{
  "best_metric": 1.150753378868103,
  "best_model_checkpoint": "squarerun_earlystop/checkpoint-145",
  "epoch": 13.0,
  "eval_steps": 500,
  "global_step": 377,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06896551724137931,
      "grad_norm": 19.357681274414062,
      "learning_rate": 1.724137931034483e-06,
      "loss": 1.9617,
      "step": 2
    },
    {
      "epoch": 0.13793103448275862,
      "grad_norm": 10.07545280456543,
      "learning_rate": 3.448275862068966e-06,
      "loss": 2.0829,
      "step": 4
    },
    {
      "epoch": 0.20689655172413793,
      "grad_norm": 11.062702178955078,
      "learning_rate": 5.172413793103448e-06,
      "loss": 1.948,
      "step": 6
    },
    {
      "epoch": 0.27586206896551724,
      "grad_norm": 7.888413429260254,
      "learning_rate": 6.896551724137932e-06,
      "loss": 1.9238,
      "step": 8
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 12.095210075378418,
      "learning_rate": 8.620689655172414e-06,
      "loss": 1.8641,
      "step": 10
    },
    {
      "epoch": 0.41379310344827586,
      "grad_norm": 12.549093246459961,
      "learning_rate": 1.0344827586206897e-05,
      "loss": 2.1869,
      "step": 12
    },
    {
      "epoch": 0.4827586206896552,
      "grad_norm": 10.326892852783203,
      "learning_rate": 1.206896551724138e-05,
      "loss": 2.0025,
      "step": 14
    },
    {
      "epoch": 0.5517241379310345,
      "grad_norm": 8.114046096801758,
      "learning_rate": 1.3793103448275863e-05,
      "loss": 2.0149,
      "step": 16
    },
    {
      "epoch": 0.6206896551724138,
      "grad_norm": 9.516056060791016,
      "learning_rate": 1.5517241379310346e-05,
      "loss": 1.8154,
      "step": 18
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 8.580568313598633,
      "learning_rate": 1.7241379310344828e-05,
      "loss": 1.8289,
      "step": 20
    },
    {
      "epoch": 0.7586206896551724,
      "grad_norm": 6.422548770904541,
      "learning_rate": 1.896551724137931e-05,
      "loss": 1.9361,
      "step": 22
    },
    {
      "epoch": 0.8275862068965517,
      "grad_norm": 5.681264400482178,
      "learning_rate": 2.0689655172413793e-05,
      "loss": 1.8934,
      "step": 24
    },
    {
      "epoch": 0.896551724137931,
      "grad_norm": 11.326376914978027,
      "learning_rate": 2.2413793103448276e-05,
      "loss": 1.8371,
      "step": 26
    },
    {
      "epoch": 0.9655172413793104,
      "grad_norm": 7.500190258026123,
      "learning_rate": 2.413793103448276e-05,
      "loss": 1.9437,
      "step": 28
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.25757575757575757,
      "eval_f1_macro": 0.14848660111818004,
      "eval_f1_micro": 0.25757575757575757,
      "eval_f1_weighted": 0.16799165746534167,
      "eval_loss": 1.898682713508606,
      "eval_precision_macro": 0.11923314780457638,
      "eval_precision_micro": 0.25757575757575757,
      "eval_precision_weighted": 0.13213301849665487,
      "eval_recall_macro": 0.2206802721088435,
      "eval_recall_micro": 0.25757575757575757,
      "eval_recall_weighted": 0.25757575757575757,
      "eval_runtime": 2.9681,
      "eval_samples_per_second": 44.473,
      "eval_steps_per_second": 5.728,
      "step": 29
    },
    {
      "epoch": 1.0344827586206897,
      "grad_norm": 12.50450611114502,
      "learning_rate": 2.5862068965517244e-05,
      "loss": 1.9287,
      "step": 30
    },
    {
      "epoch": 1.103448275862069,
      "grad_norm": 7.673898696899414,
      "learning_rate": 2.7586206896551727e-05,
      "loss": 1.664,
      "step": 32
    },
    {
      "epoch": 1.1724137931034484,
      "grad_norm": 5.811491966247559,
      "learning_rate": 2.9310344827586206e-05,
      "loss": 1.8535,
      "step": 34
    },
    {
      "epoch": 1.2413793103448276,
      "grad_norm": 8.861312866210938,
      "learning_rate": 3.103448275862069e-05,
      "loss": 1.9855,
      "step": 36
    },
    {
      "epoch": 1.3103448275862069,
      "grad_norm": 8.68062973022461,
      "learning_rate": 3.275862068965517e-05,
      "loss": 1.8194,
      "step": 38
    },
    {
      "epoch": 1.3793103448275863,
      "grad_norm": 10.850172996520996,
      "learning_rate": 3.4482758620689657e-05,
      "loss": 1.8562,
      "step": 40
    },
    {
      "epoch": 1.4482758620689655,
      "grad_norm": 7.273862361907959,
      "learning_rate": 3.620689655172414e-05,
      "loss": 1.887,
      "step": 42
    },
    {
      "epoch": 1.5172413793103448,
      "grad_norm": 9.375494956970215,
      "learning_rate": 3.793103448275862e-05,
      "loss": 1.6063,
      "step": 44
    },
    {
      "epoch": 1.5862068965517242,
      "grad_norm": 7.466917991638184,
      "learning_rate": 3.965517241379311e-05,
      "loss": 1.7104,
      "step": 46
    },
    {
      "epoch": 1.6551724137931034,
      "grad_norm": 6.921249866485596,
      "learning_rate": 4.1379310344827587e-05,
      "loss": 1.7771,
      "step": 48
    },
    {
      "epoch": 1.7241379310344827,
      "grad_norm": 8.85164737701416,
      "learning_rate": 4.3103448275862066e-05,
      "loss": 1.7949,
      "step": 50
    },
    {
      "epoch": 1.793103448275862,
