{
  "best_metric": 0.5749279856681824,
  "best_model_checkpoint": "models/lusa_en/checkpoint-110",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 4.094762325286865,
      "learning_rate": 1.9990909090909092e-05,
      "loss": 2.1525,
      "step": 1
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 4.10725212097168,
      "learning_rate": 1.9981818181818185e-05,
      "loss": 2.0303,
      "step": 2
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 4.080411434173584,
      "learning_rate": 1.9972727272727275e-05,
      "loss": 1.926,
      "step": 3
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 3.544022560119629,
      "learning_rate": 1.9963636363636365e-05,
      "loss": 1.8315,
      "step": 4
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 2.855754852294922,
      "learning_rate": 1.9954545454545455e-05,
      "loss": 1.7865,
      "step": 5
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 2.752898931503296,
      "learning_rate": 1.994545454545455e-05,
      "loss": 1.682,
      "step": 6
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 2.3124074935913086,
      "learning_rate": 1.993636363636364e-05,
      "loss": 1.6458,
      "step": 7
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.361560583114624,
      "learning_rate": 1.992727272727273e-05,
      "loss": 1.5782,
      "step": 8
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 2.4446144104003906,
      "learning_rate": 1.991818181818182e-05,
      "loss": 1.5693,
      "step": 9
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 2.2963356971740723,
      "learning_rate": 1.9909090909090913e-05,
      "loss": 1.5906,
      "step": 10
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.9563844203948975,
      "learning_rate": 1.9900000000000003e-05,
      "loss": 1.4818,
      "step": 11
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 1.904161810874939,
      "learning_rate": 1.9890909090909093e-05,
      "loss": 1.4469,
      "step": 12
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 1.6757051944732666,
      "learning_rate": 1.9881818181818183e-05,
      "loss": 1.3387,
      "step": 13
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 1.670788049697876,
      "learning_rate": 1.9872727272727276e-05,
      "loss": 1.3976,
      "step": 14
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 1.7997887134552002,
      "learning_rate": 1.9863636363636366e-05,
      "loss": 1.2961,
      "step": 15
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 1.6230303049087524,
      "learning_rate": 1.9854545454545456e-05,
      "loss": 1.2923,
      "step": 16
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 1.810758352279663,
      "learning_rate": 1.9845454545454546e-05,
      "loss": 1.2559,
      "step": 17
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 2.564798593521118,
      "learning_rate": 1.9836363636363636e-05,
      "loss": 1.2239,
      "step": 18
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 1.6320985555648804,
      "learning_rate": 1.982727272727273e-05,
      "loss": 1.1662,
      "step": 19
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 1.5779709815979004,
      "learning_rate": 1.981818181818182e-05,
      "loss": 1.0843,
      "step": 20
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 1.7842929363250732,
      "learning_rate": 1.980909090909091e-05,
      "loss": 1.0595,
      "step": 21
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.1895947456359863,
      "learning_rate": 1.98e-05,
      "loss": 1.2116,
      "step": 22
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7246807246807246,
      "eval_f1": 0.5378067100650976,
      "eval_loss": 0.9455885291099548,
      "eval_precision": 0.5496417604912999,
      "eval_recall": 0.5264705882352941,
      "eval_runtime": 5.3772,
      "eval_samples_per_second": 24.362,
      "eval_steps_per_second": 0.93,
      "step": 22
    },
    {
      "epoch": 1.0454545454545454,
      "grad_norm": 1.5596168041229248,
      "learning_rate": 1.979090909090909e-05,
