food101.txt

******* loading model args.model='vitsmart'
******* loading model args.model='vitsmart'
******* loading model args.model='vitsmart'
******* loading model args.model='vitsmart'
--> World Size = 4

--> Device_count = 4
--> running with these defaults train_config(seed=2022, verbose=True, total_steps_to_run=None, print_memory_summary=False, num_epochs=2, model_weights_bf16=False, use_mixed_precision=False, use_low_precision_gradient_policy=False, use_tf32=False, optimizer='AnyPrecision', ap_use_kahan_summation=False, sharding_strategy=<ShardingStrategy.FULL_SHARD: 1>, print_sharding_plan=False, run_profiler=False, profile_folder='fsdp/profile_tracing', log_every=1, num_workers_dataloader=2, batch_size_training=68, fsdp_activation_checkpointing=False, run_validation=True, memory_report=True, nccl_debug_handler=True, distributed_debug=True, use_non_recursive_wrapping=False, use_tp=False, image_size=224, use_synthetic_data=False, use_pokemon_dataset=False, use_beans_dataset=False, save_model_checkpoint=False, load_model_checkpoint=False, checkpoint_max_save_count=2, save_optimizer=False, load_optimizer=False, optimizer_checkpoint_file='Adam-vit--1.pt', checkpoint_model_filename='vit--1.pt')
clearing gpu cache for all ranks
--> running with torch dist debug set to detail
--> total memory per gpu (GB) = 22.0626
policy is None

--> Prepping vit_relpos_base_patch16_rpn_224 model ...

stats is ready....? _stats=defaultdict(<class 'list'>, {}), local_rank=0, rank=0
--> vit_relpos_base_patch16_rpn_224 built.
built model with 85.722869M params
--> Warning - bf16 support not available.  Using fp32
backward prefetch set to None
sharding set to ShardingStrategy.FULL_SHARD
--> Batch Size = 68
local rank 0 init time = 1.5327604980000018
memory stats reset, ready to track
Running with AnyPrecision Optimizer, momo=torch.float32, var = torch.float32, kahan summation =  False
Epoch: 1 starting...
step: 1: time taken for the last 1 steps is 6.224457420999997, loss is 4.556710243225098
step: 2: time taken for the last 1 steps is 0.25443180500001006, loss is 4.726100444793701
step: 3: time taken for the last 1 steps is 0.26126896999998905, loss is 4.740593910217285
step: 4: time taken for the last 1 steps is 0.25712853800000346, loss is 4.724956512451172
step: 5: time taken for the last 1 steps is 0.26038229899999976, loss is 4.608603477478027
step: 6: time taken for the last 1 steps is 0.2569102459999897, loss is 4.639562606811523
step: 7: time taken for the last 1 steps is 0.2609058249999947, loss is 4.620149612426758
step: 8: time taken for the last 1 steps is 0.2560444850000039, loss is 4.645939826965332
step: 9: time taken for the last 1 steps is 0.2588406399999883, loss is 4.646860599517822
step: 10: time taken for the last 1 steps is 0.2588266599999969, loss is 4.529321193695068
step: 11: time taken for the last 1 steps is 0.2554669780000012, loss is 4.625144958496094
step: 12: time taken for the last 1 steps is 0.25876852000000383, loss is 4.520711898803711
step: 13: time taken for the last 1 steps is 0.25901369199999635, loss is 4.676128387451172
step: 14: time taken for the last 1 steps is 0.255653690999992, loss is 4.4814324378967285
step: 15: time taken for the last 1 steps is 0.2611768480000052, loss is 4.547496795654297
step: 16: time taken for the last 1 steps is 0.2544821259999992, loss is 4.657937526702881
step: 17: time taken for the last 1 steps is 0.2574680120000039, loss is 4.442592620849609
step: 18: time taken for the last 1 steps is 0.26373780000000124, loss is 4.521785736083984
step: 19: time taken for the last 1 steps is 0.2592381829999937, loss is 4.626273155212402
step: 20: time taken for the last 1 steps is 0.2570713380000029, loss is 4.532219409942627
step: 21: time taken for the last 1 steps is 0.25521710499999983, loss is 4.586917877197266
step: 22: time taken for the last 1 steps is 0.2537483569999921, loss is 4.631921291351318
step: 23: time taken for the last 1 steps is 0.25214174799999967, loss is 4.854366302490234
step: 24: time taken for the last 1 steps is 0.24851453299999093, loss is 4.5460991859436035
step: 25: time taken for the last 1 steps is 0.2523288790000038, loss is 4.5151166915893555
step: 26: time taken for the last 1 steps is 0.259327356, loss is 4.580170631408691
step: 27: time taken for the last 1 steps is 0.25792064799999537, loss is 4.560575485229492
step: 28: time taken for the last 1 steps is 0.25086665200001335, loss is 4.456768035888672
step: 29: time taken for the last 1 steps is 0.26047701900000675, loss is 4.499762535095215
step: 30: time taken for the last 1 steps is 0.25528731700001117, loss is 4.523378849029541
step: 31: time taken for the last 1 steps is 0.26271464800001354, loss is 4.533198833465576
step: 32: time taken for the last 1 steps is 0.25917369399999757, loss is 4.610552787780762
step: 33: time taken for the last 1 steps is 0.25706605700000296, loss is 4.555049896240234
step: 34: time taken for the last 1 steps is 0.26019912700002124, loss is 4.644559383392334
step: 35: time taken for the last 1 steps is 0.2515043689999743, loss is 4.4100236892700195
step: 36: time taken for the last 1 steps is 0.25164398100000085, loss is 4.489560604095459
step: 37: time taken for the last 1 steps is 0.2521807489999901, loss is 4.469703674316406
step: 38: time taken for the last 1 steps is 0.2548025700000096, loss is 4.491578102111816
step: 39: time taken for the last 1 steps is 0.26133294999999634, loss is 4.50607967376709
step: 40: time taken for the last 1 steps is 0.2578487179999911, loss is 4.486103057861328
step: 41: time taken for the last 1 steps is 0.26081843400001503, loss is 4.702195644378662
step: 42: time taken for the last 1 steps is 0.2574591220000002, loss is 4.504721641540527
step: 43: time taken for the last 1 steps is 0.2620693590000087, loss is 4.42141056060791
step: 44: time taken for the last 1 steps is 0.2550191830000017, loss is 4.46730899810791
step: 45: time taken for the last 1 steps is 0.25533965600001807, loss is 4.464085102081299
step: 46: time taken for the last 1 steps is 0.2582529330000227, loss is 4.499287128448486
step: 47: time taken for the last 1 steps is 0.26063145099999474, loss is 4.5415873527526855
step: 48: time taken for the last 1 steps is 0.25658790299999623, loss is 4.539662837982178
step: 49: time taken for the last 1 steps is 0.2536832860000118, loss is 4.5748209953308105
step: 50: time taken for the last 1 steps is 0.260121995999981, loss is 4.369707107543945
step: 51: time taken for the last 1 steps is 0.26197083800002474, loss is 4.47456693649292
step: 52: time taken for the last 1 steps is 0.2603090570000006, loss is 4.582790374755859
step: 53: time taken for the last 1 steps is 0.2510197630000164, loss is 4.347904682159424
step: 54: time taken for the last 1 steps is 0.2516130710000084, loss is 4.510412216186523
step: 55: time taken for the last 1 steps is 0.2569418369999994, loss is 4.485291004180908