      "grad_norm": 9.841817855834961,
      "learning_rate": 4.482758620689655e-05,
      "loss": 1.7742,
      "step": 52
    },
    {
      "epoch": 1.8620689655172413,
      "grad_norm": 9.186838150024414,
      "learning_rate": 4.655172413793104e-05,
      "loss": 1.6552,
      "step": 54
    },
    {
      "epoch": 1.9310344827586206,
      "grad_norm": 12.096390724182129,
      "learning_rate": 4.827586206896552e-05,
      "loss": 1.7408,
      "step": 56
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.921807289123535,
      "learning_rate": 5e-05,
      "loss": 1.4616,
      "step": 58
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.42424242424242425,
      "eval_f1_macro": 0.35690013239708984,
      "eval_f1_micro": 0.42424242424242425,
      "eval_f1_weighted": 0.40756753098630294,
      "eval_loss": 1.5844290256500244,
      "eval_precision_macro": 0.4336450032302567,
      "eval_precision_micro": 0.42424242424242425,
      "eval_precision_weighted": 0.473761575667734,
      "eval_recall_macro": 0.3657142857142857,
      "eval_recall_micro": 0.42424242424242425,
      "eval_recall_weighted": 0.42424242424242425,
      "eval_runtime": 2.96,
      "eval_samples_per_second": 44.594,
      "eval_steps_per_second": 5.743,
      "step": 58
    },
    {
      "epoch": 2.0689655172413794,
      "grad_norm": 11.485949516296387,
      "learning_rate": 5.172413793103449e-05,
      "loss": 1.6275,
      "step": 60
    },
    {
      "epoch": 2.1379310344827585,
      "grad_norm": 6.314526081085205,
      "learning_rate": 5.344827586206896e-05,
      "loss": 1.396,
      "step": 62
    },
    {
      "epoch": 2.206896551724138,
      "grad_norm": 11.086990356445312,
      "learning_rate": 5.517241379310345e-05,
      "loss": 1.5553,
      "step": 64
    },
    {
      "epoch": 2.2758620689655173,
      "grad_norm": 16.221271514892578,
      "learning_rate": 5.689655172413794e-05,
      "loss": 1.6025,
      "step": 66
    },
    {
      "epoch": 2.344827586206897,
      "grad_norm": 8.68588924407959,
      "learning_rate": 5.862068965517241e-05,
      "loss": 1.435,
      "step": 68
    },
    {
      "epoch": 2.413793103448276,
      "grad_norm": 10.737080574035645,
      "learning_rate": 6.03448275862069e-05,
      "loss": 1.4304,
      "step": 70
    },
    {
      "epoch": 2.4827586206896552,
      "grad_norm": 9.171552658081055,
      "learning_rate": 6.206896551724138e-05,
      "loss": 1.5959,
      "step": 72
    },
    {
      "epoch": 2.5517241379310347,
      "grad_norm": 10.185091972351074,
      "learning_rate": 6.379310344827587e-05,
      "loss": 1.2897,
      "step": 74
    },
    {
      "epoch": 2.6206896551724137,
      "grad_norm": 10.52213191986084,
      "learning_rate": 6.551724137931034e-05,
      "loss": 1.5851,
      "step": 76
    },
    {
      "epoch": 2.689655172413793,
      "grad_norm": 6.222963333129883,
      "learning_rate": 6.724137931034483e-05,
      "loss": 1.8139,
      "step": 78
    },
    {
      "epoch": 2.7586206896551726,
      "grad_norm": 9.174198150634766,
      "learning_rate": 6.896551724137931e-05,
      "loss": 1.4277,
      "step": 80
    },
    {
      "epoch": 2.8275862068965516,
      "grad_norm": 11.63707160949707,
      "learning_rate": 7.06896551724138e-05,
      "loss": 1.4775,
      "step": 82
    },
    {
      "epoch": 2.896551724137931,
      "grad_norm": 9.97467041015625,
      "learning_rate": 7.241379310344828e-05,
      "loss": 1.8332,
      "step": 84
    },
    {
      "epoch": 2.9655172413793105,
      "grad_norm": 11.130326271057129,
      "learning_rate": 7.413793103448277e-05,
      "loss": 1.9935,
      "step": 86
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.42424242424242425,
      "eval_f1_macro": 0.3059313903206654,
      "eval_f1_micro": 0.42424242424242425,
      "eval_f1_weighted": 0.358521912270671,
      "eval_loss": 1.49520742893219,
      "eval_precision_macro": 0.3794595137633113,
      "eval_precision_micro": 0.42424242424242425,
      "eval_precision_weighted": 0.40968066743383197,
      "eval_recall_macro": 0.33868480725623584,
      "eval_recall_micro": 0.42424242424242425,
      "eval_recall_weighted": 0.42424242424242425,
      "eval_runtime": 2.963,
      "eval_samples_per_second": 44.549,
      "eval_steps_per_second": 5.737,
      "step": 87
    },
    {
      "epoch": 3.0344827586206895,
      "grad_norm": 9.817953109741211,
      "learning_rate": 7.586206896551724e-05,
      "loss": 1.4279,
      "step": 88
    },
    {
      "epoch": 3.103448275862069,
      "grad_norm": 6.149507999420166,
      "learning_rate": 7.758620689655173e-05,
      "loss": 1.2738,
      "step": 90
    },
    {
      "epoch": 3.1724137931034484,
      "grad_norm": 8.348538398742676,
      "learning_rate": 7.931034482758621e-05,
      "loss": 1.464,
      "step": 92
    },
    {
      "epoch": 3.2413793103448274,
      "grad_norm": 9.717902183532715,
      "learning_rate": 8.103448275862069e-05,
      "loss": 1.4473,
      "step": 94
    },
    {
      "epoch": 3.310344827586207,
      "grad_norm": 8.710390090942383,
      "learning_rate": 8.275862068965517e-05,
      "loss": 1.1216,
      "step": 96
    },
    {
