{
  "best_global_step": 5268,
  "best_metric": 0.9470420646891236,
  "best_model_checkpoint": "C:\\Users\\Shara\\projects\\models\\run_16-lr_2e-05-acc_1-wd_0.01-bs_8-ep_7\\checkpoint-5268",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 5268,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02847380410022779,
      "grad_norm": 4.8302321434021,
      "learning_rate": 1.992840872111943e-05,
      "loss": 0.9994,
      "step": 50
    },
    {
      "epoch": 0.05694760820045558,
      "grad_norm": 3.4978649616241455,
      "learning_rate": 1.9847054995118778e-05,
      "loss": 0.3939,
      "step": 100
    },
    {
      "epoch": 0.08542141230068337,
      "grad_norm": 8.353672981262207,
      "learning_rate": 1.9765701269118128e-05,
      "loss": 0.2882,
      "step": 150
    },
    {
      "epoch": 0.11389521640091116,
      "grad_norm": 9.822871208190918,
      "learning_rate": 1.9684347543117477e-05,
      "loss": 0.1728,
      "step": 200
    },
    {
      "epoch": 0.14236902050113895,
      "grad_norm": 3.1411221027374268,
      "learning_rate": 1.9602993817116827e-05,
      "loss": 0.1251,
      "step": 250
    },
    {
      "epoch": 0.17084282460136674,
      "grad_norm": 8.493424415588379,
      "learning_rate": 1.9521640091116173e-05,
      "loss": 0.1405,
      "step": 300
    },
    {
      "epoch": 0.19931662870159453,
      "grad_norm": 4.757007122039795,
      "learning_rate": 1.9440286365115523e-05,
      "loss": 0.1431,
      "step": 350
    },
    {
      "epoch": 0.22779043280182232,
      "grad_norm": 4.339049816131592,
      "learning_rate": 1.9358932639114873e-05,
      "loss": 0.0912,
      "step": 400
    },
    {
      "epoch": 0.25626423690205014,
      "grad_norm": 14.540772438049316,
      "learning_rate": 1.9277578913114222e-05,
      "loss": 0.1048,
      "step": 450
    },
    {
      "epoch": 0.2847380410022779,
      "grad_norm": 10.503073692321777,
      "learning_rate": 1.9196225187113572e-05,
      "loss": 0.1224,
      "step": 500
    },
    {
      "epoch": 0.3132118451025057,
      "grad_norm": 2.738131284713745,
      "learning_rate": 1.911487146111292e-05,
      "loss": 0.1025,
      "step": 550
    },
    {
      "epoch": 0.3416856492027335,
      "grad_norm": 6.681102752685547,
      "learning_rate": 1.903351773511227e-05,
      "loss": 0.0869,
      "step": 600
    },
    {
      "epoch": 0.3701594533029613,
      "grad_norm": 1.4330339431762695,
      "learning_rate": 1.895216400911162e-05,
      "loss": 0.052,
      "step": 650
    },
    {
      "epoch": 0.39863325740318906,
      "grad_norm": 2.581470012664795,
      "learning_rate": 1.8870810283110967e-05,
      "loss": 0.0808,
      "step": 700
    },
    {
      "epoch": 0.4271070615034169,
      "grad_norm": 5.825100898742676,
      "learning_rate": 1.8789456557110317e-05,
      "loss": 0.0716,
      "step": 750
    },
    {
      "epoch": 0.45558086560364464,
      "grad_norm": 1.74166738986969,
      "learning_rate": 1.8708102831109666e-05,
      "loss": 0.0806,
      "step": 800
    },
    {
      "epoch": 0.48405466970387245,
      "grad_norm": 7.3097405433654785,
      "learning_rate": 1.8626749105109016e-05,
      "loss": 0.0666,
      "step": 850
    },
    {
      "epoch": 0.5125284738041003,