step: 56: time taken for the last 1 steps is 0.26207493000001136, loss is 4.45244026184082
step: 57: time taken for the last 1 steps is 0.25972696099998416, loss is 4.43674373626709
step: 58: time taken for the last 1 steps is 0.2622236219999934, loss is 4.463484764099121
step: 59: time taken for the last 1 steps is 0.2598912809999945, loss is 4.4032464027404785
step: 60: time taken for the last 1 steps is 0.25398738499998785, loss is 4.397443771362305
step: 61: time taken for the last 1 steps is 0.2520642179999868, loss is 4.250542640686035
step: 62: time taken for the last 1 steps is 0.259571655000002, loss is 4.447912216186523
step: 63: time taken for the last 1 steps is 0.2555896060000009, loss is 4.437596797943115
step: 64: time taken for the last 1 steps is 0.26227825800000915, loss is 4.372616767883301
step: 65: time taken for the last 1 steps is 0.25532826200000613, loss is 4.282342910766602
step: 66: time taken for the last 1 steps is 0.2614504619999991, loss is 4.4875030517578125
step: 67: time taken for the last 1 steps is 0.26115508600000226, loss is 4.505937099456787
step: 68: time taken for the last 1 steps is 0.25712286699999254, loss is 4.456249237060547
step: 69: time taken for the last 1 steps is 0.2519989760000101, loss is 4.468084335327148
step: 70: time taken for the last 1 steps is 0.2551300880000156, loss is 4.32630729675293
step: 71: time taken for the last 1 steps is 0.253717139999992, loss is 4.329172611236572
step: 72: time taken for the last 1 steps is 0.2555635260000031, loss is 4.283868312835693
step: 73: time taken for the last 1 steps is 0.26223194700000363, loss is 4.537152290344238
step: 74: time taken for the last 1 steps is 0.26280980699999645, loss is 4.518974781036377
step: 75: time taken for the last 1 steps is 0.25795741299998554, loss is 4.479353427886963
step: 76: time taken for the last 1 steps is 0.2609946819999891, loss is 4.544875144958496
step: 77: time taken for the last 1 steps is 0.2483915960000047, loss is 4.347236633300781
step: 78: time taken for the last 1 steps is 0.2609416909999993, loss is 4.527989864349365
step: 79: time taken for the last 1 steps is 0.25855089499998485, loss is 4.4142255783081055
step: 80: time taken for the last 1 steps is 0.2526250989999994, loss is 4.46660852432251
step: 81: time taken for the last 1 steps is 0.25598162399998614, loss is 4.463648319244385
step: 82: time taken for the last 1 steps is 0.25559938700001794, loss is 4.502534866333008
step: 83: time taken for the last 1 steps is 0.25871039800000517, loss is 4.649286270141602
step: 84: time taken for the last 1 steps is 0.25609726700000124, loss is 4.508419036865234
step: 85: time taken for the last 1 steps is 0.25164947999999754, loss is 4.464930534362793
step: 86: time taken for the last 1 steps is 0.25470685999999887, loss is 4.450496196746826
step: 87: time taken for the last 1 steps is 0.2588861419999944, loss is 4.545038223266602
step: 88: time taken for the last 1 steps is 0.25199988700001086, loss is 4.434495449066162
step: 89: time taken for the last 1 steps is 0.26075993800000674, loss is 4.518768787384033
step: 90: time taken for the last 1 steps is 0.2590612739999756, loss is 4.492814540863037
step: 91: time taken for the last 1 steps is 0.2586902680000094, loss is 4.455684661865234
step: 92: time taken for the last 1 steps is 0.2565992460000075, loss is 4.374605178833008
step: 93: time taken for the last 1 steps is 0.2528125130000092, loss is 4.327826023101807
step: 94: time taken for the last 1 steps is 0.2583574709999823, loss is 4.3085408210754395
step: 95: time taken for the last 1 steps is 0.2593954710000048, loss is 4.34464168548584
step: 96: time taken for the last 1 steps is 0.252541817000008, loss is 4.4452714920043945
step: 97: time taken for the last 1 steps is 0.25419546899999546, loss is 4.565735340118408
step: 98: time taken for the last 1 steps is 0.2565571060000025, loss is 4.539857864379883
step: 99: time taken for the last 1 steps is 0.2563246910000032, loss is 4.644400119781494
step: 100: time taken for the last 1 steps is 0.2632913180000003, loss is 4.381629467010498
step: 101: time taken for the last 1 steps is 0.2628080879999857, loss is 4.4490156173706055
step: 102: time taken for the last 1 steps is 0.2571874879999996, loss is 4.361649036407471
step: 103: time taken for the last 1 steps is 0.2600162940000246, loss is 4.6384782791137695
step: 104: time taken for the last 1 steps is 0.2600821550000205, loss is 4.630778789520264
step: 105: time taken for the last 1 steps is 0.2540322469999978, loss is 4.514150619506836
step: 106: time taken for the last 1 steps is 0.25883444999999483, loss is 4.39536714553833
step: 107: time taken for the last 1 steps is 0.2584115820000079, loss is 4.485714435577393
step: 108: time taken for the last 1 steps is 0.26006182400001876, loss is 4.468821048736572
step: 109: time taken for the last 1 steps is 0.25974721899999054, loss is 4.567099094390869
step: 110: time taken for the last 1 steps is 0.25267529999999283, loss is 4.386360168457031
step: 111: time taken for the last 1 steps is 0.26327380699999026, loss is 4.325007915496826
step: 112: time taken for the last 1 steps is 0.26067661700000144, loss is 4.396040439605713
step: 113: time taken for the last 1 steps is 0.25966461699999854, loss is 4.383045196533203
step: 114: time taken for the last 1 steps is 0.2625774740000111, loss is 4.5528082847595215
step: 115: time taken for the last 1 steps is 0.2596532260000117, loss is 4.544152736663818
step: 116: time taken for the last 1 steps is 0.2446388630000058, loss is 4.470468997955322
step: 117: time taken for the last 1 steps is 0.25887863099998754, loss is 4.473755836486816
step: 118: time taken for the last 1 steps is 0.2514864469999907, loss is 4.466084003448486
step: 119: time taken for the last 1 steps is 0.2595187439999904, loss is 4.458154678344727
step: 120: time taken for the last 1 steps is 0.25970338700000184, loss is 4.572976589202881
step: 121: time taken for the last 1 steps is 0.2571176170000058, loss is 4.582334518432617
step: 122: time taken for the last 1 steps is 0.25083667399999854, loss is 4.496822357177734
step: 123: time taken for the last 1 steps is 0.24888235599999575, loss is 4.464864253997803
step: 124: time taken for the last 1 steps is 0.2501425800000163, loss is 4.56265926361084
step: 125: time taken for the last 1 steps is 0.2562360389999867, loss is 4.4036335945129395
step: 126: time taken for the last 1 steps is 0.25835999099999185, loss is 4.376188278198242
step: 127: time taken for the last 1 steps is 0.25613184799999544, loss is 4.47650671005249
step: 128: time taken for the last 1 steps is 0.25296842599999536, loss is 4.513776779174805
step: 129: time taken for the last 1 steps is 0.259235958000005, loss is 4.417741775512695
step: 130: time taken for the last 1 steps is 0.25202945700002033, loss is 4.447234630584717