      "epoch": 3.3793103448275863,
      "grad_norm": 9.217482566833496,
      "learning_rate": 8.448275862068966e-05,
      "loss": 1.3658,
      "step": 98
    },
    {
      "epoch": 3.4482758620689653,
      "grad_norm": 7.890769004821777,
      "learning_rate": 8.620689655172413e-05,
      "loss": 1.3025,
      "step": 100
    },
    {
      "epoch": 3.5172413793103448,
      "grad_norm": 7.533488750457764,
      "learning_rate": 8.793103448275862e-05,
      "loss": 1.6855,
      "step": 102
    },
    {
      "epoch": 3.586206896551724,
      "grad_norm": 9.90977954864502,
      "learning_rate": 8.96551724137931e-05,
      "loss": 1.36,
      "step": 104
    },
    {
      "epoch": 3.655172413793103,
      "grad_norm": 7.196977138519287,
      "learning_rate": 9.137931034482759e-05,
      "loss": 1.2334,
      "step": 106
    },
    {
      "epoch": 3.7241379310344827,
      "grad_norm": 15.348875999450684,
      "learning_rate": 9.310344827586207e-05,
      "loss": 1.3841,
      "step": 108
    },
    {
      "epoch": 3.793103448275862,
      "grad_norm": 14.928166389465332,
      "learning_rate": 9.482758620689656e-05,
      "loss": 2.0163,
      "step": 110
    },
    {
      "epoch": 3.862068965517241,
      "grad_norm": 13.652559280395508,
      "learning_rate": 9.655172413793105e-05,
      "loss": 1.6106,
      "step": 112
    },
    {
      "epoch": 3.9310344827586206,
      "grad_norm": 10.011820793151855,
      "learning_rate": 9.827586206896552e-05,
      "loss": 1.6056,
      "step": 114
    },
    {
      "epoch": 4.0,
      "grad_norm": 9.423259735107422,
      "learning_rate": 0.0001,
      "loss": 1.3601,
      "step": 116
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.4166666666666667,
      "eval_f1_macro": 0.3275201621665789,
      "eval_f1_micro": 0.4166666666666667,
      "eval_f1_weighted": 0.37198349822934534,
      "eval_loss": 1.4318833351135254,
      "eval_precision_macro": 0.3223270440251572,
      "eval_precision_micro": 0.4166666666666667,
      "eval_precision_weighted": 0.3618431311398721,
      "eval_recall_macro": 0.361360544217687,
      "eval_recall_micro": 0.4166666666666667,
      "eval_recall_weighted": 0.4166666666666667,
      "eval_runtime": 2.9668,
      "eval_samples_per_second": 44.492,
      "eval_steps_per_second": 5.73,
      "step": 116
    },
    {
      "epoch": 4.068965517241379,
      "grad_norm": 12.455545425415039,
      "learning_rate": 9.980842911877395e-05,
      "loss": 1.4989,
      "step": 118
    },
    {
      "epoch": 4.137931034482759,
      "grad_norm": 7.556772232055664,
      "learning_rate": 9.96168582375479e-05,
      "loss": 1.1474,
      "step": 120
    },
    {
      "epoch": 4.206896551724138,
      "grad_norm": 7.164824962615967,
      "learning_rate": 9.942528735632183e-05,
      "loss": 1.3469,
      "step": 122
    },
    {
      "epoch": 4.275862068965517,
      "grad_norm": 12.2306489944458,
      "learning_rate": 9.92337164750958e-05,
      "loss": 1.2394,
      "step": 124
    },
    {
      "epoch": 4.344827586206897,
      "grad_norm": 10.257525444030762,
      "learning_rate": 9.904214559386974e-05,
      "loss": 1.2865,
      "step": 126
    },
    {
      "epoch": 4.413793103448276,
      "grad_norm": 8.052595138549805,
      "learning_rate": 9.885057471264369e-05,
      "loss": 1.5634,
      "step": 128
    },
    {
      "epoch": 4.482758620689655,
      "grad_norm": 10.05372142791748,
      "learning_rate": 9.865900383141762e-05,
      "loss": 1.3826,
      "step": 130
    },
    {
      "epoch": 4.551724137931035,
      "grad_norm": 8.02147102355957,
      "learning_rate": 9.846743295019157e-05,
      "loss": 1.492,
      "step": 132
    },
    {
      "epoch": 4.620689655172414,
      "grad_norm": 7.700930118560791,
      "learning_rate": 9.827586206896552e-05,
      "loss": 1.4822,
      "step": 134
    },
    {
      "epoch": 4.689655172413794,
      "grad_norm": 12.909700393676758,
      "learning_rate": 9.808429118773947e-05,
      "loss": 1.617,
      "step": 136
    },
    {
      "epoch": 4.758620689655173,
      "grad_norm": 6.239136219024658,
      "learning_rate": 9.789272030651341e-05,
      "loss": 1.3277,
      "step": 138
    },
    {
      "epoch": 4.827586206896552,
      "grad_norm": 3.8295445442199707,
      "learning_rate": 9.770114942528736e-05,
      "loss": 0.8903,
      "step": 140
    },
    {
      "epoch": 4.896551724137931,
      "grad_norm": 5.378627777099609,
      "learning_rate": 9.750957854406131e-05,
      "loss": 1.1828,
      "step": 142
    },
    {
      "epoch": 4.9655172413793105,
      "grad_norm": 7.193126201629639,
      "learning_rate": 9.731800766283526e-05,
      "loss": 1.1685,
      "step": 144
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5833333333333334,
      "eval_f1_macro": 0.49134435355199774,
      "eval_f1_micro": 0.5833333333333334,
      "eval_f1_weighted": 0.5549812296530736,
      "eval_loss": 1.150753378868103,
      "eval_precision_macro": 0.4886814574314574,
      "eval_precision_micro": 0.5833333333333334,
      "eval_precision_weighted": 0.5484221954392409,
      "eval_recall_macro": 0.5139380196523053,
