Apppublic
everythingfades/vits_personal_exploration

sourceHugging Faceupdated 3y agoView on Hugging Face
0likes
train.log2076 linesDownload Raw Back to OUTPUT_MODEL
12023-04-01 19:53:32,682	OUTPUT_MODEL	INFO	{'train': {'log_interval': 100, 'eval_interval': 1000, 'seed': 1234, 'epochs': 10000, 'learning_rate': 0.0002, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 16, 'fp16_run': False, 'lr_decay': 0.999875, 'segment_size': 8192, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'training_files': 'final_annotation_train.txt.cleaned', 'validation_files': 'final_annotation_val.txt.cleaned', 'text_cleaners': ['cjke_cleaners2'], 'max_wav_value': 32768.0, 'sampling_rate': 22050, 'filter_length': 1024, 'hop_length': 256, 'win_length': 1024, 'n_mel_channels': 80, 'mel_fmin': 0.0, 'mel_fmax': None, 'add_blank': True, 'n_speakers': 3, 'cleaned_text': True}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0.1, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [8, 8, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 256}, 'symbols': ['_', ',', '.', '!', '?', '-', '~', '…', 'A', 'E', 'I', 'N', 'O', 'Q', 'U', 'a', 'b', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'r', 's', 't', 'u', 'v', 'w', 'y', 'z', 'ʃ', 'ʧ', 'ʦ', 'ɯ', 'ɹ', 'ə', 'ɥ', '⁼', 'ʰ', '`', '→', '↓', '↑', ' '], 'speakers': {'W': 0, 'specialweek': 1, 'zhongli': 2}, 'model_dir': '././OUTPUT_MODEL', 'max_epochs': 50, 'drop_speaker_embed': True}22023-04-01 19:53:32,682	OUTPUT_MODEL	WARNING	/root/autodl-tmp/VITS-finetune is not a git repository, therefore hash value comparison will be ignored.32023-04-01 19:53:37,807	OUTPUT_MODEL	INFO	Loaded checkpoint './pretrained_models/G_0_.pth' (iteration None)42023-04-01 19:53:38,025	OUTPUT_MODEL	INFO	Loaded checkpoint './pretrained_models/D_0_.pth' (iteration None)52023-04-01 19:53:41,362	OUTPUT_MODEL	INFO	Train Epoch: 1 [0%]62023-04-01 19:53:41,363	OUTPUT_MODEL	INFO	[2.43756103515625, 2.3624532222747803, 12.411858558654785, 29.1290340423584, 1.7119799852371216, 15.800495147705078, 0, 0.0002]72023-04-01 19:53:43,842	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 1 to ././OUTPUT_MODEL/G_0.pth82023-04-01 19:53:44,659	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 1 to ././OUTPUT_MODEL/G_latest.pth92023-04-01 19:54:21,517	OUTPUT_MODEL	INFO	====> Epoch: 1102023-04-01 19:54:49,979	OUTPUT_MODEL	INFO	====> Epoch: 2112023-04-01 19:55:08,775	OUTPUT_MODEL	INFO	Train Epoch: 3 [63%]122023-04-01 19:55:08,776	OUTPUT_MODEL	INFO	[2.342874050140381, 2.588383674621582, 9.66038703918457, 20.137237548828125, 1.65578031539917, 3.755317449569702, 100, 0.000199950003125]132023-04-01 19:55:19,143	OUTPUT_MODEL	INFO	====> Epoch: 3142023-04-01 19:55:47,809	OUTPUT_MODEL	INFO	====> Epoch: 4152023-04-01 19:56:16,533	OUTPUT_MODEL	INFO	====> Epoch: 5162023-04-01 19:56:24,924	OUTPUT_MODEL	INFO	Train Epoch: 6 [26%]172023-04-01 19:56:24,925	OUTPUT_MODEL	INFO	[2.4329569339752197, 2.8931806087493896, 12.206804275512695, 21.895294189453125, -0.25430524349212646, 3.6739888191223145, 200, 0.00019987503124609398]182023-04-01 19:56:45,727	OUTPUT_MODEL	INFO	====> Epoch: 6192023-04-01 19:57:14,238	OUTPUT_MODEL	INFO	====> Epoch: 7202023-04-01 19:57:40,348	OUTPUT_MODEL	INFO	Train Epoch: 8 [89%]212023-04-01 19:57:40,349	OUTPUT_MODEL	INFO	[2.024712085723877, 2.710695743560791, 12.191858291625977, 21.886186599731445, -10.907732963562012, 3.398862838745117, 300, 0.00019982506561132978]222023-04-01 19:57:43,468	OUTPUT_MODEL	INFO	====> Epoch: 8232023-04-01 19:58:12,085	OUTPUT_MODEL	INFO	====> Epoch: 9242023-04-01 19:58:40,712	OUTPUT_MODEL	INFO	====> Epoch: 10252023-04-01 19:58:56,780	OUTPUT_MODEL	INFO	Train Epoch: 11 [53%]262023-04-01 19:58:56,781	OUTPUT_MODEL	INFO	[2.36210560798645, 2.4637057781219482, 11.60049057006836, 21.200698852539062, 1.639676570892334, 3.1409823894500732, 400, 0.00019975014057813518]272023-04-01 19:59:10,334	OUTPUT_MODEL	INFO	====> Epoch: 11282023-04-01 19:59:39,453	OUTPUT_MODEL	INFO	====> Epoch: 12292023-04-01 20:00:08,565	OUTPUT_MODEL	INFO	====> Epoch: 13302023-04-01 20:00:14,061	OUTPUT_MODEL	INFO	Train Epoch: 14 [16%]312023-04-01 20:00:14,062	OUTPUT_MODEL	INFO	[2.257652759552002, 2.6586077213287354, 11.006087303161621, 20.864177703857422, -11.809783935546875, 2.4259958267211914, 500, 0.00019967524363831608]322023-04-01 20:00:37,878	OUTPUT_MODEL	INFO	====> Epoch: 14332023-04-01 20:01:06,416	OUTPUT_MODEL	INFO	====> Epoch: 15342023-04-01 20:01:29,563	OUTPUT_MODEL	INFO	Train Epoch: 16 [79%]352023-04-01 20:01:29,564	OUTPUT_MODEL	INFO	[2.0433905124664307, 3.2565577030181885, 12.459961891174316, 21.76738739013672, -11.99836540222168, 2.282912254333496, 600, 0.00019962532794733217]362023-04-01 20:01:35,631	OUTPUT_MODEL	INFO	====> Epoch: 16372023-04-01 20:02:04,516	OUTPUT_MODEL	INFO	====> Epoch: 17382023-04-01 20:02:33,802	OUTPUT_MODEL	INFO	====> Epoch: 18392023-04-01 20:02:46,969	OUTPUT_MODEL	INFO	Train Epoch: 19 [42%]402023-04-01 20:02:46,969	OUTPUT_MODEL	INFO	[2.0517044067382812, 2.847269058227539, 11.27221393585205, 20.923763275146484, -2.043724536895752, 2.2113757133483887, 700, 0.00019955047780639926]412023-04-01 20:03:03,553	OUTPUT_MODEL	INFO	====> Epoch: 19422023-04-01 20:03:32,614	OUTPUT_MODEL	INFO	====> Epoch: 20432023-04-01 20:04:01,729	OUTPUT_MODEL	INFO	====> Epoch: 21442023-04-01 20:04:04,350	OUTPUT_MODEL	INFO	Train Epoch: 22 [5%]452023-04-01 20:04:04,351	OUTPUT_MODEL	INFO	[2.428856372833252, 2.838590145111084, 10.0092191696167, 19.597076416015625, -2.3467044830322266, 3.0596983432769775, 800, 0.00019947565573076072]462023-04-01 20:04:31,506	OUTPUT_MODEL	INFO	====> Epoch: 22472023-04-01 20:05:00,068	OUTPUT_MODEL	INFO	====> Epoch: 23482023-04-01 20:05:20,341	OUTPUT_MODEL	INFO	Train Epoch: 24 [68%]492023-04-01 20:05:20,342	OUTPUT_MODEL	INFO	[2.386040449142456, 2.6730833053588867, 11.994549751281738, 20.608755111694336, 1.1624445915222168, 3.2508630752563477, 900, 0.00019942578993363514]502023-04-01 20:05:29,252	OUTPUT_MODEL	INFO	====> Epoch: 24512023-04-01 20:05:57,813	OUTPUT_MODEL	INFO	====> Epoch: 25522023-04-01 20:06:26,345	OUTPUT_MODEL	INFO	====> Epoch: 26532023-04-01 20:06:36,250	OUTPUT_MODEL	INFO	Train Epoch: 27 [32%]542023-04-01 20:06:36,250	OUTPUT_MODEL	INFO	[2.1966512203216553, 2.9480409622192383, 12.397226333618164, 20.305404663085938, -4.156848430633545, 2.21818208694458, 1000, 0.00019935101461010442]552023-04-01 20:06:37,937	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 27 to ././OUTPUT_MODEL/G_1000.pth562023-04-01 20:06:38,231	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 27 to ././OUTPUT_MODEL/G_latest.pth572023-04-01 20:06:57,090	OUTPUT_MODEL	INFO	====> Epoch: 27582023-04-01 20:07:25,886	OUTPUT_MODEL	INFO	====> Epoch: 28592023-04-01 20:07:53,627	OUTPUT_MODEL	INFO	Train Epoch: 29 [95%]602023-04-01 20:07:53,628	OUTPUT_MODEL	INFO	[2.1096105575561523, 2.9250495433807373, 9.789108276367188, 19.14834976196289, 1.7025477886199951, 2.565619468688965, 1100, 0.0001993011799713115]612023-04-01 20:07:55,354	OUTPUT_MODEL	INFO	====> Epoch: 29622023-04-01 20:08:23,905	OUTPUT_MODEL	INFO	====> Epoch: 30632023-04-01 20:08:52,487	OUTPUT_MODEL	INFO	====> Epoch: 31642023-04-01 20:09:09,787	OUTPUT_MODEL	INFO	Train Epoch: 32 [58%]652023-04-01 20:09:09,787	OUTPUT_MODEL	INFO	[2.2273025512695312, 2.8273305892944336, 10.551189422607422, 19.758804321289062, 1.5942449569702148, 2.9775378704071045, 1200, 0.00019922645137067577]662023-04-01 20:09:21,674	OUTPUT_MODEL	INFO	====> Epoch: 32672023-04-01 20:09:50,188	OUTPUT_MODEL	INFO	====> Epoch: 33682023-04-01 20:10:18,695	OUTPUT_MODEL	INFO	====> Epoch: 34692023-04-01 20:10:25,627	OUTPUT_MODEL	INFO	Train Epoch: 35 [21%]702023-04-01 20:10:25,628	OUTPUT_MODEL	INFO	[1.9143316745758057, 3.0564258098602295, 11.68256950378418, 19.006193161010742, -11.325153350830078, 1.6387269496917725, 1300, 0.00019915175078976256]712023-04-01 20:10:47,726	OUTPUT_MODEL	INFO	====> Epoch: 35722023-04-01 20:11:16,224	OUTPUT_MODEL	INFO	====> Epoch: 36732023-04-01 20:11:40,816	OUTPUT_MODEL	INFO	Train Epoch: 37 [84%]742023-04-01 20:11:40,817	OUTPUT_MODEL	INFO	[2.0267980098724365, 3.114558458328247, 11.208110809326172, 21.545438766479492, 1.3404040336608887, 1.5887115001678467, 1400, 0.0001991019659638112]752023-04-01 20:11:45,362	OUTPUT_MODEL	INFO	====> Epoch: 37762023-04-01 20:12:13,856	OUTPUT_MODEL	INFO	====> Epoch: 38772023-04-01 20:12:42,567	OUTPUT_MODEL	INFO	====> Epoch: 39782023-04-01 20:12:56,917	OUTPUT_MODEL	INFO	Train Epoch: 40 [47%]792023-04-01 20:12:56,918	OUTPUT_MODEL	INFO	[2.335745334625244, 2.798825740814209, 10.016450881958008, 19.950170516967773, 1.5736958980560303, 2.4486825466156006, 1500, 0.0001990273120590905]802023-04-01 20:13:11,647	OUTPUT_MODEL	INFO	====> Epoch: 40812023-04-01 20:13:40,138	OUTPUT_MODEL	INFO	====> Epoch: 41822023-04-01 20:14:08,668	OUTPUT_MODEL	INFO	====> Epoch: 42832023-04-01 20:14:12,745	OUTPUT_MODEL	INFO	Train Epoch: 43 [11%]842023-04-01 20:14:12,746	OUTPUT_MODEL	INFO	[2.075737237930298, 2.675563097000122, 12.081186294555664, 20.160640716552734, 0.18310785293579102, 1.7894562482833862, 1600, 0.00019895268614608487]852023-04-01 20:14:37,782	OUTPUT_MODEL	INFO	====> Epoch: 43862023-04-01 20:15:06,267	OUTPUT_MODEL	INFO	====> Epoch: 44872023-04-01 20:15:27,900	OUTPUT_MODEL	INFO	Train Epoch: 45 [74%]882023-04-01 20:15:27,901	OUTPUT_MODEL	INFO	[2.3112261295318604, 2.6306426525115967, 10.623164176940918, 19.264175415039062, -0.9052133560180664, 2.291731595993042, 1700, 0.00019890295108318404]892023-04-01 20:15:35,381	OUTPUT_MODEL	INFO	====> Epoch: 45902023-04-01 20:16:03,876	OUTPUT_MODEL	INFO	====> Epoch: 46912023-04-01 20:16:32,429	OUTPUT_MODEL	INFO	====> Epoch: 47922023-04-01 20:16:43,864	OUTPUT_MODEL	INFO	Train Epoch: 48 [37%]932023-04-01 20:16:43,865	OUTPUT_MODEL	INFO	[2.161428689956665, 2.740361213684082, 9.265002250671387, 18.804906845092773, -1.0740303993225098, 2.197094678878784, 1800, 0.00019882837179971516]942023-04-01 20:17:01,750	OUTPUT_MODEL	INFO	====> Epoch: 48952023-04-01 20:17:30,215	OUTPUT_MODEL	INFO	====> Epoch: 49962023-04-01 20:17:58,739	OUTPUT_MODEL	INFO	====> Epoch: 50972023-04-01 20:17:59,850	OUTPUT_MODEL	INFO	Train Epoch: 51 [0%]982023-04-01 20:17:59,851	OUTPUT_MODEL	INFO	[2.148890972137451, 2.7295050621032715, 10.641341209411621, 18.238801956176758, -1.2642438411712646, 1.9557304382324219, 1900, 0.00019875382047998183]992023-04-01 20:21:41,236	OUTPUT_MODEL	INFO	{'train': {'log_interval': 100, 'eval_interval': 1000, 'seed': 1234, 'epochs': 10000, 'learning_rate': 0.0002, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 16, 'fp16_run': False, 'lr_decay': 0.999875, 'segment_size': 8192, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'training_files': 'final_annotation_train.txt.cleaned', 'validation_files': 'final_annotation_val.txt.cleaned', 'text_cleaners': ['cjke_cleaners2'], 'max_wav_value': 32768.0, 'sampling_rate': 22050, 'filter_length': 1024, 'hop_length': 256, 'win_length': 1024, 'n_mel_channels': 80, 'mel_fmin': 0.0, 'mel_fmax': None, 'add_blank': True, 'n_speakers': 3, 'cleaned_text': True}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0.1, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [8, 8, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 256}, 'symbols': ['_', ',', '.', '!', '?', '-', '~', '…', 'A', 'E', 'I', 'N', 'O', 'Q', 'U', 'a', 'b', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'r', 's', 't', 'u', 'v', 'w', 'y', 'z', 'ʃ', 'ʧ', 'ʦ', 'ɯ', 'ɹ', 'ə', 'ɥ', '⁼', 'ʰ', '`', '→', '↓', '↑', ' '], 'speakers': {'W': 0, 'specialweek': 1, 'zhongli': 2}, 'model_dir': '././OUTPUT_MODEL', 'max_epochs': 300, 'drop_speaker_embed': True}1002023-04-01 20:21:41,236	OUTPUT_MODEL	WARNING	/root/autodl-tmp/VITS-finetune is not a git repository, therefore hash value comparison will be ignored.1012023-04-01 20:21:46,117	OUTPUT_MODEL	INFO	Loaded checkpoint './pretrained_models/G_0_.pth' (iteration None)1022023-04-01 20:21:46,302	OUTPUT_MODEL	INFO	Loaded checkpoint './pretrained_models/D_0_.pth' (iteration None)1032023-04-01 20:21:49,337	OUTPUT_MODEL	INFO	Train Epoch: 1 [0%]1042023-04-01 20:21:49,337	OUTPUT_MODEL	INFO	[2.4375598430633545, 2.3624346256256104, 12.411884307861328, 29.129026412963867, 1.7119799852371216, 15.800495147705078, 