step: 131: time taken for the last 1 steps is 0.2531651790000069, loss is 4.208217620849609
step: 132: time taken for the last 1 steps is 0.25711992600000144, loss is 4.3844733238220215
step: 133: time taken for the last 1 steps is 0.2544991860000039, loss is 4.48995304107666
step: 134: time taken for the last 1 steps is 0.2609652120000021, loss is 4.435860633850098
step: 135: time taken for the last 1 steps is 0.252543916999997, loss is 4.402706623077393
step: 136: time taken for the last 1 steps is 0.258415862000021, loss is 4.3937554359436035
step: 137: time taken for the last 1 steps is 0.2603776600000174, loss is 4.373472213745117
step: 138: time taken for the last 1 steps is 0.2575525449999816, loss is 4.507457733154297
step: 139: time taken for the last 1 steps is 0.2555811770000105, loss is 4.530117511749268
step: 140: time taken for the last 1 steps is 0.2552334000000087, loss is 4.448877811431885
step: 141: time taken for the last 1 steps is 0.2534439799999859, loss is 4.451408386230469
step: 142: time taken for the last 1 steps is 0.2559829719999982, loss is 4.331961631774902
step: 143: time taken for the last 1 steps is 0.2625455049999914, loss is 4.558147430419922
step: 144: time taken for the last 1 steps is 0.25998349399998233, loss is 4.4368486404418945
step: 145: time taken for the last 1 steps is 0.25940637200000083, loss is 4.276172161102295
step: 146: time taken for the last 1 steps is 0.25792453099998625, loss is 4.553081512451172
step: 147: time taken for the last 1 steps is 0.2584908629999916, loss is 4.38977575302124
step: 148: time taken for the last 1 steps is 0.2631084880000003, loss is 4.492251396179199
step: 149: time taken for the last 1 steps is 0.2568482789999962, loss is 4.420027732849121
step: 150: time taken for the last 1 steps is 0.2574529120000193, loss is 4.313426971435547
step: 151: time taken for the last 1 steps is 0.256303067999994, loss is 4.543499946594238
step: 152: time taken for the last 1 steps is 0.2547805269999799, loss is 4.285205841064453
step: 153: time taken for the last 1 steps is 0.2508665259999816, loss is 4.411813735961914
step: 154: time taken for the last 1 steps is 0.25922828800000275, loss is 4.2857441902160645
step: 155: time taken for the last 1 steps is 0.2597400989999983, loss is 4.444000244140625
step: 156: time taken for the last 1 steps is 0.2532377250000195, loss is 4.442224979400635
step: 157: time taken for the last 1 steps is 0.257684936000004, loss is 4.592156887054443
step: 158: time taken for the last 1 steps is 0.25736490100001674, loss is 4.472250938415527
step: 159: time taken for the last 1 steps is 0.2531340939999893, loss is 4.346929550170898
step: 160: time taken for the last 1 steps is 0.2568183190000184, loss is 4.5280914306640625
step: 161: time taken for the last 1 steps is 0.2600725150000187, loss is 4.414948463439941
step: 162: time taken for the last 1 steps is 0.26214661900002056, loss is 4.439939498901367
step: 163: time taken for the last 1 steps is 0.26022669799999676, loss is 4.286535263061523
step: 164: time taken for the last 1 steps is 0.2507720549999988, loss is 4.532018661499023
step: 165: time taken for the last 1 steps is 0.25475988700000585, loss is 4.342003345489502
step: 166: time taken for the last 1 steps is 0.2607287280000037, loss is 4.426819324493408
step: 167: time taken for the last 1 steps is 0.2584712130000071, loss is 4.397274017333984
step: 168: time taken for the last 1 steps is 0.2588808910000182, loss is 4.305877208709717
step: 169: time taken for the last 1 steps is 0.25874874800001635, loss is 4.4019880294799805
step: 170: time taken for the last 1 steps is 0.25662401400001045, loss is 4.406705856323242
step: 171: time taken for the last 1 steps is 0.262720929000011, loss is 4.458943843841553
step: 172: time taken for the last 1 steps is 0.2637851009999963, loss is 4.4185333251953125
step: 173: time taken for the last 1 steps is 0.2594104310000205, loss is 4.379662990570068
step: 174: time taken for the last 1 steps is 0.258292689000001, loss is 4.401475429534912
step: 175: time taken for the last 1 steps is 0.252365387999987, loss is 4.25689697265625
step: 176: time taken for the last 1 steps is 0.2542289060000087, loss is 4.24041223526001
step: 177: time taken for the last 1 steps is 0.25809521500002575, loss is 4.1480817794799805
step: 178: time taken for the last 1 steps is 0.26435420300001056, loss is 4.138119697570801
step: 179: time taken for the last 1 steps is 0.25605084299999703, loss is 4.343449592590332
step: 180: time taken for the last 1 steps is 0.2604353130000163, loss is 4.479880332946777
step: 181: time taken for the last 1 steps is 0.2586327859999926, loss is 4.525196075439453
step: 182: time taken for the last 1 steps is 0.2607958609999912, loss is 4.313002586364746
step: 183: time taken for the last 1 steps is 0.2533237970000073, loss is 4.448480129241943
step: 184: time taken for the last 1 steps is 0.25938049199999114, loss is 4.382685661315918
step: 185: time taken for the last 1 steps is 0.25864964600000917, loss is 4.193593502044678
step: 186: time taken for the last 1 steps is 0.25800690300002316, loss is 4.353750705718994
step: 187: time taken for the last 1 steps is 0.2638172919999988, loss is 4.274607181549072
step: 188: time taken for the last 1 steps is 0.25893050199999834, loss is 4.38017463684082
step: 189: time taken for the last 1 steps is 0.26112918699999454, loss is 4.4130964279174805
step: 190: time taken for the last 1 steps is 0.2585761850000381, loss is 4.518107891082764
step: 191: time taken for the last 1 steps is 0.257553683000026, loss is 4.45909309387207
step: 192: time taken for the last 1 steps is 0.2611592580000206, loss is 4.433404445648193
step: 193: time taken for the last 1 steps is 0.24741916699997546, loss is 4.434021472930908
step: 194: time taken for the last 1 steps is 0.26111826700002894, loss is 4.334896087646484
step: 195: time taken for the last 1 steps is 0.25549793199996884, loss is 4.103496551513672
step: 196: time taken for the last 1 steps is 0.2583862700000168, loss is 4.123104095458984
step: 197: time taken for the last 1 steps is 0.25070317300003353, loss is 4.374506950378418
step: 198: time taken for the last 1 steps is 0.26513947900002677, loss is 4.312832355499268
step: 199: time taken for the last 1 steps is 0.257064583999977, loss is 4.364517688751221
step: 200: time taken for the last 1 steps is 0.25475813700001027, loss is 4.276547908782959
step: 201: time taken for the last 1 steps is 0.2602753290000237, loss is 4.392114162445068
step: 202: time taken for the last 1 steps is 0.2628212509999912, loss is 4.169902801513672
step: 203: time taken for the last 1 steps is 0.26160398700000087, loss is 4.260707855224609
step: 204: time taken for the last 1 steps is 0.2558927890000291, loss is 4.295074939727783
step: 205: time taken for the last 1 steps is 0.25681487800000014, loss is 4.263187885284424
