yexter's picture
End of training
30c4792 verified
{
"best_metric": 0.7619883040935672,
"best_model_checkpoint": "videomae-base-Badminton_strokes-finetuned-stroke-classification\\checkpoint-1225",
"epoch": 4.196734693877551,
"eval_steps": 500,
"global_step": 1225,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00816326530612245,
"grad_norm": 5.244400501251221,
"learning_rate": 4.0650406504065046e-06,
"loss": 2.4952,
"step": 10
},
{
"epoch": 0.0163265306122449,
"grad_norm": 6.468714714050293,
"learning_rate": 8.130081300813009e-06,
"loss": 2.3526,
"step": 20
},
{
"epoch": 0.024489795918367346,
"grad_norm": 4.259028434753418,
"learning_rate": 1.2195121951219513e-05,
"loss": 2.1971,
"step": 30
},
{
"epoch": 0.0326530612244898,
"grad_norm": 4.142731666564941,
"learning_rate": 1.6260162601626018e-05,
"loss": 2.1394,
"step": 40
},
{
"epoch": 0.04081632653061224,
"grad_norm": 4.3925089836120605,
"learning_rate": 2.032520325203252e-05,
"loss": 2.1323,
"step": 50
},
{
"epoch": 0.04897959183673469,
"grad_norm": 4.224646091461182,
"learning_rate": 2.4390243902439026e-05,
"loss": 2.0748,
"step": 60
},
{
"epoch": 0.05714285714285714,
"grad_norm": 5.832901954650879,
"learning_rate": 2.8455284552845528e-05,
"loss": 2.0847,
"step": 70
},
{
"epoch": 0.0653061224489796,
"grad_norm": 4.4013671875,
"learning_rate": 3.2520325203252037e-05,
"loss": 2.0667,
"step": 80
},
{
"epoch": 0.07346938775510205,
"grad_norm": 4.626805305480957,
"learning_rate": 3.6585365853658535e-05,
"loss": 1.9221,
"step": 90
},
{
"epoch": 0.08163265306122448,
"grad_norm": 7.152433395385742,
"learning_rate": 4.065040650406504e-05,
"loss": 1.8691,
"step": 100
},
{
"epoch": 0.08979591836734693,
"grad_norm": 4.98500394821167,
"learning_rate": 4.4715447154471546e-05,
"loss": 1.7676,
"step": 110
},
{
"epoch": 0.09795918367346938,
"grad_norm": 12.184016227722168,
"learning_rate": 4.878048780487805e-05,
"loss": 1.7009,
"step": 120
},
{
"epoch": 0.10612244897959183,
"grad_norm": 5.2860894203186035,
"learning_rate": 4.9682395644283126e-05,
"loss": 1.5885,
"step": 130
},
{
"epoch": 0.11428571428571428,
"grad_norm": 7.862862586975098,
"learning_rate": 4.922867513611615e-05,
"loss": 1.5489,
"step": 140
},
{
"epoch": 0.12244897959183673,
"grad_norm": 5.597222328186035,
"learning_rate": 4.877495462794919e-05,
"loss": 1.5169,
"step": 150
},
{
"epoch": 0.1306122448979592,
"grad_norm": 5.168361186981201,
"learning_rate": 4.8321234119782216e-05,
"loss": 1.429,
"step": 160
},
{
"epoch": 0.13877551020408163,
"grad_norm": 4.200538158416748,
"learning_rate": 4.786751361161525e-05,
"loss": 1.4782,
"step": 170
},
{
"epoch": 0.1469387755102041,
"grad_norm": 6.290266513824463,
"learning_rate": 4.741379310344828e-05,
"loss": 1.4558,
"step": 180
},
{
"epoch": 0.15510204081632653,
"grad_norm": 5.306058406829834,
"learning_rate": 4.6960072595281306e-05,
"loss": 1.3866,
"step": 190
},
{
"epoch": 0.16326530612244897,
"grad_norm": 4.555312156677246,
"learning_rate": 4.650635208711434e-05,
"loss": 1.3229,
"step": 200
},
{
"epoch": 0.17142857142857143,
"grad_norm": 6.407901763916016,
"learning_rate": 4.605263157894737e-05,