      "eval_recall_micro": 0.5833333333333334,
      "eval_recall_weighted": 0.5833333333333334,
      "eval_runtime": 2.9609,
      "eval_samples_per_second": 44.58,
      "eval_steps_per_second": 5.741,
      "step": 145
    },
    {
      "epoch": 5.0344827586206895,
      "grad_norm": 8.835988998413086,
      "learning_rate": 9.71264367816092e-05,
      "loss": 1.4503,
      "step": 146
    },
    {
      "epoch": 5.103448275862069,
      "grad_norm": 11.152828216552734,
      "learning_rate": 9.693486590038314e-05,
      "loss": 1.1148,
      "step": 148
    },
    {
      "epoch": 5.172413793103448,
      "grad_norm": 5.95009183883667,
      "learning_rate": 9.674329501915709e-05,
      "loss": 0.7798,
      "step": 150
    },
    {
      "epoch": 5.241379310344827,
      "grad_norm": 9.28747272491455,
      "learning_rate": 9.655172413793105e-05,
      "loss": 1.071,
      "step": 152
    },
    {
      "epoch": 5.310344827586207,
      "grad_norm": 9.649368286132812,
      "learning_rate": 9.6360153256705e-05,
      "loss": 1.129,
      "step": 154
    },
    {
      "epoch": 5.379310344827586,
      "grad_norm": 6.515026569366455,
      "learning_rate": 9.616858237547893e-05,
      "loss": 1.256,
      "step": 156
    },
    {
      "epoch": 5.448275862068965,
      "grad_norm": 12.087512969970703,
      "learning_rate": 9.597701149425288e-05,
      "loss": 1.8989,
      "step": 158
    },
    {
      "epoch": 5.517241379310345,
      "grad_norm": 7.530760288238525,
      "learning_rate": 9.578544061302682e-05,
      "loss": 0.9788,
      "step": 160
    },
    {
      "epoch": 5.586206896551724,
      "grad_norm": 7.923486709594727,
      "learning_rate": 9.559386973180077e-05,
      "loss": 1.2471,
      "step": 162
    },
    {
      "epoch": 5.655172413793103,
      "grad_norm": 4.997186183929443,
      "learning_rate": 9.540229885057472e-05,
      "loss": 1.1195,
      "step": 164
    },
    {
      "epoch": 5.724137931034483,
      "grad_norm": 8.351778030395508,
      "learning_rate": 9.521072796934867e-05,
      "loss": 1.2892,
      "step": 166
    },
    {
      "epoch": 5.793103448275862,
      "grad_norm": 6.890372276306152,
      "learning_rate": 9.501915708812261e-05,
      "loss": 1.1941,
      "step": 168
    },
    {
      "epoch": 5.862068965517241,
      "grad_norm": 10.095701217651367,
      "learning_rate": 9.482758620689656e-05,
      "loss": 1.1857,
      "step": 170
    },
    {
      "epoch": 5.931034482758621,
      "grad_norm": 6.678011417388916,
      "learning_rate": 9.463601532567051e-05,
      "loss": 1.1152,
      "step": 172
    },
    {
      "epoch": 6.0,
      "grad_norm": 5.188634395599365,
      "learning_rate": 9.444444444444444e-05,
      "loss": 1.2228,
      "step": 174
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5075757575757576,
      "eval_f1_macro": 0.48649389792977665,
      "eval_f1_micro": 0.5075757575757576,
      "eval_f1_weighted": 0.504583670632264,
      "eval_loss": 1.2663319110870361,
      "eval_precision_macro": 0.5338627386438447,
      "eval_precision_micro": 0.5075757575757576,
      "eval_precision_weighted": 0.5644310326770005,
      "eval_recall_macro": 0.49635676492819353,
      "eval_recall_micro": 0.5075757575757576,
      "eval_recall_weighted": 0.5075757575757576,
      "eval_runtime": 2.9553,
      "eval_samples_per_second": 44.666,
      "eval_steps_per_second": 5.752,
      "step": 174
    },
    {
      "epoch": 6.068965517241379,
      "grad_norm": 8.04442024230957,
      "learning_rate": 9.425287356321839e-05,
      "loss": 0.813,
      "step": 176
    },
    {
      "epoch": 6.137931034482759,
      "grad_norm": 4.239109516143799,
      "learning_rate": 9.406130268199235e-05,
      "loss": 0.7334,
      "step": 178
    },
    {
      "epoch": 6.206896551724138,
      "grad_norm": 11.466559410095215,
      "learning_rate": 9.38697318007663e-05,
      "loss": 0.9938,
      "step": 180
    },
    {
      "epoch": 6.275862068965517,
      "grad_norm": 6.6499199867248535,
      "learning_rate": 9.367816091954023e-05,
      "loss": 1.4748,
      "step": 182
    },
    {
      "epoch": 6.344827586206897,
      "grad_norm": 6.700629234313965,
      "learning_rate": 9.348659003831418e-05,
      "loss": 0.7446,
      "step": 184
    },
    {
      "epoch": 6.413793103448276,
      "grad_norm": 5.955834865570068,
      "learning_rate": 9.329501915708813e-05,
      "loss": 0.5876,
      "step": 186
    },
    {
      "epoch": 6.482758620689655,
      "grad_norm": 4.36069393157959,
      "learning_rate": 9.310344827586207e-05,
      "loss": 0.6486,
      "step": 188
    },
    {
      "epoch": 6.551724137931035,
      "grad_norm": 6.722736358642578,
      "learning_rate": 9.291187739463601e-05,
      "loss": 0.9317,
      "step": 190
    },
    {
      "epoch": 6.620689655172414,
      "grad_norm": 10.725391387939453,
      "learning_rate": 9.272030651340997e-05,
      "loss": 1.0865,
      "step": 192
    },
    {
      "epoch": 6.689655172413794,
      "grad_norm": 7.119555950164795,
      "learning_rate": 9.252873563218392e-05,
      "loss": 1.0571,
      "step": 194
    },
    {
      "epoch": 6.758620689655173,