step: 206: time taken for the last 1 steps is 0.260273159999997, loss is 4.278339385986328
step: 207: time taken for the last 1 steps is 0.26173398899999256, loss is 4.581784248352051
step: 208: time taken for the last 1 steps is 0.2598755809999602, loss is 4.12169075012207
step: 209: time taken for the last 1 steps is 0.25582867899998973, loss is 4.376415252685547
step: 210: time taken for the last 1 steps is 0.2619955050000158, loss is 4.300075531005859
step: 211: time taken for the last 1 steps is 0.258408390999989, loss is 4.371187686920166
step: 212: time taken for the last 1 steps is 0.24944178800001282, loss is 4.292278289794922
step: 213: time taken for the last 1 steps is 0.25588329900000417, loss is 4.3001275062561035
step: 214: time taken for the last 1 steps is 0.2590421250000077, loss is 4.370543956756592
step: 215: time taken for the last 1 steps is 0.25961762600002203, loss is 4.191922664642334
step: 216: time taken for the last 1 steps is 0.2650899879999997, loss is 4.38754415512085
step: 217: time taken for the last 1 steps is 0.262825351999993, loss is 4.216153621673584
step: 218: time taken for the last 1 steps is 0.25955601499998693, loss is 4.374068737030029
step: 219: time taken for the last 1 steps is 0.2557204959999808, loss is 4.335903644561768
step: 220: time taken for the last 1 steps is 0.25875234799997315, loss is 4.248699188232422
step: 221: time taken for the last 1 steps is 0.2553890199999955, loss is 4.281352519989014
step: 222: time taken for the last 1 steps is 0.26401346699998385, loss is 4.3788275718688965
step: 223: time taken for the last 1 steps is 0.25741274899996824, loss is 4.4351677894592285
step: 224: time taken for the last 1 steps is 0.2508081200000447, loss is 4.27348518371582
step: 225: time taken for the last 1 steps is 0.25407534499998974, loss is 4.3527655601501465
step: 226: time taken for the last 1 steps is 0.26032811700002867, loss is 4.1881303787231445
step: 227: time taken for the last 1 steps is 0.24877194100002953, loss is 4.4105305671691895
step: 228: time taken for the last 1 steps is 0.2571053639999832, loss is 4.311103820800781
step: 229: time taken for the last 1 steps is 0.25710870400001795, loss is 4.210919380187988
step: 230: time taken for the last 1 steps is 0.25830068699997355, loss is 4.263632774353027
step: 231: time taken for the last 1 steps is 0.2617945559999839, loss is 4.136380672454834
step: 232: time taken for the last 1 steps is 0.2586165639999649, loss is 4.133800983428955
step: 233: time taken for the last 1 steps is 0.26150511999998116, loss is 4.268002033233643
step: 234: time taken for the last 1 steps is 0.25724366600002213, loss is 4.23779821395874
step: 235: time taken for the last 1 steps is 0.2510931360000086, loss is 4.327415943145752
step: 236: time taken for the last 1 steps is 0.2607689559999926, loss is 4.083348751068115
step: 237: time taken for the last 1 steps is 0.256901809999988, loss is 4.1864705085754395
step: 238: time taken for the last 1 steps is 0.2605832630000009, loss is 4.30706787109375
step: 239: time taken for the last 1 steps is 0.2559698719999801, loss is 4.1464643478393555
step: 240: time taken for the last 1 steps is 0.25319333700002744, loss is 4.3162994384765625
step: 241: time taken for the last 1 steps is 0.26174438499998587, loss is 4.037209510803223
step: 242: time taken for the last 1 steps is 0.2614033579999955, loss is 4.227962493896484
step: 243: time taken for the last 1 steps is 0.2579666109999721, loss is 4.183880805969238
step: 244: time taken for the last 1 steps is 0.25777276700000584, loss is 4.078238010406494
step: 245: time taken for the last 1 steps is 0.2545846749999896, loss is 4.299968719482422
step: 246: time taken for the last 1 steps is 0.25669459599998845, loss is 4.384758472442627
step: 247: time taken for the last 1 steps is 0.265473218000011, loss is 4.18385124206543
step: 248: time taken for the last 1 steps is 0.25879014700001335, loss is 3.889302968978882
step: 249: time taken for the last 1 steps is 0.26663682100002006, loss is 4.418885231018066
step: 250: time taken for the last 1 steps is 0.2566412140000125, loss is 4.30267333984375
step: 251: time taken for the last 1 steps is 0.259615182999994, loss is 4.105579376220703
step: 252: time taken for the last 1 steps is 0.2547257669999681, loss is 4.181215763092041
step: 253: time taken for the last 1 steps is 0.26540830599998344, loss is 4.274713516235352
step: 254: time taken for the last 1 steps is 0.25243632200005095, loss is 4.273143291473389
step: 255: time taken for the last 1 steps is 0.25957230199998094, loss is 4.336678981781006
step: 256: time taken for the last 1 steps is 0.2635708809999642, loss is 4.1258111000061035
step: 257: time taken for the last 1 steps is 0.25923046600001953, loss is 4.173645496368408
step: 258: time taken for the last 1 steps is 0.2581271239999978, loss is 4.333664417266846
step: 259: time taken for the last 1 steps is 0.24891347299995914, loss is 4.020784854888916
step: 260: time taken for the last 1 steps is 0.2584670709999841, loss is 4.313625335693359
step: 261: time taken for the last 1 steps is 0.2507348390000175, loss is 4.3096137046813965
step: 262: time taken for the last 1 steps is 0.26164700399999674, loss is 3.9310176372528076
step: 263: time taken for the last 1 steps is 0.2514092129999881, loss is 4.145771026611328
step: 264: time taken for the last 1 steps is 0.26232634699999835, loss is 4.142434120178223
step: 265: time taken for the last 1 steps is 0.2544166220000079, loss is 4.321177005767822
step: 266: time taken for the last 1 steps is 0.2597196650000342, loss is 4.194943904876709
step: 267: time taken for the last 1 steps is 0.2504601229999821, loss is 4.267314910888672
step: 268: time taken for the last 1 steps is 0.25638195100003713, loss is 3.9375503063201904
step: 269: time taken for the last 1 steps is 0.25710876499999813, loss is 4.302390098571777
step: 270: time taken for the last 1 steps is 0.26005489200002785, loss is 4.018846035003662
step: 271: time taken for the last 1 steps is 0.2612267349999797, loss is 4.288052558898926
step: 272: time taken for the last 1 steps is 0.2636828830000013, loss is 3.987633228302002
step: 273: time taken for the last 1 steps is 0.26190039800002296, loss is 4.17900276184082
step: 274: time taken for the last 1 steps is 0.2585914029999685, loss is 4.28294038772583
step: 275: time taken for the last 1 steps is 0.2609577389999913, loss is 4.20253849029541
step: 276: time taken for the last 1 steps is 0.2546831170000132, loss is 4.150814056396484
step: 277: time taken for the last 1 steps is 0.2545747549999646, loss is 4.421744346618652
step: 278: time taken for the last 1 steps is 0.2627312150000307, loss is 4.14412784576416
step: 279: time taken for the last 1 steps is 0.23578439599998546, loss is 4.081680774688721
val_loss : 4.0692 :  val_acc: 0.0797

updating stats...