0, 0.0002]1052023-04-01 20:21:51,641	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 1 to ././OUTPUT_MODEL/G_0.pth1062023-04-01 20:21:52,496	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 1 to ././OUTPUT_MODEL/G_latest.pth1072023-04-01 20:22:28,039	OUTPUT_MODEL	INFO	====> Epoch: 11082023-04-01 20:22:57,526	OUTPUT_MODEL	INFO	====> Epoch: 21092023-04-01 20:23:16,153	OUTPUT_MODEL	INFO	Train Epoch: 3 [63%]1102023-04-01 20:23:16,154	OUTPUT_MODEL	INFO	[2.3004679679870605, 2.573570966720581, 9.878453254699707, 19.76036834716797, 1.6178990602493286, 3.690793037414551, 100, 0.000199950003125]1112023-04-01 20:23:26,460	OUTPUT_MODEL	INFO	====> Epoch: 31122023-04-01 20:23:54,742	OUTPUT_MODEL	INFO	====> Epoch: 41132023-04-01 20:24:23,153	OUTPUT_MODEL	INFO	====> Epoch: 51142023-04-01 20:24:31,453	OUTPUT_MODEL	INFO	Train Epoch: 6 [26%]1152023-04-01 20:24:31,454	OUTPUT_MODEL	INFO	[2.316682815551758, 2.6559932231903076, 12.123086929321289, 21.720273971557617, -0.1735425591468811, 3.694751739501953, 200, 0.00019987503124609398]1162023-04-01 20:24:52,200	OUTPUT_MODEL	INFO	====> Epoch: 61172023-04-01 20:25:20,832	OUTPUT_MODEL	INFO	====> Epoch: 71182023-04-01 20:25:47,266	OUTPUT_MODEL	INFO	Train Epoch: 8 [89%]1192023-04-01 20:25:47,267	OUTPUT_MODEL	INFO	[1.9829189777374268, 3.1194260120391846, 12.70658016204834, 21.909568786621094, -11.380332946777344, 3.263878345489502, 300, 0.00019982506561132978]1202023-04-01 20:25:50,308	OUTPUT_MODEL	INFO	====> Epoch: 81212023-04-01 20:26:18,583	OUTPUT_MODEL	INFO	====> Epoch: 91222023-04-01 20:26:46,866	OUTPUT_MODEL	INFO	====> Epoch: 101232023-04-01 20:27:02,609	OUTPUT_MODEL	INFO	Train Epoch: 11 [53%]1242023-04-01 20:27:02,610	OUTPUT_MODEL	INFO	[2.3107752799987793, 2.5289764404296875, 11.249608039855957, 20.733383178710938, 1.6141700744628906, 3.217594861984253, 400, 0.00019975014057813518]1252023-04-01 20:27:15,854	OUTPUT_MODEL	INFO	====> Epoch: 111262023-04-01 20:27:44,107	OUTPUT_MODEL	INFO	====> Epoch: 121272023-04-01 20:28:12,345	OUTPUT_MODEL	INFO	====> Epoch: 131282023-04-01 20:28:17,781	OUTPUT_MODEL	INFO	Train Epoch: 14 [16%]1292023-04-01 20:28:17,782	OUTPUT_MODEL	INFO	[2.1659035682678223, 2.6708106994628906, 10.741387367248535, 21.08696174621582, -9.378087997436523, 2.377328872680664, 500, 0.00019967524363831608]1302023-04-01 20:28:41,700	OUTPUT_MODEL	INFO	====> Epoch: 141312023-04-01 20:29:09,985	OUTPUT_MODEL	INFO	====> Epoch: 151322023-04-01 20:29:32,985	OUTPUT_MODEL	INFO	Train Epoch: 16 [79%]1332023-04-01 20:29:32,986	OUTPUT_MODEL	INFO	[1.9090330600738525, 3.3202145099639893, 12.73327922821045, 21.87517738342285, -11.954466819763184, 2.3047335147857666, 600, 0.00019962532794733217]1342023-04-01 20:29:38,922	OUTPUT_MODEL	INFO	====> Epoch: 161352023-04-01 20:30:07,226	OUTPUT_MODEL	INFO	====> Epoch: 171362023-04-01 20:30:35,441	OUTPUT_MODEL	INFO	====> Epoch: 181372023-04-01 20:30:48,193	OUTPUT_MODEL	INFO	Train Epoch: 19 [42%]1382023-04-01 20:30:48,194	OUTPUT_MODEL	INFO	[2.1797142028808594, 2.782947063446045, 10.988595008850098, 20.78213119506836, -1.6678411960601807, 2.221092462539673, 700, 0.00019955047780639926]1392023-04-01 20:31:04,365	OUTPUT_MODEL	INFO	====> Epoch: 191402023-04-01 20:31:32,609	OUTPUT_MODEL	INFO	====> Epoch: 201412023-04-01 20:32:00,890	OUTPUT_MODEL	INFO	====> Epoch: 211422023-04-01 20:32:03,398	OUTPUT_MODEL	INFO	Train Epoch: 22 [5%]1432023-04-01 20:32:03,399	OUTPUT_MODEL	INFO	[2.4440159797668457, 2.707535743713379, 9.90103530883789, 19.83087921142578, -2.4169583320617676, 3.132272958755493, 800, 0.00019947565573076072]1442023-04-01 20:32:29,987	OUTPUT_MODEL	INFO	====> Epoch: 221452023-04-01 20:32:58,282	OUTPUT_MODEL	INFO	====> Epoch: 231462023-04-01 20:33:18,336	OUTPUT_MODEL	INFO	Train Epoch: 24 [68%]1472023-04-01 20:33:18,337	OUTPUT_MODEL	INFO	[2.3530569076538086, 2.549492597579956, 12.166970252990723, 20.932912826538086, 1.1648480892181396, 3.304389238357544, 900, 0.00019942578993363514]1482023-04-01 20:33:27,298	OUTPUT_MODEL	INFO	====> Epoch: 241492023-04-01 20:33:55,677	OUTPUT_MODEL	INFO	====> Epoch: 251502023-04-01 20:34:23,959	OUTPUT_MODEL	INFO	====> Epoch: 261512023-04-01 20:34:33,852	OUTPUT_MODEL	INFO	Train Epoch: 27 [32%]1522023-04-01 20:34:33,853	OUTPUT_MODEL	INFO	[2.1642932891845703, 2.4612655639648438, 12.356361389160156, 20.548171997070312, -3.9624850749969482, 2.1475045680999756, 1000, 0.00019935101461010442]1532023-04-01 20:34:35,527	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 27 to ././OUTPUT_MODEL/G_1000.pth1542023-04-01 20:34:35,849	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 27 to ././OUTPUT_MODEL/G_latest.pth1552023-04-01 20:34:54,592	OUTPUT_MODEL	INFO	====> Epoch: 271562023-04-01 20:35:22,946	OUTPUT_MODEL	INFO	====> Epoch: 281572023-04-01 20:35:50,252	OUTPUT_MODEL	INFO	Train Epoch: 29 [95%]1582023-04-01 20:35:50,253	OUTPUT_MODEL	INFO	[2.3261852264404297, 2.744123935699463, 8.713574409484863, 18.628137588500977, 1.7040754556655884, 2.576793909072876, 1100, 0.0001993011799713115]1592023-04-01 20:35:51,929	OUTPUT_MODEL	INFO	====> Epoch: 291602023-04-01 20:36:20,239	OUTPUT_MODEL	INFO	====> Epoch: 301612023-04-01 20:36:48,592	OUTPUT_MODEL	INFO	====> Epoch: 311622023-04-01 20:37:05,733	OUTPUT_MODEL	INFO	Train Epoch: 32 [58%]1632023-04-01 20:37:05,734	OUTPUT_MODEL	INFO	[2.2347471714019775, 2.6439948081970215, 10.143767356872559, 20.319557189941406, 1.5722490549087524, 2.9286253452301025, 1200, 0.00019922645137067577]1642023-04-01 20:37:17,505	OUTPUT_MODEL	INFO	====> Epoch: 321652023-04-01 20:37:45,760	OUTPUT_MODEL	INFO	====> Epoch: 331662023-04-01 20:38:13,950	OUTPUT_MODEL	INFO	====> Epoch: 341672023-04-01 20:38:20,843	OUTPUT_MODEL	INFO	Train Epoch: 35 [21%]1682023-04-01 20:38:20,844	OUTPUT_MODEL	INFO	[2.0306572914123535, 2.7175259590148926, 11.321948051452637, 19.064626693725586, -11.772246360778809, 1.5952112674713135, 1300, 0.00019915175078976256]1692023-04-01 20:38:42,834	OUTPUT_MODEL	INFO	====> Epoch: 351702023-04-01 20:39:11,109	OUTPUT_MODEL	INFO	====> Epoch: 361712023-04-01 20:39:35,457	OUTPUT_MODEL	INFO	Train Epoch: 37 [84%]1722023-04-01 20:39:35,458	OUTPUT_MODEL	INFO	[2.1177778244018555, 3.10746169090271, 11.059700965881348, 21.63502311706543, 1.3195078372955322, 1.4998723268508911, 1400, 0.0001991019659638112]1732023-04-01 20:39:39,908	OUTPUT_MODEL	INFO	====> Epoch: 371742023-04-01 20:40:08,225	OUTPUT_MODEL	INFO	====> Epoch: 381752023-04-01 20:40:36,574	OUTPUT_MODEL	INFO	====> Epoch: 391762023-04-01 20:40:50,829	OUTPUT_MODEL	INFO	Train Epoch: 40 [47%]1772023-04-01 20:40:50,830	OUTPUT_MODEL	INFO	[2.2306501865386963, 2.8473596572875977, 10.019280433654785, 20.41650390625, 1.6591042280197144, 2.4784228801727295, 1500, 0.0001990273120590905]1782023-04-01 20:41:06,532	OUTPUT_MODEL	INFO	====> Epoch: 401792023-04-01 20:41:36,120	OUTPUT_MODEL	INFO	====> Epoch: 411802023-04-01 20:42:04,321	OUTPUT_MODEL	INFO	====> Epoch: 421812023-04-01 20:42:08,341	OUTPUT_MODEL	INFO	Train Epoch: 43 [11%]1822023-04-01 20:42:08,342	OUTPUT_MODEL	INFO	[2.001770257949829, 2.9447221755981445, 12.044673919677734, 20.553495407104492, 0.1577376127243042, 1.7922543287277222, 1600, 0.00019895268614608487]1832023-04-01 20:42:33,140	OUTPUT_MODEL	INFO	====> Epoch: 431842023-04-01 20:43:01,374	OUTPUT_MODEL	INFO	====> Epoch: 441852023-04-01 20:43:22,857	OUTPUT_MODEL	INFO	Train Epoch: 45 [74%]1862023-04-01 20:43:22,858	OUTPUT_MODEL	INFO	[2.1759135723114014, 2.8011791706085205, 10.697421073913574, 19.67866325378418, -0.9190690517425537, 2.2757043838500977, 1700, 0.00019890295108318404]1872023-04-01 20:43:30,271	OUTPUT_MODEL	INFO	====> Epoch: 451882023-04-01 20:43:58,496	OUTPUT_MODEL	INFO	====> Epoch: 461892023-04-01 20:44:26,694	OUTPUT_MODEL	INFO	====> Epoch: 471902023-04-01 20:44:37,989	OUTPUT_MODEL	INFO	Train Epoch: 48 [37%]1912023-04-01 20:44:37,990	OUTPUT_MODEL	INFO	[2.01068115234375, 3.0750083923339844, 9.949893951416016, 19.216224670410156, -1.092572569847107, 2.2098004817962646, 1800, 0.00019882837179971516]1922023-04-01 20:44:55,704	OUTPUT_MODEL	INFO	====> Epoch: 481932023-04-01 20:45:23,939	OUTPUT_MODEL	INFO	====> Epoch: 491942023-04-01 20:45:52,162	OUTPUT_MODEL	INFO	====> Epoch: 501952023-04-01 20:45:53,249	OUTPUT_MODEL	INFO	Train Epoch: 51 [0%]1962023-04-01 20:45:53,250	OUTPUT_MODEL	INFO	[2.1125893592834473, 2.552051305770874, 10.734039306640625, 18.52950668334961, -1.2038230895996094, 1.9616706371307373, 1900, 0.00019875382047998183]1972023-04-01 20:46:20,962	OUTPUT_MODEL	INFO	====> Epoch: 511982023-04-01 20:46:49,256	OUTPUT_MODEL	INFO	====> Epoch: 521992023-04-01 20:47:07,819	OUTPUT_MODEL	INFO	Train Epoch: 53 [63%]2002023-04-01 20:47:07,820	OUTPUT_MODEL	INFO	[2.532742500305176, 2.2387194633483887, 8.750190734863281, 16.344234466552734, 1.6563026905059814, 2.8147976398468018, 2000, 0.00019870413513039026]2012023-04-01 20:47:09,386	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 53 to ././OUTPUT_MODEL/G_2000.pth2022023-04-01 20:47:09,665	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 53 to ././OUTPUT_MODEL/G_latest.pth2032023-04-01 20:47:19,560	OUTPUT_MODEL	INFO	====> Epoch: 532042023-04-01 20:47:47,788	OUTPUT_MODEL	INFO	====> Epoch: 542052023-04-01 20:48:16,012	OUTPUT_MODEL	INFO	====> Epoch: 552062023-04-01 20:48:24,302	OUTPUT_MODEL	INFO	Train Epoch: 56 [26%]2072023-04-01 20:48:24,303	OUTPUT_MODEL	INFO	[2.216426372528076, 2.8888823986053467, 13.85486125946045, 20.348722457885742, -0.6113383769989014, 3.0847461223602295, 2100, 0.00019862963039358455]2082023-04-01 20:48:45,114	OUTPUT_MODEL	INFO	====> Epoch: 562092023-04-01 20:49:13,365	OUTPUT_MODEL	INFO	====> Epoch: 572102023-04-01 20:49:39,241	OUTPUT_MODEL	INFO	Train Epoch: 58 [89%]2112023-04-01 20:49:39,242	OUTPUT_MODEL	INFO	[1.6626222133636475, 3.210665225982666, 13.894440650939941, 19.891311645507812, -11.80707836151123, 1.8686481714248657, 2200, 0.0001985799760895741]2122023-04-01 20:49:42,228	OUTPUT_MODEL	INFO	====> Epoch: 582132023-04-01 20:50:10,481	OUTPUT_MODEL	INFO	====> Epoch: 592142023-04-01 20:50:38,702	OUTPUT_MODEL	INFO	====> Epoch: 602152023-04-01 20:50:54,398	OUTPUT_MODEL	INFO	Train Epoch: 61 [53%]2162023-04-01 20:50:54,399	OUTPUT_MODEL	INFO	[2.2988102436065674, 2.772601366043091, 10.960488319396973, 20.549671173095703, 1.5968568325042725, 3.0915069580078125, 2300, 0.000198505517906589]2172023-04-01 20:51:07,620	OUTPUT_MODEL	INFO	====> Epoch: 612182023-04-01 20:51:35,848	OUTPUT_MODEL	INFO	====> Epoch: 622192023-04-01 20:52:04,164	OUTPUT_MODEL	INFO	====> Epoch: 632202023-04-01 20:52:09,601	OUTPUT_MODEL	INFO	Train Epoch: 64 [16%]2212023-04-01 20:52:09,602	OUTPUT_MODEL	INFO	[1.9010006189346313, 2.798306703567505, 12.567076683044434, 19.431026458740234, -11.987998962402344, 2.368818998336792, 2400, 0.00019843108764193245]2222023-04-01 20:52:33,206	OUTPUT_MODEL	INFO	====> Epoch: 642232023-04-01 20:53:01,426	OUTPUT_MODEL	INFO	====> Epoch: 652242023-04-01 20:53:24,331	OUTPUT_MODEL	INFO	Train Epoch: 66 [79%]2252023-04-01 20:53:24,332	OUTPUT_MODEL	INFO	[1.7727984189987183, 3.2705061435699463, 12.106109619140625, 19.250953674316406, -12.490021705627441, 2.039381980895996, 2500, 0.00019838148297050769]2262023-04-01 20:53:30,486	OUTPUT_MODEL	INFO	====> Epoch: 662272023-04-01 20:53:59,032	OUTPUT_MODEL	INFO	====> Epoch: 672282023-04-01 20:54:27,858	OUTPUT_MODEL	INFO	====> Epoch: 682292023-04-01 20:54:40,686	OUTPUT_MODEL	INFO	Train Epoch: 69 [42%]2302023-04-01 20:54:40,687	OUTPUT_MODEL	INFO	[2.105959415435791, 3.1132960319519043, 10.637681007385254, 17.871028900146484, -2.7587201595306396, 1.6874209642410278, 2600, 0.0001983070992131383]2312023-04-01 20:54:56,852	OUTPUT_MODEL	INFO	====> Epoch: 692322023-04-01 20:55:25,153	OUTPUT_MODEL	INFO	====> Epoch: 702332023-04-01 20:55:53,460	OUTPUT_MODEL	INFO	====> Epoch: 712342023-04-01 20:55:55,976	OUTPUT_MODEL	INFO	Train Epoch: 72 [5%]2352023-04-01 20:55:55,977	OUTPUT_MODEL	INFO	[2.259666919708252, 2.9097671508789062, 11.962706565856934, 20.395341873168945, -2.6158740520477295, 3.0627148151397705, 2700, 0.0001982327433461913]2362023-04-01 20:56:22,417	OUTPUT_MODEL	INFO	====> Epoch: 722372023-04-01 20:56:50,894	OUTPUT_MODEL	INFO	====> Epoch: 732382023-04-01 20:57:10,987	OUTPUT_MODEL	INFO	Train Epoch: 74 [68%]2392023-04-01 20:57:10,988	OUTPUT_MODEL	