983,
      "grad_norm": 0.49798956513404846,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.2461,
      "step": 107
    },
    {
      "epoch": 0.026020961329960245,
      "grad_norm": 0.48084595799446106,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.2691,
      "step": 108
    },
    {
      "epoch": 0.026261896157089508,
      "grad_norm": 0.3514276146888733,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.1864,
      "step": 109
    },
    {
      "epoch": 0.02650283098421877,
      "grad_norm": 0.41042467951774597,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.2592,
      "step": 110
    },
    {
      "epoch": 0.02674376581134803,
      "grad_norm": 0.3872998356819153,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.1788,
      "step": 111
    },
    {
      "epoch": 0.026984700638477292,
      "grad_norm": 0.608724057674408,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.2868,
      "step": 112
    },
    {
      "epoch": 0.027225635465606555,
      "grad_norm": 0.4436226785182953,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.2693,
      "step": 113
    },
    {
      "epoch": 0.027466570292735814,
      "grad_norm": 0.4061850309371948,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.2495,
      "step": 114
    },
    {
      "epoch": 0.027707505119865077,
      "grad_norm": 0.4942147135734558,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.2648,
      "step": 115
    },
    {
      "epoch": 0.02794843994699434,
      "grad_norm": 0.34462204575538635,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.2915,
      "step": 116
    },
    {
      "epoch": 0.028189374774123598,
      "grad_norm": 0.28052186965942383,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.2219,
      "step": 117
    },
    {
      "epoch": 0.02843030960125286,
      "grad_norm": 0.43760791420936584,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.2565,
      "step": 118
    },
    {
      "epoch": 0.028671244428382123,
      "grad_norm": 0.3319215178489685,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.2432,
      "step": 119
    },
    {
      "epoch": 0.028912179255511383,
      "grad_norm": 0.4012322723865509,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.2829,
      "step": 120
    },
    {
      "epoch": 0.029153114082640645,
      "grad_norm": 0.38858529925346375,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.2454,
      "step": 121
    },
    {
      "epoch": 0.029394048909769908,
      "grad_norm": 0.48614102602005005,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.2771,
      "step": 122
    },
    {
      "epoch": 0.02963498373689917,
      "grad_norm": 0.42235130071640015,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.2195,
      "step": 123
    },
    {
      "epoch": 0.02987591856402843,
      "grad_norm": 0.44765040278434753,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2445,
      "step": 124
    },
    {
      "epoch": 0.030116853391157692,
      "grad_norm": 0.37631118297576904,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.2543,
      "step": 125
    },
    {
      "epoch": 0.030357788218286955,
      "grad_norm": 0.32950347661972046,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.2062,
      "step": 126
    },
    {
      "epoch": 0.030598723045416214,
      "grad_norm": 0.3097626268863678,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.2535,
      "step": 127
    },
    {
      "epoch": 0.030839657872545476,
      "grad_norm": 0.2358478158712387,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.2372,
      "step": 128
    },
    {
      "epoch": 0.03108059269967474,
      "grad_norm": 0.297639936208725,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.2487,
      "step": 129
    },
    {
      "epoch": 0.031321527526804,
      "grad_norm": 0.36787149310112,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.286,
      "step": 130
    },
    {
      "epoch": 0.031562462353933264,
      "grad_norm": 0.4113162159919739,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.23,
      "step": 131
    },
    {
      "epoch": 0.03180339718106252,
      "grad_norm": 0.3847804367542267,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.2484,
      "step": 132
    },
    {
      "epoch": 0.03204433200819178,
      "grad_norm": 0.4859013259410858,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.2798,
      "step": 133
    },
    {
      "epoch": 0.03228526683532105,
      "grad_norm": 0.4559577405452728,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.297,
      "step": 134
    },
    {
      "epoch": 0.03252620166245031,
      "grad_norm": 0.3224296271800995,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.2755,
      "step": 135
    },
    {
      "epoch": 0.03276713648957957,
      "grad_norm": 0.3775584101676941,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.2777,
      "step": 136
    },
    {
      "epoch": 0.03300807131670883,
      "grad_norm": 0.4507180154323578,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.2451,
      "step": 137
    },
    {
      "epoch": 0.03324900614383809,
      "grad_norm": 0.31897252798080444,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.2243,
      "step": 138
    },
    {
      "epoch": 0.03348994097096735,
      "grad_norm": 0.32704704999923706,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.2427,
      "step": 139
    },
    {
      "epoch": 0.03373087579809662,
      "grad_norm": 0.4815594553947449,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.2677,
      "step": 140
    },
    {
      "epoch": 0.033971810625225876,
      "grad_norm": 0.47970694303512573,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.2616,
      "step": 141
    },
    {
      "epoch": 0.034212745452355135,
      "grad_norm": 0.3669702708721161,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.2284,
      "step": 142
    },
    {
      "epoch": 0.0344536802794844,
      "grad_norm": 0.40922677516937256,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2523,
      "step": 143
    },
    {
      "epoch": 0.03469461510661366,
      "grad_norm": 0.4762136936187744,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.2084,
      "step": 144
    },
    {
      "epoch": 0.03493554993374292,
      "grad_norm": 0.3162444531917572,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.2679,
      "step": 145
    },
    {
      "epoch": 0.035176484760872186,
      "grad_norm": 0.2927365005016327,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.2542,
      "step": 146
    },
    {
      "epoch": 0.035417419588001445,
      "grad_norm": 0.264660120010376,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.2465,
      "step": 147
    },
    {
      "epoch": 0.035658354415130704,
      "grad_norm": 0.2650972306728363,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.2268,
      "step": 148
    },
    {
      "epoch": 0.03589928924225997,
      "grad_norm": 0.46045494079589844,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.2513,
      "step": 149
    },
    {
      "epoch": 0.03614022406938923,
      "grad_norm": 0.6368746757507324,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.2629,
      "step": 150
    },
    {
      "epoch": 0.03614022406938923,
      "eval_loss": 0.2537326514720917,
      "eval_runtime": 511.6054,
      "eval_samples_per_second": 13.663,
      "eval_steps_per_second": 3.417,
      "step": 150
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.012692217730171e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}