Epoch: 2 starting...
step: 1: time taken for the last 1 steps is 0.6895236540000269, loss is 4.060554027557373
step: 2: time taken for the last 1 steps is 0.255047229000013, loss is 4.1662750244140625
step: 3: time taken for the last 1 steps is 0.257597928999985, loss is 4.416499137878418
step: 4: time taken for the last 1 steps is 0.25465816199999836, loss is 4.190380096435547
step: 5: time taken for the last 1 steps is 0.25246123699997725, loss is 4.199824333190918
step: 6: time taken for the last 1 steps is 0.25101609900002586, loss is 4.1920366287231445
step: 7: time taken for the last 1 steps is 0.2520030090000205, loss is 3.890657424926758
step: 8: time taken for the last 1 steps is 0.2571485010000174, loss is 4.049408435821533
step: 9: time taken for the last 1 steps is 0.25378751400000965, loss is 4.208953380584717
step: 10: time taken for the last 1 steps is 0.25124547399997255, loss is 4.103820323944092
step: 11: time taken for the last 1 steps is 0.25142426799999384, loss is 4.126346588134766
step: 12: time taken for the last 1 steps is 0.2537671740000178, loss is 4.031586170196533
step: 13: time taken for the last 1 steps is 0.2543134239999745, loss is 4.236934185028076
step: 14: time taken for the last 1 steps is 0.24835310699995716, loss is 4.272700309753418
step: 15: time taken for the last 1 steps is 0.24928251500000442, loss is 3.9991979598999023
step: 16: time taken for the last 1 steps is 0.25865470000002233, loss is 4.10144567489624
step: 17: time taken for the last 1 steps is 0.2431046329999731, loss is 4.187726020812988
step: 18: time taken for the last 1 steps is 0.2513429559999736, loss is 4.126735687255859
step: 19: time taken for the last 1 steps is 0.24605886099999452, loss is 4.2733988761901855
step: 20: time taken for the last 1 steps is 0.2512526750000461, loss is 4.1199822425842285
step: 21: time taken for the last 1 steps is 0.2494953399999531, loss is 4.3857197761535645
step: 22: time taken for the last 1 steps is 0.2521242509999979, loss is 4.071629047393799
step: 23: time taken for the last 1 steps is 0.2556379209999591, loss is 4.299444675445557
step: 24: time taken for the last 1 steps is 0.2507160539999518, loss is 4.1478352546691895
step: 25: time taken for the last 1 steps is 0.25028089500000306, loss is 3.9528934955596924
step: 26: time taken for the last 1 steps is 0.24598034999996798, loss is 4.102459907531738
step: 27: time taken for the last 1 steps is 0.2484587689999671, loss is 4.148408889770508
step: 28: time taken for the last 1 steps is 0.24950185000000147, loss is 4.009032249450684
step: 29: time taken for the last 1 steps is 0.24847834899998134, loss is 4.109431266784668
step: 30: time taken for the last 1 steps is 0.2538478459999851, loss is 4.0545477867126465
step: 31: time taken for the last 1 steps is 0.2520302300000026, loss is 4.252261161804199
step: 32: time taken for the last 1 steps is 0.25529340399998546, loss is 4.322540283203125
step: 33: time taken for the last 1 steps is 0.2528188150000119, loss is 4.501019477844238
step: 34: time taken for the last 1 steps is 0.24769680299999663, loss is 4.263233661651611
step: 35: time taken for the last 1 steps is 0.2544575469999586, loss is 3.9750115871429443
step: 36: time taken for the last 1 steps is 0.2559571869999786, loss is 4.203736305236816
step: 37: time taken for the last 1 steps is 0.2529225369999608, loss is 4.022042751312256
step: 38: time taken for the last 1 steps is 0.25179738499997484, loss is 4.098234176635742
step: 39: time taken for the last 1 steps is 0.2539763579999885, loss is 4.185070037841797
step: 40: time taken for the last 1 steps is 0.25534832599998936, loss is 4.022120475769043
step: 41: time taken for the last 1 steps is 0.2565016880000144, loss is 4.226497650146484
step: 42: time taken for the last 1 steps is 0.25094139800000903, loss is 4.202787399291992
step: 43: time taken for the last 1 steps is 0.24928080500001215, loss is 3.866891384124756
step: 44: time taken for the last 1 steps is 0.2496636330000115, loss is 4.1885809898376465
step: 45: time taken for the last 1 steps is 0.2540368489999878, loss is 4.051706790924072
step: 46: time taken for the last 1 steps is 0.2575352080000357, loss is 4.0146074295043945
step: 47: time taken for the last 1 steps is 0.25197204800002737, loss is 4.0135087966918945
step: 48: time taken for the last 1 steps is 0.25425183399994467, loss is 4.074001312255859
step: 49: time taken for the last 1 steps is 0.26017739100001336, loss is 4.126014232635498
step: 50: time taken for the last 1 steps is 0.24913729299998977, loss is 4.017709732055664
step: 51: time taken for the last 1 steps is 0.24822025399998893, loss is 4.087454795837402
step: 52: time taken for the last 1 steps is 0.2576250600000094, loss is 4.096774578094482
step: 53: time taken for the last 1 steps is 0.25192096699998956, loss is 3.8628809452056885
step: 54: time taken for the last 1 steps is 0.2502871949999985, loss is 4.042823791503906
step: 55: time taken for the last 1 steps is 0.2551518509999937, loss is 4.096584320068359
step: 56: time taken for the last 1 steps is 0.24927577500000098, loss is 4.093833923339844
step: 57: time taken for the last 1 steps is 0.25601656899999625, loss is 4.1299357414245605
step: 58: time taken for the last 1 steps is 0.25305437899999106, loss is 3.8931045532226562
step: 59: time taken for the last 1 steps is 0.25280408499997975, loss is 4.020094394683838
step: 60: time taken for the last 1 steps is 0.25229055500000186, loss is 3.9865925312042236
step: 61: time taken for the last 1 steps is 0.2509068280000406, loss is 3.7625646591186523
step: 62: time taken for the last 1 steps is 0.25223026299994444, loss is 4.132228851318359
step: 63: time taken for the last 1 steps is 0.25400657899996304, loss is 4.251020431518555
step: 64: time taken for the last 1 steps is 0.2543748550000373, loss is 3.9893126487731934
step: 65: time taken for the last 1 steps is 0.2478567969999972, loss is 4.047043800354004
step: 66: time taken for the last 1 steps is 0.25233300600001485, loss is 4.010395050048828
step: 67: time taken for the last 1 steps is 0.25430066400002715, loss is 4.039310455322266
step: 68: time taken for the last 1 steps is 0.25297912799999267, loss is 3.915067672729492
step: 69: time taken for the last 1 steps is 0.24731605699997772, loss is 4.043298244476318
step: 70: time taken for the last 1 steps is 0.2510627600000248, loss is 3.990957736968994
step: 71: time taken for the last 1 steps is 0.252221703000032, loss is 3.917525291442871