INFO	[2.3592357635498047, 2.5142979621887207, 12.231461524963379, 19.440689086914062, 1.1374359130859375, 3.2891640663146973, 2800, 0.00019818318825774137]2402023-04-01 20:57:19,869	OUTPUT_MODEL	INFO	====> Epoch: 742412023-04-01 20:57:48,210	OUTPUT_MODEL	INFO	====> Epoch: 752422023-04-01 20:58:16,490	OUTPUT_MODEL	INFO	====> Epoch: 762432023-04-01 20:58:26,333	OUTPUT_MODEL	INFO	Train Epoch: 77 [32%]2442023-04-01 20:58:26,334	OUTPUT_MODEL	INFO	[1.9153430461883545, 3.012155771255493, 14.383950233459473, 21.450504302978516, -3.789599895477295, 2.002673387527466, 2900, 0.00019810887885159456]2452023-04-01 20:58:45,429	OUTPUT_MODEL	INFO	====> Epoch: 772462023-04-01 20:59:13,705	OUTPUT_MODEL	INFO	====> Epoch: 782472023-04-01 20:59:41,105	OUTPUT_MODEL	INFO	Train Epoch: 79 [95%]2482023-04-01 20:59:41,106	OUTPUT_MODEL	INFO	[2.2756524085998535, 2.8459408283233643, 8.687479019165039, 18.669836044311523, 1.703197717666626, 2.655886650085449, 3000, 0.00019805935472733287]2492023-04-01 20:59:42,671	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 79 to ././OUTPUT_MODEL/G_3000.pth2502023-04-01 20:59:42,955	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 79 to ././OUTPUT_MODEL/G_latest.pth2512023-04-01 20:59:44,091	OUTPUT_MODEL	INFO	====> Epoch: 792522023-04-01 21:00:12,371	OUTPUT_MODEL	INFO	====> Epoch: 802532023-04-01 21:00:40,755	OUTPUT_MODEL	INFO	====> Epoch: 812542023-04-01 21:00:57,883	OUTPUT_MODEL	INFO	Train Epoch: 82 [58%]2552023-04-01 21:00:57,884	OUTPUT_MODEL	INFO	[2.0532608032226562, 2.9153032302856445, 11.187215805053711, 20.76382064819336, 1.5815839767456055, 2.883345603942871, 3100, 0.00019798509175295552]2562023-04-01 21:01:09,675	OUTPUT_MODEL	INFO	====> Epoch: 822572023-04-01 21:01:37,951	OUTPUT_MODEL	INFO	====> Epoch: 832582023-04-01 21:02:06,221	OUTPUT_MODEL	INFO	====> Epoch: 842592023-04-01 21:02:13,113	OUTPUT_MODEL	INFO	Train Epoch: 85 [21%]2602023-04-01 21:02:13,114	OUTPUT_MODEL	INFO	[1.643869161605835, 3.233929395675659, 11.687270164489746, 17.910696029663086, -13.064292907714844, 1.5001578330993652, 3200, 0.00019791085662371262]2612023-04-01 21:02:35,074	OUTPUT_MODEL	INFO	====> Epoch: 852622023-04-01 21:03:03,295	OUTPUT_MODEL	INFO	====> Epoch: 862632023-04-01 21:03:27,700	OUTPUT_MODEL	INFO	Train Epoch: 87 [84%]2642023-04-01 21:03:27,701	OUTPUT_MODEL	INFO	[2.145949602127075, 2.9439826011657715, 9.532683372497559, 19.49867057800293, 1.2903923988342285, 1.6686525344848633, 3300, 0.0001978613820019138]2652023-04-01 21:03:32,160	OUTPUT_MODEL	INFO	====> Epoch: 872662023-04-01 21:04:00,401	OUTPUT_MODEL	INFO	====> Epoch: 882672023-04-01 21:04:28,621	OUTPUT_MODEL	INFO	====> Epoch: 892682023-04-01 21:04:42,821	OUTPUT_MODEL	INFO	Train Epoch: 90 [47%]2692023-04-01 21:04:42,822	OUTPUT_MODEL	INFO	[2.2133443355560303, 2.801147937774658, 10.252163887023926, 18.677053451538086, 1.6001298427581787, 2.3371832370758057, 3400, 0.0001977871932580289]2702023-04-01 21:04:57,668	OUTPUT_MODEL	INFO	====> Epoch: 902712023-04-01 21:05:25,935	OUTPUT_MODEL	INFO	====> Epoch: 912722023-04-01 21:05:54,540	OUTPUT_MODEL	INFO	====> Epoch: 922732023-04-01 21:05:58,865	OUTPUT_MODEL	INFO	Train Epoch: 93 [11%]2742023-04-01 21:05:58,865	OUTPUT_MODEL	INFO	[1.9969345331192017, 2.923940896987915, 11.813675880432129, 19.107725143432617, 0.1933351755142212, 1.7891744375228882, 3500, 0.0001977130323314455]2752023-04-01 21:06:24,588	OUTPUT_MODEL	INFO	====> Epoch: 932762023-04-01 21:06:52,840	OUTPUT_MODEL	INFO	====> Epoch: 942772023-04-01 21:07:14,264	OUTPUT_MODEL	INFO	Train Epoch: 95 [74%]2782023-04-01 21:07:14,265	OUTPUT_MODEL	INFO	[2.3439600467681885, 2.5634207725524902, 7.46201753616333, 15.348529815673828, -1.0369162559509277, 1.9235759973526, 3600, 0.00019766360716262876]2792023-04-01 21:07:21,666	OUTPUT_MODEL	INFO	====> Epoch: 952802023-04-01 21:07:49,900	OUTPUT_MODEL	INFO	====> Epoch: 962812023-04-01 21:08:18,208	OUTPUT_MODEL	INFO	====> Epoch: 972822023-04-01 21:08:29,527	OUTPUT_MODEL	INFO	Train Epoch: 98 [37%]2832023-04-01 21:08:29,528	OUTPUT_MODEL	INFO	[2.0122194290161133, 3.1866912841796875, 11.290575981140137, 19.412662506103516, -1.5466058254241943, 1.9937984943389893, 3700, 0.0001975894925750383]2842023-04-01 21:08:47,332	OUTPUT_MODEL	INFO	====> Epoch: 982852023-04-01 21:09:15,656	OUTPUT_MODEL	INFO	====> Epoch: 992862023-04-01 21:09:43,943	OUTPUT_MODEL	INFO	====> Epoch: 1002872023-04-01 21:09:45,126	OUTPUT_MODEL	INFO	Train Epoch: 101 [0%]2882023-04-01 21:09:45,126	OUTPUT_MODEL	INFO	[1.8743896484375, 2.996459722518921, 13.618461608886719, 17.853689193725586, -1.4698283672332764, 1.9548090696334839, 3800, 0.00019751540577694416]2892023-04-01 21:10:13,163	OUTPUT_MODEL	INFO	====> Epoch: 1012902023-04-01 21:10:41,436	OUTPUT_MODEL	INFO	====> Epoch: 1022912023-04-01 21:11:00,019	OUTPUT_MODEL	INFO	Train Epoch: 103 [63%]2922023-04-01 21:11:00,020	OUTPUT_MODEL	INFO	[2.1118063926696777, 2.8113186359405518, 12.235113143920898, 18.980497360229492, 1.6438294649124146, 2.938556671142578, 3900, 0.00019746603001167813]2932023-04-01 21:11:10,326	OUTPUT_MODEL	INFO	====> Epoch: 1032942023-04-01 21:11:38,595	OUTPUT_MODEL	INFO	====> Epoch: 1042952023-04-01 21:12:07,396	OUTPUT_MODEL	INFO	====> Epoch: 1052962023-04-01 21:12:15,912	OUTPUT_MODEL	INFO	Train Epoch: 106 [26%]2972023-04-01 21:12:15,913	OUTPUT_MODEL	INFO	[1.8586927652359009, 3.3810672760009766, 13.343268394470215, 20.137205123901367, -0.4417956471443176, 2.6269264221191406, 4000, 0.0001973919895062582]2982023-04-01 21:12:17,618	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 106 to ././OUTPUT_MODEL/G_4000.pth2992023-04-01 21:12:18,093	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 106 to ././OUTPUT_MODEL/G_latest.pth3002023-04-01 21:12:38,618	OUTPUT_MODEL	INFO	====> Epoch: 1063012023-04-01 21:13:07,328	OUTPUT_MODEL	INFO	====> Epoch: 1073022023-04-01 21:13:33,624	OUTPUT_MODEL	INFO	Train Epoch: 108 [89%]3032023-04-01 21:13:33,624	OUTPUT_MODEL	INFO	[1.6505424976348877, 2.9870612621307373, 13.03627872467041, 18.783489227294922, -10.146822929382324, 2.032058000564575, 4100, 0.00019734264459313146]3042023-04-01 21:13:36,700	OUTPUT_MODEL	INFO	====> Epoch: 1083052023-04-01 21:14:05,413	OUTPUT_MODEL	INFO	====> Epoch: 1093062023-04-01 21:14:34,201	OUTPUT_MODEL	INFO	====> Epoch: 1103072023-04-01 21:14:50,230	OUTPUT_MODEL	INFO	Train Epoch: 111 [53%]3082023-04-01 21:14:50,231	OUTPUT_MODEL	INFO	[2.3677585124969482, 2.783352851867676, 11.805437088012695, 19.111225128173828, 1.6201564073562622, 2.9434289932250977, 4200, 0.00019726865035146003]3092023-04-01 21:15:03,620	OUTPUT_MODEL	INFO	====> Epoch: 1113102023-04-01 21:15:32,331	OUTPUT_MODEL	INFO	====> Epoch: 1123112023-04-01 21:16:00,926	OUTPUT_MODEL	INFO	====> Epoch: 1133122023-04-01 21:16:06,534	OUTPUT_MODEL	INFO	Train Epoch: 114 [16%]3132023-04-01 21:16:06,535	OUTPUT_MODEL	INFO	[1.6243027448654175, 3.134901523590088, 13.659550666809082, 19.221235275268555, -12.278924942016602, 2.404970645904541, 4300, 0.0001971946838541609]3142023-04-01 21:16:30,145	OUTPUT_MODEL	INFO	====> Epoch: 1143152023-04-01 21:16:59,048	OUTPUT_MODEL	INFO	====> Epoch: 1153162023-04-01 21:17:22,920	OUTPUT_MODEL	INFO	Train Epoch: 116 [79%]3172023-04-01 21:17:22,921	OUTPUT_MODEL	INFO	[1.651923656463623, 3.175049066543579, 12.224478721618652, 18.135395050048828, -12.968050003051758, 1.6472457647323608, 4400, 0.00019714538826436426]3182023-04-01 21:17:29,051	OUTPUT_MODEL	INFO	====> Epoch: 1163192023-04-01 21:17:57,853	OUTPUT_MODEL	INFO	====> Epoch: 1173202023-04-01 21:18:26,468	OUTPUT_MODEL	INFO	====> Epoch: 1183212023-04-01 21:18:39,415	OUTPUT_MODEL	INFO	Train Epoch: 119 [42%]3222023-04-01 21:18:39,416	OUTPUT_MODEL	INFO	[2.016754627227783, 3.1086857318878174, 11.541909217834473, 19.65251922607422, -2.6304268836975098, 1.5623911619186401, 4500, 0.0001970714679845701]3232023-04-01 21:18:55,740	OUTPUT_MODEL	INFO	====> Epoch: 1193242023-04-01 21:19:24,367	OUTPUT_MODEL	INFO	====> Epoch: 1203252023-04-01 21:19:52,998	OUTPUT_MODEL	INFO	====> Epoch: 1213262023-04-01 21:19:55,646	OUTPUT_MODEL	INFO	Train Epoch: 122 [5%]3272023-04-01 21:19:55,647	OUTPUT_MODEL	INFO	[2.361518383026123, 2.496669292449951, 7.626200199127197, 16.623342514038086, -2.9150681495666504, 2.8930749893188477, 4600, 0.000196997575421416]3282023-04-01 21:20:22,285	OUTPUT_MODEL	INFO	====> Epoch: 1223292023-04-01 21:20:51,076	OUTPUT_MODEL	INFO	====> Epoch: 1233302023-04-01 21:21:11,368	OUTPUT_MODEL	INFO	Train Epoch: 124 [68%]3312023-04-01 21:21:11,369	OUTPUT_MODEL	INFO	[2.2961606979370117, 2.6525673866271973, 11.420563697814941, 17.905733108520508, 1.131430745124817, 3.2383358478546143, 4700, 0.00019694832910564775]3322023-04-01 21:21:20,491	OUTPUT_MODEL	INFO	====> Epoch: 1243332023-04-01 21:21:49,122	OUTPUT_MODEL	INFO	====> Epoch: 1253342023-04-01 21:22:18,266	OUTPUT_MODEL	INFO	====> Epoch: 1263352023-04-01 21:22:28,230	OUTPUT_MODEL	INFO	Train Epoch: 127 [32%]3362023-04-01 21:22:28,231	OUTPUT_MODEL	INFO	[1.6137442588806152, 3.2500104904174805, 16.020240783691406, 21.62045669555664, -4.596685886383057, 1.8337711095809937, 4800, 0.0001968744827138014]3372023-04-01 21:22:47,584	OUTPUT_MODEL	INFO	====> Epoch: 1273382023-04-01 21:23:16,135	OUTPUT_MODEL	INFO	====> Epoch: 1283392023-04-01 21:23:43,800	OUTPUT_MODEL	INFO	Train Epoch: 129 [95%]3402023-04-01 21:23:43,800	OUTPUT_MODEL	INFO	[2.293550491333008, 2.675025701522827, 10.056646347045898, 17.6656436920166, 1.6982519626617432, 2.494636058807373, 4900, 0.00019682526716928672]3412023-04-01 21:23:45,425	OUTPUT_MODEL	INFO	====> Epoch: 1293422023-04-01 21:24:14,107	OUTPUT_MODEL	INFO	====> Epoch: 1303432023-04-01 21:24:42,666	OUTPUT_MODEL	INFO	====> Epoch: 1313442023-04-01 21:25:00,471	OUTPUT_MODEL	INFO	Train Epoch: 132 [58%]3452023-04-01 21:25:00,472	OUTPUT_MODEL	INFO	[2.2363390922546387, 2.6870620250701904, 10.713981628417969, 17.778270721435547, 1.5524137020111084, 2.671760082244873, 5000, 0.00019675146691989817]3462023-04-01 21:25:02,309	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 132 to ././OUTPUT_MODEL/G_5000.pth3472023-04-01 21:25:02,591	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 132 to ././OUTPUT_MODEL/G_latest.pth3482023-04-01 21:25:14,210	OUTPUT_MODEL	INFO	====> Epoch: 1323492023-04-01 21:25:43,930	OUTPUT_MODEL	INFO	====> Epoch: 1333502023-04-01 21:26:13,566	OUTPUT_MODEL	INFO	====> Epoch: 1343512023-04-01 21:26:20,826	OUTPUT_MODEL	INFO	Train Epoch: 135 [21%]3522023-04-01 21:26:20,828	OUTPUT_MODEL	INFO	[1.6733953952789307, 3.365739107131958, 11.957690238952637, 17.09334373474121, -12.619682312011719, 1.4618717432022095, 5100, 0.00019667769434214392]3532023-04-01 21:26:43,556	OUTPUT_MODEL	INFO	====> Epoch: 1353542023-04-01 21:27:12,276	OUTPUT_MODEL	INFO	====> Epoch: 1363552023-04-01 21:27:37,052	OUTPUT_MODEL	INFO	Train Epoch: 137 [84%]3562023-04-01 21:27:37,053	OUTPUT_MODEL	INFO	[1.8592383861541748, 3.4546754360198975, 11.757536888122559, 19.513423919677734, 1.2718679904937744, 1.5284785032272339, 5200, 0.00019662852799164733]3572023-04-01 21:27:41,579	OUTPUT_MODEL	INFO	====> Epoch: 1373582023-04-02 08:03:55,666	OUTPUT_MODEL	INFO	{'train': {'log_interval': 100, 'eval_interval': 1000, 'seed': 1234, 'epochs': 10000, 'learning_rate': 0.0002, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 16, 'fp16_run': True, 'lr_decay': 0.999875, 'segment_size': 8192, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'training_files': 'final_annotation_train.txt.cleaned', 'validation_files': 'final_annotation_val.txt.cleaned', 'text_cleaners': ['cjke_cleaners2'], 'max_wav_value': 32768.0, 'sampling_rate': 22050, 'filter_length': 1024, 'hop_length': 256, 'win_length': 1024, 'n_mel_channels': 80, 'mel_fmin': 0.0, 'mel_fmax': None, 'add_blank': True, 'n_speakers': 3, 'cleaned_text': True}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0.1, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [8, 8, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 256}, 'symbols': ['_', ',', '.', '!', '?', '-', '~', '…', 'N', 'Q', 'a', 'b', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', 'ɑ', 'æ', 'ʃ', 'ʑ', 'ç', 'ɯ', 'ɪ', 'ɔ', 'ɛ', 'ɹ', 'ð', 'ə', 'ɫ', 'ɥ', 'ɸ', 'ʊ', 'ɾ', 'ʒ', 'θ', 'β', 'ŋ', 'ɦ', '⁼', 'ʰ', '`', '^', '#', '*', '=', 'ˈ', 'ˌ', '→', '↓', '↑', ' '], 'speakers': {'嵯峨': 