      "grad_norm": 2.220766067504883,
      "learning_rate": 1.8545395379108362e-05,
      "loss": 0.0768,
      "step": 900
    },
    {
      "epoch": 0.541002277904328,
      "grad_norm": 4.0566511154174805,
      "learning_rate": 1.8464041653107715e-05,
      "loss": 0.0707,
      "step": 950
    },
    {
      "epoch": 0.5694760820045558,
      "grad_norm": 0.2833240330219269,
      "learning_rate": 1.8382687927107065e-05,
      "loss": 0.0858,
      "step": 1000
    },
    {
      "epoch": 0.5979498861047836,
      "grad_norm": 21.131481170654297,
      "learning_rate": 1.8301334201106415e-05,
      "loss": 0.0595,
      "step": 1050
    },
    {
      "epoch": 0.6264236902050114,
      "grad_norm": 27.655433654785156,
      "learning_rate": 1.821998047510576e-05,
      "loss": 0.0466,
      "step": 1100
    },
    {
      "epoch": 0.6548974943052391,
      "grad_norm": 3.4721717834472656,
      "learning_rate": 1.813862674910511e-05,
      "loss": 0.0776,
      "step": 1150
    },
    {
      "epoch": 0.683371298405467,
      "grad_norm": 2.4811441898345947,
      "learning_rate": 1.805727302310446e-05,
      "loss": 0.0647,
      "step": 1200
    },
    {
      "epoch": 0.7118451025056948,
      "grad_norm": 6.169066429138184,
      "learning_rate": 1.797591929710381e-05,
      "loss": 0.0724,
      "step": 1250
    },
    {
      "epoch": 0.7403189066059226,
      "grad_norm": 8.984748840332031,
      "learning_rate": 1.7894565571103156e-05,
      "loss": 0.0838,
      "step": 1300
    },
    {
      "epoch": 0.7687927107061503,
      "grad_norm": 5.944505214691162,
      "learning_rate": 1.7813211845102506e-05,
      "loss": 0.0683,
      "step": 1350
    },
    {
      "epoch": 0.7972665148063781,
      "grad_norm": 0.28812381625175476,
      "learning_rate": 1.7731858119101856e-05,
      "loss": 0.0614,
      "step": 1400
    },
    {
      "epoch": 0.8257403189066059,
      "grad_norm": 6.176011085510254,
      "learning_rate": 1.7650504393101205e-05,
      "loss": 0.0615,
      "step": 1450
    },
    {
      "epoch": 0.8542141230068337,
      "grad_norm": 2.5244405269622803,
      "learning_rate": 1.7569150667100555e-05,
      "loss": 0.0714,
      "step": 1500
    },
    {
      "epoch": 0.8826879271070615,
      "grad_norm": 3.3508074283599854,
      "learning_rate": 1.7487796941099904e-05,
      "loss": 0.0563,
      "step": 1550
    },
    {
      "epoch": 0.9111617312072893,
      "grad_norm": 9.980842590332031,
      "learning_rate": 1.7406443215099254e-05,
      "loss": 0.0647,
      "step": 1600
    },
    {
      "epoch": 0.9396355353075171,
      "grad_norm": 3.6959774494171143,
      "learning_rate": 1.7325089489098604e-05,
      "loss": 0.0682,
      "step": 1650
    },
    {
      "epoch": 0.9681093394077449,
      "grad_norm": 0.626620888710022,
      "learning_rate": 1.724373576309795e-05,
      "loss": 0.0499,
      "step": 1700
    },
    {
      "epoch": 0.9965831435079726,
      "grad_norm": 7.145672798156738,
      "learning_rate": 1.71623820370973e-05,
      "loss": 0.0569,
      "step": 1750
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.9242246437552389,
      "eval_loss": 0.05600914731621742,
      "eval_precision": 0.9206746826987308,
      "eval_recall": 0.927802086839448,
      "eval_runtime": 3.7538,
