{
  "best_metric": 0.4755863547325134,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.005905744320642545,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.937162880428363e-05,
      "grad_norm": 1.02256441116333,
      "learning_rate": 1e-05,
      "loss": 0.6653,
      "step": 1
    },
    {
      "epoch": 3.937162880428363e-05,
      "eval_loss": 2.0401175022125244,
      "eval_runtime": 1963.3936,
      "eval_samples_per_second": 21.788,
      "eval_steps_per_second": 5.447,
      "step": 1
    },
    {
      "epoch": 7.874325760856726e-05,
      "grad_norm": 1.1648401021957397,
      "learning_rate": 2e-05,
      "loss": 0.6528,
      "step": 2
    },
    {
      "epoch": 0.0001181148864128509,
      "grad_norm": 1.2922242879867554,
      "learning_rate": 3e-05,
      "loss": 0.6958,
      "step": 3
    },
    {
      "epoch": 0.00015748651521713453,
      "grad_norm": 1.711512565612793,
      "learning_rate": 4e-05,
      "loss": 0.9842,
      "step": 4
    },
    {
      "epoch": 0.00019685814402141817,
      "grad_norm": 2.0927672386169434,
      "learning_rate": 5e-05,
      "loss": 1.165,
      "step": 5
    },
    {
      "epoch": 0.0002362297728257018,
      "grad_norm": 2.2099623680114746,
      "learning_rate": 6e-05,
      "loss": 1.0422,
      "step": 6
    },
    {
      "epoch": 0.00027560140162998545,
      "grad_norm": 2.201043128967285,
      "learning_rate": 7e-05,
      "loss": 1.0076,
      "step": 7
    },
    {
      "epoch": 0.00031497303043426906,
      "grad_norm": 1.8493530750274658,
      "learning_rate": 8e-05,
      "loss": 0.8828,
      "step": 8
    },
    {
      "epoch": 0.0003543446592385527,
      "grad_norm": 1.8940231800079346,
      "learning_rate": 9e-05,
      "loss": 0.8789,
      "step": 9
    },
    {
      "epoch": 0.00039371628804283634,
      "grad_norm": 1.6951254606246948,
      "learning_rate": 0.0001,
      "loss": 0.7942,
      "step": 10
    },
    {
      "epoch": 0.00043308791684711995,
      "grad_norm": 1.5717829465866089,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.7426,
      "step": 11
    },
    {
      "epoch": 0.0004724595456514036,
      "grad_norm": 1.6309691667556763,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.6065,
      "step": 12
    },
    {
      "epoch": 0.0005118311744556872,
      "grad_norm": 1.7245391607284546,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.6492,
      "step": 13
    },
    {
      "epoch": 0.0005512028032599709,
      "grad_norm": 1.3676433563232422,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.6407,
      "step": 14
    },
    {
      "epoch": 0.0005905744320642545,
      "grad_norm": 1.4679405689239502,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.5274,
      "step": 15
    },
    {
      "epoch": 0.0006299460608685381,
      "grad_norm": 1.4089184999465942,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.5273,
      "step": 16
    },
    {
      "epoch": 0.0006693176896728218,
      "grad_norm": 1.5161076784133911,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.6176,
      "step": 17
    },
    {
      "epoch": 0.0007086893184771055,
      "grad_norm": 1.3749370574951172,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.5369,
      "step": 18
    },
    {
      "epoch": 0.000748060947281389,
      "grad_norm": 1.707553505897522,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.6345,
      "step": 19
    },
    {
      "epoch": 0.0007874325760856727,
      "grad_norm": 1.5158611536026,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.601,
      "step": 20
    },
    {
      "epoch": 0.0008268042048899563,
      "grad_norm": 1.3462746143341064,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.5207,
      "step": 21
    },
    {
      "epoch": 0.0008661758336942399,
      "grad_norm": 1.358368158340454,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.5192,
      "step": 22
    },
    {
      "epoch": 0.0009055474624985236,
      "grad_norm": 1.4276319742202759,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.5678,
      "step": 23
    },
    {
      "epoch": 0.0009449190913028072,
      "grad_norm": 1.4815235137939453,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.5764,
      "step": 24
    },
    {
      "epoch": 0.0009842907201070908,
      "grad_norm": 1.3998855352401733,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.5395,
      "step": 25
    },
    {
      "epoch": 0.0010236623489113745,
      "grad_norm": 1.4529114961624146,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.5424,
      "step": 26
    },
    {
      "epoch": 0.0010630339777156581,
      "grad_norm": 1.7836538553237915,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.5755,
      "step": 27
    },
    {
      "epoch": 0.0011024056065199418,
      "grad_norm": 1.4714139699935913,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.4163,
      "step": 28
    },
    {
      "epoch": 0.0011417772353242255,
      "grad_norm": 1.8692817687988281,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.5678,
      "step": 29
    },
    {
      "epoch": 0.001181148864128509,