0, 'specialweek': 1, 'zhongli': 2}, 'model_dir': '././OUTPUT_MODEL', 'max_epochs': 300, 'drop_speaker_embed': True}3592023-04-02 08:03:55,666	OUTPUT_MODEL	WARNING	/root/autodl-tmp/VITS-finetune is not a git repository, therefore hash value comparison will be ignored.3602023-04-02 08:05:34,240	OUTPUT_MODEL	INFO	{'train': {'log_interval': 100, 'eval_interval': 1000, 'seed': 1234, 'epochs': 10000, 'learning_rate': 0.0002, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 16, 'fp16_run': True, 'lr_decay': 0.999875, 'segment_size': 8192, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'training_files': 'final_annotation_train.txt.cleaned', 'validation_files': 'final_annotation_val.txt.cleaned', 'text_cleaners': ['cjke_cleaners2'], 'max_wav_value': 32768.0, 'sampling_rate': 22050, 'filter_length': 1024, 'hop_length': 256, 'win_length': 1024, 'n_mel_channels': 80, 'mel_fmin': 0.0, 'mel_fmax': None, 'add_blank': True, 'n_speakers': 3, 'cleaned_text': True}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0.1, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [8, 8, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 256}, 'symbols': ['_', ',', '.', '!', '?', '-', '~', '…', 'A', 'E', 'I', 'N', 'O', 'Q', 'U', 'a', 'b', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'r', 's', 't', 'u', 'v', 'w', 'y', 'z', 'ʃ', 'ʧ', 'ʦ', 'ɯ', 'ɹ', 'ə', 'ɥ', '⁼', 'ʰ', '`', '→', '↓', '↑', ' '], 'speakers': {'嵯峨': 0, 'specialweek': 1, 'zhongli': 2}, 'model_dir': '././OUTPUT_MODEL', 'max_epochs': 100, 'drop_speaker_embed': True}3612023-04-02 08:05:34,240	OUTPUT_MODEL	WARNING	/root/autodl-tmp/VITS-finetune is not a git repository, therefore hash value comparison will be ignored.3622023-04-02 08:05:39,195	OUTPUT_MODEL	INFO	Loaded checkpoint './pretrained_models/G_0_.pth' (iteration None)3632023-04-02 08:05:39,365	OUTPUT_MODEL	INFO	Loaded checkpoint './pretrained_models/D_0_.pth' (iteration None)3642023-04-02 08:05:51,798	OUTPUT_MODEL	INFO	{'train': {'log_interval': 100, 'eval_interval': 1000, 'seed': 1234, 'epochs': 10000, 'learning_rate': 0.0002, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 16, 'fp16_run': False, 'lr_decay': 0.999875, 'segment_size': 8192, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'training_files': 'final_annotation_train.txt.cleaned', 'validation_files': 'final_annotation_val.txt.cleaned', 'text_cleaners': ['cjke_cleaners2'], 'max_wav_value': 32768.0, 'sampling_rate': 22050, 'filter_length': 1024, 'hop_length': 256, 'win_length': 1024, 'n_mel_channels': 80, 'mel_fmin': 0.0, 'mel_fmax': None, 'add_blank': True, 'n_speakers': 3, 'cleaned_text': True}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0.1, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [8, 8, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 256}, 'symbols': ['_', ',', '.', '!', '?', '-', '~', '…', 'A', 'E', 'I', 'N', 'O', 'Q', 'U', 'a', 'b', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'r', 's', 't', 'u', 'v', 'w', 'y', 'z', 'ʃ', 'ʧ', 'ʦ', 'ɯ', 'ɹ', 'ə', 'ɥ', '⁼', 'ʰ', '`', '→', '↓', '↑', ' '], 'speakers': {'嵯峨': 0, 'specialweek': 1, 'zhongli': 2}, 'model_dir': '././OUTPUT_MODEL', 'max_epochs': 100, 'drop_speaker_embed': True}3652023-04-02 08:05:51,798	OUTPUT_MODEL	WARNING	/root/autodl-tmp/VITS-finetune is not a git repository, therefore hash value comparison will be ignored.3662023-04-02 08:05:56,712	OUTPUT_MODEL	INFO	Loaded checkpoint './pretrained_models/G_0_.pth' (iteration None)3672023-04-02 08:05:56,881	OUTPUT_MODEL	INFO	Loaded checkpoint './pretrained_models/D_0_.pth' (iteration None)3682023-04-02 08:06:00,326	OUTPUT_MODEL	INFO	Train Epoch: 1 [0%]3692023-04-02 08:06:00,327	OUTPUT_MODEL	INFO	[2.593557357788086, 2.796135425567627, 10.371471405029297, 24.40696144104004, 1.3767321109771729, 13.33885383605957, 0, 0.0002]3702023-04-02 08:06:02,829	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 1 to ././OUTPUT_MODEL/G_0.pth3712023-04-02 08:06:03,812	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 1 to ././OUTPUT_MODEL/G_latest.pth3722023-04-02 08:06:54,426	OUTPUT_MODEL	INFO	====> Epoch: 13732023-04-02 08:07:30,608	OUTPUT_MODEL	INFO	Train Epoch: 2 [85%]3742023-04-02 08:07:30,609	OUTPUT_MODEL	INFO	[2.4275856018066406, 2.817660331726074, 12.290006637573242, 22.89241600036621, -0.22586512565612793, 3.6342716217041016, 100, 0.000199975]3752023-04-02 08:07:36,362	OUTPUT_MODEL	INFO	====> Epoch: 23762023-04-02 08:08:17,786	OUTPUT_MODEL	INFO	====> Epoch: 33772023-04-02 08:08:47,700	OUTPUT_MODEL	INFO	Train Epoch: 4 [70%]3782023-04-02 08:08:47,701	OUTPUT_MODEL	INFO	[2.473052501678467, 2.181903839111328, 8.69401741027832, 20.988800048828125, 1.826810598373413, 3.1271934509277344, 200, 0.00019992500937460937]3792023-04-02 08:08:59,526	OUTPUT_MODEL	INFO	====> Epoch: 43802023-04-02 08:09:40,682	OUTPUT_MODEL	INFO	====> Epoch: 53812023-04-02 08:10:04,597	OUTPUT_MODEL	INFO	Train Epoch: 6 [56%]3822023-04-02 08:10:04,598	OUTPUT_MODEL	INFO	[2.175513982772827, 2.755709171295166, 10.869695663452148, 23.847232818603516, 1.3772954940795898, 3.0808327198028564, 300, 0.00019987503124609398]3832023-04-02 08:10:22,466	OUTPUT_MODEL	INFO	====> Epoch: 63842023-04-02 08:11:03,588	OUTPUT_MODEL	INFO	====> Epoch: 73852023-04-02 08:11:21,281	OUTPUT_MODEL	INFO	Train Epoch: 8 [41%]3862023-04-02 08:11:21,283	OUTPUT_MODEL	INFO	[1.9202440977096558, 2.802624464035034, 11.524502754211426, 24.399473190307617, -9.801231384277344, 2.862459421157837, 400, 0.00019982506561132978]3872023-04-02 08:11:45,321	OUTPUT_MODEL	INFO	====> Epoch: 83882023-04-02 08:12:26,453	OUTPUT_MODEL	INFO	====> Epoch: 93892023-04-02 08:12:38,189	OUTPUT_MODEL	INFO	Train Epoch: 10 [26%]3902023-04-02 08:12:38,190	OUTPUT_MODEL	INFO	[2.418809413909912, 2.3852057456970215, 13.668684005737305, 23.5804386138916, 1.8111464977264404, 3.324195146560669, 500, 0.0001997751124671936]3912023-04-02 08:13:08,406	OUTPUT_MODEL	INFO	====> Epoch: 103922023-04-02 08:13:49,520	OUTPUT_MODEL	INFO	====> Epoch: 113932023-04-02 08:13:55,306	OUTPUT_MODEL	INFO	Train Epoch: 12 [11%]3942023-04-02 08:13:55,306	OUTPUT_MODEL	INFO	[1.9247490167617798, 3.101287364959717, 12.769336700439453, 24.33500099182129, -7.790776252746582, 2.8895723819732666, 600, 0.00019972517181056292]3952023-04-02 08:14:31,199	OUTPUT_MODEL	INFO	====> Epoch: 123962023-04-02 08:15:11,583	OUTPUT_MODEL	INFO	Train Epoch: 13 [96%]3972023-04-02 08:15:11,584	OUTPUT_MODEL	INFO	[1.8826727867126465, 3.55073618888855, 11.896066665649414, 24.267080307006836, -9.683765411376953, 2.21333646774292, 700, 0.0001997002061640866]3982023-04-02 08:15:13,005	OUTPUT_MODEL	INFO	====> Epoch: 133992023-04-02 08:15:54,140	OUTPUT_MODEL	INFO	====> Epoch: 144002023-04-02 08:16:28,664	OUTPUT_MODEL	INFO	Train Epoch: 15 [81%]4012023-04-02 08:16:28,664	OUTPUT_MODEL	INFO	[1.7579543590545654, 3.144364833831787, 12.891899108886719, 21.95943832397461, -8.847193717956543, 2.879302978515625, 800, 0.0001996502842328613]4022023-04-02 08:16:36,067	OUTPUT_MODEL	INFO	====> Epoch: 154032023-04-02 08:17:17,161	OUTPUT_MODEL	INFO	====> Epoch: 164042023-04-02 08:17:45,488	OUTPUT_MODEL	INFO	Train Epoch: 17 [67%]4052023-04-02 08:17:45,489	OUTPUT_MODEL	INFO	[2.0389797687530518, 2.9549930095672607, 11.394433975219727, 18.888858795166016, 1.837241530418396, 2.851008415222168, 900, 0.00019960037478133875]4062023-04-02 08:17:58,868	OUTPUT_MODEL	INFO	====> Epoch: 174072023-04-02 08:18:39,951	OUTPUT_MODEL	INFO	====> Epoch: 184082023-04-02 08:19:02,251	OUTPUT_MODEL	INFO	Train Epoch: 19 [52%]4092023-04-02 08:19:02,251	OUTPUT_MODEL	INFO	[2.532696485519409, 2.779465675354004, 10.006392478942871, 20.532094955444336, 1.566396713256836, 3.2004644870758057, 1000, 0.00019955047780639926]4102023-04-02 08:19:03,966	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 19 to ././OUTPUT_MODEL/G_1000.pth4112023-04-02 08:19:04,315	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 19 to ././OUTPUT_MODEL/G_latest.pth4122023-04-02 08:19:23,354	OUTPUT_MODEL	INFO	====> Epoch: 194132023-04-02 08:20:04,514	OUTPUT_MODEL	INFO	====> Epoch: 204142023-04-02 08:20:20,728	OUTPUT_MODEL	INFO	Train Epoch: 21 [37%]4152023-04-02 08:20:20,731	OUTPUT_MODEL	INFO	[2.427015781402588, 2.5202009677886963, 9.195467948913574, 18.589218139648438, -1.7568871974945068, 2.614956855773926, 1100, 0.00019950059330492385]4162023-04-02 08:20:46,987	OUTPUT_MODEL	INFO	====> Epoch: 214172023-04-02 08:21:28,233	OUTPUT_MODEL	INFO	====> Epoch: 224182023-04-02 08:21:38,492	OUTPUT_MODEL	INFO	Train Epoch: 23 [22%]4192023-04-02 08:21:38,493	OUTPUT_MODEL	INFO	[2.505979061126709, 2.4804940223693848, 10.06444263458252, 18.88034439086914, 1.8149194717407227, 3.130533456802368, 1200, 0.00019945072127379438]4202023-04-02 08:22:09,933	OUTPUT_MODEL	INFO	====> Epoch: 234212023-04-02 08:22:51,041	OUTPUT_MODEL	INFO	====> Epoch: 244222023-04-02 08:22:55,410	OUTPUT_MODEL	INFO	Train Epoch: 25 [7%]4232023-04-02 08:22:55,411	OUTPUT_MODEL	INFO	[2.0037426948547363, 3.0507564544677734, 11.73446273803711, 21.265640258789062, -10.574641227722168, 2.3407726287841797, 1300, 0.00019940086170989343]4242023-04-02 08:23:32,810	OUTPUT_MODEL	INFO	====> Epoch: 254252023-04-02 08:24:11,720	OUTPUT_MODEL	INFO	Train Epoch: 26 [93%]4262023-04-02 08:24:11,721	OUTPUT_MODEL	INFO	[1.726310133934021, 3.018616199493408, 13.034422874450684, 22.230361938476562, -12.056370735168457, 2.429583787918091, 1400, 0.0001993759366021797]4272023-04-02 08:24:14,546	OUTPUT_MODEL	INFO	====> Epoch: 264282023-04-02 08:24:55,626	OUTPUT_MODEL	INFO	====> Epoch: 274292023-04-02 08:25:28,794	OUTPUT_MODEL	INFO	Train Epoch: 28 [78%]4302023-04-02 08:25:28,794	OUTPUT_MODEL	INFO	[2.315506935119629, 2.744453191757202, 11.075987815856934, 19.659725189208984, -1.3932281732559204, 2.4669113159179688, 1500, 0.00019932609573327815]4312023-04-02 08:25:37,534	OUTPUT_MODEL	INFO	====> Epoch: 284322023-04-02 08:26:18,669	OUTPUT_MODEL	INFO	====> Epoch: 294332023-04-02 08:26:45,536	OUTPUT_MODEL	INFO	Train Epoch: 30 [63%]4342023-04-02 08:26:45,537	OUTPUT_MODEL	INFO	[1.8989074230194092, 3.0943710803985596, 16.087366104125977, 22.54070472717285, -2.8876514434814453, 2.785585880279541, 1600, 0.00019927626732381507]4352023-04-02 08:27:00,460	OUTPUT_MODEL	INFO	====> Epoch: 304362023-04-02 08:27:41,591	OUTPUT_MODEL	INFO	====> Epoch: 314372023-04-02 08:28:02,416	OUTPUT_MODEL	INFO	Train Epoch: 32 [48%]4382023-04-02 08:28:02,417	OUTPUT_MODEL	INFO	[2.159681558609009, 2.6746606826782227, 9.747285842895508, 19.671459197998047, 1.5466499328613281, 2.7470340728759766, 1700, 0.00019922645137067577]4392023-04-02 08:28:23,374	OUTPUT_MODEL	INFO	====> Epoch: 324402023-04-02 08:29:04,513	OUTPUT_MODEL	INFO	====> Epoch: 334412023-04-02 08:29:19,231	OUTPUT_MODEL	INFO	Train Epoch: 34 [33%]4422023-04-02 08:29:19,232	OUTPUT_MODEL	INFO	[2.2777280807495117, 2.7869505882263184, 9.548517227172852, 18.354806900024414, 1.573028564453125, 2.6403048038482666, 1800, 0.0001991766478707464]4432023-04-02 08:29:46,501	OUTPUT_MODEL	INFO	====> Epoch: 344442023-04-02 08:30:27,700	OUTPUT_MODEL	INFO	====> Epoch: 354452023-04-02 08:30:36,494	OUTPUT_MODEL	INFO	Train Epoch: 36 [19%]4462023-04-02 08:30:36,495	OUTPUT_MODEL	INFO	[2.1121110916137695, 3.0220553874969482, 12.114409446716309, 20.390918731689453, 2.1517772674560547, 2.6338870525360107, 1900, 0.00019912685682091382]4472023-04-02 08:31:09,455	OUTPUT_MODEL	INFO	====> Epoch: 364482023-04-02 08:31:50,580	OUTPUT_MODEL	INFO	====> Epoch: 374492023-04-02 08:31:53,493	OUTPUT_MODEL	INFO	Train Epoch: 38 [4%]4502023-04-02 08:31:53,494	OUTPUT_MODEL	INFO	[1.5856082439422607, 3.1184563636779785, 12.907395362854004, 21.220754623413086, -6.261523246765137, 2.334676504135132, 2000, 0.0001990770782180657]4512023-04-02 08:31:55,112	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 38 to ././OUTPUT_MODEL/G_2000.pth4522023-04-02 08:31:55,467	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 38 to ././OUTPUT_MODEL/G_latest.pth4532023-04-02 08:32:33,858	OUTPUT_MODEL	INFO	====> Epoch: 384542023-04-02 08:33:11,321	OUTPUT_MODEL	INFO	Train Epoch: 39 [89%]4552023-04-02 08:33:11,322	OUTPUT_MODEL	INFO	[2.201404333114624, 2.776482105255127, 11.334125518798828, 18.44577980041504, -6.585959434509277, 2.651789665222168, 2100, 0.00019905219358328844]4562023-04-02 