"loss": 1.3421,
"step": 210
},
{
"epoch": 0.17959183673469387,
"grad_norm": 5.324537754058838,
"learning_rate": 4.55989110707804e-05,
"loss": 1.2384,
"step": 220
},
{
"epoch": 0.18775510204081633,
"grad_norm": 5.129929542541504,
"learning_rate": 4.5145190562613434e-05,
"loss": 1.2475,
"step": 230
},
{
"epoch": 0.19591836734693877,
"grad_norm": 7.351629257202148,
"learning_rate": 4.469147005444646e-05,
"loss": 1.2138,
"step": 240
},
{
"epoch": 0.20081632653061224,
"eval_accuracy": 0.512280701754386,
"eval_loss": 1.4943147897720337,
"eval_runtime": 765.4217,
"eval_samples_per_second": 2.234,
"eval_steps_per_second": 0.094,
"step": 246
},
{
"epoch": 1.003265306122449,
"grad_norm": 3.978257179260254,
"learning_rate": 4.423774954627949e-05,
"loss": 1.1764,
"step": 250
},
{
"epoch": 1.0114285714285713,
"grad_norm": 4.829442977905273,
"learning_rate": 4.3784029038112524e-05,
"loss": 1.0118,
"step": 260
},
{
"epoch": 1.019591836734694,
"grad_norm": 5.639930725097656,
"learning_rate": 4.3330308529945556e-05,
"loss": 1.2025,
"step": 270
},
{
"epoch": 1.0277551020408162,
"grad_norm": 4.805947780609131,
"learning_rate": 4.287658802177859e-05,
"loss": 1.0476,
"step": 280
},
{
"epoch": 1.0359183673469388,
"grad_norm": 4.968803882598877,
"learning_rate": 4.242286751361162e-05,
"loss": 1.0606,
"step": 290
},
{
"epoch": 1.0440816326530613,
"grad_norm": 7.550710201263428,
"learning_rate": 4.1969147005444646e-05,
"loss": 1.1504,
"step": 300
},
{
"epoch": 1.0522448979591836,
"grad_norm": 9.26010799407959,
"learning_rate": 4.151542649727768e-05,
"loss": 1.1346,
"step": 310
},
{
"epoch": 1.0604081632653062,
"grad_norm": 12.30020523071289,
"learning_rate": 4.106170598911071e-05,
"loss": 0.9971,
"step": 320
},
{
"epoch": 1.0685714285714285,
"grad_norm": 9.262853622436523,
"learning_rate": 4.0607985480943736e-05,
"loss": 1.0591,
"step": 330
},
{
"epoch": 1.076734693877551,
"grad_norm": 9.531743049621582,
"learning_rate": 4.0154264972776775e-05,
"loss": 0.9533,
"step": 340
},
{
"epoch": 1.0848979591836734,
"grad_norm": 11.760782241821289,
"learning_rate": 3.97005444646098e-05,
"loss": 1.0115,
"step": 350
},
{
"epoch": 1.093061224489796,
"grad_norm": 8.676046371459961,
"learning_rate": 3.924682395644283e-05,
"loss": 1.0866,
"step": 360
},
{
"epoch": 1.1012244897959185,
"grad_norm": 6.559369087219238,
"learning_rate": 3.8793103448275865e-05,
"loss": 0.9825,
"step": 370
},
{
"epoch": 1.1093877551020408,
"grad_norm": 8.812031745910645,
"learning_rate": 3.833938294010889e-05,
"loss": 1.121,
"step": 380
},
{
"epoch": 1.1175510204081633,
"grad_norm": 5.920422077178955,
"learning_rate": 3.788566243194193e-05,
"loss": 1.0367,
"step": 390
},
{
"epoch": 1.1257142857142857,
"grad_norm": 6.096667289733887,
"learning_rate": 3.7431941923774954e-05,
"loss": 0.9247,
"step": 400
},
{
"epoch": 1.1338775510204082,
"grad_norm": 8.243738174438477,
"learning_rate": 3.6978221415607986e-05,
"loss": 0.8421,
"step": 410
},
{
"epoch": 1.1420408163265305,
"grad_norm": 13.763681411743164,
"learning_rate": 3.652450090744102e-05,
"loss": 0.7692,
"step": 420
},
{
"epoch": 1.150204081632653,
