{
  "best_metric": 1.0,
  "best_model_checkpoint": "bridalMakeupClassifier_binary/checkpoint-414",
  "epoch": 20.0,
  "eval_steps": 500,
  "global_step": 460,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 7.482993125915527,
      "learning_rate": 5.4347826086956525e-06,
      "loss": 0.7413,
      "step": 5
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 5.045105934143066,
      "learning_rate": 1.0869565217391305e-05,
      "loss": 0.6285,
      "step": 10
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 3.057001829147339,
      "learning_rate": 1.630434782608696e-05,
      "loss": 0.4579,
      "step": 15
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 2.394951581954956,
      "learning_rate": 2.173913043478261e-05,
      "loss": 0.2966,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9661538461538461,
      "eval_f1": 0.9378531073446328,
      "eval_loss": 0.12898202240467072,
      "eval_precision": 0.9431818181818182,
      "eval_recall": 0.9325842696629213,
      "eval_runtime": 0.6116,
      "eval_samples_per_second": 531.418,
      "eval_steps_per_second": 17.986,
      "step": 23
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 2.818490982055664,
      "learning_rate": 2.7173913043478262e-05,
      "loss": 0.1788,
      "step": 25
    },
    {
      "epoch": 1.3043478260869565,
      "grad_norm": 2.19661545753479,
      "learning_rate": 3.260869565217392e-05,
      "loss": 0.1157,
      "step": 30
    },
    {
      "epoch": 1.5217391304347827,
      "grad_norm": 1.980846643447876,
      "learning_rate": 3.804347826086957e-05,
      "loss": 0.077,
      "step": 35
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 1.7503933906555176,
      "learning_rate": 4.347826086956522e-05,
      "loss": 0.076,
      "step": 40
    },
    {
      "epoch": 1.9565217391304348,
      "grad_norm": 4.313005447387695,
      "learning_rate": 4.891304347826087e-05,
      "loss": 0.1233,
      "step": 45
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9876923076923076,
      "eval_f1": 0.9777777777777779,
      "eval_loss": 0.04074087738990784,
      "eval_precision": 0.967032967032967,
      "eval_recall": 0.9887640449438202,
      "eval_runtime": 0.614,
      "eval_samples_per_second": 529.309,
      "eval_steps_per_second": 17.915,
      "step": 46
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 2.5787644386291504,
      "learning_rate": 4.9516908212560386e-05,
      "loss": 0.0834,
      "step": 50
    },
    {
      "epoch": 2.391304347826087,
      "grad_norm": 2.1645395755767822,
      "learning_rate": 4.891304347826087e-05,
      "loss": 0.0538,
      "step": 55
    },
    {
      "epoch": 2.608695652173913,
      "grad_norm": 2.0289194583892822,
      "learning_rate": 4.830917874396135e-05,
      "loss": 0.0749,
      "step": 60
    },
    {
      "epoch": 2.8260869565217392,
      "grad_norm": 1.7418752908706665,
      "learning_rate": 4.770531400966184e-05,
      "loss": 0.0469,
      "step": 65
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9815384615384616,
      "eval_f1": 0.967391304347826,
      "eval_loss": 0.059426549822092056,
      "eval_precision": 0.9368421052631579,
      "eval_recall": 1.0,
      "eval_runtime": 0.6222,
      "eval_samples_per_second": 522.372,
      "eval_steps_per_second": 17.68,
      "step": 69
    },
    {
      "epoch": 3.0434782608695654,
      "grad_norm": 4.78839635848999,
      "learning_rate": 4.710144927536232e-05,
      "loss": 0.0729,
      "step": 70
    },
    {
      "epoch": 3.260869565217391,
      "grad_norm": 2.100724697113037,
      "learning_rate": 4.64975845410628e-05,
      "loss": 0.0588,
      "step": 75
    },
    {
      "epoch": 3.4782608695652173,
      "grad_norm": 2.4715771675109863,
      "learning_rate": 4.589371980676328e-05,
      "loss": 0.0537,
      "step": 80
    },