08:33:15,849	OUTPUT_MODEL	INFO	====> Epoch: 394572023-04-02 08:33:56,972	OUTPUT_MODEL	INFO	====> Epoch: 404582023-04-02 08:34:28,452	OUTPUT_MODEL	INFO	Train Epoch: 41 [74%]4592023-04-02 08:34:28,453	OUTPUT_MODEL	INFO	[2.194279432296753, 2.9755187034606934, 9.401860237121582, 18.446229934692383, 1.8193480968475342, 2.702861785888672, 2200, 0.00019900243364508313]4602023-04-02 08:34:38,818	OUTPUT_MODEL	INFO	====> Epoch: 414612023-04-02 08:35:20,009	OUTPUT_MODEL	INFO	====> Epoch: 424622023-04-02 08:35:46,190	OUTPUT_MODEL	INFO	Train Epoch: 43 [59%]4632023-04-02 08:35:46,191	OUTPUT_MODEL	INFO	[1.7320513725280762, 3.4617080688476562, 12.731840133666992, 20.121170043945312, -9.054081916809082, 2.3697478771209717, 2300, 0.00019895268614608487]4642023-04-02 08:36:02,824	OUTPUT_MODEL	INFO	====> Epoch: 434652023-04-02 08:36:44,300	OUTPUT_MODEL	INFO	====> Epoch: 444662023-04-02 08:37:03,770	OUTPUT_MODEL	INFO	Train Epoch: 45 [44%]4672023-04-02 08:37:03,771	OUTPUT_MODEL	INFO	[2.4324495792388916, 2.401845932006836, 12.172236442565918, 18.721378326416016, -1.7267624139785767, 2.657869577407837, 2400, 0.00019890295108318404]4682023-04-02 08:37:26,628	OUTPUT_MODEL	INFO	====> Epoch: 454692023-04-02 08:38:08,260	OUTPUT_MODEL	INFO	====> Epoch: 464702023-04-02 08:38:21,573	OUTPUT_MODEL	INFO	Train Epoch: 47 [30%]4712023-04-02 08:38:21,574	OUTPUT_MODEL	INFO	[2.129554033279419, 2.6322038173675537, 9.280620574951172, 19.18245506286621, -6.231853008270264, 2.509270668029785, 2500, 0.00019885322845327182]4722023-04-02 08:42:40,166	OUTPUT_MODEL	INFO	{'train': {'log_interval': 100, 'eval_interval': 1000, 'seed': 1234, 'epochs': 10000, 'learning_rate': 0.0002, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 16, 'fp16_run': True, 'lr_decay': 0.999875, 'segment_size': 8192, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'training_files': 'final_annotation_train.txt', 'validation_files': 'final_annotation_val.txt', 'text_cleaners': ['cjke_cleaners2'], 'max_wav_value': 32768.0, 'sampling_rate': 22050, 'filter_length': 1024, 'hop_length': 256, 'win_length': 1024, 'n_mel_channels': 80, 'mel_fmin': 0.0, 'mel_fmax': None, 'add_blank': True, 'n_speakers': 3, 'cleaned_text': True}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0.1, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [8, 8, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 256}, 'symbols': ['_', ',', '.', '!', '?', '-', '~', '…', 'N', 'Q', 'a', 'b', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', 'ɑ', 'æ', 'ʃ', 'ʑ', 'ç', 'ɯ', 'ɪ', 'ɔ', 'ɛ', 'ɹ', 'ð', 'ə', 'ɫ', 'ɥ', 'ɸ', 'ʊ', 'ɾ', 'ʒ', 'θ', 'β', 'ŋ', 'ɦ', '⁼', 'ʰ', '`', '^', '#', '*', '=', 'ˈ', 'ˌ', '→', '↓', '↑', ' '], 'speakers': {'嵯峨': 0, 'specialweek': 1, 'zhongli': 2}, 'model_dir': '././OUTPUT_MODEL', 'max_epochs': 100, 'drop_speaker_embed': True}4732023-04-02 08:42:40,166	OUTPUT_MODEL	WARNING	/root/autodl-tmp/VITS-finetune is not a git repository, therefore hash value comparison will be ignored.4742023-04-03 08:07:02,011	OUTPUT_MODEL	INFO	{'train': {'log_interval': 100, 'eval_interval': 1000, 'seed': 1234, 'epochs': 10000, 'learning_rate': 0.0002, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 16, 'fp16_run': False, 'lr_decay': 0.999875, 'segment_size': 8192, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'training_files': 'final_annotation_train.txt.cleaned', 'validation_files': 'final_annotation_val.txt.cleaned', 'text_cleaners': ['cjke_cleaners2'], 'max_wav_value': 32768.0, 'sampling_rate': 22050, 'filter_length': 1024, 'hop_length': 256, 'win_length': 1024, 'n_mel_channels': 80, 'mel_fmin': 0.0, 'mel_fmax': None, 'add_blank': True, 'n_speakers': 3, 'cleaned_text': True}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0.1, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [8, 8, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 256}, 'symbols': ['_', ',', '.', '!', '?', '-', '~', '…', 'N', 'Q', 'a', 'b', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', 'ɑ', 'æ', 'ʃ', 'ʑ', 'ç', 'ɯ', 'ɪ', 'ɔ', 'ɛ', 'ɹ', 'ð', 'ə', 'ɫ', 'ɥ', 'ɸ', 'ʊ', 'ɾ', 'ʒ', 'θ', 'β', 'ŋ', 'ɦ', '⁼', 'ʰ', '`', '^', '#', '*', '=', 'ˈ', 'ˌ', '→', '↓', '↑', ' '], 'speakers': {'嵯峨': 0, 'specialweek': 1, 'zhongli': 2}, 'model_dir': '././OUTPUT_MODEL', 'max_epochs': 100, 'drop_speaker_embed': True}4752023-04-03 08:07:02,011	OUTPUT_MODEL	WARNING	/root/autodl-tmp/VITS-finetune is not a git repository, therefore hash value comparison will be ignored.4762023-04-03 08:09:37,663	OUTPUT_MODEL	INFO	{'train': {'log_interval': 100, 'eval_interval': 1000, 'seed': 1234, 'epochs': 10000, 'learning_rate': 0.0002, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 16, 'fp16_run': False, 'lr_decay': 0.999875, 'segment_size': 8192, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'training_files': 'final_annotation_train.txt.cleaned', 'validation_files': 'final_annotation_val.txt.cleaned', 'text_cleaners': ['cjke_cleaners2'], 'max_wav_value': 32768.0, 'sampling_rate': 22050, 'filter_length': 1024, 'hop_length': 256, 'win_length': 1024, 'n_mel_channels': 80, 'mel_fmin': 0.0, 'mel_fmax': None, 'add_blank': True, 'n_speakers': 3, 'cleaned_text': True}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0.1, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [8, 8, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 256}, 'symbols': ['_', ',', '.', '!', '?', '-', '~', '…', 'N', 'Q', 'a', 'b', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', 'ɑ', 'æ', 'ʃ', 'ʑ', 'ç', 'ɯ', 'ɪ', 'ɔ', 'ɛ', 'ɹ', 'ð', 'ə', 'ɫ', 'ɥ', 'ɸ', 'ʊ', 'ɾ', 'ʒ', 'θ', 'β', 'ŋ', 'ɦ', '⁼', 'ʰ', '`', '^', '#', '*', '=', 'ˈ', 'ˌ', '→', '↓', '↑', ' '], 'speakers': {'嵯峨': 0, 'specialweek': 1, 'zhongli': 2}, 'model_dir': '././OUTPUT_MODEL', 'max_epochs': 600, 'drop_speaker_embed': True}4772023-04-03 08:09:37,663	OUTPUT_MODEL	WARNING	/root/autodl-tmp/VITS-finetune is not a git repository, therefore hash value comparison will be ignored.4782023-04-03 17:25:44,434	OUTPUT_MODEL	INFO	{'train': {'log_interval': 100, 'eval_interval': 1000, 'seed': 1234, 'epochs': 10000, 'learning_rate': 0.0002, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 16, 'fp16_run': False, 'lr_decay': 0.999875, 'segment_size': 8192, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'training_files': 'final_annotation_train.txt', 'validation_files': 'final_annotation_val.txt', 'text_cleaners': ['cjke_cleaners2'], 'max_wav_value': 32768.0, 'sampling_rate': 22050, 'filter_length': 1024, 'hop_length': 256, 'win_length': 1024, 'n_mel_channels': 80, 'mel_fmin': 0.0, 'mel_fmax': None, 'add_blank': True, 'n_speakers': 68, 'cleaned_text': True}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0.1, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [8, 8, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 256}, 'symbols': ['_', ',', '.', '!', '?', '-', '~', '…', 'N', 'Q', 'a', 'b', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', 'ɑ', 'æ', 'ʃ', 'ʑ', 'ç', 'ɯ', 'ɪ', 'ɔ', 'ɛ', 'ɹ', 'ð', 'ə', 'ɫ', 'ɥ', 'ɸ', 'ʊ', 'ɾ', 'ʒ', 'θ', 'β', 'ŋ', 'ɦ', '⁼', 'ʰ', '`', '^', '#', '*', '=', 'ˈ', 'ˌ', '→', '↓', '↑', ' '], 'speakers': {'W': 0, '仇白': 1, '令': 2, '伊芙利特': 3, '伺夜': 4, '假日威龙陈': 5, '傀影': 6, '刻俄柏': 7, '史尔特尔': 8, '号角': 9, '塞雷娅': 10, '夕': 11, '多萝西': 12, '夜莺': 13, '山': 14, '嵯峨': 15, '帕拉斯': 16, '年': 17, '异客': 18, '归溟幽灵鲨': 19, '推进之王': 20, '斥罪': 21, '斯卡蒂': 22, '早露': 23, '星熊': 24, '棘刺': 25, '森蚺': 26, '泥岩': 27, '流明': 28, '浊心斯卡蒂': 29, '温蒂': 30, '澄闪': 31, '灵知': 32, '焰尾': 33, '焰影苇草': 34, '煌': 35, '玛恩纳': 36, '琴柳': 37, '瑕光': 38, '白铁': 39, '百炼嘉维尔': 40, '空弦': 41, '缄默德克萨斯': 42, '耀骑士临光': 43, '老鲤': 44, '能天使': 45, '艾丽妮': 46, '艾雅法拉': 47, '莫斯提马': 48, '菲亚梅塔': 49, '谜图': 50, '赫拉格': 51, '远牙': 52, '迷迭香': 53, '重岳': 54, '铃兰': 55, '银灰': 56, '闪灵': 57, '阿': 58, '陈': 59, '风笛': 60, '鸿雪': 61, '麒麟X夜刀': 62, '麦哲伦': 63, '黑': 64, '黑键': 65, 'specialweek': 66, 'zhongli': 67}, 'model_dir': '././OUTPUT_MODEL', 'max_epochs': 1000, 'drop_speaker_embed': True}4792023-04-03 17:25:44,434	OUTPUT_MODEL	WARNING	/root/autodl-tmp/VITS-finetune is not a git repository, therefore hash value comparison will be ignored.4802023-04-03 17:27:21,953	OUTPUT_MODEL	INFO	{'train': {'log_interval': 100, 'eval_interval': 1000, 'seed': 1234, 'epochs': 10000, 'learning_rate': 0.0002, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 16, 'fp16_run': False, 'lr_decay': 0.999875, 'segment_size': 8192, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'training_files': 'final_annotation_train.txt', 'validation_files': 'final_annotation_val.txt', 'text_cleaners': ['cjke_cleaners2'], 'max_wav_value': 32768.0, 'sampling_rate': 22050, 'filter_length': 1024, 'hop_length': 256, 'win_length': 1024, 'n_mel_channels': 80, 'mel_fmin': 0.0, 'mel_fmax': None, 'add_blank': True, 'n_speakers': 68, 'cleaned_text': True}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0.1, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [8, 8, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 256}, 'symbols': ['_', ',', '.', '!', '?', '-', '~', '…', 'N', 'Q', 'a', 'b', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', 'ɑ', 'æ', 'ʃ', 'ʑ', 'ç', 'ɯ', 'ɪ', 'ɔ', 'ɛ', 'ɹ', 'ð', 'ə', 'ɫ', 'ɥ', 'ɸ', 'ʊ', 'ɾ', 'ʒ', 'θ', 'β', 'ŋ', 'ɦ', '⁼', 'ʰ', '`', '^', '#', '*', '=', 'ˈ', 'ˌ', '→', '↓', '↑', ' '], 'speakers': {'W': 0, '仇白': 1, '令': 2, '伊芙利特': 3, '伺夜': 4, '假日威龙陈': 5, '傀影': 6, '刻俄柏': 7, '史尔特尔': 8, '号角': 9, '塞雷娅': 10, '夕': 11, '多萝西': 12, '夜莺': 13, '山': 14, '嵯峨': 15, '帕拉斯': 16, '年': 17, '异客': 18, '归溟幽灵鲨': 19, '推进之王': 20, '斥罪': 21, '斯卡蒂': 22, '早露': 23, '星熊': 24, '棘刺': 25, '森蚺': 26, '泥岩': 27, '流明': 28, '浊心斯卡蒂': 29, '温蒂': 30, '澄闪': 31, '灵知': 32, '焰尾': 33, '焰影苇草': 34, '煌': 35, '玛恩纳': 36, '琴柳': 37, '瑕光': 38, '白铁': 39, '百炼嘉维尔': 40, '空弦': 41, '缄默德克萨斯': 42, '耀骑士临光': 43, '老鲤': 44, '能天使': 45, '艾丽妮': 46, '艾雅法拉': 47, '莫斯提马': 48, '菲亚梅塔': 49, '谜图': 50, '赫拉格': 51, '远牙': 52, '迷迭香': 53, '重岳': 54, '铃兰': 55, '银灰': 56, '闪灵': 57, '阿': 58, '陈': 59, '风笛': 60, '鸿雪': 61, '麒麟X夜刀': 62, '麦哲伦': 63, '黑': 64, '黑键': 65, 'specialweek': 66, 'zhongli': 67}, 'model_dir': '././OUTPUT_MODEL', 'max_epochs': 1000, 'drop_speaker_embed': True}4812023-04-03 17:27:21,954	OUTPUT_MODEL	WARNING	/root/autodl-tmp/VITS-finetune is not a git repository, therefore hash value comparison will be ignored.4822023-04-03 17:34:05,042	OUTPUT_MODEL	INFO	{'train': {'log_interval': 100, 'eval_interval': 1000, 'seed': 1234, 'epochs': 10000, 'learning_rate': 0.0002, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 16, 'fp16_run': True, 'lr_decay': 0.999875, 'segment_size': 8192, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'training_files': 'final_annotation_train.txt', 'validation_files': 'final_annotation_val.txt', 'text_cleaners': ['cjke_cleaners2'], 'max_wav_value': 32768.0, 'sampling_rate': 22050, 'filter_length': 1024, 'hop_length': 256, 'win_length': 1024, 'n_mel_channels': 80, 'mel_fmin': 0.0, 'mel_fmax': None, 'add_blank': True, 'n_speakers': 68, 'cleaned_text': True}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0.1, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [8, 8, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 256}, 'symbols': ['_', ',', '.', '!', '?', '-', '~', '…', 'N', 'Q', 'a', 'b', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', 'ɑ', 'æ', 'ʃ', 'ʑ', 'ç', 'ɯ', 'ɪ', 'ɔ', 'ɛ', 'ɹ', 'ð', 'ə', 'ɫ', 'ɥ', 'ɸ', 'ʊ', 'ɾ', 'ʒ', 'θ', 'β', 'ŋ', 'ɦ', '⁼', 'ʰ', '`', '^', '#', '*', '=', 'ˈ', 'ˌ', '→', '↓', '↑', ' '], 'speakers': {'W': 0, '仇白': 1, '令': 2, '伊芙利特': 3, '伺夜': 4, '假日威龙陈': 5, '傀影': 6, '刻俄柏': 7, '史尔特尔': 8, '号角': 9, '塞雷娅': 10, '夕': 11, '多萝西': 12, '夜莺': 13, '山': 14, '嵯峨': 15, '帕拉斯': 16, '年': 17, '异客': 18, '归溟幽灵鲨': 19, '推进之王': 20, '斥罪': 21, '斯卡蒂': 22, '早露': 23, '星熊': 24, '棘刺': 25, '森蚺': 26, '泥岩': 27, '流明': 28, '浊心斯卡蒂': 29, '温蒂': 30, '澄闪': 31, '灵知': 32, '焰尾': 33, '焰影苇草': 34, '煌': 35, '玛恩纳': 36, '琴柳': 37, '瑕光': 38, '白铁': 39, '百炼嘉维尔': 40, '空弦': 41, '缄默德克萨斯': 42, '耀骑士临光': 43, '老鲤': 44, '能天使': 45, '艾丽妮': 46, '艾雅法拉': 47, '莫斯提马': 48, '菲亚梅塔': 49, '谜图': 50, '赫拉格': 51, '远牙': 52, '迷迭香': 53, '重岳': 54, '铃兰': 55, '银灰': 56, '闪灵': 57, '阿': 58, '陈': 59, '风笛': 60, '鸿雪': 61, '麒麟X夜刀': 62, '麦哲伦': 63, '黑': 64, '黑键': 65, 'specialweek': 66, 'zhongli': 67}, 'model_dir': '././OUTPUT_MODEL', 'max_epochs': 1000, 'drop_speaker_embed': True}4832023-04-03 