"grad_norm": 13.45505428314209,
"learning_rate": 3.607078039927405e-05,
"loss": 0.9248,
"step": 430
},
{
"epoch": 1.1583673469387756,
"grad_norm": 6.331974506378174,
"learning_rate": 3.561705989110708e-05,
"loss": 1.011,
"step": 440
},
{
"epoch": 1.166530612244898,
"grad_norm": 7.715512275695801,
"learning_rate": 3.516333938294011e-05,
"loss": 0.8162,
"step": 450
},
{
"epoch": 1.1746938775510205,
"grad_norm": 6.705671787261963,
"learning_rate": 3.470961887477314e-05,
"loss": 0.8677,
"step": 460
},
{
"epoch": 1.1828571428571428,
"grad_norm": 11.03935718536377,
"learning_rate": 3.425589836660617e-05,
"loss": 0.9038,
"step": 470
},
{
"epoch": 1.1910204081632654,
"grad_norm": 5.334926605224609,
"learning_rate": 3.3802177858439205e-05,
"loss": 0.8735,
"step": 480
},
{
"epoch": 1.1991836734693877,
"grad_norm": 9.334040641784668,
"learning_rate": 3.334845735027223e-05,
"loss": 0.8947,
"step": 490
},
{
"epoch": 1.2008163265306122,
"eval_accuracy": 0.6771929824561403,
"eval_loss": 1.2374348640441895,
"eval_runtime": 753.5154,
"eval_samples_per_second": 2.269,
"eval_steps_per_second": 0.096,
"step": 492
},
{
"epoch": 2.006530612244898,
"grad_norm": 7.620924472808838,
"learning_rate": 3.289473684210527e-05,
"loss": 0.7791,
"step": 500
},
{
"epoch": 2.0146938775510206,
"grad_norm": 5.360889911651611,
"learning_rate": 3.2441016333938295e-05,
"loss": 0.6921,
"step": 510
},
{
"epoch": 2.0228571428571427,
"grad_norm": 32.47731018066406,
"learning_rate": 3.198729582577133e-05,
"loss": 0.5907,
"step": 520
},
{
"epoch": 2.0310204081632652,
"grad_norm": 6.6628289222717285,
"learning_rate": 3.153357531760436e-05,
"loss": 0.7626,
"step": 530
},
{
"epoch": 2.039183673469388,
"grad_norm": 6.246597766876221,
"learning_rate": 3.1079854809437384e-05,
"loss": 0.731,
"step": 540
},
{
"epoch": 2.0473469387755103,
"grad_norm": 5.773654937744141,
"learning_rate": 3.062613430127042e-05,
"loss": 0.7799,
"step": 550
},
{
"epoch": 2.0555102040816324,
"grad_norm": 8.651352882385254,
"learning_rate": 3.017241379310345e-05,
"loss": 0.7187,
"step": 560
},
{
"epoch": 2.063673469387755,
"grad_norm": 8.399853706359863,
"learning_rate": 2.9718693284936484e-05,
"loss": 0.7076,
"step": 570
},
{
"epoch": 2.0718367346938775,
"grad_norm": 10.44221305847168,
"learning_rate": 2.9264972776769513e-05,
"loss": 0.7123,
"step": 580
},
{
"epoch": 2.08,
"grad_norm": 8.12469482421875,
"learning_rate": 2.881125226860254e-05,
"loss": 0.6117,
"step": 590
},
{
"epoch": 2.0881632653061226,
"grad_norm": 12.644967079162598,
"learning_rate": 2.8357531760435574e-05,
"loss": 0.7665,
"step": 600
},
{
"epoch": 2.0963265306122447,
"grad_norm": 8.58361530303955,
"learning_rate": 2.7903811252268603e-05,
"loss": 0.5814,
"step": 610
},
{
"epoch": 2.1044897959183673,
"grad_norm": 8.686047554016113,
"learning_rate": 2.7450090744101635e-05,
"loss": 0.879,
"step": 620
},
{
"epoch": 2.11265306122449,
"grad_norm": 6.443877696990967,
"learning_rate": 2.6996370235934664e-05,
"loss": 0.661,
"step": 630
},
{
"epoch": 2.1208163265306124,
"grad_norm": 18.404951095581055,
"learning_rate": 2.65426497277677e-05,
"loss": 0.7436,
"step": 640