step: 72: time taken for the last 1 steps is 0.2518561360000149, loss is 3.5985665321350098
step: 73: time taken for the last 1 steps is 0.2528815359999612, loss is 3.968690872192383
step: 74: time taken for the last 1 steps is 0.2578979450000247, loss is 3.951397657394409
step: 75: time taken for the last 1 steps is 0.2597007910000002, loss is 3.9562714099884033
step: 76: time taken for the last 1 steps is 0.2527217329999871, loss is 4.12548828125
step: 77: time taken for the last 1 steps is 0.25109309100002974, loss is 3.622377872467041
step: 78: time taken for the last 1 steps is 0.2581781509999814, loss is 3.7929651737213135
step: 79: time taken for the last 1 steps is 0.2570306339999888, loss is 3.689714193344116
step: 80: time taken for the last 1 steps is 0.24850777599999674, loss is 3.8619191646575928
step: 81: time taken for the last 1 steps is 0.25081470200001377, loss is 4.062615394592285
step: 82: time taken for the last 1 steps is 0.2585468339999579, loss is 4.077060222625732
step: 83: time taken for the last 1 steps is 0.25180443200002856, loss is 4.073394775390625
step: 84: time taken for the last 1 steps is 0.24951591699999653, loss is 4.137074947357178
step: 85: time taken for the last 1 steps is 0.25397839400000066, loss is 4.117764472961426
step: 86: time taken for the last 1 steps is 0.251094237000018, loss is 3.9760029315948486
step: 87: time taken for the last 1 steps is 0.2530821359999891, loss is 4.024318695068359
step: 88: time taken for the last 1 steps is 0.25651510399995914, loss is 4.068992614746094
step: 89: time taken for the last 1 steps is 0.2539558839999927, loss is 4.054355621337891
step: 90: time taken for the last 1 steps is 0.24800747699998738, loss is 4.033942699432373
step: 91: time taken for the last 1 steps is 0.2541161970000303, loss is 4.038212299346924
step: 92: time taken for the last 1 steps is 0.25360788699998693, loss is 3.9520492553710938
step: 93: time taken for the last 1 steps is 0.2506446589999882, loss is 3.8900487422943115
step: 94: time taken for the last 1 steps is 0.2521775089999778, loss is 3.825072765350342
step: 95: time taken for the last 1 steps is 0.2520350560000111, loss is 3.8265624046325684
step: 96: time taken for the last 1 steps is 0.25294021299998803, loss is 3.9427266120910645
step: 97: time taken for the last 1 steps is 0.24719355099995255, loss is 4.084011077880859
step: 98: time taken for the last 1 steps is 0.25724487800005136, loss is 4.029963970184326
step: 99: time taken for the last 1 steps is 0.2536463269999558, loss is 4.29442024230957
step: 100: time taken for the last 1 steps is 0.2539252429999692, loss is 4.036984920501709
step: 101: time taken for the last 1 steps is 0.24771063200000754, loss is 4.077581882476807
step: 102: time taken for the last 1 steps is 0.25306863699995574, loss is 3.823577404022217
step: 103: time taken for the last 1 steps is 0.2508145720000243, loss is 4.06989860534668
step: 104: time taken for the last 1 steps is 0.24493633599996656, loss is 4.044546604156494
step: 105: time taken for the last 1 steps is 0.25689133200000924, loss is 4.241550445556641
step: 106: time taken for the last 1 steps is 0.2465660980000166, loss is 3.9005274772644043
step: 107: time taken for the last 1 steps is 0.2574096010000062, loss is 3.9601924419403076
step: 108: time taken for the last 1 steps is 0.2569696730000146, loss is 3.9257404804229736
step: 109: time taken for the last 1 steps is 0.2519359140000006, loss is 4.191210746765137
step: 110: time taken for the last 1 steps is 0.25879740900001025, loss is 3.7536303997039795
step: 111: time taken for the last 1 steps is 0.25032065300001705, loss is 3.822922706604004
step: 112: time taken for the last 1 steps is 0.2596106149999855, loss is 3.990379810333252
step: 113: time taken for the last 1 steps is 0.2434905380000032, loss is 3.814377784729004
step: 114: time taken for the last 1 steps is 0.25473566800002345, loss is 4.110430717468262
step: 115: time taken for the last 1 steps is 0.24308763999999883, loss is 4.144354343414307
step: 116: time taken for the last 1 steps is 0.2531678579999834, loss is 3.8247945308685303
step: 117: time taken for the last 1 steps is 0.24499736700005315, loss is 4.005329608917236
step: 118: time taken for the last 1 steps is 0.24327732300002936, loss is 3.952025890350342
step: 119: time taken for the last 1 steps is 0.25320832900001733, loss is 3.9203929901123047
step: 120: time taken for the last 1 steps is 0.24508568999999625, loss is 4.096575736999512
step: 121: time taken for the last 1 steps is 0.25340446300003805, loss is 3.988690137863159
step: 122: time taken for the last 1 steps is 0.2477578019999669, loss is 3.873231887817383
step: 123: time taken for the last 1 steps is 0.24619195100001434, loss is 4.040771007537842
step: 124: time taken for the last 1 steps is 0.2529802249999875, loss is 3.9246785640716553
step: 125: time taken for the last 1 steps is 0.2514415050000025, loss is 4.095849514007568
step: 126: time taken for the last 1 steps is 0.25678181999995786, loss is 3.991701126098633
step: 127: time taken for the last 1 steps is 0.2541619080000146, loss is 3.820143699645996
step: 128: time taken for the last 1 steps is 0.2580276239999648, loss is 3.8458521366119385
step: 129: time taken for the last 1 steps is 0.26074380700003985, loss is 4.060593605041504
step: 130: time taken for the last 1 steps is 0.2500258950000216, loss is 3.8175909519195557
step: 131: time taken for the last 1 steps is 0.2533995229999846, loss is 3.787524461746216
step: 132: time taken for the last 1 steps is 0.2557434080000007, loss is 3.849271535873413
step: 133: time taken for the last 1 steps is 0.2488642240000445, loss is 3.757674217224121
step: 134: time taken for the last 1 steps is 0.24563854999996693, loss is 3.9758071899414062
step: 135: time taken for the last 1 steps is 0.24942779399998471, loss is 3.9901294708251953
step: 136: time taken for the last 1 steps is 0.2534782440000072, loss is 3.977137327194214
step: 137: time taken for the last 1 steps is 0.2473351829999615, loss is 4.172210216522217
step: 138: time taken for the last 1 steps is 0.2552080180000189, loss is 3.9610865116119385
step: 139: time taken for the last 1 steps is 0.25595652399999835, loss is 4.180133819580078
step: 140: time taken for the last 1 steps is 0.24921426099996324, loss is 3.8822977542877197
step: 141: time taken for the last 1 steps is 0.25635792099996024, loss is 3.9525887966156006
step: 142: time taken for the last 1 steps is 0.2552621599999725, loss is 4.059017658233643