17:34:05,042	OUTPUT_MODEL	WARNING	/root/autodl-tmp/VITS-finetune is not a git repository, therefore hash value comparison will be ignored.4842023-04-03 17:34:35,283	OUTPUT_MODEL	INFO	{'train': {'log_interval': 100, 'eval_interval': 1000, 'seed': 1234, 'epochs': 10000, 'learning_rate': 0.0002, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 16, 'fp16_run': True, 'lr_decay': 0.999875, 'segment_size': 8192, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'training_files': 'final_annotation_train.txt', 'validation_files': 'final_annotation_val.txt', 'text_cleaners': ['cjke_cleaners2'], 'max_wav_value': 32768.0, 'sampling_rate': 22050, 'filter_length': 1024, 'hop_length': 256, 'win_length': 1024, 'n_mel_channels': 80, 'mel_fmin': 0.0, 'mel_fmax': None, 'add_blank': True, 'n_speakers': 68, 'cleaned_text': True}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0.1, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [8, 8, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 256}, 'symbols': ['_', ',', '.', '!', '?', '-', '~', '…', 'A', 'E', 'I', 'N', 'O', 'Q', 'U', 'a', 'b', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'r', 's', 't', 'u', 'v', 'w', 'y', 'z', 'ʃ', 'ʧ', 'ʦ', 'ɯ', 'ɹ', 'ə', 'ɥ', '⁼', 'ʰ', '`', '→', '↓', '↑', ' '], 'speakers': {'W': 0, '仇白': 1, '令': 2, '伊芙利特': 3, '伺夜': 4, '假日威龙陈': 5, '傀影': 6, '刻俄柏': 7, '史尔特尔': 8, '号角': 9, '塞雷娅': 10, '夕': 11, '多萝西': 12, '夜莺': 13, '山': 14, '嵯峨': 15, '帕拉斯': 16, '年': 17, '异客': 18, '归溟幽灵鲨': 19, '推进之王': 20, '斥罪': 21, '斯卡蒂': 22, '早露': 23, '星熊': 24, '棘刺': 25, '森蚺': 26, '泥岩': 27, '流明': 28, '浊心斯卡蒂': 29, '温蒂': 30, '澄闪': 31, '灵知': 32, '焰尾': 33, '焰影苇草': 34, '煌': 35, '玛恩纳': 36, '琴柳': 37, '瑕光': 38, '白铁': 39, '百炼嘉维尔': 40, '空弦': 41, '缄默德克萨斯': 42, '耀骑士临光': 43, '老鲤': 44, '能天使': 45, '艾丽妮': 46, '艾雅法拉': 47, '莫斯提马': 48, '菲亚梅塔': 49, '谜图': 50, '赫拉格': 51, '远牙': 52, '迷迭香': 53, '重岳': 54, '铃兰': 55, '银灰': 56, '闪灵': 57, '阿': 58, '陈': 59, '风笛': 60, '鸿雪': 61, '麒麟X夜刀': 62, '麦哲伦': 63, '黑': 64, '黑键': 65, 'specialweek': 66, 'zhongli': 67}, 'model_dir': '././OUTPUT_MODEL', 'max_epochs': 1000, 'drop_speaker_embed': True}4852023-04-03 17:34:35,283	OUTPUT_MODEL	WARNING	/root/autodl-tmp/VITS-finetune is not a git repository, therefore hash value comparison will be ignored.4862023-04-03 17:34:40,217	OUTPUT_MODEL	INFO	Loaded checkpoint './pretrained_models/G_0_.pth' (iteration None)4872023-04-03 17:34:40,399	OUTPUT_MODEL	INFO	Loaded checkpoint './pretrained_models/D_0_.pth' (iteration None)4882023-04-03 17:34:53,488	OUTPUT_MODEL	INFO	{'train': {'log_interval': 100, 'eval_interval': 1000, 'seed': 1234, 'epochs': 10000, 'learning_rate': 0.0002, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 16, 'fp16_run': False, 'lr_decay': 0.999875, 'segment_size': 8192, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'training_files': 'final_annotation_train.txt', 'validation_files': 'final_annotation_val.txt', 'text_cleaners': ['cjke_cleaners2'], 'max_wav_value': 32768.0, 'sampling_rate': 22050, 'filter_length': 1024, 'hop_length': 256, 'win_length': 1024, 'n_mel_channels': 80, 'mel_fmin': 0.0, 'mel_fmax': None, 'add_blank': True, 'n_speakers': 68, 'cleaned_text': True}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0.1, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [8, 8, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 256}, 'symbols': ['_', ',', '.', '!', '?', '-', '~', '…', 'A', 'E', 'I', 'N', 'O', 'Q', 'U', 'a', 'b', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'r', 's', 't', 'u', 'v', 'w', 'y', 'z', 'ʃ', 'ʧ', 'ʦ', 'ɯ', 'ɹ', 'ə', 'ɥ', '⁼', 'ʰ', '`', '→', '↓', '↑', ' '], 'speakers': {'W': 0, '仇白': 1, '令': 2, '伊芙利特': 3, '伺夜': 4, '假日威龙陈': 5, '傀影': 6, '刻俄柏': 7, '史尔特尔': 8, '号角': 9, '塞雷娅': 10, '夕': 11, '多萝西': 12, '夜莺': 13, '山': 14, '嵯峨': 15, '帕拉斯': 16, '年': 17, '异客': 18, '归溟幽灵鲨': 19, '推进之王': 20, '斥罪': 21, '斯卡蒂': 22, '早露': 23, '星熊': 24, '棘刺': 25, '森蚺': 26, '泥岩': 27, '流明': 28, '浊心斯卡蒂': 29, '温蒂': 30, '澄闪': 31, '灵知': 32, '焰尾': 33, '焰影苇草': 34, '煌': 35, '玛恩纳': 36, '琴柳': 37, '瑕光': 38, '白铁': 39, '百炼嘉维尔': 40, '空弦': 41, '缄默德克萨斯': 42, '耀骑士临光': 43, '老鲤': 44, '能天使': 45, '艾丽妮': 46, '艾雅法拉': 47, '莫斯提马': 48, '菲亚梅塔': 49, '谜图': 50, '赫拉格': 51, '远牙': 52, '迷迭香': 53, '重岳': 54, '铃兰': 55, '银灰': 56, '闪灵': 57, '阿': 58, '陈': 59, '风笛': 60, '鸿雪': 61, '麒麟X夜刀': 62, '麦哲伦': 63, '黑': 64, '黑键': 65, 'specialweek': 66, 'zhongli': 67}, 'model_dir': '././OUTPUT_MODEL', 'max_epochs': 1000, 'drop_speaker_embed': True}4892023-04-03 17:34:53,489	OUTPUT_MODEL	WARNING	/root/autodl-tmp/VITS-finetune is not a git repository, therefore hash value comparison will be ignored.4902023-04-03 17:34:58,417	OUTPUT_MODEL	INFO	Loaded checkpoint './pretrained_models/G_0_.pth' (iteration None)4912023-04-03 17:34:58,583	OUTPUT_MODEL	INFO	Loaded checkpoint './pretrained_models/D_0_.pth' (iteration None)4922023-04-03 17:35:02,402	OUTPUT_MODEL	INFO	Train Epoch: 1 [0%]4932023-04-03 17:35:02,402	OUTPUT_MODEL	INFO	[2.883575916290283, 2.849888324737549, 8.81806755065918, 28.832805633544922, 1.6273704767227173, 15.779275894165039, 0, 0.0002]4942023-04-03 17:35:04,391	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 1 to ././OUTPUT_MODEL/G_0.pth4952023-04-03 17:35:04,874	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 1 to ././OUTPUT_MODEL/G_latest.pth4962023-04-03 17:36:41,042	OUTPUT_MODEL	INFO	Train Epoch: 1 [88%]4972023-04-03 17:36:41,043	OUTPUT_MODEL	INFO	[2.126120090484619, 3.227421522140503, 10.382025718688965, 24.092864990234375, 2.0809521675109863, 3.363316774368286, 100, 0.0002]4982023-04-03 17:36:53,224	OUTPUT_MODEL	INFO	====> Epoch: 14992023-04-03 17:38:00,624	OUTPUT_MODEL	INFO	Train Epoch: 2 [75%]5002023-04-03 17:38:00,625	OUTPUT_MODEL	INFO	[2.2672109603881836, 2.6909427642822266, 11.481657981872559, 23.00012969970703, 1.982515811920166, 2.99998140335083, 200, 0.000199975]5012023-04-03 17:38:21,691	OUTPUT_MODEL	INFO	====> Epoch: 25022023-04-03 17:39:18,282	OUTPUT_MODEL	INFO	Train Epoch: 3 [63%]5032023-04-03 17:39:18,283	OUTPUT_MODEL	INFO	[2.543654441833496, 2.612675905227661, 7.856821537017822, 19.864307403564453, 2.0243849754333496, 2.3998990058898926, 300, 0.000199950003125]5042023-04-03 17:39:49,568	OUTPUT_MODEL	INFO	====> Epoch: 35052023-04-03 17:40:35,559	OUTPUT_MODEL	INFO	Train Epoch: 4 [51%]5062023-04-03 17:40:35,560	OUTPUT_MODEL	INFO	[2.1909379959106445, 2.7035040855407715, 10.775943756103516, 25.569534301757812, -0.11794114112854004, 2.8421332836151123, 400, 0.00019992500937460937]5072023-04-03 17:41:17,765	OUTPUT_MODEL	INFO	====> Epoch: 45082023-04-03 17:41:52,551	OUTPUT_MODEL	INFO	Train Epoch: 5 [39%]5092023-04-03 17:41:52,552	OUTPUT_MODEL	INFO	[2.353250026702881, 2.762183427810669, 11.0252046585083, 22.656118392944336, 1.9327819347381592, 2.5769901275634766, 500, 0.00019990001874843754]5102023-04-03 17:42:45,501	OUTPUT_MODEL	INFO	====> Epoch: 55112023-04-03 17:43:09,587	OUTPUT_MODEL	INFO	Train Epoch: 6 [26%]5122023-04-03 17:43:09,588	OUTPUT_MODEL	INFO	[2.336354970932007, 2.568533420562744, 9.803567886352539, 22.78739356994629, -2.0094127655029297, 2.732025623321533, 600, 0.00019987503124609398]5132023-04-03 17:44:13,125	OUTPUT_MODEL	INFO	====> Epoch: 65142023-04-03 17:44:26,707	OUTPUT_MODEL	INFO	Train Epoch: 7 [14%]5152023-04-03 17:44:26,707	OUTPUT_MODEL	INFO	[2.0875496864318848, 3.3505945205688477, 12.806187629699707, 25.34189224243164, -1.7046337127685547, 2.1406097412109375, 700, 0.0001998500468671882]5162023-04-03 17:45:40,859	OUTPUT_MODEL	INFO	====> Epoch: 75172023-04-03 17:45:43,833	OUTPUT_MODEL	INFO	Train Epoch: 8 [2%]5182023-04-03 17:45:43,834	OUTPUT_MODEL	INFO	[2.1476335525512695, 3.006258487701416, 11.923463821411133, 25.215974807739258, -0.14190739393234253, 2.613332509994507, 800, 0.00019982506561132978]5192023-04-03 17:47:00,368	OUTPUT_MODEL	INFO	Train Epoch: 8 [89%]5202023-04-03 17:47:00,369	OUTPUT_MODEL	INFO	[2.3043453693389893, 2.528203010559082, 11.949944496154785, 23.296077728271484, -2.239248275756836, 2.2097973823547363, 900, 0.00019982506561132978]5212023-04-03 17:47:09,335	OUTPUT_MODEL	INFO	====> Epoch: 85222023-04-03 17:48:17,883	OUTPUT_MODEL	INFO	Train Epoch: 9 [77%]5232023-04-03 17:48:17,884	OUTPUT_MODEL	INFO	[1.843817114830017, 3.352471113204956, 12.461740493774414, 24.924837112426758, -2.428142547607422, 2.353303909301758, 1000, 0.00019980008747812837]5242023-04-03 17:48:19,491	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 9 to ././OUTPUT_MODEL/G_1000.pth5252023-04-03 17:48:19,909	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 9 to ././OUTPUT_MODEL/G_latest.pth5262023-04-03 17:48:39,193	OUTPUT_MODEL	INFO	====> Epoch: 95272023-04-03 17:49:37,160	OUTPUT_MODEL	INFO	Train Epoch: 10 [65%]5282023-04-03 17:49:37,160	OUTPUT_MODEL	INFO	[2.481649398803711, 2.4475173950195312, 9.066485404968262, 19.993356704711914, 2.169219732284546, 2.2176802158355713, 1100, 0.0001997751124671936]5292023-04-03 17:50:07,014	OUTPUT_MODEL	INFO	====> Epoch: 105302023-04-03 17:50:54,936	OUTPUT_MODEL	INFO	Train Epoch: 11 [53%]5312023-04-03 17:50:54,938	OUTPUT_MODEL	INFO	[2.26631498336792, 2.7235050201416016, 9.756125450134277, 22.847627639770508, 0.6514445543289185, 1.7733663320541382, 1200, 0.00019975014057813518]5322023-04-03 17:51:35,837	OUTPUT_MODEL	INFO	====> Epoch: 115332023-04-03 17:52:12,629	OUTPUT_MODEL	INFO	Train Epoch: 12 [40%]5342023-04-03 17:52:12,631	OUTPUT_MODEL	INFO	[2.118321657180786, 2.740729808807373, 12.556720733642578, 21.54199981689453, 1.8733832836151123, 1.9896936416625977, 1300, 0.00019972517181056292]5352023-04-03 17:53:04,558	OUTPUT_MODEL	INFO	====> Epoch: 125362023-04-03 17:53:30,396	OUTPUT_MODEL	INFO	Train Epoch: 13 [28%]5372023-04-03 17:53:30,396	OUTPUT_MODEL	INFO	[2.252021551132202, 2.4648919105529785, 10.9974365234375, 24.130077362060547, -2.396230697631836, 2.4088845252990723, 1400, 0.0001997002061640866]5382023-04-03 17:54:32,848	OUTPUT_MODEL	INFO	====> Epoch: 135392023-04-03 17:54:48,036	OUTPUT_MODEL	INFO	Train Epoch: 14 [16%]5402023-04-03 17:54:48,038	OUTPUT_MODEL	INFO	[2.4896793365478516, 2.4286742210388184, 9.248808860778809, 19.004425048828125, 1.9860906600952148, 2.189650297164917, 1500, 0.00019967524363831608]5412023-04-03 17:56:00,502	OUTPUT_MODEL	INFO	====> Epoch: 145422023-04-03 17:56:04,886	OUTPUT_MODEL	INFO	Train Epoch: 15 [4%]5432023-04-03 17:56:04,887	OUTPUT_MODEL	INFO	[2.2933292388916016, 2.5737290382385254, 10.00172233581543, 23.86634635925293, 1.9578237533569336, 2.175370454788208, 1600, 0.0001996502842328613]5442023-04-03 17:57:21,228	OUTPUT_MODEL	INFO	Train Epoch: 15 [91%]5452023-04-03 17:57:21,230	OUTPUT_MODEL	INFO	[2.401820421218872, 2.5527098178863525, 9.029986381530762, 21.52157211303711, 1.8881731033325195, 2.151684522628784, 1700, 0.0001996502842328613]5462023-04-03 17:57:28,629	OUTPUT_MODEL	INFO	====> Epoch: 155472023-04-03 17:58:38,141	OUTPUT_MODEL	INFO	Train Epoch: 16 [79%]5482023-04-03 17:58:38,142	OUTPUT_MODEL	INFO	[2.154818534851074, 3.0658318996429443, 12.021906852722168, 25.783180236816406, -5.721470355987549, 2.4151930809020996, 1800, 0.00019962532794733217]5492023-04-03 17:58:56,421	OUTPUT_MODEL	INFO	====> Epoch: 165502023-04-03 17:59:55,636	OUTPUT_MODEL	INFO	Train Epoch: 17 [67%]5512023-04-03 17:59:55,638	OUTPUT_MODEL	INFO	[2.101888656616211, 2.9113993644714355, 12.894486427307129, 25.92900848388672, -0.0362696647644043, 2.200535297393799, 1900, 0.00019960037478133875]5522023-04-03 18:00:24,099	OUTPUT_MODEL	INFO	====> Epoch: 175532023-04-03 18:01:12,883	OUTPUT_MODEL	INFO	Train Epoch: 18 [54%]5542023-04-03 18:01:12,884	OUTPUT_MODEL	INFO	[2.397923469543457, 2.5889699459075928, 9.154419898986816, 23.283952713012695, 2.155075788497925, 1.7946531772613525, 2000, 0.00019957542473449108]5552023-04-03 18:01:14,189	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 18 to ././OUTPUT_MODEL/G_2000.pth5562023-04-03 18:01:14,619	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 18 to ././OUTPUT_MODEL/G_latest.pth5572023-04-03 18:01:53,252	OUTPUT_MODEL	INFO	====> Epoch: 185582023-04-03 18:02:31,068	OUTPUT_MODEL	INFO	Train Epoch: 19 [42%]5592023-04-03 18:02:31,069	OUTPUT_MODEL	INFO	[2.346362352371216, 2.4029130935668945, 9.819686889648438, 21.627655029296875, -1.092447280883789, 2.4224514961242676, 2100, 0.00019955047780639926]5602023-04-03 18:03:21,007	