      "grad_norm": 7.10548210144043,
      "learning_rate": 9.233716475095786e-05,
      "loss": 1.2002,
      "step": 196
    },
    {
      "epoch": 6.827586206896552,
      "grad_norm": 7.357244968414307,
      "learning_rate": 9.21455938697318e-05,
      "loss": 0.9461,
      "step": 198
    },
    {
      "epoch": 6.896551724137931,
      "grad_norm": 9.458577156066895,
      "learning_rate": 9.195402298850575e-05,
      "loss": 1.0334,
      "step": 200
    },
    {
      "epoch": 6.9655172413793105,
      "grad_norm": 7.48079252243042,
      "learning_rate": 9.17624521072797e-05,
      "loss": 1.2811,
      "step": 202
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5303030303030303,
      "eval_f1_macro": 0.40842438013755056,
      "eval_f1_micro": 0.5303030303030303,
      "eval_f1_weighted": 0.4751581109098944,
      "eval_loss": 1.4595577716827393,
      "eval_precision_macro": 0.5581683833407971,
      "eval_precision_micro": 0.5303030303030303,
      "eval_precision_weighted": 0.6067953833000855,
      "eval_recall_macro": 0.43830687830687826,
      "eval_recall_micro": 0.5303030303030303,
      "eval_recall_weighted": 0.5303030303030303,
      "eval_runtime": 2.9603,
      "eval_samples_per_second": 44.59,
      "eval_steps_per_second": 5.743,
      "step": 203
    },
    {
      "epoch": 7.0344827586206895,
      "grad_norm": 6.276855945587158,
      "learning_rate": 9.157088122605364e-05,
      "loss": 1.2212,
      "step": 204
    },
    {
      "epoch": 7.103448275862069,
      "grad_norm": 13.91729736328125,
      "learning_rate": 9.137931034482759e-05,
      "loss": 0.9592,
      "step": 206
    },
    {
      "epoch": 7.172413793103448,
      "grad_norm": 8.206171035766602,
      "learning_rate": 9.118773946360154e-05,
      "loss": 1.0261,
      "step": 208
    },
    {
      "epoch": 7.241379310344827,
      "grad_norm": 6.51706075668335,
      "learning_rate": 9.099616858237548e-05,
      "loss": 1.0831,
      "step": 210
    },
    {
      "epoch": 7.310344827586207,
      "grad_norm": 10.827319145202637,
      "learning_rate": 9.080459770114943e-05,
      "loss": 1.048,
      "step": 212
    },
    {
      "epoch": 7.379310344827586,
      "grad_norm": 8.241643905639648,
      "learning_rate": 9.061302681992338e-05,
      "loss": 1.0182,
      "step": 214
    },
    {
      "epoch": 7.448275862068965,
      "grad_norm": 6.14633321762085,
      "learning_rate": 9.042145593869731e-05,
      "loss": 0.6089,
      "step": 216
    },
    {
      "epoch": 7.517241379310345,
      "grad_norm": 7.247577667236328,
      "learning_rate": 9.022988505747126e-05,
      "loss": 0.775,
      "step": 218
    },
    {
      "epoch": 7.586206896551724,
      "grad_norm": 8.919748306274414,
      "learning_rate": 9.003831417624522e-05,
      "loss": 0.9039,
      "step": 220
    },
    {
      "epoch": 7.655172413793103,
      "grad_norm": 7.243560791015625,
      "learning_rate": 8.984674329501917e-05,
      "loss": 0.7609,
      "step": 222
    },
    {
      "epoch": 7.724137931034483,
      "grad_norm": 10.010783195495605,
      "learning_rate": 8.96551724137931e-05,
      "loss": 0.7431,
      "step": 224
    },
    {
      "epoch": 7.793103448275862,
      "grad_norm": 11.02781867980957,
      "learning_rate": 8.946360153256705e-05,
      "loss": 1.5126,
      "step": 226
    },
    {
      "epoch": 7.862068965517241,
      "grad_norm": 7.93005895614624,
      "learning_rate": 8.9272030651341e-05,
      "loss": 0.5022,
      "step": 228
    },
    {
      "epoch": 7.931034482758621,
      "grad_norm": 12.424070358276367,
      "learning_rate": 8.908045977011495e-05,
      "loss": 0.9272,
      "step": 230
    },
    {
      "epoch": 8.0,
      "grad_norm": 12.335293769836426,
      "learning_rate": 8.888888888888889e-05,
      "loss": 1.7256,
      "step": 232
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5681818181818182,
      "eval_f1_macro": 0.4805299838894464,
      "eval_f1_micro": 0.5681818181818182,
      "eval_f1_weighted": 0.5434771053711297,
      "eval_loss": 1.490796446800232,
      "eval_precision_macro": 0.5332785669808334,
      "eval_precision_micro": 0.5681818181818182,
      "eval_precision_weighted": 0.6122299205283115,
      "eval_recall_macro": 0.5219198790627363,
      "eval_recall_micro": 0.5681818181818182,
      "eval_recall_weighted": 0.5681818181818182,
      "eval_runtime": 2.9681,
      "eval_samples_per_second": 44.473,
      "eval_steps_per_second": 5.728,
      "step": 232
    },
    {
      "epoch": 8.068965517241379,
      "grad_norm": 8.515727996826172,
      "learning_rate": 8.869731800766284e-05,
      "loss": 0.6998,
      "step": 234
    },
    {
      "epoch": 8.137931034482758,
      "grad_norm": 6.3350934982299805,
      "learning_rate": 8.850574712643679e-05,
      "loss": 0.6902,
      "step": 236
    },
    {
      "epoch": 8.206896551724139,
      "grad_norm": 6.2341132164001465,
      "learning_rate": 8.831417624521074e-05,
      "loss": 0.7862,
      "step": 238
    },
    {
      "epoch": 8.275862068965518,
      "grad_norm": 5.668937683105469,
      "learning_rate": 8.812260536398468e-05,
      "loss": 0.8759,