      "eval_samples_per_second": 865.798,
      "eval_steps_per_second": 108.425,
      "step": 1756
    },
    {
      "epoch": 1.0250569476082005,
      "grad_norm": 4.280463695526123,
      "learning_rate": 1.708102831109665e-05,
      "loss": 0.0673,
      "step": 1800
    },
    {
      "epoch": 1.0535307517084282,
      "grad_norm": 0.06692535430192947,
      "learning_rate": 1.6999674585096e-05,
      "loss": 0.0403,
      "step": 1850
    },
    {
      "epoch": 1.082004555808656,
      "grad_norm": 0.03789375349879265,
      "learning_rate": 1.691832085909535e-05,
      "loss": 0.0496,
      "step": 1900
    },
    {
      "epoch": 1.1104783599088839,
      "grad_norm": 3.698348045349121,
      "learning_rate": 1.6836967133094698e-05,
      "loss": 0.0381,
      "step": 1950
    },
    {
      "epoch": 1.1389521640091116,
      "grad_norm": 2.753032684326172,
      "learning_rate": 1.6755613407094048e-05,
      "loss": 0.0432,
      "step": 2000
    },
    {
      "epoch": 1.1674259681093395,
      "grad_norm": 0.06336130946874619,
      "learning_rate": 1.6674259681093398e-05,
      "loss": 0.0482,
      "step": 2050
    },
    {
      "epoch": 1.1958997722095672,
      "grad_norm": 3.9503254890441895,
      "learning_rate": 1.6592905955092744e-05,
      "loss": 0.0436,
      "step": 2100
    },
    {
      "epoch": 1.224373576309795,
      "grad_norm": 0.08679741621017456,
      "learning_rate": 1.6511552229092093e-05,
      "loss": 0.0346,
      "step": 2150
    },
    {
      "epoch": 1.2528473804100229,
      "grad_norm": 2.1995127201080322,
      "learning_rate": 1.6430198503091443e-05,
      "loss": 0.0312,
      "step": 2200
    },
    {
      "epoch": 1.2813211845102506,
      "grad_norm": 5.7709808349609375,
      "learning_rate": 1.634884477709079e-05,
      "loss": 0.032,
      "step": 2250
    },
    {
      "epoch": 1.3097949886104785,
      "grad_norm": 0.2031829059123993,
      "learning_rate": 1.626749105109014e-05,
      "loss": 0.053,
      "step": 2300
    },
    {
      "epoch": 1.3382687927107062,
      "grad_norm": 4.292157173156738,
      "learning_rate": 1.6186137325089492e-05,
      "loss": 0.0413,
      "step": 2350
    },
    {
      "epoch": 1.366742596810934,
      "grad_norm": 0.07821401953697205,
      "learning_rate": 1.6104783599088842e-05,
      "loss": 0.0304,
      "step": 2400
    },
    {
      "epoch": 1.3952164009111616,
      "grad_norm": 0.5930206179618835,
      "learning_rate": 1.6023429873088188e-05,
      "loss": 0.0525,
      "step": 2450
    },
    {
      "epoch": 1.4236902050113895,
      "grad_norm": 1.6114712953567505,
      "learning_rate": 1.5942076147087538e-05,
      "loss": 0.0391,
      "step": 2500
    },
    {
      "epoch": 1.4521640091116172,
      "grad_norm": 0.28632065653800964,
      "learning_rate": 1.5860722421086887e-05,
      "loss": 0.0491,
      "step": 2550
    },
    {
      "epoch": 1.4806378132118452,
      "grad_norm": 1.0017669200897217,
      "learning_rate": 1.5779368695086237e-05,
      "loss": 0.0395,
      "step": 2600
    },
    {
      "epoch": 1.5091116173120729,
      "grad_norm": 0.03409272059798241,
      "learning_rate": 1.5698014969085583e-05,
      "loss": 0.0399,
      "step": 2650
    },
    {
      "epoch": 1.5375854214123006,