},
{
"epoch": 2.1289795918367345,
"grad_norm": 7.879423141479492,
"learning_rate": 2.6088929219600728e-05,
"loss": 0.4849,
"step": 650
},
{
"epoch": 2.137142857142857,
"grad_norm": 6.912235736846924,
"learning_rate": 2.5635208711433757e-05,
"loss": 0.6246,
"step": 660
},
{
"epoch": 2.1453061224489796,
"grad_norm": 10.059391975402832,
"learning_rate": 2.518148820326679e-05,
"loss": 0.6314,
"step": 670
},
{
"epoch": 2.153469387755102,
"grad_norm": 8.129505157470703,
"learning_rate": 2.472776769509982e-05,
"loss": 0.7015,
"step": 680
},
{
"epoch": 2.1616326530612247,
"grad_norm": 9.07080364227295,
"learning_rate": 2.427404718693285e-05,
"loss": 0.6986,
"step": 690
},
{
"epoch": 2.1697959183673468,
"grad_norm": 8.254867553710938,
"learning_rate": 2.3820326678765882e-05,
"loss": 0.684,
"step": 700
},
{
"epoch": 2.1779591836734693,
"grad_norm": 8.124053955078125,
"learning_rate": 2.336660617059891e-05,
"loss": 0.5424,
"step": 710
},
{
"epoch": 2.186122448979592,
"grad_norm": 5.182572364807129,
"learning_rate": 2.2912885662431943e-05,
"loss": 0.6461,
"step": 720
},
{
"epoch": 2.1942857142857144,
"grad_norm": 10.561123847961426,
"learning_rate": 2.2459165154264975e-05,
"loss": 0.5704,
"step": 730
},
{
"epoch": 2.2008163265306124,
"eval_accuracy": 0.6871345029239766,
"eval_loss": 1.2350349426269531,
"eval_runtime": 759.3483,
"eval_samples_per_second": 2.252,
"eval_steps_per_second": 0.095,
"step": 738
},
{
"epoch": 3.0016326530612245,
"grad_norm": 9.009034156799316,
"learning_rate": 2.2005444646098004e-05,
"loss": 0.7604,
"step": 740
},
{
"epoch": 3.009795918367347,
"grad_norm": 8.081964492797852,
"learning_rate": 2.1551724137931033e-05,
"loss": 0.5601,
"step": 750
},
{
"epoch": 3.0179591836734696,
"grad_norm": 5.625163555145264,
"learning_rate": 2.1098003629764065e-05,
"loss": 0.5588,
"step": 760
},
{
"epoch": 3.0261224489795917,
"grad_norm": 18.619417190551758,
"learning_rate": 2.0644283121597097e-05,
"loss": 0.5016,
"step": 770
},
{
"epoch": 3.0342857142857143,
"grad_norm": 4.800343036651611,
"learning_rate": 2.019056261343013e-05,
"loss": 0.5072,
"step": 780
},
{
"epoch": 3.042448979591837,
"grad_norm": 7.775487422943115,
"learning_rate": 1.9736842105263158e-05,
"loss": 0.6298,
"step": 790
},
{
"epoch": 3.0506122448979593,
"grad_norm": 7.29972505569458,
"learning_rate": 1.928312159709619e-05,
"loss": 0.564,
"step": 800
},
{
"epoch": 3.0587755102040814,
"grad_norm": 4.456672668457031,
"learning_rate": 1.8829401088929222e-05,
"loss": 0.5806,
"step": 810
},
{
"epoch": 3.066938775510204,
"grad_norm": 8.3887300491333,
"learning_rate": 1.837568058076225e-05,
"loss": 0.4955,
"step": 820
},
{
"epoch": 3.0751020408163265,
"grad_norm": 7.33532190322876,
"learning_rate": 1.792196007259528e-05,
"loss": 0.5767,
"step": 830
},
{
"epoch": 3.083265306122449,
"grad_norm": 15.156110763549805,
"learning_rate": 1.7468239564428312e-05,
"loss": 0.4801,
"step": 840
},
{
"epoch": 3.0914285714285716,
"grad_norm": 7.68253231048584,
"learning_rate": 1.7014519056261344e-05,
"loss": 0.5923,
"step": 850
},
{
"epoch": 3.0995918367346937,
"grad_norm": 11.319337844848633,