      "step": 240
    },
    {
      "epoch": 8.344827586206897,
      "grad_norm": 6.639297962188721,
      "learning_rate": 8.793103448275862e-05,
      "loss": 0.5213,
      "step": 242
    },
    {
      "epoch": 8.413793103448276,
      "grad_norm": 8.357873916625977,
      "learning_rate": 8.773946360153256e-05,
      "loss": 0.7463,
      "step": 244
    },
    {
      "epoch": 8.482758620689655,
      "grad_norm": 6.915083885192871,
      "learning_rate": 8.754789272030651e-05,
      "loss": 0.7049,
      "step": 246
    },
    {
      "epoch": 8.551724137931034,
      "grad_norm": 7.055286407470703,
      "learning_rate": 8.735632183908047e-05,
      "loss": 0.731,
      "step": 248
    },
    {
      "epoch": 8.620689655172415,
      "grad_norm": 10.977728843688965,
      "learning_rate": 8.716475095785441e-05,
      "loss": 0.9833,
      "step": 250
    },
    {
      "epoch": 8.689655172413794,
      "grad_norm": 10.40459156036377,
      "learning_rate": 8.697318007662835e-05,
      "loss": 0.6566,
      "step": 252
    },
    {
      "epoch": 8.758620689655173,
      "grad_norm": 7.625058650970459,
      "learning_rate": 8.67816091954023e-05,
      "loss": 0.9152,
      "step": 254
    },
    {
      "epoch": 8.827586206896552,
      "grad_norm": 12.976395606994629,
      "learning_rate": 8.659003831417625e-05,
      "loss": 1.1152,
      "step": 256
    },
    {
      "epoch": 8.89655172413793,
      "grad_norm": 7.554351329803467,
      "learning_rate": 8.63984674329502e-05,
      "loss": 0.794,
      "step": 258
    },
    {
      "epoch": 8.96551724137931,
      "grad_norm": 10.101217269897461,
      "learning_rate": 8.620689655172413e-05,
      "loss": 0.4549,
      "step": 260
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.6136363636363636,
      "eval_f1_macro": 0.5270088365794784,
      "eval_f1_micro": 0.6136363636363636,
      "eval_f1_weighted": 0.5647711520056131,
      "eval_loss": 1.296909213066101,
      "eval_precision_macro": 0.6663623344074471,
      "eval_precision_micro": 0.6136363636363636,
      "eval_precision_weighted": 0.675660742766006,
      "eval_recall_macro": 0.5526152683295541,
      "eval_recall_micro": 0.6136363636363636,
      "eval_recall_weighted": 0.6136363636363636,
      "eval_runtime": 2.9637,
      "eval_samples_per_second": 44.538,
      "eval_steps_per_second": 5.736,
      "step": 261
    },
    {
      "epoch": 9.03448275862069,
      "grad_norm": 7.993361949920654,
      "learning_rate": 8.601532567049809e-05,
      "loss": 0.9663,
      "step": 262
    },
    {
      "epoch": 9.10344827586207,
      "grad_norm": 7.356778621673584,
      "learning_rate": 8.582375478927204e-05,
      "loss": 0.8349,
      "step": 264
    },
    {
      "epoch": 9.172413793103448,
      "grad_norm": 7.286875247955322,
      "learning_rate": 8.563218390804599e-05,
      "loss": 0.6199,
      "step": 266
    },
    {
      "epoch": 9.241379310344827,
      "grad_norm": 7.223015785217285,
      "learning_rate": 8.544061302681992e-05,
      "loss": 0.389,
      "step": 268
    },
    {
      "epoch": 9.310344827586206,
      "grad_norm": 8.316946029663086,
      "learning_rate": 8.524904214559387e-05,
      "loss": 0.4572,
      "step": 270
    },
    {
      "epoch": 9.379310344827585,
      "grad_norm": 9.565052032470703,
      "learning_rate": 8.505747126436782e-05,
      "loss": 0.5443,
      "step": 272
    },
    {
      "epoch": 9.448275862068966,
      "grad_norm": 7.592960357666016,
      "learning_rate": 8.486590038314178e-05,
      "loss": 0.6893,
      "step": 274
    },
    {
      "epoch": 9.517241379310345,
      "grad_norm": 9.539419174194336,
      "learning_rate": 8.467432950191571e-05,
      "loss": 0.485,
      "step": 276
    },
    {
      "epoch": 9.586206896551724,
      "grad_norm": 5.9389729499816895,
      "learning_rate": 8.448275862068966e-05,
      "loss": 0.4296,
      "step": 278
    },
    {
      "epoch": 9.655172413793103,
      "grad_norm": 7.698464393615723,
      "learning_rate": 8.42911877394636e-05,
      "loss": 0.361,
      "step": 280
    },
    {
      "epoch": 9.724137931034482,
      "grad_norm": 7.502455234527588,
      "learning_rate": 8.409961685823755e-05,
      "loss": 0.6901,
      "step": 282
    },
    {
      "epoch": 9.793103448275861,
      "grad_norm": 6.852280616760254,
      "learning_rate": 8.39080459770115e-05,
      "loss": 0.8456,
      "step": 284
    },
    {
      "epoch": 9.862068965517242,
      "grad_norm": 12.406436920166016,
      "learning_rate": 8.371647509578544e-05,
      "loss": 0.6653,
      "step": 286
    },
    {
      "epoch": 9.931034482758621,
      "grad_norm": 9.554862022399902,
      "learning_rate": 8.35249042145594e-05,
      "loss": 0.6775,
      "step": 288
    },
    {
      "epoch": 10.0,
      "grad_norm": 4.816894054412842,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.5877,
      "step": 290
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.5757575757575758,
      "eval_f1_macro": 0.46384154004925054,
      "eval_f1_micro": 0.5757575757575758,
      "eval_f1_weighted": 0.5271337941318629,
      "eval_loss": 1.358140468597412,