      "grad_norm": 3.5108702182769775,
      "learning_rate": 1.5616661243084933e-05,
      "loss": 0.0424,
      "step": 2700
    },
    {
      "epoch": 1.5660592255125285,
      "grad_norm": 3.5875349044799805,
      "learning_rate": 1.5535307517084283e-05,
      "loss": 0.0497,
      "step": 2750
    },
    {
      "epoch": 1.5945330296127562,
      "grad_norm": 0.10498251020908356,
      "learning_rate": 1.5453953791083632e-05,
      "loss": 0.0461,
      "step": 2800
    },
    {
      "epoch": 1.6230068337129842,
      "grad_norm": 7.618963718414307,
      "learning_rate": 1.5374227139602996e-05,
      "loss": 0.0394,
      "step": 2850
    },
    {
      "epoch": 1.6514806378132119,
      "grad_norm": 3.3920793533325195,
      "learning_rate": 1.5292873413602346e-05,
      "loss": 0.0339,
      "step": 2900
    },
    {
      "epoch": 1.6799544419134396,
      "grad_norm": 0.04736129939556122,
      "learning_rate": 1.5211519687601692e-05,
      "loss": 0.0358,
      "step": 2950
    },
    {
      "epoch": 1.7084282460136673,
      "grad_norm": 0.17463508248329163,
      "learning_rate": 1.5130165961601042e-05,
      "loss": 0.034,
      "step": 3000
    },
    {
      "epoch": 1.7369020501138952,
      "grad_norm": 0.058148205280303955,
      "learning_rate": 1.5048812235600392e-05,
      "loss": 0.0317,
      "step": 3050
    },
    {
      "epoch": 1.7653758542141231,
      "grad_norm": 3.5262815952301025,
      "learning_rate": 1.4967458509599741e-05,
      "loss": 0.0477,
      "step": 3100
    },
    {
      "epoch": 1.7938496583143508,
      "grad_norm": 2.971937894821167,
      "learning_rate": 1.488610478359909e-05,
      "loss": 0.0364,
      "step": 3150
    },
    {
      "epoch": 1.8223234624145785,
      "grad_norm": 0.05181724950671196,
      "learning_rate": 1.4804751057598439e-05,
      "loss": 0.0394,
      "step": 3200
    },
    {
      "epoch": 1.8507972665148062,
      "grad_norm": 0.2712370455265045,
      "learning_rate": 1.4723397331597789e-05,
      "loss": 0.0456,
      "step": 3250
    },
    {
      "epoch": 1.8792710706150342,
      "grad_norm": 1.608622431755066,
      "learning_rate": 1.4642043605597138e-05,
      "loss": 0.05,
      "step": 3300
    },
    {
      "epoch": 1.907744874715262,
      "grad_norm": 5.2423529624938965,
      "learning_rate": 1.4560689879596486e-05,
      "loss": 0.0371,
      "step": 3350
    },
    {
      "epoch": 1.9362186788154898,
      "grad_norm": 0.04786211624741554,
      "learning_rate": 1.4479336153595836e-05,
      "loss": 0.0329,
      "step": 3400
    },
    {
      "epoch": 1.9646924829157175,
      "grad_norm": 0.5264931917190552,
      "learning_rate": 1.4397982427595185e-05,
      "loss": 0.0379,
      "step": 3450
    },
    {
      "epoch": 1.9931662870159452,
      "grad_norm": 0.236006498336792,
      "learning_rate": 1.4316628701594535e-05,
      "loss": 0.0253,
      "step": 3500
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.9406438631790744,
      "eval_loss": 0.05223705992102623,
      "eval_precision": 0.9371867691279653,
      "eval_recall": 0.9441265567149109,
      "eval_runtime": 3.7109,
      "eval_samples_per_second": 875.791,
      "eval_steps_per_second": 109.676,
      "step": 3512
    },
    {