    {
      "epoch": 3.6956521739130435,
      "grad_norm": 2.045220375061035,
      "learning_rate": 4.528985507246377e-05,
      "loss": 0.0451,
      "step": 85
    },
    {
      "epoch": 3.9130434782608696,
      "grad_norm": 2.7747068405151367,
      "learning_rate": 4.4685990338164255e-05,
      "loss": 0.0394,
      "step": 90
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9876923076923076,
      "eval_f1": 0.9777777777777779,
      "eval_loss": 0.055703382939100266,
      "eval_precision": 0.967032967032967,
      "eval_recall": 0.9887640449438202,
      "eval_runtime": 0.6278,
      "eval_samples_per_second": 517.661,
      "eval_steps_per_second": 17.521,
      "step": 92
    },
    {
      "epoch": 4.130434782608695,
      "grad_norm": 1.9641977548599243,
      "learning_rate": 4.408212560386474e-05,
      "loss": 0.0728,
      "step": 95
    },
    {
      "epoch": 4.3478260869565215,
      "grad_norm": 3.0312821865081787,
      "learning_rate": 4.347826086956522e-05,
      "loss": 0.0611,
      "step": 100
    },
    {
      "epoch": 4.565217391304348,
      "grad_norm": 2.8319077491760254,
      "learning_rate": 4.2874396135265707e-05,
      "loss": 0.0467,
      "step": 105
    },
    {
      "epoch": 4.782608695652174,
      "grad_norm": 0.7883936762809753,
      "learning_rate": 4.2270531400966186e-05,
      "loss": 0.0433,
      "step": 110
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.4693968296051025,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.0909,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9907692307692307,
      "eval_f1": 0.9834254143646408,
      "eval_loss": 0.04008618742227554,
      "eval_precision": 0.967391304347826,
      "eval_recall": 1.0,
      "eval_runtime": 0.6227,
      "eval_samples_per_second": 521.945,
      "eval_steps_per_second": 17.666,
      "step": 115
    },
    {
      "epoch": 5.217391304347826,
      "grad_norm": 2.560603618621826,
      "learning_rate": 4.106280193236715e-05,
      "loss": 0.0683,
      "step": 120
    },
    {
      "epoch": 5.434782608695652,
      "grad_norm": 1.258954644203186,
      "learning_rate": 4.045893719806764e-05,
      "loss": 0.045,
      "step": 125
    },
    {
      "epoch": 5.6521739130434785,
      "grad_norm": 1.6040618419647217,
      "learning_rate": 3.985507246376812e-05,
      "loss": 0.0334,
      "step": 130
    },
    {
      "epoch": 5.869565217391305,
      "grad_norm": 2.980376720428467,
      "learning_rate": 3.92512077294686e-05,
      "loss": 0.05,
      "step": 135
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9876923076923076,
      "eval_f1": 0.9777777777777779,
      "eval_loss": 0.025248104706406593,
      "eval_precision": 0.967032967032967,
      "eval_recall": 0.9887640449438202,
      "eval_runtime": 0.6255,
      "eval_samples_per_second": 519.608,
      "eval_steps_per_second": 17.587,
      "step": 138
    },
    {
      "epoch": 6.086956521739131,
      "grad_norm": 1.547420859336853,
      "learning_rate": 3.864734299516908e-05,
      "loss": 0.0215,
      "step": 140
    },
    {
      "epoch": 6.304347826086957,
      "grad_norm": 1.0269052982330322,
      "learning_rate": 3.804347826086957e-05,
      "loss": 0.0513,
      "step": 145
    },
    {
      "epoch": 6.521739130434782,
      "grad_norm": 1.4050897359848022,
      "learning_rate": 3.743961352657005e-05,
      "loss": 0.0324,
      "step": 150
    },
    {
      "epoch": 6.739130434782608,
      "grad_norm": 2.9087464809417725,
      "learning_rate": 3.6835748792270534e-05,
      "loss": 0.0246,
      "step": 155
    },
    {
      "epoch": 6.956521739130435,
      "grad_norm": 2.945462942123413,
      "learning_rate": 3.6231884057971014e-05,
      "loss": 0.0451,
      "step": 160
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9876923076923076,
      "eval_f1": 0.9772727272727273,