      "eval_precision_macro": 0.5631969710961309,
      "eval_precision_micro": 0.5757575757575758,
      "eval_precision_weighted": 0.6293128440187263,
      "eval_recall_macro": 0.5095389266817837,
      "eval_recall_micro": 0.5757575757575758,
      "eval_recall_weighted": 0.5757575757575758,
      "eval_runtime": 2.9551,
      "eval_samples_per_second": 44.668,
      "eval_steps_per_second": 5.753,
      "step": 290
    },
    {
      "epoch": 10.068965517241379,
      "grad_norm": 12.736379623413086,
      "learning_rate": 8.314176245210729e-05,
      "loss": 0.522,
      "step": 292
    },
    {
      "epoch": 10.137931034482758,
      "grad_norm": 7.122078895568848,
      "learning_rate": 8.295019157088123e-05,
      "loss": 0.572,
      "step": 294
    },
    {
      "epoch": 10.206896551724139,
      "grad_norm": 8.840079307556152,
      "learning_rate": 8.275862068965517e-05,
      "loss": 0.6279,
      "step": 296
    },
    {
      "epoch": 10.275862068965518,
      "grad_norm": 8.563687324523926,
      "learning_rate": 8.256704980842912e-05,
      "loss": 0.5381,
      "step": 298
    },
    {
      "epoch": 10.344827586206897,
      "grad_norm": 4.0482587814331055,
      "learning_rate": 8.237547892720307e-05,
      "loss": 0.3322,
      "step": 300
    },
    {
      "epoch": 10.413793103448276,
      "grad_norm": 8.282402038574219,
      "learning_rate": 8.218390804597702e-05,
      "loss": 0.4547,
      "step": 302
    },
    {
      "epoch": 10.482758620689655,
      "grad_norm": 5.410398960113525,
      "learning_rate": 8.199233716475096e-05,
      "loss": 0.4316,
      "step": 304
    },
    {
      "epoch": 10.551724137931034,
      "grad_norm": 9.745489120483398,
      "learning_rate": 8.180076628352491e-05,
      "loss": 0.9735,
      "step": 306
    },
    {
      "epoch": 10.620689655172415,
      "grad_norm": 5.827289581298828,
      "learning_rate": 8.160919540229886e-05,
      "loss": 0.3934,
      "step": 308
    },
    {
      "epoch": 10.689655172413794,
      "grad_norm": 12.345109939575195,
      "learning_rate": 8.14176245210728e-05,
      "loss": 0.8064,
      "step": 310
    },
    {
      "epoch": 10.758620689655173,
      "grad_norm": 9.329832077026367,
      "learning_rate": 8.122605363984674e-05,
      "loss": 0.6792,
      "step": 312
    },
    {
      "epoch": 10.827586206896552,
      "grad_norm": 5.181191444396973,
      "learning_rate": 8.103448275862069e-05,
      "loss": 0.4054,
      "step": 314
    },
    {
      "epoch": 10.89655172413793,
      "grad_norm": 7.552645206451416,
      "learning_rate": 8.084291187739465e-05,
      "loss": 0.1956,
      "step": 316
    },
    {
      "epoch": 10.96551724137931,
      "grad_norm": 5.599520206451416,
      "learning_rate": 8.06513409961686e-05,
      "loss": 0.3451,
      "step": 318
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.6136363636363636,
      "eval_f1_macro": 0.5613081171482324,
      "eval_f1_micro": 0.6136363636363636,
      "eval_f1_weighted": 0.6066036873275266,
      "eval_loss": 1.2490617036819458,
      "eval_precision_macro": 0.5909090909090909,
      "eval_precision_micro": 0.6136363636363636,
      "eval_precision_weighted": 0.6110537190082644,
      "eval_recall_macro": 0.5589115646258503,
      "eval_recall_micro": 0.6136363636363636,
      "eval_recall_weighted": 0.6136363636363636,
      "eval_runtime": 2.9702,
      "eval_samples_per_second": 44.441,
      "eval_steps_per_second": 5.723,
      "step": 319
    },
    {
      "epoch": 11.03448275862069,
      "grad_norm": 4.307100772857666,
      "learning_rate": 8.045977011494253e-05,
      "loss": 0.2913,
      "step": 320
    },
    {
      "epoch": 11.10344827586207,
      "grad_norm": 4.337777137756348,
      "learning_rate": 8.026819923371648e-05,
      "loss": 0.223,
      "step": 322
    },
    {
      "epoch": 11.172413793103448,
      "grad_norm": 5.760768413543701,
      "learning_rate": 8.007662835249042e-05,
      "loss": 0.4768,
      "step": 324
    },
    {
      "epoch": 11.241379310344827,
      "grad_norm": 11.01797103881836,
      "learning_rate": 7.988505747126437e-05,
      "loss": 0.4892,
      "step": 326
    },
    {
      "epoch": 11.310344827586206,
      "grad_norm": 8.456830024719238,
      "learning_rate": 7.969348659003832e-05,
      "loss": 0.3436,
      "step": 328
    },
    {
      "epoch": 11.379310344827585,
      "grad_norm": 8.432597160339355,
      "learning_rate": 7.950191570881227e-05,
      "loss": 0.406,
      "step": 330
    },
    {
      "epoch": 11.448275862068966,
      "grad_norm": 10.220959663391113,
      "learning_rate": 7.931034482758621e-05,
      "loss": 0.3734,
      "step": 332
    },
    {
      "epoch": 11.517241379310345,
      "grad_norm": 5.659406661987305,
      "learning_rate": 7.911877394636016e-05,
      "loss": 0.2822,
      "step": 334
    },
    {
      "epoch": 11.586206896551724,
      "grad_norm": 1.9529658555984497,
      "learning_rate": 7.892720306513411e-05,
      "loss": 0.3656,
      "step": 336
    },
    {
      "epoch": 11.655172413793103,
      "grad_norm": 6.910799980163574,
      "learning_rate": 7.873563218390804e-05,
      "loss": 0.5396,
      "step": 338