      "grad_norm": 1.8492319583892822,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.5329,
      "step": 30
    },
    {
      "epoch": 0.0012205204929327926,
      "grad_norm": 1.5785956382751465,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.4777,
      "step": 31
    },
    {
      "epoch": 0.0012598921217370762,
      "grad_norm": 1.6650912761688232,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.4997,
      "step": 32
    },
    {
      "epoch": 0.00129926375054136,
      "grad_norm": 1.9529163837432861,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.577,
      "step": 33
    },
    {
      "epoch": 0.0013386353793456436,
      "grad_norm": 1.7996156215667725,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.5334,
      "step": 34
    },
    {
      "epoch": 0.0013780070081499272,
      "grad_norm": 1.7110034227371216,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.5201,
      "step": 35
    },
    {
      "epoch": 0.001417378636954211,
      "grad_norm": 1.8501421213150024,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.5089,
      "step": 36
    },
    {
      "epoch": 0.0014567502657584943,
      "grad_norm": 2.0073397159576416,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.6491,
      "step": 37
    },
    {
      "epoch": 0.001496121894562778,
      "grad_norm": 1.9730331897735596,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.5395,
      "step": 38
    },
    {
      "epoch": 0.0015354935233670617,
      "grad_norm": 2.027768135070801,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.5505,
      "step": 39
    },
    {
      "epoch": 0.0015748651521713453,
      "grad_norm": 2.7377169132232666,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7136,
      "step": 40
    },
    {
      "epoch": 0.001614236780975629,
      "grad_norm": 2.628161907196045,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.6519,
      "step": 41
    },
    {
      "epoch": 0.0016536084097799127,
      "grad_norm": 3.1375608444213867,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.8701,
      "step": 42
    },
    {
      "epoch": 0.0016929800385841961,
      "grad_norm": 2.631460189819336,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7225,
      "step": 43
    },
    {
      "epoch": 0.0017323516673884798,
      "grad_norm": 2.65053391456604,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7696,
      "step": 44
    },
    {
      "epoch": 0.0017717232961927635,
      "grad_norm": 3.0114426612854004,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.7981,
      "step": 45
    },
    {
      "epoch": 0.0018110949249970471,
      "grad_norm": 3.490697145462036,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7679,
      "step": 46
    },
    {
      "epoch": 0.0018504665538013308,
      "grad_norm": 3.9303817749023438,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.9967,
      "step": 47
    },
    {
      "epoch": 0.0018898381826056145,
      "grad_norm": 4.211299419403076,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8935,
      "step": 48
    },
    {
      "epoch": 0.0019292098114098981,
      "grad_norm": 4.635986804962158,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.9208,
      "step": 49
    },
    {
      "epoch": 0.0019685814402141816,
      "grad_norm": 6.054840087890625,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7544,
      "step": 50
    },
    {
      "epoch": 0.0019685814402141816,
      "eval_loss": 0.62474524974823,
      "eval_runtime": 1962.3949,
      "eval_samples_per_second": 21.799,
      "eval_steps_per_second": 5.45,
      "step": 50
    },
    {
      "epoch": 0.0020079530690184652,
      "grad_norm": 1.4681363105773926,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.6131,
      "step": 51
    },
    {
      "epoch": 0.002047324697822749,
      "grad_norm": 0.8419048190116882,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.4649,
      "step": 52
    },
    {
      "epoch": 0.0020866963266270326,
      "grad_norm": 0.7242401242256165,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.4772,
      "step": 53
    },
    {
      "epoch": 0.0021260679554313162,
      "grad_norm": 1.0355290174484253,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.5924,
      "step": 54
    },
    {
      "epoch": 0.0021654395842356,
      "grad_norm": 1.2674163579940796,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.7106,
      "step": 55
    },
    {
      "epoch": 0.0022048112130398836,
      "grad_norm": 1.0684322118759155,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.5397,
      "step": 56
    },
    {
      "epoch": 0.0022441828418441672,
      "grad_norm": 1.023458480834961,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.4722,
      "step": 57
    },
    {
      "epoch": 0.002283554470648451,
      "grad_norm": 1.130386233329773,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.5505,
      "step": 58
    },
    {
      "epoch": 0.0023229260994527346,
      "grad_norm": 1.0275880098342896,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.4878,
      "step": 59
    },
    {
      "epoch": 0.002362297728257018,