      "eval_loss": 0.02794536016881466,
      "eval_precision": 0.9885057471264368,
      "eval_recall": 0.9662921348314607,
      "eval_runtime": 0.638,
      "eval_samples_per_second": 509.374,
      "eval_steps_per_second": 17.24,
      "step": 161
    },
    {
      "epoch": 7.173913043478261,
      "grad_norm": 0.28256598114967346,
      "learning_rate": 3.56280193236715e-05,
      "loss": 0.0499,
      "step": 165
    },
    {
      "epoch": 7.391304347826087,
      "grad_norm": 2.3740286827087402,
      "learning_rate": 3.502415458937198e-05,
      "loss": 0.0358,
      "step": 170
    },
    {
      "epoch": 7.608695652173913,
      "grad_norm": 1.025823950767517,
      "learning_rate": 3.4420289855072465e-05,
      "loss": 0.0306,
      "step": 175
    },
    {
      "epoch": 7.826086956521739,
      "grad_norm": 0.7179997563362122,
      "learning_rate": 3.381642512077295e-05,
      "loss": 0.0231,
      "step": 180
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9938461538461538,
      "eval_f1": 0.9888888888888888,
      "eval_loss": 0.02782590501010418,
      "eval_precision": 0.978021978021978,
      "eval_recall": 1.0,
      "eval_runtime": 0.6231,
      "eval_samples_per_second": 521.596,
      "eval_steps_per_second": 17.654,
      "step": 184
    },
    {
      "epoch": 8.043478260869565,
      "grad_norm": 0.5594707131385803,
      "learning_rate": 3.321256038647343e-05,
      "loss": 0.024,
      "step": 185
    },
    {
      "epoch": 8.26086956521739,
      "grad_norm": 2.8453502655029297,
      "learning_rate": 3.260869565217392e-05,
      "loss": 0.03,
      "step": 190
    },
    {
      "epoch": 8.478260869565217,
      "grad_norm": 1.5159822702407837,
      "learning_rate": 3.2004830917874396e-05,
      "loss": 0.0203,
      "step": 195
    },
    {
      "epoch": 8.695652173913043,
      "grad_norm": 2.250065326690674,
      "learning_rate": 3.140096618357488e-05,
      "loss": 0.0282,
      "step": 200
    },
    {
      "epoch": 8.91304347826087,
      "grad_norm": 3.3784470558166504,
      "learning_rate": 3.079710144927536e-05,
      "loss": 0.0404,
      "step": 205
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9876923076923076,
      "eval_f1": 0.9775280898876404,
      "eval_loss": 0.025601999834179878,
      "eval_precision": 0.9775280898876404,
      "eval_recall": 0.9775280898876404,
      "eval_runtime": 0.6288,
      "eval_samples_per_second": 516.888,
      "eval_steps_per_second": 17.495,
      "step": 207
    },
    {
      "epoch": 9.130434782608695,
      "grad_norm": 4.156078815460205,
      "learning_rate": 3.0193236714975848e-05,
      "loss": 0.0135,
      "step": 210
    },
    {
      "epoch": 9.347826086956522,
      "grad_norm": 1.2355906963348389,
      "learning_rate": 2.9589371980676327e-05,
      "loss": 0.0377,
      "step": 215
    },
    {
      "epoch": 9.565217391304348,
      "grad_norm": 4.165219783782959,
      "learning_rate": 2.8985507246376814e-05,
      "loss": 0.0354,
      "step": 220
    },
    {
      "epoch": 9.782608695652174,
      "grad_norm": 1.0178390741348267,
      "learning_rate": 2.8381642512077293e-05,
      "loss": 0.0331,
      "step": 225
    },
    {
      "epoch": 10.0,
      "grad_norm": 4.175224304199219,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.0297,
      "step": 230
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9907692307692307,
      "eval_f1": 0.9832402234636872,
      "eval_loss": 0.02601032890379429,
      "eval_precision": 0.9777777777777777,
      "eval_recall": 0.9887640449438202,
      "eval_runtime": 0.6221,
      "eval_samples_per_second": 522.441,
      "eval_steps_per_second": 17.683,
      "step": 230
    },
    {
      "epoch": 10.217391304347826,
      "grad_norm": 0.14615581929683685,
      "learning_rate": 2.7173913043478262e-05,