      "loss": 1.1374,
      "step": 23
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 1.4826650619506836,
      "learning_rate": 1.9781818181818184e-05,
      "loss": 0.9918,
      "step": 24
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 1.6731046438217163,
      "learning_rate": 1.9772727272727274e-05,
      "loss": 0.8705,
      "step": 25
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 1.8360694646835327,
      "learning_rate": 1.9763636363636364e-05,
      "loss": 1.0117,
      "step": 26
    },
    {
      "epoch": 1.2272727272727273,
      "grad_norm": 1.6999843120574951,
      "learning_rate": 1.9754545454545454e-05,
      "loss": 0.9752,
      "step": 27
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 1.629109263420105,
      "learning_rate": 1.9745454545454547e-05,
      "loss": 0.9142,
      "step": 28
    },
    {
      "epoch": 1.3181818181818181,
      "grad_norm": 1.4835275411605835,
      "learning_rate": 1.9736363636363637e-05,
      "loss": 0.8984,
      "step": 29
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 1.3297476768493652,
      "learning_rate": 1.9727272727272728e-05,
      "loss": 0.9224,
      "step": 30
    },
    {
      "epoch": 1.4090909090909092,
      "grad_norm": 1.582480788230896,
      "learning_rate": 1.971818181818182e-05,
      "loss": 0.8557,
      "step": 31
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 1.3994060754776,
      "learning_rate": 1.970909090909091e-05,
      "loss": 0.748,
      "step": 32
    },
    {
      "epoch": 1.5,
      "grad_norm": 2.084137201309204,
      "learning_rate": 1.97e-05,
      "loss": 1.1522,
      "step": 33
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 1.8021726608276367,
      "learning_rate": 1.969090909090909e-05,
      "loss": 0.8038,
      "step": 34
    },
    {
      "epoch": 1.5909090909090908,
      "grad_norm": 1.3661516904830933,
      "learning_rate": 1.9681818181818185e-05,
      "loss": 0.8233,
      "step": 35
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 1.5308856964111328,
      "learning_rate": 1.9672727272727275e-05,
      "loss": 0.8182,
      "step": 36
    },
    {
      "epoch": 1.6818181818181817,
      "grad_norm": 1.5709282159805298,
      "learning_rate": 1.9663636363636365e-05,
      "loss": 0.7915,
      "step": 37
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 1.6001756191253662,
      "learning_rate": 1.9654545454545458e-05,
      "loss": 0.8671,
      "step": 38
    },
    {
      "epoch": 1.7727272727272727,
      "grad_norm": 1.243642807006836,
      "learning_rate": 1.964545454545455e-05,
      "loss": 0.8128,
      "step": 39
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 1.9662197828292847,
      "learning_rate": 1.963636363636364e-05,
      "loss": 0.7816,
      "step": 40
    },
    {
      "epoch": 1.8636363636363638,
      "grad_norm": 1.392984390258789,
      "learning_rate": 1.962727272727273e-05,
      "loss": 0.7299,
      "step": 41
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 1.7500344514846802,
      "learning_rate": 1.9618181818181822e-05,
      "loss": 0.8295,
      "step": 42
    },
    {
      "epoch": 1.9545454545454546,
      "grad_norm": 1.3700010776519775,
      "learning_rate": 1.9609090909090912e-05,
      "loss": 0.7227,
      "step": 43
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.7891302108764648,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.8371,
      "step": 44
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7840807840807841,
      "eval_f1": 0.6456470588235295,
      "eval_loss": 0.68104088306427,
      "eval_precision": 0.6208144796380091,
      "eval_recall": 0.6725490196078432,
      "eval_runtime": 5.7284,
      "eval_samples_per_second": 22.869,
      "eval_steps_per_second": 0.873,
      "step": 44
    },
    {
      "epoch": 2.0454545454545454,
      "grad_norm": 1.324338436126709,
      "learning_rate": 1.9590909090909092e-05,
      "loss": 0.6347,
      "step": 45
    },
    {
      "epoch": 2.090909090909091,