step: 143: time taken for the last 1 steps is 0.2514825350000365, loss is 4.070084571838379
step: 144: time taken for the last 1 steps is 0.2565383049999923, loss is 4.012814044952393
step: 145: time taken for the last 1 steps is 0.2613172380000037, loss is 3.870054244995117
step: 146: time taken for the last 1 steps is 0.24905203800000209, loss is 4.240328788757324
step: 147: time taken for the last 1 steps is 0.24596436699999913, loss is 3.921361207962036
step: 148: time taken for the last 1 steps is 0.25676491900003384, loss is 3.908442735671997
step: 149: time taken for the last 1 steps is 0.25625224799995294, loss is 3.8179917335510254
step: 150: time taken for the last 1 steps is 0.2557446790000313, loss is 3.8214547634124756
step: 151: time taken for the last 1 steps is 0.2406664530000171, loss is 4.048144340515137
step: 152: time taken for the last 1 steps is 0.2537321990000123, loss is 3.8156778812408447
step: 153: time taken for the last 1 steps is 0.252552105999996, loss is 3.6674673557281494
step: 154: time taken for the last 1 steps is 0.2544121130000008, loss is 3.79384708404541
step: 155: time taken for the last 1 steps is 0.25277454100000796, loss is 3.996262550354004
step: 156: time taken for the last 1 steps is 0.253717689000041, loss is 3.8331313133239746
step: 157: time taken for the last 1 steps is 0.2543513319999988, loss is 4.0882134437561035
step: 158: time taken for the last 1 steps is 0.2510073760000182, loss is 3.9235732555389404
step: 159: time taken for the last 1 steps is 0.2459378159999801, loss is 3.9841980934143066
step: 160: time taken for the last 1 steps is 0.25027798100001064, loss is 4.073812007904053
step: 161: time taken for the last 1 steps is 0.25966157100003784, loss is 3.716912031173706
step: 162: time taken for the last 1 steps is 0.25909871999999723, loss is 3.886120080947876
step: 163: time taken for the last 1 steps is 0.2563324060000127, loss is 3.8924529552459717
step: 164: time taken for the last 1 steps is 0.2573229449999985, loss is 3.8922181129455566
step: 165: time taken for the last 1 steps is 0.2515256130000125, loss is 3.8636953830718994
step: 166: time taken for the last 1 steps is 0.2533797990000153, loss is 3.7816336154937744
step: 167: time taken for the last 1 steps is 0.2560928010000225, loss is 3.526089906692505
step: 168: time taken for the last 1 steps is 0.2527447470000084, loss is 3.8599436283111572
step: 169: time taken for the last 1 steps is 0.2515059119999705, loss is 3.696331024169922
step: 170: time taken for the last 1 steps is 0.25794713799996316, loss is 3.927506446838379
step: 171: time taken for the last 1 steps is 0.25362101299998585, loss is 3.8404932022094727
step: 172: time taken for the last 1 steps is 0.25688296699996727, loss is 3.868551731109619
step: 173: time taken for the last 1 steps is 0.2534251399999903, loss is 3.814709424972534
step: 174: time taken for the last 1 steps is 0.2518525990000171, loss is 3.9838602542877197
step: 175: time taken for the last 1 steps is 0.24380251200000203, loss is 3.748842716217041
step: 176: time taken for the last 1 steps is 0.2538228679999861, loss is 3.817082643508911
step: 177: time taken for the last 1 steps is 0.25673818399997117, loss is 3.6511948108673096
step: 178: time taken for the last 1 steps is 0.2505686040000228, loss is 3.578589677810669
step: 179: time taken for the last 1 steps is 0.2542758460000414, loss is 3.9722259044647217
step: 180: time taken for the last 1 steps is 0.2530582919999915, loss is 3.8177130222320557
step: 181: time taken for the last 1 steps is 0.25506143100000145, loss is 4.040961742401123
step: 182: time taken for the last 1 steps is 0.24902076400002215, loss is 3.745741605758667
step: 183: time taken for the last 1 steps is 0.2505137820000414, loss is 3.9821670055389404
step: 184: time taken for the last 1 steps is 0.25556414200002564, loss is 4.015752792358398
step: 185: time taken for the last 1 steps is 0.24718692799996234, loss is 3.8230693340301514
step: 186: time taken for the last 1 steps is 0.25544902000001457, loss is 3.804311752319336
step: 187: time taken for the last 1 steps is 0.25311335300000337, loss is 3.91082763671875
step: 188: time taken for the last 1 steps is 0.25685841699998946, loss is 3.861664295196533
step: 189: time taken for the last 1 steps is 0.25431159599997955, loss is 3.89089298248291
step: 190: time taken for the last 1 steps is 0.2452378099999919, loss is 4.118781566619873
step: 191: time taken for the last 1 steps is 0.2539693100000022, loss is 3.999220848083496
step: 192: time taken for the last 1 steps is 0.2536703640000155, loss is 3.9700286388397217
step: 193: time taken for the last 1 steps is 0.24752892499998325, loss is 4.015350341796875
step: 194: time taken for the last 1 steps is 0.2586442510000211, loss is 3.9552369117736816
step: 195: time taken for the last 1 steps is 0.2508691900000031, loss is 3.662324905395508
step: 196: time taken for the last 1 steps is 0.24761721599998054, loss is 3.624174118041992
step: 197: time taken for the last 1 steps is 0.25599907999998095, loss is 3.678323745727539
step: 198: time taken for the last 1 steps is 0.25487487800000963, loss is 3.817084312438965
step: 199: time taken for the last 1 steps is 0.24435280299996975, loss is 3.858469247817993
step: 200: time taken for the last 1 steps is 0.2553516269999818, loss is 3.921903610229492
step: 201: time taken for the last 1 steps is 0.2503238689999989, loss is 3.938459873199463
step: 202: time taken for the last 1 steps is 0.25415111300003446, loss is 3.6183090209960938
step: 203: time taken for the last 1 steps is 0.24515994900002624, loss is 3.6317505836486816
step: 204: time taken for the last 1 steps is 0.2545516719999341, loss is 3.7844176292419434
step: 205: time taken for the last 1 steps is 0.25750616899995293, loss is 3.894787073135376
step: 206: time taken for the last 1 steps is 0.2506427360000316, loss is 3.838219165802002
step: 207: time taken for the last 1 steps is 0.25419664399998965, loss is 4.095887184143066
step: 208: time taken for the last 1 steps is 0.2532784960000072, loss is 3.713913917541504
step: 209: time taken for the last 1 steps is 0.2560210299999426, loss is 3.9571402072906494
step: 210: time taken for the last 1 steps is 0.2566587129999789, loss is 3.9521591663360596
step: 211: time taken for the last 1 steps is 0.24923003800006427, loss is 3.9129881858825684
step: 212: time taken for the last 1 steps is 0.2555076999999528, loss is 3.869257688522339
step: 213: time taken for the last 1 steps is 0.257520649000071, loss is 3.799757957458496