      "loss": 0.009,
      "step": 235
    },
    {
      "epoch": 10.434782608695652,
      "grad_norm": 5.359668731689453,
      "learning_rate": 2.6570048309178748e-05,
      "loss": 0.0176,
      "step": 240
    },
    {
      "epoch": 10.652173913043478,
      "grad_norm": 0.387389212846756,
      "learning_rate": 2.5966183574879227e-05,
      "loss": 0.0251,
      "step": 245
    },
    {
      "epoch": 10.869565217391305,
      "grad_norm": 1.7574446201324463,
      "learning_rate": 2.5362318840579714e-05,
      "loss": 0.0327,
      "step": 250
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.9938461538461538,
      "eval_f1": 0.9888888888888888,
      "eval_loss": 0.02298262156546116,
      "eval_precision": 0.978021978021978,
      "eval_recall": 1.0,
      "eval_runtime": 0.63,
      "eval_samples_per_second": 515.887,
      "eval_steps_per_second": 17.461,
      "step": 253
    },
    {
      "epoch": 11.08695652173913,
      "grad_norm": 1.124037504196167,
      "learning_rate": 2.4758454106280193e-05,
      "loss": 0.0397,
      "step": 255
    },
    {
      "epoch": 11.304347826086957,
      "grad_norm": 2.474566698074341,
      "learning_rate": 2.4154589371980676e-05,
      "loss": 0.0427,
      "step": 260
    },
    {
      "epoch": 11.521739130434783,
      "grad_norm": 1.6105717420578003,
      "learning_rate": 2.355072463768116e-05,
      "loss": 0.0157,
      "step": 265
    },
    {
      "epoch": 11.73913043478261,
      "grad_norm": 0.6210281252861023,
      "learning_rate": 2.294685990338164e-05,
      "loss": 0.0297,
      "step": 270
    },
    {
      "epoch": 11.956521739130435,
      "grad_norm": 2.6540639400482178,
      "learning_rate": 2.2342995169082127e-05,
      "loss": 0.0221,
      "step": 275
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.9969230769230769,
      "eval_f1": 0.9944134078212291,
      "eval_loss": 0.01398832444101572,
      "eval_precision": 0.9888888888888889,
      "eval_recall": 1.0,
      "eval_runtime": 0.6237,
      "eval_samples_per_second": 521.045,
      "eval_steps_per_second": 17.635,
      "step": 276
    },
    {
      "epoch": 12.173913043478262,
      "grad_norm": 2.6183152198791504,
      "learning_rate": 2.173913043478261e-05,
      "loss": 0.0267,
      "step": 280
    },
    {
      "epoch": 12.391304347826088,
      "grad_norm": 0.8627565503120422,
      "learning_rate": 2.1135265700483093e-05,
      "loss": 0.0195,
      "step": 285
    },
    {
      "epoch": 12.608695652173914,
      "grad_norm": 0.576085090637207,
      "learning_rate": 2.0531400966183576e-05,
      "loss": 0.0322,
      "step": 290
    },
    {
      "epoch": 12.826086956521738,
      "grad_norm": 3.6716318130493164,
      "learning_rate": 1.992753623188406e-05,
      "loss": 0.0294,
      "step": 295
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.9969230769230769,
      "eval_f1": 0.9944134078212291,
      "eval_loss": 0.01057437900453806,
      "eval_precision": 0.9888888888888889,
      "eval_recall": 1.0,
      "eval_runtime": 0.6324,
      "eval_samples_per_second": 513.948,
      "eval_steps_per_second": 17.395,
      "step": 299
    },
    {
      "epoch": 13.043478260869565,
      "grad_norm": 0.19212637841701508,
      "learning_rate": 1.932367149758454e-05,
      "loss": 0.0298,
      "step": 300
    },
    {
      "epoch": 13.26086956521739,
      "grad_norm": 1.9307483434677124,
      "learning_rate": 1.8719806763285024e-05,
      "loss": 0.0231,
      "step": 305
    },
    {
      "epoch": 13.478260869565217,
      "grad_norm": 2.444979667663574,
      "learning_rate": 1.8115942028985507e-05,
      "loss": 0.0201,
      "step": 310
    },
    {
      "epoch": 13.695652173913043,
      "grad_norm": 2.9044065475463867,
      "learning_rate": 1.751207729468599e-05,
      "loss": 0.0243,
      "step": 315
    },