    },
    {
      "epoch": 11.724137931034482,
      "grad_norm": 9.418132781982422,
      "learning_rate": 7.854406130268199e-05,
      "loss": 0.4497,
      "step": 340
    },
    {
      "epoch": 11.793103448275861,
      "grad_norm": 10.316533088684082,
      "learning_rate": 7.835249042145594e-05,
      "loss": 0.3782,
      "step": 342
    },
    {
      "epoch": 11.862068965517242,
      "grad_norm": 5.654300689697266,
      "learning_rate": 7.81609195402299e-05,
      "loss": 0.3447,
      "step": 344
    },
    {
      "epoch": 11.931034482758621,
      "grad_norm": 6.8490800857543945,
      "learning_rate": 7.796934865900383e-05,
      "loss": 0.205,
      "step": 346
    },
    {
      "epoch": 12.0,
      "grad_norm": 10.45013427734375,
      "learning_rate": 7.777777777777778e-05,
      "loss": 0.4885,
      "step": 348
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.6287878787878788,
      "eval_f1_macro": 0.5380526246743514,
      "eval_f1_micro": 0.6287878787878788,
      "eval_f1_weighted": 0.6086896087349808,
      "eval_loss": 1.6861677169799805,
      "eval_precision_macro": 0.5514896867838044,
      "eval_precision_micro": 0.6287878787878788,
      "eval_precision_weighted": 0.6224606432716949,
      "eval_recall_macro": 0.5575736961451246,
      "eval_recall_micro": 0.6287878787878788,
      "eval_recall_weighted": 0.6287878787878788,
      "eval_runtime": 2.9665,
      "eval_samples_per_second": 44.497,
      "eval_steps_per_second": 5.731,
      "step": 348
    },
    {
      "epoch": 12.068965517241379,
      "grad_norm": 13.315044403076172,
      "learning_rate": 7.758620689655173e-05,
      "loss": 0.6786,
      "step": 350
    },
    {
      "epoch": 12.137931034482758,
      "grad_norm": 7.0229034423828125,
      "learning_rate": 7.739463601532568e-05,
      "loss": 0.4346,
      "step": 352
    },
    {
      "epoch": 12.206896551724139,
      "grad_norm": 9.44849967956543,
      "learning_rate": 7.720306513409961e-05,
      "loss": 0.4842,
      "step": 354
    },
    {
      "epoch": 12.275862068965518,
      "grad_norm": 2.0537302494049072,
      "learning_rate": 7.701149425287356e-05,
      "loss": 0.0921,
      "step": 356
    },
    {
      "epoch": 12.344827586206897,
      "grad_norm": 7.648636341094971,
      "learning_rate": 7.681992337164752e-05,
      "loss": 0.4003,
      "step": 358
    },
    {
      "epoch": 12.413793103448276,
      "grad_norm": 8.219009399414062,
      "learning_rate": 7.662835249042147e-05,
      "loss": 0.57,
      "step": 360
    },
    {
      "epoch": 12.482758620689655,
      "grad_norm": 8.560858726501465,
      "learning_rate": 7.64367816091954e-05,
      "loss": 0.2207,
      "step": 362
    },
    {
      "epoch": 12.551724137931034,
      "grad_norm": 4.989181995391846,
      "learning_rate": 7.624521072796935e-05,
      "loss": 0.1446,
      "step": 364
    },
    {
      "epoch": 12.620689655172415,
      "grad_norm": 5.454369068145752,
      "learning_rate": 7.60536398467433e-05,
      "loss": 0.6619,
      "step": 366
    },
    {
      "epoch": 12.689655172413794,
      "grad_norm": 4.803226470947266,
      "learning_rate": 7.586206896551724e-05,
      "loss": 0.2908,
      "step": 368
    },
    {
      "epoch": 12.758620689655173,
      "grad_norm": 14.855594635009766,
      "learning_rate": 7.567049808429119e-05,
      "loss": 0.8779,
      "step": 370
    },
    {
      "epoch": 12.827586206896552,
      "grad_norm": 6.69237756729126,
      "learning_rate": 7.547892720306514e-05,
      "loss": 0.2755,
      "step": 372
    },
    {
      "epoch": 12.89655172413793,
      "grad_norm": 11.00119400024414,
      "learning_rate": 7.528735632183909e-05,
      "loss": 0.2853,
      "step": 374
    },
    {
      "epoch": 12.96551724137931,
      "grad_norm": 12.996737480163574,
      "learning_rate": 7.509578544061303e-05,
      "loss": 0.3835,
      "step": 376
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.5378787878787878,
      "eval_f1_macro": 0.5317693409365079,
      "eval_f1_micro": 0.5378787878787878,
      "eval_f1_weighted": 0.5440018882102533,
      "eval_loss": 1.8354477882385254,
      "eval_precision_macro": 0.6396235326975365,
      "eval_precision_micro": 0.5378787878787878,
      "eval_precision_weighted": 0.6577377477843236,
      "eval_recall_macro": 0.5264021164021164,
      "eval_recall_micro": 0.5378787878787878,
      "eval_recall_weighted": 0.5378787878787878,
      "eval_runtime": 2.966,
      "eval_samples_per_second": 44.504,
      "eval_steps_per_second": 5.732,
      "step": 377
    },
    {
      "epoch": 13.0,
      "step": 377,
      "total_flos": 1.6452764844550595e+18,
      "train_loss": 1.068754496403651,
      "train_runtime": 506.3845,
      "train_samples_per_second": 36.494,
      "train_steps_per_second": 2.291
    }
  ],
  "logging_steps": 2,
  "max_steps": 1160,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 40,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 8,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 8
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6452764844550595e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}