      "grad_norm": 1.5182204246520996,
      "learning_rate": 1.9581818181818186e-05,
      "loss": 0.713,
      "step": 46
    },
    {
      "epoch": 2.1363636363636362,
      "grad_norm": 1.2550334930419922,
      "learning_rate": 1.9572727272727276e-05,
      "loss": 0.7751,
      "step": 47
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 1.2773672342300415,
      "learning_rate": 1.9563636363636366e-05,
      "loss": 0.6857,
      "step": 48
    },
    {
      "epoch": 2.227272727272727,
      "grad_norm": 1.2220115661621094,
      "learning_rate": 1.9554545454545456e-05,
      "loss": 0.6481,
      "step": 49
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 1.2490642070770264,
      "learning_rate": 1.9545454545454546e-05,
      "loss": 0.6727,
      "step": 50
    },
    {
      "epoch": 2.3181818181818183,
      "grad_norm": 1.7800368070602417,
      "learning_rate": 1.953636363636364e-05,
      "loss": 0.7261,
      "step": 51
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 1.466561198234558,
      "learning_rate": 1.952727272727273e-05,
      "loss": 0.679,
      "step": 52
    },
    {
      "epoch": 2.409090909090909,
      "grad_norm": 1.6164387464523315,
      "learning_rate": 1.951818181818182e-05,
      "loss": 0.6693,
      "step": 53
    },
    {
      "epoch": 2.4545454545454546,
      "grad_norm": 1.4198397397994995,
      "learning_rate": 1.950909090909091e-05,
      "loss": 0.608,
      "step": 54
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.4696757793426514,
      "learning_rate": 1.95e-05,
      "loss": 0.749,
      "step": 55
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 1.4631857872009277,
      "learning_rate": 1.9490909090909093e-05,
      "loss": 0.6256,
      "step": 56
    },
    {
      "epoch": 2.590909090909091,
      "grad_norm": 1.4575796127319336,
      "learning_rate": 1.9481818181818183e-05,
      "loss": 0.6964,
      "step": 57
    },
    {
      "epoch": 2.6363636363636362,
      "grad_norm": 1.2283692359924316,
      "learning_rate": 1.9472727272727273e-05,
      "loss": 0.7201,
      "step": 58
    },
    {
      "epoch": 2.6818181818181817,
      "grad_norm": 1.2565014362335205,
      "learning_rate": 1.9463636363636363e-05,
      "loss": 0.6112,
      "step": 59
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 1.3832677602767944,
      "learning_rate": 1.9454545454545457e-05,
      "loss": 0.5858,
      "step": 60
    },
    {
      "epoch": 2.7727272727272725,
      "grad_norm": 1.679886817932129,
      "learning_rate": 1.9445454545454547e-05,
      "loss": 0.8611,
      "step": 61
    },
    {
      "epoch": 2.8181818181818183,
      "grad_norm": 1.3422367572784424,
      "learning_rate": 1.9436363636363637e-05,
      "loss": 0.6522,
      "step": 62
    },
    {
      "epoch": 2.8636363636363638,
      "grad_norm": 1.2293131351470947,
      "learning_rate": 1.9427272727272727e-05,
      "loss": 0.5756,
      "step": 63
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 1.7241827249526978,
      "learning_rate": 1.941818181818182e-05,
      "loss": 0.5771,
      "step": 64
    },
    {
      "epoch": 2.9545454545454546,
      "grad_norm": 1.3407361507415771,
      "learning_rate": 1.940909090909091e-05,
      "loss": 0.6396,
      "step": 65
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.4412184953689575,
      "learning_rate": 1.94e-05,
      "loss": 0.7121,
      "step": 66
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.809028809028809,
      "eval_f1": 0.6716697936210131,
      "eval_loss": 0.6103370189666748,
      "eval_precision": 0.6438848920863309,
      "eval_recall": 0.7019607843137254,
      "eval_runtime": 6.4253,
      "eval_samples_per_second": 20.388,
      "eval_steps_per_second": 0.778,
      "step": 66
    },
    {
      "epoch": 3.0454545454545454,
      "grad_norm": 1.5174870491027832,
      "learning_rate": 1.9390909090909094e-05,
      "loss": 0.5993,
      "step": 67
    },
    {
      "epoch": 3.090909090909091,
      "grad_norm": 1.2559189796447754,