OUTPUT_MODEL	INFO	====> Epoch: 195612023-04-03 18:03:48,112	OUTPUT_MODEL	INFO	Train Epoch: 20 [30%]5622023-04-03 18:03:48,113	OUTPUT_MODEL	INFO	[2.3750386238098145, 2.447031259536743, 9.931506156921387, 20.613086700439453, 1.9809997081756592, 2.097426414489746, 2200, 0.00019952553399667344]5632023-04-03 18:04:48,617	OUTPUT_MODEL	INFO	====> Epoch: 205642023-04-03 18:05:05,170	OUTPUT_MODEL	INFO	Train Epoch: 21 [18%]5652023-04-03 18:05:05,171	OUTPUT_MODEL	INFO	[2.408599376678467, 2.5121846199035645, 8.670358657836914, 21.029401779174805, -1.803628921508789, 1.9808580875396729, 2300, 0.00019950059330492385]5662023-04-03 18:06:16,225	OUTPUT_MODEL	INFO	====> Epoch: 215672023-04-03 18:06:22,207	OUTPUT_MODEL	INFO	Train Epoch: 22 [5%]5682023-04-03 18:06:22,208	OUTPUT_MODEL	INFO	[2.2451071739196777, 2.7908763885498047, 10.36267375946045, 23.354270935058594, 2.115962505340576, 2.0170466899871826, 2400, 0.00019947565573076072]5692023-04-03 18:07:38,785	OUTPUT_MODEL	INFO	Train Epoch: 22 [93%]5702023-04-03 18:07:38,786	OUTPUT_MODEL	INFO	[2.070988655090332, 3.0271549224853516, 10.413193702697754, 22.586515426635742, -0.691889762878418, 2.076547384262085, 2500, 0.00019947565573076072]5712023-04-03 18:07:44,651	OUTPUT_MODEL	INFO	====> Epoch: 225722023-04-03 18:08:55,872	OUTPUT_MODEL	INFO	Train Epoch: 23 [81%]5732023-04-03 18:08:55,873	OUTPUT_MODEL	INFO	[2.323744535446167, 2.8809573650360107, 10.546944618225098, 22.269115447998047, 2.09257173538208, 1.8240234851837158, 2600, 0.00019945072127379438]5742023-04-03 18:09:12,443	OUTPUT_MODEL	INFO	====> Epoch: 235752023-04-03 18:10:13,185	OUTPUT_MODEL	INFO	Train Epoch: 24 [68%]5762023-04-03 18:10:13,186	OUTPUT_MODEL	INFO	[2.1116280555725098, 2.740499496459961, 11.60500431060791, 24.89236068725586, -4.852882385253906, 2.2877602577209473, 2700, 0.00019942578993363514]5772023-04-03 18:10:40,070	OUTPUT_MODEL	INFO	====> Epoch: 245782023-04-03 18:11:31,377	OUTPUT_MODEL	INFO	Train Epoch: 25 [56%]5792023-04-03 18:11:31,378	OUTPUT_MODEL	INFO	[2.1622862815856934, 2.4922940731048584, 10.552733421325684, 24.144865036010742, -4.110525131225586, 1.9041494131088257, 2800, 0.00019940086170989343]5802023-04-03 18:12:09,267	OUTPUT_MODEL	INFO	====> Epoch: 255812023-04-03 18:12:48,997	OUTPUT_MODEL	INFO	Train Epoch: 26 [44%]5822023-04-03 18:12:48,998	OUTPUT_MODEL	INFO	[2.26088285446167, 2.9081714153289795, 9.61971664428711, 21.04912757873535, 1.9197332859039307, 2.208096504211426, 2900, 0.0001993759366021797]5832023-04-03 18:13:37,280	OUTPUT_MODEL	INFO	====> Epoch: 265842023-04-03 18:14:06,032	OUTPUT_MODEL	INFO	Train Epoch: 27 [32%]5852023-04-03 18:14:06,033	OUTPUT_MODEL	INFO	[2.464216709136963, 2.592272996902466, 10.165121078491211, 19.225229263305664, 2.268317699432373, 1.8599681854248047, 3000, 0.00019935101461010442]5862023-04-03 18:14:07,315	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 27 to ././OUTPUT_MODEL/G_3000.pth5872023-04-03 18:14:07,735	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 27 to ././OUTPUT_MODEL/G_latest.pth5882023-04-03 18:15:06,278	OUTPUT_MODEL	INFO	====> Epoch: 275892023-04-03 18:15:24,308	OUTPUT_MODEL	INFO	Train Epoch: 28 [19%]5902023-04-03 18:15:24,309	OUTPUT_MODEL	INFO	[2.2397589683532715, 2.7125351428985596, 11.01107406616211, 23.90734100341797, -3.7303178310394287, 2.0584716796875, 3100, 0.00019932609573327815]5912023-04-03 18:16:34,061	OUTPUT_MODEL	INFO	====> Epoch: 285922023-04-03 18:16:41,511	OUTPUT_MODEL	INFO	Train Epoch: 29 [7%]5932023-04-03 18:16:41,512	OUTPUT_MODEL	INFO	[2.065443992614746, 2.890993595123291, 11.66160774230957, 22.960586547851562, -8.243396759033203, 2.2218680381774902, 3200, 0.0001993011799713115]5942023-04-03 18:17:58,641	OUTPUT_MODEL	INFO	Train Epoch: 29 [95%]5952023-04-03 18:17:58,642	OUTPUT_MODEL	INFO	[2.33392596244812, 2.5291802883148193, 8.077815055847168, 20.01274299621582, 1.7341415882110596, 2.0366580486297607, 3300, 0.0001993011799713115]5962023-04-03 18:18:03,089	OUTPUT_MODEL	INFO	====> Epoch: 295972023-04-03 18:19:15,942	OUTPUT_MODEL	INFO	Train Epoch: 30 [82%]5982023-04-03 18:19:15,943	OUTPUT_MODEL	INFO	[2.1846020221710205, 3.057891607284546, 10.79426097869873, 22.911407470703125, -1.498633861541748, 2.0883469581604004, 3400, 0.00019927626732381507]5992023-04-03 18:19:31,235	OUTPUT_MODEL	INFO	====> Epoch: 306002023-04-03 18:20:33,291	OUTPUT_MODEL	INFO	Train Epoch: 31 [70%]6012023-04-03 18:20:33,291	OUTPUT_MODEL	INFO	[2.482564926147461, 2.4980084896087646, 7.5842719078063965, 19.998611450195312, 1.8887499570846558, 2.183359384536743, 3500, 0.00019925135779039958]6022023-04-03 18:20:58,723	OUTPUT_MODEL	INFO	====> Epoch: 316032023-04-03 18:21:50,477	OUTPUT_MODEL	INFO	Train Epoch: 32 [58%]6042023-04-03 18:21:50,478	OUTPUT_MODEL	INFO	[2.2978014945983887, 2.4473774433135986, 10.045271873474121, 21.48757553100586, 2.239805221557617, 2.227947235107422, 3600, 0.00019922645137067577]6052023-04-03 18:22:26,451	OUTPUT_MODEL	INFO	====> Epoch: 326062023-04-03 18:23:07,618	OUTPUT_MODEL	INFO	Train Epoch: 33 [46%]6072023-04-03 18:23:07,619	OUTPUT_MODEL	INFO	[2.237431049346924, 2.447709083557129, 10.290753364562988, 19.436735153198242, 1.7436903715133667, 2.032357692718506, 3700, 0.00019920154806425444]6082023-04-03 18:23:54,112	OUTPUT_MODEL	INFO	====> Epoch: 336092023-04-03 18:24:24,291	OUTPUT_MODEL	INFO	Train Epoch: 34 [33%]6102023-04-03 18:24:24,292	OUTPUT_MODEL	INFO	[2.26959490776062, 2.605912446975708, 9.52496337890625, 20.383407592773438, -2.905646324157715, 1.5085349082946777, 3800, 0.0001991766478707464]6112023-04-03 18:25:21,806	OUTPUT_MODEL	INFO	====> Epoch: 346122023-04-03 18:25:41,379	OUTPUT_MODEL	INFO	Train Epoch: 35 [21%]6132023-04-03 18:25:41,380	OUTPUT_MODEL	INFO	[2.0927138328552246, 2.7200331687927246, 12.064619064331055, 24.195743560791016, -8.027067184448242, 2.2311747074127197, 3900, 0.00019915175078976256]6142023-04-03 18:26:50,390	OUTPUT_MODEL	INFO	====> Epoch: 356152023-04-03 18:26:59,423	OUTPUT_MODEL	INFO	Train Epoch: 36 [9%]6162023-04-03 18:26:59,425	OUTPUT_MODEL	INFO	[2.1338024139404297, 2.7548766136169434, 10.37733268737793, 23.2735538482666, 1.9825363159179688, 1.962978720664978, 4000, 0.00019912685682091382]6172023-04-03 18:27:00,744	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 36 to ././OUTPUT_MODEL/G_4000.pth6182023-04-03 18:27:01,121	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 36 to ././OUTPUT_MODEL/G_latest.pth6192023-04-03 18:28:17,011	OUTPUT_MODEL	INFO	Train Epoch: 36 [96%]6202023-04-03 18:28:17,012	OUTPUT_MODEL	INFO	[2.2706918716430664, 2.542262077331543, 8.60193157196045, 17.953332901000977, 0.320243775844574, 1.8192373514175415, 4100, 0.00019912685682091382]6212023-04-03 18:28:20,043	OUTPUT_MODEL	INFO	====> Epoch: 366222023-04-03 18:29:34,678	OUTPUT_MODEL	INFO	Train Epoch: 37 [84%]6232023-04-03 18:29:34,679	OUTPUT_MODEL	INFO	[2.139925479888916, 2.913670539855957, 13.524847030639648, 25.258798599243164, -3.641890048980713, 2.0086541175842285, 4200, 0.0001991019659638112]6242023-04-03 18:29:48,300	OUTPUT_MODEL	INFO	====> Epoch: 376252023-04-03 18:30:52,092	OUTPUT_MODEL	INFO	Train Epoch: 38 [72%]6262023-04-03 18:30:52,093	OUTPUT_MODEL	INFO	[2.1857120990753174, 2.5104198455810547, 11.219225883483887, 22.81366539001465, -5.734277248382568, 1.8997604846954346, 4300, 0.0001990770782180657]6272023-04-03 18:31:16,097	OUTPUT_MODEL	INFO	====> Epoch: 386282023-04-03 18:32:09,201	OUTPUT_MODEL	INFO	Train Epoch: 39 [60%]6292023-04-03 18:32:09,202	OUTPUT_MODEL	INFO	[2.3248777389526367, 2.6550004482269287, 10.908079147338867, 21.18838119506836, 2.1329407691955566, 1.913070559501648, 4400, 0.00019905219358328844]6302023-04-03 18:32:43,657	OUTPUT_MODEL	INFO	====> Epoch: 396312023-04-03 18:33:26,172	OUTPUT_MODEL	INFO	Train Epoch: 40 [47%]6322023-04-03 18:33:26,173	OUTPUT_MODEL	INFO	[2.091306447982788, 2.663189649581909, 10.168686866760254, 21.072172164916992, 2.0812251567840576, 1.6893799304962158, 4500, 0.0001990273120590905]6332023-04-03 18:34:11,198	OUTPUT_MODEL	INFO	====> Epoch: 406342023-04-03 18:34:42,832	OUTPUT_MODEL	INFO	Train Epoch: 41 [35%]6352023-04-03 18:34:42,833	OUTPUT_MODEL	INFO	[2.341952085494995, 2.47149395942688, 8.220488548278809, 20.790433883666992, 0.33565908670425415, 1.9910286664962769, 4600, 0.00019900243364508313]6362023-04-03 18:35:38,773	OUTPUT_MODEL	INFO	====> Epoch: 416372023-04-03 18:35:59,890	OUTPUT_MODEL	INFO	Train Epoch: 42 [23%]6382023-04-03 18:35:59,891	OUTPUT_MODEL	INFO	[1.9716335535049438, 3.024003505706787, 12.878390312194824, 24.293899536132812, -2.134439468383789, 2.0434868335723877, 4700, 0.0001989775583408775]6392023-04-03 18:37:06,488	OUTPUT_MODEL	INFO	====> Epoch: 426402023-04-03 18:37:17,190	OUTPUT_MODEL	INFO	Train Epoch: 43 [11%]6412023-04-03 18:37:17,191	OUTPUT_MODEL	INFO	[2.376145362854004, 2.6130778789520264, 8.256499290466309, 19.45535659790039, 0.4582523703575134, 2.0465145111083984, 4800, 0.00019895268614608487]6422023-04-03 18:38:33,094	OUTPUT_MODEL	INFO	Train Epoch: 43 [98%]6432023-04-03 18:38:33,095	OUTPUT_MODEL	INFO	[2.153395652770996, 2.9200758934020996, 11.029375076293945, 24.64362907409668, 2.093207836151123, 1.7287591695785522, 4900, 0.00019895268614608487]6442023-04-03 18:38:34,728	OUTPUT_MODEL	INFO	====> Epoch: 436452023-04-03 18:39:50,243	OUTPUT_MODEL	INFO	Train Epoch: 44 [86%]6462023-04-03 18:39:50,245	OUTPUT_MODEL	INFO	[1.9359724521636963, 3.0628817081451416, 13.323565483093262, 24.308717727661133, -1.0886633396148682, 1.9104527235031128, 5000, 0.0001989278170603166]6472023-04-03 18:39:51,501	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 44 to ././OUTPUT_MODEL/G_5000.pth6482023-04-03 18:39:51,875	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 44 to ././OUTPUT_MODEL/G_latest.pth6492023-04-03 18:40:03,565	OUTPUT_MODEL	INFO	====> Epoch: 446502023-04-03 18:41:08,845	OUTPUT_MODEL	INFO	Train Epoch: 45 [74%]6512023-04-03 18:41:08,846	OUTPUT_MODEL	INFO	[2.050382137298584, 3.118987798690796, 11.539374351501465, 24.53913116455078, 2.0387063026428223, 1.794594645500183, 5100, 0.00019890295108318404]6522023-04-03 18:41:31,372	OUTPUT_MODEL	INFO	====> Epoch: 456532023-04-03 18:42:26,177	OUTPUT_MODEL	INFO	Train Epoch: 46 [61%]6542023-04-03 18:42:26,178	OUTPUT_MODEL	INFO	[2.122774124145508, 2.826982021331787, 10.553146362304688, 23.472335815429688, 2.0314512252807617, 2.0211353302001953, 5200, 0.00019887808821429862]6552023-04-03 18:42:59,117	OUTPUT_MODEL	INFO	====> Epoch: 466562023-04-03 18:43:43,959	OUTPUT_MODEL	INFO	Train Epoch: 47 [49%]6572023-04-03 18:43:43,961	OUTPUT_MODEL	INFO	[1.9996843338012695, 2.906951427459717, 11.369466781616211, 24.093414306640625, -2.9310624599456787, 2.318174123764038, 5300, 0.00019885322845327182]6582023-04-03 18:44:27,346	OUTPUT_MODEL	INFO	====> Epoch: 476592023-04-03 18:45:00,720	OUTPUT_MODEL	INFO	Train Epoch: 48 [37%]6602023-04-03 18:45:00,721	OUTPUT_MODEL	INFO	[2.467015027999878, 2.473910331726074, 9.096479415893555, 21.683549880981445, 2.1773414611816406, 2.215325355529785, 5400, 0.00019882837179971516]6612023-04-03 18:45:55,395	OUTPUT_MODEL	INFO	====> Epoch: 486622023-04-03 18:46:18,124	OUTPUT_MODEL	INFO	Train Epoch: 49 [25%]6632023-04-03 18:46:18,125	OUTPUT_MODEL	INFO	[2.311033010482788, 2.383761405944824, 8.15893840789795, 18.83953094482422, 2.215975046157837, 1.775266408920288, 5500, 0.00019880351825324018]6642023-04-03 18:47:23,454	OUTPUT_MODEL	INFO	====> Epoch: 496652023-04-03 18:47:35,669	OUTPUT_MODEL	INFO	Train Epoch: 50 [12%]6662023-04-03 18:47:35,670	OUTPUT_MODEL	INFO	[2.218064308166504, 2.764418125152588, 10.227273941040039, 20.519620895385742, 1.8447258472442627, 2.038357734680176, 5600, 0.00019877866781345852]6672023-04-03 18:48:52,742	OUTPUT_MODEL	INFO	====> Epoch: 506682023-04-03 18:48:54,110	OUTPUT_MODEL	INFO	Train Epoch: 51 [0%]6692023-04-03 18:48:54,111	OUTPUT_MODEL	INFO	[2.2543153762817383, 2.6189889907836914, 8.637146949768066, 20.101539611816406, 0.18849259614944458, 1.8429911136627197, 5700, 0.00019875382047998183]6702023-04-03 18:50:10,930	OUTPUT_MODEL	INFO	Train Epoch: 51 [88%]6712023-04-03 18:50:10,931	OUTPUT_MODEL	INFO	[2.109736442565918, 2.770822525024414, 12.264480590820312, 22.425352096557617, 2.110776901245117, 2.2937865257263184, 5800, 0.00019875382047998183]6722023-04-03 18:50:21,192	