      "epoch": 2.021640091116173,
      "grad_norm": 4.225963115692139,
      "learning_rate": 1.4235274975593883e-05,
      "loss": 0.0373,
      "step": 3550
    },
    {
      "epoch": 2.050113895216401,
      "grad_norm": 0.15388111770153046,
      "learning_rate": 1.4153921249593233e-05,
      "loss": 0.0258,
      "step": 3600
    },
    {
      "epoch": 2.078587699316629,
      "grad_norm": 6.3911895751953125,
      "learning_rate": 1.4072567523592582e-05,
      "loss": 0.0217,
      "step": 3650
    },
    {
      "epoch": 2.1070615034168565,
      "grad_norm": 0.03075530007481575,
      "learning_rate": 1.3991213797591932e-05,
      "loss": 0.019,
      "step": 3700
    },
    {
      "epoch": 2.135535307517084,
      "grad_norm": 0.16612432897090912,
      "learning_rate": 1.3909860071591278e-05,
      "loss": 0.0175,
      "step": 3750
    },
    {
      "epoch": 2.164009111617312,
      "grad_norm": 0.14543022215366364,
      "learning_rate": 1.382850634559063e-05,
      "loss": 0.0289,
      "step": 3800
    },
    {
      "epoch": 2.19248291571754,
      "grad_norm": 2.9880359172821045,
      "learning_rate": 1.374715261958998e-05,
      "loss": 0.0208,
      "step": 3850
    },
    {
      "epoch": 2.2209567198177678,
      "grad_norm": 9.878133773803711,
      "learning_rate": 1.3665798893589329e-05,
      "loss": 0.021,
      "step": 3900
    },
    {
      "epoch": 2.2494305239179955,
      "grad_norm": 9.684176445007324,
      "learning_rate": 1.3584445167588675e-05,
      "loss": 0.0267,
      "step": 3950
    },
    {
      "epoch": 2.277904328018223,
      "grad_norm": 33.15859603881836,
      "learning_rate": 1.3503091441588025e-05,
      "loss": 0.0295,
      "step": 4000
    },
    {
      "epoch": 2.306378132118451,
      "grad_norm": 2.559544086456299,
      "learning_rate": 1.3421737715587374e-05,
      "loss": 0.0292,
      "step": 4050
    },
    {
      "epoch": 2.334851936218679,
      "grad_norm": 0.07091552764177322,
      "learning_rate": 1.3340383989586724e-05,
      "loss": 0.0262,
      "step": 4100
    },
    {
      "epoch": 2.3633257403189067,
      "grad_norm": 1.8119585514068604,
      "learning_rate": 1.3259030263586072e-05,
      "loss": 0.03,
      "step": 4150
    },
    {
      "epoch": 2.3917995444191344,
      "grad_norm": 0.1476636379957199,
      "learning_rate": 1.3177676537585422e-05,
      "loss": 0.0196,
      "step": 4200
    },
    {
      "epoch": 2.420273348519362,
      "grad_norm": 0.04482650011777878,
      "learning_rate": 1.3096322811584771e-05,
      "loss": 0.0263,
      "step": 4250
    },
    {
      "epoch": 2.44874715261959,
      "grad_norm": 0.09201560169458389,
      "learning_rate": 1.3014969085584121e-05,
      "loss": 0.0172,
      "step": 4300
    },
    {
      "epoch": 2.477220956719818,
      "grad_norm": 0.02215876244008541,
      "learning_rate": 1.2933615359583469e-05,
      "loss": 0.0149,
      "step": 4350
    },
    {
      "epoch": 2.5056947608200457,
      "grad_norm": 0.6993932127952576,
      "learning_rate": 1.2852261633582819e-05,
      "loss": 0.0331,
      "step": 4400
    },
    {
      "epoch": 2.5341685649202734,
      "grad_norm": 0.030453965067863464,
      "learning_rate": 1.2770907907582168e-05,
      "loss": 0.0307,
      "step": 4450
    },