"learning_rate": 1.6560798548094377e-05,
"loss": 0.4914,
"step": 860
},
{
"epoch": 3.1077551020408163,
"grad_norm": 13.500849723815918,
"learning_rate": 1.6107078039927405e-05,
"loss": 0.5273,
"step": 870
},
{
"epoch": 3.115918367346939,
"grad_norm": 8.655684471130371,
"learning_rate": 1.5653357531760438e-05,
"loss": 0.5035,
"step": 880
},
{
"epoch": 3.1240816326530614,
"grad_norm": 7.286762237548828,
"learning_rate": 1.5199637023593466e-05,
"loss": 0.5134,
"step": 890
},
{
"epoch": 3.1322448979591835,
"grad_norm": 4.1852641105651855,
"learning_rate": 1.4745916515426497e-05,
"loss": 0.4418,
"step": 900
},
{
"epoch": 3.140408163265306,
"grad_norm": 15.295413970947266,
"learning_rate": 1.4292196007259529e-05,
"loss": 0.563,
"step": 910
},
{
"epoch": 3.1485714285714286,
"grad_norm": 14.049315452575684,
"learning_rate": 1.383847549909256e-05,
"loss": 0.5778,
"step": 920
},
{
"epoch": 3.156734693877551,
"grad_norm": 5.061805725097656,
"learning_rate": 1.3384754990925592e-05,
"loss": 0.5193,
"step": 930
},
{
"epoch": 3.1648979591836737,
"grad_norm": 3.378352403640747,
"learning_rate": 1.2931034482758622e-05,
"loss": 0.4423,
"step": 940
},
{
"epoch": 3.1730612244897958,
"grad_norm": 12.00133991241455,
"learning_rate": 1.2477313974591653e-05,
"loss": 0.3907,
"step": 950
},
{
"epoch": 3.1812244897959183,
"grad_norm": 5.577662944793701,
"learning_rate": 1.2023593466424683e-05,
"loss": 0.5331,
"step": 960
},
{
"epoch": 3.189387755102041,
"grad_norm": 10.945758819580078,
"learning_rate": 1.1569872958257714e-05,
"loss": 0.5347,
"step": 970
},
{
"epoch": 3.1975510204081634,
"grad_norm": 8.133883476257324,
"learning_rate": 1.1116152450090744e-05,
"loss": 0.5847,
"step": 980
},
{
"epoch": 3.2008163265306124,
"eval_accuracy": 0.7397660818713451,
"eval_loss": 1.1260349750518799,
"eval_runtime": 756.6531,
"eval_samples_per_second": 2.26,
"eval_steps_per_second": 0.095,
"step": 984
},
{
"epoch": 4.0048979591836735,
"grad_norm": 10.616361618041992,
"learning_rate": 1.0662431941923776e-05,
"loss": 0.511,
"step": 990
},
{
"epoch": 4.013061224489796,
"grad_norm": 17.12271499633789,
"learning_rate": 1.0208711433756807e-05,
"loss": 0.5201,
"step": 1000
},
{
"epoch": 4.021224489795919,
"grad_norm": 7.298173427581787,
"learning_rate": 9.754990925589837e-06,
"loss": 0.4441,
"step": 1010
},
{
"epoch": 4.029387755102041,
"grad_norm": 11.826898574829102,
"learning_rate": 9.301270417422868e-06,
"loss": 0.3371,
"step": 1020
},
{
"epoch": 4.037551020408163,
"grad_norm": 8.964632987976074,
"learning_rate": 8.8475499092559e-06,
"loss": 0.3911,
"step": 1030
},
{
"epoch": 4.045714285714285,
"grad_norm": 6.960618495941162,
"learning_rate": 8.393829401088929e-06,
"loss": 0.4594,
"step": 1040
},
{
"epoch": 4.053877551020408,
"grad_norm": 4.924427509307861,
"learning_rate": 7.94010889292196e-06,
"loss": 0.5469,
"step": 1050
},
{
"epoch": 4.0620408163265305,
"grad_norm": 4.707489967346191,
"learning_rate": 7.486388384754991e-06,
"loss": 0.3609,
"step": 1060
},
{
"epoch": 4.070204081632653,
"grad_norm": 10.195731163024902,
"learning_rate": 7.0326678765880225e-06,
"loss": 0.4136,
"step": 1070
},