      "learning_rate": 1.9381818181818184e-05,
      "loss": 0.599,
      "step": 68
    },
    {
      "epoch": 3.1363636363636362,
      "grad_norm": 1.3573830127716064,
      "learning_rate": 1.9372727272727274e-05,
      "loss": 0.6561,
      "step": 69
    },
    {
      "epoch": 3.1818181818181817,
      "grad_norm": 1.2237664461135864,
      "learning_rate": 1.9363636363636364e-05,
      "loss": 0.5644,
      "step": 70
    },
    {
      "epoch": 3.227272727272727,
      "grad_norm": 1.7508504390716553,
      "learning_rate": 1.9354545454545458e-05,
      "loss": 0.6542,
      "step": 71
    },
    {
      "epoch": 3.2727272727272725,
      "grad_norm": 1.35462486743927,
      "learning_rate": 1.9345454545454548e-05,
      "loss": 0.5616,
      "step": 72
    },
    {
      "epoch": 3.3181818181818183,
      "grad_norm": 1.3244951963424683,
      "learning_rate": 1.9336363636363638e-05,
      "loss": 0.6016,
      "step": 73
    },
    {
      "epoch": 3.3636363636363638,
      "grad_norm": 1.3806241750717163,
      "learning_rate": 1.9327272727272728e-05,
      "loss": 0.5168,
      "step": 74
    },
    {
      "epoch": 3.409090909090909,
      "grad_norm": 1.3947114944458008,
      "learning_rate": 1.931818181818182e-05,
      "loss": 0.5554,
      "step": 75
    },
    {
      "epoch": 3.4545454545454546,
      "grad_norm": 1.4679116010665894,
      "learning_rate": 1.930909090909091e-05,
      "loss": 0.5753,
      "step": 76
    },
    {
      "epoch": 3.5,
      "grad_norm": 1.2916615009307861,
      "learning_rate": 1.93e-05,
      "loss": 0.4835,
      "step": 77
    },
    {
      "epoch": 3.5454545454545454,
      "grad_norm": 1.713321328163147,
      "learning_rate": 1.9290909090909095e-05,
      "loss": 0.5753,
      "step": 78
    },
    {
      "epoch": 3.590909090909091,
      "grad_norm": 1.3171674013137817,
      "learning_rate": 1.9281818181818185e-05,
      "loss": 0.5477,
      "step": 79
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 1.6939257383346558,
      "learning_rate": 1.9272727272727275e-05,
      "loss": 0.7424,
      "step": 80
    },
    {
      "epoch": 3.6818181818181817,
      "grad_norm": 1.6177845001220703,
      "learning_rate": 1.9263636363636365e-05,
      "loss": 0.6225,
      "step": 81
    },
    {
      "epoch": 3.7272727272727275,
      "grad_norm": 1.7323453426361084,
      "learning_rate": 1.9254545454545455e-05,
      "loss": 0.4644,
      "step": 82
    },
    {
      "epoch": 3.7727272727272725,
      "grad_norm": 1.2443021535873413,
      "learning_rate": 1.924545454545455e-05,
      "loss": 0.524,
      "step": 83
    },
    {
      "epoch": 3.8181818181818183,
      "grad_norm": 1.6111009120941162,
      "learning_rate": 1.923636363636364e-05,
      "loss": 0.6301,
      "step": 84
    },
    {
      "epoch": 3.8636363636363638,
      "grad_norm": 1.3090589046478271,
      "learning_rate": 1.922727272727273e-05,
      "loss": 0.6209,
      "step": 85
    },
    {
      "epoch": 3.909090909090909,
      "grad_norm": 1.2143287658691406,
      "learning_rate": 1.921818181818182e-05,
      "loss": 0.523,
      "step": 86
    },
    {
      "epoch": 3.9545454545454546,
      "grad_norm": 1.551576018333435,
      "learning_rate": 1.920909090909091e-05,
      "loss": 0.6025,
      "step": 87
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.606203317642212,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.59,
      "step": 88
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8238788238788238,
      "eval_f1": 0.7027790861987753,
      "eval_loss": 0.5813168883323669,
      "eval_precision": 0.6763372620126926,
      "eval_recall": 0.7313725490196078,
      "eval_runtime": 5.433,
      "eval_samples_per_second": 24.112,
      "eval_steps_per_second": 0.92,
      "step": 88
    },
    {
      "epoch": 4.045454545454546,
      "grad_norm": 1.6170856952667236,
      "learning_rate": 1.9190909090909093e-05,
      "loss": 0.5609,
      "step": 89
    },
    {
      "epoch": 4.090909090909091,