      "grad_norm": 1.2688953876495361,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.5625,
      "step": 60
    },
    {
      "epoch": 0.0024016693570613015,
      "grad_norm": 1.0798358917236328,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.455,
      "step": 61
    },
    {
      "epoch": 0.002441040985865585,
      "grad_norm": 1.1489145755767822,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.4756,
      "step": 62
    },
    {
      "epoch": 0.002480412614669869,
      "grad_norm": 1.0758352279663086,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.4719,
      "step": 63
    },
    {
      "epoch": 0.0025197842434741525,
      "grad_norm": 1.1072825193405151,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.4388,
      "step": 64
    },
    {
      "epoch": 0.002559155872278436,
      "grad_norm": 1.059680461883545,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.42,
      "step": 65
    },
    {
      "epoch": 0.00259852750108272,
      "grad_norm": 1.0395857095718384,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.4328,
      "step": 66
    },
    {
      "epoch": 0.0026378991298870035,
      "grad_norm": 1.2434015274047852,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.464,
      "step": 67
    },
    {
      "epoch": 0.002677270758691287,
      "grad_norm": 1.3831180334091187,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.6026,
      "step": 68
    },
    {
      "epoch": 0.002716642387495571,
      "grad_norm": 1.1558599472045898,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.4435,
      "step": 69
    },
    {
      "epoch": 0.0027560140162998545,
      "grad_norm": 1.0922515392303467,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.4497,
      "step": 70
    },
    {
      "epoch": 0.002795385645104138,
      "grad_norm": 1.132048487663269,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.4135,
      "step": 71
    },
    {
      "epoch": 0.002834757273908422,
      "grad_norm": 1.2695519924163818,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.4738,
      "step": 72
    },
    {
      "epoch": 0.002874128902712705,
      "grad_norm": 1.169937252998352,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.4338,
      "step": 73
    },
    {
      "epoch": 0.0029135005315169887,
      "grad_norm": 1.3878920078277588,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.5076,
      "step": 74
    },
    {
      "epoch": 0.0029528721603212724,
      "grad_norm": 1.1474246978759766,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.4431,
      "step": 75
    },
    {
      "epoch": 0.002992243789125556,
      "grad_norm": 1.1987924575805664,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.4218,
      "step": 76
    },
    {
      "epoch": 0.0030316154179298397,
      "grad_norm": 1.1889253854751587,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.454,
      "step": 77
    },
    {
      "epoch": 0.0030709870467341234,
      "grad_norm": 1.2669168710708618,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.4485,
      "step": 78
    },
    {
      "epoch": 0.003110358675538407,
      "grad_norm": 1.1950857639312744,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.4234,
      "step": 79
    },
    {
      "epoch": 0.0031497303043426907,
      "grad_norm": 1.3883540630340576,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.4564,
      "step": 80
    },
    {
      "epoch": 0.0031891019331469744,
      "grad_norm": 1.6918472051620483,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.5781,
      "step": 81
    },
    {
      "epoch": 0.003228473561951258,
      "grad_norm": 1.3038713932037354,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.4174,
      "step": 82
    },
    {
      "epoch": 0.0032678451907555417,
      "grad_norm": 1.435478925704956,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.4292,
      "step": 83
    },
    {
      "epoch": 0.0033072168195598254,
      "grad_norm": 1.9486966133117676,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.561,
      "step": 84
    },
    {
      "epoch": 0.003346588448364109,
      "grad_norm": 1.6429029703140259,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.4658,
      "step": 85
    },
    {
      "epoch": 0.0033859600771683923,
      "grad_norm": 1.6745431423187256,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4302,
      "step": 86
    },
    {
      "epoch": 0.003425331705972676,
      "grad_norm": 1.627824068069458,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.53,
      "step": 87
    },
    {
      "epoch": 0.0034647033347769596,
      "grad_norm": 1.6169121265411377,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.4768,
      "step": 88
    },
    {
      "epoch": 0.0035040749635812433,
      "grad_norm": 1.7247333526611328,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.5279,
      "step": 89
    },
    {
      "epoch": 0.003543446592385527,
      "grad_norm": 2.0350518226623535,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.5958,
      "step": 90
    },
    {
      "epoch": 0.0035828182211898106,
      "grad_norm": 1.9901599884033203,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.5022,