{
"epoch": 4.078367346938776,
"grad_norm": 7.881709098815918,
"learning_rate": 6.578947368421053e-06,
"loss": 0.3424,
"step": 1080
},
{
"epoch": 4.086530612244898,
"grad_norm": 12.66398811340332,
"learning_rate": 6.1252268602540835e-06,
"loss": 0.3489,
"step": 1090
},
{
"epoch": 4.094693877551021,
"grad_norm": 8.235493659973145,
"learning_rate": 5.671506352087114e-06,
"loss": 0.3887,
"step": 1100
},
{
"epoch": 4.102857142857143,
"grad_norm": 10.095196723937988,
"learning_rate": 5.217785843920145e-06,
"loss": 0.4551,
"step": 1110
},
{
"epoch": 4.111020408163265,
"grad_norm": 5.204263687133789,
"learning_rate": 4.764065335753176e-06,
"loss": 0.3242,
"step": 1120
},
{
"epoch": 4.119183673469387,
"grad_norm": 6.840783596038818,
"learning_rate": 4.310344827586207e-06,
"loss": 0.4693,
"step": 1130
},
{
"epoch": 4.12734693877551,
"grad_norm": 9.000433921813965,
"learning_rate": 3.8566243194192376e-06,
"loss": 0.4683,
"step": 1140
},
{
"epoch": 4.1355102040816325,
"grad_norm": 10.167008399963379,
"learning_rate": 3.4029038112522685e-06,
"loss": 0.4362,
"step": 1150
},
{
"epoch": 4.143673469387755,
"grad_norm": 4.929052352905273,
"learning_rate": 2.9491833030852998e-06,
"loss": 0.3308,
"step": 1160
},
{
"epoch": 4.151836734693878,
"grad_norm": 9.885331153869629,
"learning_rate": 2.4954627949183303e-06,
"loss": 0.3296,
"step": 1170
},
{
"epoch": 4.16,
"grad_norm": 8.994477272033691,
"learning_rate": 2.041742286751361e-06,
"loss": 0.3484,
"step": 1180
},
{
"epoch": 4.168163265306123,
"grad_norm": 10.2811918258667,
"learning_rate": 1.588021778584392e-06,
"loss": 0.4507,
"step": 1190
},
{
"epoch": 4.176326530612245,
"grad_norm": 4.625392913818359,
"learning_rate": 1.134301270417423e-06,
"loss": 0.3656,
"step": 1200
},
{
"epoch": 4.184489795918367,
"grad_norm": 4.338553428649902,
"learning_rate": 6.805807622504538e-07,
"loss": 0.4143,
"step": 1210
},
{
"epoch": 4.192653061224489,
"grad_norm": 7.271970748901367,
"learning_rate": 2.268602540834846e-07,
"loss": 0.4343,
"step": 1220
},
{
"epoch": 4.196734693877551,
"eval_accuracy": 0.7619883040935672,
"eval_loss": 1.0475685596466064,
"eval_runtime": 742.0109,
"eval_samples_per_second": 2.305,
"eval_steps_per_second": 0.097,
"step": 1225
},
{
"epoch": 4.196734693877551,
"step": 1225,
"total_flos": 3.6552500125909254e+19,
"train_loss": 0.8672810672253979,
"train_runtime": 16546.435,
"train_samples_per_second": 1.777,
"train_steps_per_second": 0.074
},
{
"epoch": 4.196734693877551,
"eval_accuracy": 0.8441558441558441,
"eval_loss": 0.5236970782279968,
"eval_runtime": 645.1565,
"eval_samples_per_second": 2.268,
"eval_steps_per_second": 0.095,
"step": 1225
},
{
"epoch": 4.196734693877551,
"eval_accuracy": 0.8441558441558441,
"eval_loss": 0.5236971378326416,
"eval_runtime": 632.6262,
"eval_samples_per_second": 2.313,
"eval_steps_per_second": 0.096,
"step": 1225
}
],
"logging_steps": 10,
"max_steps": 1225,
"num_input_tokens_seen": 0,
"num_train_epochs": 9223372036854775807,
"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": 3.6552500125909254e+19,
"train_batch_size": 24,
"trial_name": null,
"trial_params": null
}