    {
      "epoch": 2.562642369020501,
      "grad_norm": 0.22211593389511108,
      "learning_rate": 1.2689554181581518e-05,
      "loss": 0.0183,
      "step": 4500
    },
    {
      "epoch": 2.591116173120729,
      "grad_norm": 1.2842738628387451,
      "learning_rate": 1.2608200455580866e-05,
      "loss": 0.0226,
      "step": 4550
    },
    {
      "epoch": 2.619589977220957,
      "grad_norm": 3.9048423767089844,
      "learning_rate": 1.2526846729580216e-05,
      "loss": 0.0239,
      "step": 4600
    },
    {
      "epoch": 2.6480637813211843,
      "grad_norm": 0.9887784719467163,
      "learning_rate": 1.2445493003579565e-05,
      "loss": 0.0271,
      "step": 4650
    },
    {
      "epoch": 2.6765375854214124,
      "grad_norm": 4.759728908538818,
      "learning_rate": 1.2364139277578915e-05,
      "loss": 0.0201,
      "step": 4700
    },
    {
      "epoch": 2.70501138952164,
      "grad_norm": 0.2671191096305847,
      "learning_rate": 1.2282785551578263e-05,
      "loss": 0.0212,
      "step": 4750
    },
    {
      "epoch": 2.733485193621868,
      "grad_norm": 0.036626849323511124,
      "learning_rate": 1.2201431825577612e-05,
      "loss": 0.0155,
      "step": 4800
    },
    {
      "epoch": 2.7619589977220955,
      "grad_norm": 6.877408027648926,
      "learning_rate": 1.2120078099576962e-05,
      "loss": 0.0266,
      "step": 4850
    },
    {
      "epoch": 2.7904328018223232,
      "grad_norm": 4.725896835327148,
      "learning_rate": 1.2038724373576312e-05,
      "loss": 0.0163,
      "step": 4900
    },
    {
      "epoch": 2.8189066059225514,
      "grad_norm": 0.11965059489011765,
      "learning_rate": 1.195737064757566e-05,
      "loss": 0.0246,
      "step": 4950
    },
    {
      "epoch": 2.847380410022779,
      "grad_norm": 0.6634079813957214,
      "learning_rate": 1.187601692157501e-05,
      "loss": 0.0304,
      "step": 5000
    },
    {
      "epoch": 2.875854214123007,
      "grad_norm": 3.952694892883301,
      "learning_rate": 1.1794663195574359e-05,
      "loss": 0.0183,
      "step": 5050
    },
    {
      "epoch": 2.9043280182232345,
      "grad_norm": 19.788942337036133,
      "learning_rate": 1.1713309469573709e-05,
      "loss": 0.0193,
      "step": 5100
    },
    {
      "epoch": 2.932801822323462,
      "grad_norm": 4.989261627197266,
      "learning_rate": 1.1631955743573055e-05,
      "loss": 0.023,
      "step": 5150
    },
    {
      "epoch": 2.9612756264236904,
      "grad_norm": 9.020853996276855,
      "learning_rate": 1.1550602017572406e-05,
      "loss": 0.0231,
      "step": 5200
    },
    {
      "epoch": 2.989749430523918,
      "grad_norm": 0.9151140451431274,
      "learning_rate": 1.1469248291571756e-05,
      "loss": 0.0314,
      "step": 5250
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.9470420646891236,
      "eval_loss": 0.04870199039578438,
      "eval_precision": 0.943090787716956,
      "eval_recall": 0.9510265903736116,
      "eval_runtime": 3.7494,
      "eval_samples_per_second": 866.805,
      "eval_steps_per_second": 108.551,
      "step": 5268
    }
  ],
  "logging_steps": 50,
  "max_steps": 12292,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 1034617415983686.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}