      "step": 91
    },
    {
      "epoch": 0.0036221898499940943,
      "grad_norm": 2.2938389778137207,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.606,
      "step": 92
    },
    {
      "epoch": 0.003661561478798378,
      "grad_norm": 2.3475186824798584,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.6537,
      "step": 93
    },
    {
      "epoch": 0.0037009331076026616,
      "grad_norm": 2.820521831512451,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.6219,
      "step": 94
    },
    {
      "epoch": 0.0037403047364069453,
      "grad_norm": 3.1900765895843506,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.8085,
      "step": 95
    },
    {
      "epoch": 0.003779676365211229,
      "grad_norm": 3.7130322456359863,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.9369,
      "step": 96
    },
    {
      "epoch": 0.0038190479940155126,
      "grad_norm": 3.98307728767395,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.8162,
      "step": 97
    },
    {
      "epoch": 0.0038584196228197963,
      "grad_norm": 3.4590582847595215,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.7228,
      "step": 98
    },
    {
      "epoch": 0.0038977912516240795,
      "grad_norm": 4.0625,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.9072,
      "step": 99
    },
    {
      "epoch": 0.003937162880428363,
      "grad_norm": 7.270034313201904,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.0212,
      "step": 100
    },
    {
      "epoch": 0.003937162880428363,
      "eval_loss": 0.5313294529914856,
      "eval_runtime": 1964.4559,
      "eval_samples_per_second": 21.776,
      "eval_steps_per_second": 5.444,
      "step": 100
    },
    {
      "epoch": 0.003976534509232647,
      "grad_norm": 0.6821577548980713,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.4472,
      "step": 101
    },
    {
      "epoch": 0.0040159061380369305,
      "grad_norm": 0.6033506989479065,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.4505,
      "step": 102
    },
    {
      "epoch": 0.004055277766841214,
      "grad_norm": 0.6802194118499756,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.4243,
      "step": 103
    },
    {
      "epoch": 0.004094649395645498,
      "grad_norm": 1.0940698385238647,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.5355,
      "step": 104
    },
    {
      "epoch": 0.0041340210244497815,
      "grad_norm": 1.0095839500427246,
      "learning_rate": 5e-05,
      "loss": 0.4859,
      "step": 105
    },
    {
      "epoch": 0.004173392653254065,
      "grad_norm": 0.9586552381515503,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.4559,
      "step": 106
    },
    {
      "epoch": 0.004212764282058349,
      "grad_norm": 1.0491364002227783,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.5536,
      "step": 107
    },
    {
      "epoch": 0.0042521359108626325,
      "grad_norm": 1.0424336194992065,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.531,
      "step": 108
    },
    {
      "epoch": 0.004291507539666916,
      "grad_norm": 1.1021971702575684,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.4656,
      "step": 109
    },
    {
      "epoch": 0.0043308791684712,
      "grad_norm": 1.0408269166946411,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.4715,
      "step": 110
    },
    {
      "epoch": 0.0043702507972754835,
      "grad_norm": 1.21599543094635,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.527,
      "step": 111
    },
    {
      "epoch": 0.004409622426079767,
      "grad_norm": 1.0973793268203735,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.4781,
      "step": 112
    },
    {
      "epoch": 0.004448994054884051,
      "grad_norm": 1.0023589134216309,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.3882,
      "step": 113
    },
    {
      "epoch": 0.0044883656836883345,
      "grad_norm": 1.0988465547561646,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.4012,
      "step": 114
    },
    {
      "epoch": 0.004527737312492618,
      "grad_norm": 1.2344098091125488,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.4895,
      "step": 115
    },
    {
      "epoch": 0.004567108941296902,
      "grad_norm": 1.0267789363861084,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.4079,
      "step": 116
    },
    {
      "epoch": 0.0046064805701011855,
      "grad_norm": 1.1937060356140137,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.4989,
      "step": 117
    },
    {
      "epoch": 0.004645852198905469,
      "grad_norm": 1.0652450323104858,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.4234,
      "step": 118
    },
    {
      "epoch": 0.004685223827709752,
      "grad_norm": 1.1903423070907593,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.3993,
      "step": 119
    },
    {
      "epoch": 0.004724595456514036,
      "grad_norm": 1.204135537147522,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.3806,
      "step": 120
    },
    {
      "epoch": 0.004763967085318319,
      "grad_norm": 1.1541450023651123,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.4245,