step: 214: time taken for the last 1 steps is 0.2443356930000391, loss is 3.9002232551574707
step: 215: time taken for the last 1 steps is 0.25321700599999986, loss is 3.7885563373565674
step: 216: time taken for the last 1 steps is 0.25528722599995035, loss is 3.834613084793091
step: 217: time taken for the last 1 steps is 0.25569950399994923, loss is 3.5112221240997314
step: 218: time taken for the last 1 steps is 0.25716096199994354, loss is 3.905047655105591
step: 219: time taken for the last 1 steps is 0.2559244190000527, loss is 3.730198860168457
step: 220: time taken for the last 1 steps is 0.2553120970000009, loss is 3.8626229763031006
step: 221: time taken for the last 1 steps is 0.2575756910000564, loss is 3.7866694927215576
step: 222: time taken for the last 1 steps is 0.2508513389999507, loss is 3.9708120822906494
step: 223: time taken for the last 1 steps is 0.25141810100001294, loss is 4.011201858520508
step: 224: time taken for the last 1 steps is 0.25715839200006485, loss is 3.9431447982788086
step: 225: time taken for the last 1 steps is 0.25817251199998736, loss is 4.010535717010498
step: 226: time taken for the last 1 steps is 0.2538321880000467, loss is 3.9456958770751953
step: 227: time taken for the last 1 steps is 0.2550697920000857, loss is 4.164735794067383
step: 228: time taken for the last 1 steps is 0.25393684000005123, loss is 3.784292221069336
step: 229: time taken for the last 1 steps is 0.25452005100009956, loss is 3.7148101329803467
step: 230: time taken for the last 1 steps is 0.2524506309999879, loss is 3.8933990001678467
step: 231: time taken for the last 1 steps is 0.25317876500002967, loss is 3.461291790008545
step: 232: time taken for the last 1 steps is 0.2507163359999822, loss is 3.664804458618164
step: 233: time taken for the last 1 steps is 0.25696423899989895, loss is 3.606860637664795
step: 234: time taken for the last 1 steps is 0.25430755699994734, loss is 3.821992874145508
step: 235: time taken for the last 1 steps is 0.25036125999997694, loss is 3.9950404167175293
step: 236: time taken for the last 1 steps is 0.2534058990000858, loss is 3.7123961448669434
step: 237: time taken for the last 1 steps is 0.2577454539999735, loss is 3.6645419597625732
step: 238: time taken for the last 1 steps is 0.24497987399990961, loss is 3.897904396057129
step: 239: time taken for the last 1 steps is 0.25467665299993314, loss is 3.7769601345062256
step: 240: time taken for the last 1 steps is 0.24843114199995853, loss is 3.9095804691314697
step: 241: time taken for the last 1 steps is 0.25231481799994526, loss is 3.7583563327789307
step: 242: time taken for the last 1 steps is 0.2469408359999079, loss is 3.8762714862823486
step: 243: time taken for the last 1 steps is 0.25697288899993964, loss is 3.4795138835906982
step: 244: time taken for the last 1 steps is 0.2522369680000338, loss is 3.8226609230041504
step: 245: time taken for the last 1 steps is 0.25324653699999544, loss is 3.9292125701904297
step: 246: time taken for the last 1 steps is 0.25298608299999614, loss is 4.060460090637207
step: 247: time taken for the last 1 steps is 0.2493032109999831, loss is 3.7012999057769775
step: 248: time taken for the last 1 steps is 0.2509841039999401, loss is 3.2624080181121826
step: 249: time taken for the last 1 steps is 0.2549889809999968, loss is 3.9142446517944336
step: 250: time taken for the last 1 steps is 0.25917626199998267, loss is 3.756697177886963
step: 251: time taken for the last 1 steps is 0.25079305999997814, loss is 3.7828471660614014
step: 252: time taken for the last 1 steps is 0.2496865489999891, loss is 3.9785420894622803
step: 253: time taken for the last 1 steps is 0.2571733930000164, loss is 3.918090343475342
step: 254: time taken for the last 1 steps is 0.25692794799999774, loss is 3.9352080821990967
step: 255: time taken for the last 1 steps is 0.257614440999987, loss is 3.782555103302002
step: 256: time taken for the last 1 steps is 0.246064279000052, loss is 3.760831117630005
step: 257: time taken for the last 1 steps is 0.25145027199994274, loss is 3.706961154937744
step: 258: time taken for the last 1 steps is 0.252839799999947, loss is 3.647899866104126
step: 259: time taken for the last 1 steps is 0.25370151599997826, loss is 3.4003546237945557
step: 260: time taken for the last 1 steps is 0.253571093000005, loss is 3.8092315196990967
step: 261: time taken for the last 1 steps is 0.25282441899992136, loss is 3.8218555450439453
step: 262: time taken for the last 1 steps is 0.24722660099996574, loss is 3.36043381690979
step: 263: time taken for the last 1 steps is 0.2503766119999682, loss is 3.7000207901000977
step: 264: time taken for the last 1 steps is 0.2539465999999493, loss is 3.578587293624878
step: 265: time taken for the last 1 steps is 0.255111812999985, loss is 3.832127809524536
step: 266: time taken for the last 1 steps is 0.25609357200005434, loss is 3.6265101432800293
step: 267: time taken for the last 1 steps is 0.25074284899994836, loss is 3.893702745437622
step: 268: time taken for the last 1 steps is 0.2574886389999165, loss is 3.5314197540283203
step: 269: time taken for the last 1 steps is 0.2507302289999416, loss is 4.000232219696045
step: 270: time taken for the last 1 steps is 0.253859858999931, loss is 3.567129135131836
step: 271: time taken for the last 1 steps is 0.24726073199997245, loss is 3.6589467525482178
step: 272: time taken for the last 1 steps is 0.2539466299999731, loss is 3.6705353260040283
step: 273: time taken for the last 1 steps is 0.2534541109999964, loss is 3.7243568897247314
step: 274: time taken for the last 1 steps is 0.2536771549999912, loss is 3.790518283843994
step: 275: time taken for the last 1 steps is 0.26001827799996136, loss is 3.783092737197876
step: 276: time taken for the last 1 steps is 0.2520900850000771, loss is 3.7121379375457764
step: 277: time taken for the last 1 steps is 0.24970304900000428, loss is 4.211219787597656
step: 278: time taken for the last 1 steps is 0.2483935240001074, loss is 3.8870503902435303
step: 279: time taken for the last 1 steps is 0.21861689900003967, loss is 3.7971079349517822
val_loss : 3.5785 :  val_acc: 0.1617

updating stats...

--> cuda max reserved memory = 12.5
--> max reserved percentage = 56.66 %

--> cuda max memory allocated = 11.0791
--> max allocated percentage = 50.22 %

--> peak active memory = 11.0791
--> peak active memory 50.22 %

cudaMalloc retries = 0
cuda OOM = 0

loss='4.0692', acc='0.0797'
loss='3.5785', acc='0.1617'

--> Highest Val Accuracy =  16.17


--> Model Size =  85.722869 M Params