    {
      "epoch": 13.91304347826087,
      "grad_norm": 1.5113251209259033,
      "learning_rate": 1.6908212560386476e-05,
      "loss": 0.0292,
      "step": 320
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.9969230769230769,
      "eval_f1": 0.9944134078212291,
      "eval_loss": 0.013215974904596806,
      "eval_precision": 0.9888888888888889,
      "eval_recall": 1.0,
      "eval_runtime": 0.6382,
      "eval_samples_per_second": 509.263,
      "eval_steps_per_second": 17.237,
      "step": 322
    },
    {
      "epoch": 14.130434782608695,
      "grad_norm": 0.16032224893569946,
      "learning_rate": 1.630434782608696e-05,
      "loss": 0.0056,
      "step": 325
    },
    {
      "epoch": 14.347826086956522,
      "grad_norm": 1.7882447242736816,
      "learning_rate": 1.570048309178744e-05,
      "loss": 0.0203,
      "step": 330
    },
    {
      "epoch": 14.565217391304348,
      "grad_norm": 1.206709861755371,
      "learning_rate": 1.5096618357487924e-05,
      "loss": 0.0205,
      "step": 335
    },
    {
      "epoch": 14.782608695652174,
      "grad_norm": 2.7993412017822266,
      "learning_rate": 1.4492753623188407e-05,
      "loss": 0.0227,
      "step": 340
    },
    {
      "epoch": 15.0,
      "grad_norm": 1.1518446207046509,
      "learning_rate": 1.388888888888889e-05,
      "loss": 0.0064,
      "step": 345
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.9907692307692307,
      "eval_f1": 0.9834254143646408,
      "eval_loss": 0.02308599278330803,
      "eval_precision": 0.967391304347826,
      "eval_recall": 1.0,
      "eval_runtime": 0.6311,
      "eval_samples_per_second": 514.958,
      "eval_steps_per_second": 17.429,
      "step": 345
    },
    {
      "epoch": 15.217391304347826,
      "grad_norm": 1.4991214275360107,
      "learning_rate": 1.3285024154589374e-05,
      "loss": 0.0152,
      "step": 350
    },
    {
      "epoch": 15.434782608695652,
      "grad_norm": 1.1912800073623657,
      "learning_rate": 1.2681159420289857e-05,
      "loss": 0.0066,
      "step": 355
    },
    {
      "epoch": 15.652173913043478,
      "grad_norm": 0.4402332603931427,
      "learning_rate": 1.2077294685990338e-05,
      "loss": 0.0051,
      "step": 360
    },
    {
      "epoch": 15.869565217391305,
      "grad_norm": 0.8945227861404419,
      "learning_rate": 1.147342995169082e-05,
      "loss": 0.02,
      "step": 365
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.9969230769230769,
      "eval_f1": 0.9944134078212291,
      "eval_loss": 0.008727076463401318,
      "eval_precision": 0.9888888888888889,
      "eval_recall": 1.0,
      "eval_runtime": 0.6362,
      "eval_samples_per_second": 510.858,
      "eval_steps_per_second": 17.291,
      "step": 368
    },
    {
      "epoch": 16.08695652173913,
      "grad_norm": 1.353935718536377,
      "learning_rate": 1.0869565217391305e-05,
      "loss": 0.0422,
      "step": 370
    },
    {
      "epoch": 16.304347826086957,
      "grad_norm": 2.2760603427886963,
      "learning_rate": 1.0265700483091788e-05,
      "loss": 0.0314,
      "step": 375
    },
    {
      "epoch": 16.52173913043478,
      "grad_norm": 1.7415324449539185,
      "learning_rate": 9.66183574879227e-06,
      "loss": 0.0105,
      "step": 380
    },
    {
      "epoch": 16.73913043478261,
      "grad_norm": 0.31125152111053467,
      "learning_rate": 9.057971014492753e-06,
      "loss": 0.0249,
      "step": 385
    },
    {
      "epoch": 16.956521739130434,
      "grad_norm": 3.789961814880371,
      "learning_rate": 8.454106280193238e-06,
      "loss": 0.0356,
      "step": 390
    },
    {
      "epoch": 17.0,
      "eval_accuracy": 0.9969230769230769,
      "eval_f1": 0.9944134078212291,
      "eval_loss": 0.011419730260968208,
      "eval_precision": 0.9888888888888889,
      "eval_recall": 1.0,
      "eval_runtime": 0.6273,