      "step": 121
    },
    {
      "epoch": 0.004803338714122603,
      "grad_norm": 1.1386463642120361,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.4182,
      "step": 122
    },
    {
      "epoch": 0.004842710342926887,
      "grad_norm": 1.179220199584961,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.4101,
      "step": 123
    },
    {
      "epoch": 0.00488208197173117,
      "grad_norm": 1.2795960903167725,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.4203,
      "step": 124
    },
    {
      "epoch": 0.004921453600535454,
      "grad_norm": 1.6313341856002808,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.4771,
      "step": 125
    },
    {
      "epoch": 0.004960825229339738,
      "grad_norm": 1.3297889232635498,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.4054,
      "step": 126
    },
    {
      "epoch": 0.005000196858144021,
      "grad_norm": 1.3898698091506958,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.4196,
      "step": 127
    },
    {
      "epoch": 0.005039568486948305,
      "grad_norm": 1.2108392715454102,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.433,
      "step": 128
    },
    {
      "epoch": 0.005078940115752589,
      "grad_norm": 1.320252776145935,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.4027,
      "step": 129
    },
    {
      "epoch": 0.005118311744556872,
      "grad_norm": 1.3441872596740723,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.3871,
      "step": 130
    },
    {
      "epoch": 0.005157683373361156,
      "grad_norm": 1.3732396364212036,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.4692,
      "step": 131
    },
    {
      "epoch": 0.00519705500216544,
      "grad_norm": 1.471716284751892,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.3845,
      "step": 132
    },
    {
      "epoch": 0.005236426630969723,
      "grad_norm": 1.654649019241333,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.4476,
      "step": 133
    },
    {
      "epoch": 0.005275798259774007,
      "grad_norm": 1.314582109451294,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.3975,
      "step": 134
    },
    {
      "epoch": 0.005315169888578291,
      "grad_norm": 1.2855511903762817,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.3836,
      "step": 135
    },
    {
      "epoch": 0.005354541517382574,
      "grad_norm": 1.5129963159561157,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.4548,
      "step": 136
    },
    {
      "epoch": 0.005393913146186858,
      "grad_norm": 1.40498685836792,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.4161,
      "step": 137
    },
    {
      "epoch": 0.005433284774991142,
      "grad_norm": 1.7466362714767456,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.4721,
      "step": 138
    },
    {
      "epoch": 0.005472656403795425,
      "grad_norm": 1.5604318380355835,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.4564,
      "step": 139
    },
    {
      "epoch": 0.005512028032599709,
      "grad_norm": 1.6837966442108154,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.4667,
      "step": 140
    },
    {
      "epoch": 0.005551399661403993,
      "grad_norm": 1.867175579071045,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.4654,
      "step": 141
    },
    {
      "epoch": 0.005590771290208276,
      "grad_norm": 2.220432758331299,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.4996,
      "step": 142
    },
    {
      "epoch": 0.00563014291901256,
      "grad_norm": 2.555483341217041,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6215,
      "step": 143
    },
    {
      "epoch": 0.005669514547816844,
      "grad_norm": 3.0226290225982666,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.5752,
      "step": 144
    },
    {
      "epoch": 0.005708886176621126,
      "grad_norm": 2.8674111366271973,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.5822,
      "step": 145
    },
    {
      "epoch": 0.00574825780542541,
      "grad_norm": 2.833491563796997,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.6672,
      "step": 146
    },
    {
      "epoch": 0.005787629434229694,
      "grad_norm": 3.3857784271240234,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.7152,
      "step": 147
    },
    {
      "epoch": 0.005827001063033977,
      "grad_norm": 3.082288980484009,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.622,
      "step": 148
    },
    {
      "epoch": 0.005866372691838261,
      "grad_norm": 3.570404291152954,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.6337,
      "step": 149
    },
    {
      "epoch": 0.005905744320642545,
      "grad_norm": 4.106326580047607,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.7418,
      "step": 150
    },
    {
      "epoch": 0.005905744320642545,
      "eval_loss": 0.4755863547325134,
      "eval_runtime": 1963.7539,
      "eval_samples_per_second": 21.784,
      "eval_steps_per_second": 5.446,
      "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": 6.391626802082611e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}