      "grad_norm": 1.21828031539917,
      "learning_rate": 1.9181818181818183e-05,
      "loss": 0.5444,
      "step": 90
    },
    {
      "epoch": 4.136363636363637,
      "grad_norm": 1.3539512157440186,
      "learning_rate": 1.9172727272727273e-05,
      "loss": 0.5608,
      "step": 91
    },
    {
      "epoch": 4.181818181818182,
      "grad_norm": 1.2486921548843384,
      "learning_rate": 1.9163636363636363e-05,
      "loss": 0.4976,
      "step": 92
    },
    {
      "epoch": 4.2272727272727275,
      "grad_norm": 1.474204659461975,
      "learning_rate": 1.9154545454545456e-05,
      "loss": 0.4646,
      "step": 93
    },
    {
      "epoch": 4.2727272727272725,
      "grad_norm": 1.4018511772155762,
      "learning_rate": 1.9145454545454546e-05,
      "loss": 0.4138,
      "step": 94
    },
    {
      "epoch": 4.318181818181818,
      "grad_norm": 1.6630454063415527,
      "learning_rate": 1.9136363636363636e-05,
      "loss": 0.6184,
      "step": 95
    },
    {
      "epoch": 4.363636363636363,
      "grad_norm": 1.681337594985962,
      "learning_rate": 1.912727272727273e-05,
      "loss": 0.4985,
      "step": 96
    },
    {
      "epoch": 4.409090909090909,
      "grad_norm": 1.1836535930633545,
      "learning_rate": 1.911818181818182e-05,
      "loss": 0.4481,
      "step": 97
    },
    {
      "epoch": 4.454545454545454,
      "grad_norm": 1.2125182151794434,
      "learning_rate": 1.910909090909091e-05,
      "loss": 0.4427,
      "step": 98
    },
    {
      "epoch": 4.5,
      "grad_norm": 1.1907086372375488,
      "learning_rate": 1.91e-05,
      "loss": 0.4656,
      "step": 99
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 1.6791960000991821,
      "learning_rate": 1.9090909090909094e-05,
      "loss": 0.5132,
      "step": 100
    },
    {
      "epoch": 4.590909090909091,
      "grad_norm": 2.0220723152160645,
      "learning_rate": 1.9081818181818184e-05,
      "loss": 0.7157,
      "step": 101
    },
    {
      "epoch": 4.636363636363637,
      "grad_norm": 1.3273769617080688,
      "learning_rate": 1.9072727272727274e-05,
      "loss": 0.5186,
      "step": 102
    },
    {
      "epoch": 4.681818181818182,
      "grad_norm": 1.971346378326416,
      "learning_rate": 1.9063636363636364e-05,
      "loss": 0.4861,
      "step": 103
    },
    {
      "epoch": 4.7272727272727275,
      "grad_norm": 1.4221469163894653,
      "learning_rate": 1.9054545454545457e-05,
      "loss": 0.5415,
      "step": 104
    },
    {
      "epoch": 4.7727272727272725,
      "grad_norm": 1.5409835577011108,
      "learning_rate": 1.9045454545454547e-05,
      "loss": 0.4741,
      "step": 105
    },
    {
      "epoch": 4.818181818181818,
      "grad_norm": 2.085914134979248,
      "learning_rate": 1.9036363636363637e-05,
      "loss": 0.5062,
      "step": 106
    },
    {
      "epoch": 4.863636363636363,
      "grad_norm": 1.571999430656433,
      "learning_rate": 1.902727272727273e-05,
      "loss": 0.6323,
      "step": 107
    },
    {
      "epoch": 4.909090909090909,
      "grad_norm": 1.3681639432907104,
      "learning_rate": 1.901818181818182e-05,
      "loss": 0.5369,
      "step": 108
    },
    {
      "epoch": 4.954545454545455,
      "grad_norm": 1.8829340934753418,
      "learning_rate": 1.900909090909091e-05,
      "loss": 0.4372,
      "step": 109
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.9513062238693237,
      "learning_rate": 1.9e-05,
      "loss": 0.5141,
      "step": 110
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8241758241758241,
      "eval_f1": 0.6876172607879925,
      "eval_loss": 0.5749279856681824,
      "eval_precision": 0.6591726618705036,
      "eval_recall": 0.7186274509803922,
      "eval_runtime": 5.3919,
      "eval_samples_per_second": 24.296,
      "eval_steps_per_second": 0.927,
      "step": 110
    }
  ],
  "logging_steps": 1,
  "max_steps": 2200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 156073447450800.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}