      "eval_samples_per_second": 518.129,
      "eval_steps_per_second": 17.537,
      "step": 391
    },
    {
      "epoch": 17.17391304347826,
      "grad_norm": 0.2875424027442932,
      "learning_rate": 7.85024154589372e-06,
      "loss": 0.0102,
      "step": 395
    },
    {
      "epoch": 17.391304347826086,
      "grad_norm": 1.2512189149856567,
      "learning_rate": 7.246376811594203e-06,
      "loss": 0.0114,
      "step": 400
    },
    {
      "epoch": 17.608695652173914,
      "grad_norm": 2.634803295135498,
      "learning_rate": 6.642512077294687e-06,
      "loss": 0.0274,
      "step": 405
    },
    {
      "epoch": 17.82608695652174,
      "grad_norm": 1.524092674255371,
      "learning_rate": 6.038647342995169e-06,
      "loss": 0.0232,
      "step": 410
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00724475271999836,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.6289,
      "eval_samples_per_second": 516.744,
      "eval_steps_per_second": 17.49,
      "step": 414
    },
    {
      "epoch": 18.043478260869566,
      "grad_norm": 0.8228383660316467,
      "learning_rate": 5.4347826086956525e-06,
      "loss": 0.0187,
      "step": 415
    },
    {
      "epoch": 18.26086956521739,
      "grad_norm": 0.26993948221206665,
      "learning_rate": 4.830917874396135e-06,
      "loss": 0.0176,
      "step": 420
    },
    {
      "epoch": 18.47826086956522,
      "grad_norm": 1.4451013803482056,
      "learning_rate": 4.227053140096619e-06,
      "loss": 0.017,
      "step": 425
    },
    {
      "epoch": 18.695652173913043,
      "grad_norm": 1.0776654481887817,
      "learning_rate": 3.6231884057971017e-06,
      "loss": 0.0225,
      "step": 430
    },
    {
      "epoch": 18.91304347826087,
      "grad_norm": 0.6803100109100342,
      "learning_rate": 3.0193236714975845e-06,
      "loss": 0.0351,
      "step": 435
    },
    {
      "epoch": 19.0,
      "eval_accuracy": 0.9969230769230769,
      "eval_f1": 0.9944134078212291,
      "eval_loss": 0.008730148896574974,
      "eval_precision": 0.9888888888888889,
      "eval_recall": 1.0,
      "eval_runtime": 0.629,
      "eval_samples_per_second": 516.656,
      "eval_steps_per_second": 17.487,
      "step": 437
    },
    {
      "epoch": 19.130434782608695,
      "grad_norm": 3.2962541580200195,
      "learning_rate": 2.4154589371980677e-06,
      "loss": 0.0138,
      "step": 440
    },
    {
      "epoch": 19.347826086956523,
      "grad_norm": 2.5289676189422607,
      "learning_rate": 1.8115942028985508e-06,
      "loss": 0.0192,
      "step": 445
    },
    {
      "epoch": 19.565217391304348,
      "grad_norm": 0.09774911403656006,
      "learning_rate": 1.2077294685990338e-06,
      "loss": 0.0136,
      "step": 450
    },
    {
      "epoch": 19.782608695652176,
      "grad_norm": 0.9112738370895386,
      "learning_rate": 6.038647342995169e-07,
      "loss": 0.0213,
      "step": 455
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.6033933162689209,
      "learning_rate": 0.0,
      "loss": 0.0155,
      "step": 460
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.9969230769230769,
      "eval_f1": 0.9944134078212291,
      "eval_loss": 0.007528003770858049,
      "eval_precision": 0.9888888888888889,
      "eval_recall": 1.0,
      "eval_runtime": 0.6414,
      "eval_samples_per_second": 506.707,
      "eval_steps_per_second": 17.15,
      "step": 460
    },
    {
      "epoch": 20.0,
      "step": 460,
      "total_flos": 1.4530811161131418e+18,
      "train_loss": 0.0580909106111073,
      "train_runtime": 291.8902,
      "train_samples_per_second": 200.281,
      "train_steps_per_second": 1.576
    }
  ],
  "logging_steps": 5,
  "max_steps": 460,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4530811161131418e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}