OUTPUT_MODEL	INFO	====> Epoch: 516732023-04-03 18:51:27,821	OUTPUT_MODEL	INFO	Train Epoch: 52 [75%]6742023-04-03 18:51:27,822	OUTPUT_MODEL	INFO	[2.3748130798339844, 2.605560779571533, 10.489823341369629, 21.706016540527344, 1.8866878747940063, 1.9989104270935059, 5900, 0.00019872897625242182]6752023-04-03 18:51:48,731	OUTPUT_MODEL	INFO	====> Epoch: 526762023-04-03 18:52:45,072	OUTPUT_MODEL	INFO	Train Epoch: 53 [63%]6772023-04-03 18:52:45,073	OUTPUT_MODEL	INFO	[2.477243185043335, 2.621230125427246, 8.247370719909668, 18.831295013427734, 1.9664958715438843, 1.9741337299346924, 6000, 0.00019870413513039026]6782023-04-03 18:52:46,366	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 53 to ././OUTPUT_MODEL/G_6000.pth6792023-04-03 18:52:46,917	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 53 to ././OUTPUT_MODEL/G_latest.pth6802023-04-03 18:53:17,799	OUTPUT_MODEL	INFO	====> Epoch: 536812023-04-03 18:54:03,511	OUTPUT_MODEL	INFO	Train Epoch: 54 [51%]6822023-04-03 18:54:03,512	OUTPUT_MODEL	INFO	[2.4787888526916504, 2.449953317642212, 8.823800086975098, 19.612260818481445, -0.21816575527191162, 2.110691785812378, 6100, 0.00019867929711349895]6832023-04-03 18:54:45,374	OUTPUT_MODEL	INFO	====> Epoch: 546842023-04-03 18:55:20,924	OUTPUT_MODEL	INFO	Train Epoch: 55 [39%]6852023-04-03 18:55:20,926	OUTPUT_MODEL	INFO	[2.353349208831787, 2.5186686515808105, 9.203422546386719, 20.825178146362305, 1.8998749256134033, 2.1684954166412354, 6200, 0.00019865446220135974]6862023-04-03 18:56:14,174	OUTPUT_MODEL	INFO	====> Epoch: 556872023-04-03 18:56:38,280	OUTPUT_MODEL	INFO	Train Epoch: 56 [26%]6882023-04-03 18:56:38,281	OUTPUT_MODEL	INFO	[2.308609962463379, 2.892343521118164, 9.42581558227539, 21.149776458740234, -2.399651527404785, 2.0232582092285156, 6300, 0.00019862963039358455]6892023-04-03 18:57:41,858	OUTPUT_MODEL	INFO	====> Epoch: 566902023-04-03 18:57:55,605	OUTPUT_MODEL	INFO	Train Epoch: 57 [14%]6912023-04-03 18:57:55,606	OUTPUT_MODEL	INFO	[1.9328200817108154, 2.9044880867004395, 13.352548599243164, 24.769920349121094, -1.3521555662155151, 1.7427117824554443, 6400, 0.00019860480168978534]6922023-04-03 18:59:09,611	OUTPUT_MODEL	INFO	====> Epoch: 576932023-04-03 18:59:12,612	OUTPUT_MODEL	INFO	Train Epoch: 58 [2%]6942023-04-03 18:59:12,613	OUTPUT_MODEL	INFO	[2.2738442420959473, 2.61395525932312, 11.258807182312012, 22.371414184570312, -0.4526987075805664, 2.1035289764404297, 6500, 0.0001985799760895741]6952023-04-03 19:00:28,999	OUTPUT_MODEL	INFO	Train Epoch: 58 [89%]6962023-04-03 19:00:29,000	OUTPUT_MODEL	INFO	[2.1149749755859375, 2.755798816680908, 12.13713550567627, 22.89972686767578, -1.6883606910705566, 1.957497000694275, 6600, 0.0001985799760895741]6972023-04-03 19:00:37,893	OUTPUT_MODEL	INFO	====> Epoch: 586982023-04-03 19:01:46,014	OUTPUT_MODEL	INFO	Train Epoch: 59 [77%]6992023-04-03 19:01:46,015	OUTPUT_MODEL	INFO	[1.8427226543426514, 3.1075778007507324, 12.690406799316406, 23.609493255615234, -3.74533748626709, 2.1364355087280273, 6700, 0.0001985551535925629]7002023-04-03 19:02:05,766	OUTPUT_MODEL	INFO	====> Epoch: 597012023-04-03 19:03:03,618	OUTPUT_MODEL	INFO	Train Epoch: 60 [65%]7022023-04-03 19:03:03,619	OUTPUT_MODEL	INFO	[2.2326865196228027, 2.8139004707336426, 10.744124412536621, 22.794784545898438, 2.088674545288086, 1.723044514656067, 6800, 0.00019853033419836382]7032023-04-03 19:03:33,299	OUTPUT_MODEL	INFO	====> Epoch: 607042023-04-03 19:04:20,572	OUTPUT_MODEL	INFO	Train Epoch: 61 [53%]7052023-04-03 19:04:20,573	OUTPUT_MODEL	INFO	[2.343691349029541, 2.4418091773986816, 7.416339874267578, 18.400928497314453, 0.5415331125259399, 1.6533516645431519, 6900, 0.000198505517906589]7062023-04-03 19:05:00,859	OUTPUT_MODEL	INFO	====> Epoch: 617072023-04-03 19:05:37,237	OUTPUT_MODEL	INFO	Train Epoch: 62 [40%]7082023-04-03 19:05:37,239	OUTPUT_MODEL	INFO	[2.194624900817871, 2.5803065299987793, 12.914298057556152, 22.950361251831055, 1.8289921283721924, 1.5573049783706665, 7000, 0.00019848070471685067]7092023-04-03 19:05:38,682	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 62 to ././OUTPUT_MODEL/G_7000.pth7102023-04-03 19:05:39,033	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 62 to ././OUTPUT_MODEL/G_latest.pth7112023-04-03 19:06:29,903	OUTPUT_MODEL	INFO	====> Epoch: 627122023-04-03 19:06:55,438	OUTPUT_MODEL	INFO	Train Epoch: 63 [28%]7132023-04-03 19:06:55,441	OUTPUT_MODEL	INFO	[2.1440670490264893, 2.6960036754608154, 12.482332229614258, 23.745338439941406, -2.7604401111602783, 1.6685200929641724, 7100, 0.00019845589462876104]7142023-04-03 19:07:57,333	OUTPUT_MODEL	INFO	====> Epoch: 637152023-04-03 19:08:12,554	OUTPUT_MODEL	INFO	Train Epoch: 64 [16%]7162023-04-03 19:08:12,555	OUTPUT_MODEL	INFO	[2.3231191635131836, 2.783243417739868, 9.341412544250488, 21.025428771972656, 1.957608938217163, 2.087961196899414, 7200, 0.00019843108764193245]7172023-04-03 19:09:24,889	OUTPUT_MODEL	INFO	====> Epoch: 647182023-04-03 19:09:29,252	OUTPUT_MODEL	INFO	Train Epoch: 65 [4%]7192023-04-03 19:09:29,253	OUTPUT_MODEL	INFO	[2.3423871994018555, 2.6366093158721924, 7.980807781219482, 19.368406295776367, 1.874494194984436, 1.626427412033081, 7300, 0.0001984062837559772]7202023-04-03 19:10:45,787	OUTPUT_MODEL	INFO	Train Epoch: 65 [91%]7212023-04-03 19:10:45,788	OUTPUT_MODEL	INFO	[2.3859703540802, 2.5738325119018555, 11.079670906066895, 22.145355224609375, 1.8510515689849854, 1.749354362487793, 7400, 0.0001984062837559772]7222023-04-03 19:10:53,235	OUTPUT_MODEL	INFO	====> Epoch: 657232023-04-03 19:12:02,677	OUTPUT_MODEL	INFO	Train Epoch: 66 [79%]7242023-04-03 19:12:02,678	OUTPUT_MODEL	INFO	[2.120370388031006, 3.2662298679351807, 12.455361366271973, 24.569854736328125, -5.756799697875977, 1.9203685522079468, 7500, 0.00019838148297050769]7252023-04-03 19:12:20,670	OUTPUT_MODEL	INFO	====> Epoch: 667262023-04-03 19:13:19,932	OUTPUT_MODEL	INFO	Train Epoch: 67 [67%]7272023-04-03 19:13:19,933	OUTPUT_MODEL	INFO	[2.00138521194458, 3.100071907043457, 12.487069129943848, 23.11647605895996, -0.13515031337738037, 2.0163161754608154, 7600, 0.00019835668528513637]7282023-04-03 19:13:48,222	OUTPUT_MODEL	INFO	====> Epoch: 677292023-04-03 19:14:36,906	OUTPUT_MODEL	INFO	Train Epoch: 68 [54%]7302023-04-03 19:14:36,907	OUTPUT_MODEL	INFO	[2.380859375, 3.009873151779175, 8.989574432373047, 20.384008407592773, 2.0471432209014893, 1.692957878112793, 7700, 0.00019833189069947573]7312023-04-03 19:15:15,992	OUTPUT_MODEL	INFO	====> Epoch: 687322023-04-03 19:15:53,867	OUTPUT_MODEL	INFO	Train Epoch: 69 [42%]7332023-04-03 19:15:53,868	OUTPUT_MODEL	INFO	[2.1940395832061768, 2.809704065322876, 11.526653289794922, 23.969032287597656, -1.5502030849456787, 2.307913064956665, 7800, 0.0001983070992131383]7342023-04-03 19:16:43,550	OUTPUT_MODEL	INFO	====> Epoch: 697352023-04-03 19:17:10,614	OUTPUT_MODEL	INFO	Train Epoch: 70 [30%]7362023-04-03 19:17:10,615	OUTPUT_MODEL	INFO	[2.31561541557312, 3.0018231868743896, 9.32812786102295, 20.502830505371094, 1.9411005973815918, 1.7170722484588623, 7900, 0.00019828231082573666]7372023-04-03 19:18:11,030	OUTPUT_MODEL	INFO	====> Epoch: 707382023-04-03 19:18:27,526	OUTPUT_MODEL	INFO	Train Epoch: 71 [18%]7392023-04-03 19:18:27,527	OUTPUT_MODEL	INFO	[2.1446502208709717, 2.7200613021850586, 11.805608749389648, 21.076885223388672, -2.1071529388427734, 1.556119441986084, 8000, 0.00019825752553688343]7402023-04-03 19:18:29,002	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 71 to ././OUTPUT_MODEL/G_8000.pth7412023-04-03 19:18:29,362	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 71 to ././OUTPUT_MODEL/G_latest.pth7422023-04-03 19:19:40,108	OUTPUT_MODEL	INFO	====> Epoch: 717432023-04-03 19:19:46,091	OUTPUT_MODEL	INFO	Train Epoch: 72 [5%]7442023-04-03 19:19:46,092	OUTPUT_MODEL	INFO	[2.3422889709472656, 2.9838404655456543, 12.841968536376953, 23.63225746154785, 2.0724387168884277, 1.8672897815704346, 8100, 0.0001982327433461913]7452023-04-03 19:21:02,394	OUTPUT_MODEL	INFO	Train Epoch: 72 [93%]7462023-04-03 19:21:02,396	OUTPUT_MODEL	INFO	[2.2252533435821533, 2.4757161140441895, 11.608266830444336, 22.711406707763672, -1.0431954860687256, 2.0403130054473877, 8200, 0.0001982327433461913]7472023-04-03 19:21:08,361	OUTPUT_MODEL	INFO	====> Epoch: 727482023-04-03 19:22:19,563	OUTPUT_MODEL	INFO	Train Epoch: 73 [81%]7492023-04-03 19:22:19,564	OUTPUT_MODEL	INFO	[2.4951765537261963, 2.4517409801483154, 7.944416046142578, 19.116697311401367, 2.0545287132263184, 2.210294246673584, 8300, 0.00019820796425327303]7502023-04-03 19:22:36,262	OUTPUT_MODEL	INFO	====> Epoch: 737512023-04-03 19:23:36,972	OUTPUT_MODEL	INFO	Train Epoch: 74 [68%]7522023-04-03 19:23:36,973	OUTPUT_MODEL	INFO	[2.078153371810913, 2.8622384071350098, 12.01279067993164, 23.816219329833984, -5.193841934204102, 1.838731288909912, 8400, 0.00019818318825774137]7532023-04-03 19:24:03,927	OUTPUT_MODEL	INFO	====> Epoch: 747542023-04-03 19:24:54,040	OUTPUT_MODEL	INFO	Train Epoch: 75 [56%]7552023-04-03 19:24:54,040	OUTPUT_MODEL	INFO	[1.9639904499053955, 2.7344160079956055, 11.238096237182617, 22.72721290588379, -4.55881404876709, 1.8278330564498901, 8500, 0.00019815841535920914]7562023-04-03 19:25:31,428	OUTPUT_MODEL	INFO	====> Epoch: 757572023-04-03 19:26:11,083	OUTPUT_MODEL	INFO	Train Epoch: 76 [44%]7582023-04-03 19:26:11,084	OUTPUT_MODEL	INFO	[2.3657093048095703, 2.422987222671509, 10.804490089416504, 21.579408645629883, 1.8844661712646484, 2.1051084995269775, 8600, 0.00019813364555728923]7592023-04-03 19:26:59,168	OUTPUT_MODEL	INFO	====> Epoch: 767602023-04-03 19:27:28,050	OUTPUT_MODEL	INFO	Train Epoch: 77 [32%]7612023-04-03 19:27:28,052	OUTPUT_MODEL	INFO	[2.1707022190093994, 2.8680686950683594, 10.03565788269043, 21.278257369995117, 2.2206437587738037, 1.8100509643554688, 8700, 0.00019810887885159456]7622023-04-03 19:28:26,881	OUTPUT_MODEL	INFO	====> Epoch: 777632023-04-03 19:28:44,861	OUTPUT_MODEL	INFO	Train Epoch: 78 [19%]7642023-04-03 19:28:44,862	OUTPUT_MODEL	INFO	[2.2001051902770996, 3.1110916137695312, 11.244915962219238, 22.617652893066406, -4.220756530761719, 1.9247193336486816, 8800, 0.0001980841152417381]7652023-04-03 19:29:54,398	OUTPUT_MODEL	INFO	====> Epoch: 787662023-04-03 19:30:01,863	OUTPUT_MODEL	INFO	Train Epoch: 79 [7%]7672023-04-03 19:30:01,864	OUTPUT_MODEL	INFO	[2.092662811279297, 2.722276210784912, 11.170878410339355, 22.300167083740234, -8.792879104614258, 1.8720600605010986, 8900, 0.00019805935472733287]7682023-04-03 19:31:18,147	OUTPUT_MODEL	INFO	Train Epoch: 79 [95%]7692023-04-03 19:31:18,148	OUTPUT_MODEL	INFO	[2.2086987495422363, 2.4866325855255127, 11.377270698547363, 20.65390968322754, 1.7215783596038818, 2.054108142852783, 9000, 0.00019805935472733287]7702023-04-03 19:31:19,970	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 79 to ././OUTPUT_MODEL/G_9000.pth7712023-04-03 19:31:20,321	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 79 to ././OUTPUT_MODEL/G_latest.pth7722023-04-03 19:31:24,432	OUTPUT_MODEL	INFO	====> Epoch: 797732023-04-03 19:32:37,004	OUTPUT_MODEL	INFO	Train Epoch: 80 [82%]7742023-04-03 19:32:37,006	OUTPUT_MODEL	INFO	[2.214087963104248, 3.276862144470215, 10.560446739196777, 21.014928817749023, -1.8667384386062622, 2.0818896293640137, 9100, 0.00019803459730799195]7752023-04-03 19:32:52,132	OUTPUT_MODEL	INFO	====> Epoch: 807762023-04-03 19:33:54,265	OUTPUT_MODEL	INFO	Train Epoch: 81 [70%]7772023-04-03 19:33:54,266	OUTPUT_MODEL	INFO	[2.2910823822021484, 2.5565247535705566, 8.475238800048828, 18.659738540649414, 1.8803985118865967, 1.925213098526001, 9200, 0.00019800984298332845]7782023-04-03 19:34:19,727	OUTPUT_MODEL	INFO	====> Epoch: 817792023-04-03 19:35:11,440	OUTPUT_MODEL	INFO	Train Epoch: 82 [58%]7802023-04-03 19:35:11,441	OUTPUT_MODEL	INFO	[2.3401410579681396, 2.6100168228149414, 8.342323303222656, 20.334266662597656, 2.184380054473877, 2.019214391708374, 9300, 0.00019798509175295552]7812023-04-03 19:35:47,380	OUTPUT_MODEL	INFO	====> Epoch: 827822023-04-03 19:36:28,624	OUTPUT_MODEL	INFO	Train Epoch: 83 [46%]7832023-04-03 19:36:28,625	OUTPUT_MODEL	INFO	[2.290769577026367, 2.5731897354125977, 8.441933631896973, 19.34797477722168, 1.7283148765563965, 2.0907037258148193, 9400, 0.0001979603436164864]7842023-04-03 19:37:15,020	OUTPUT_MODEL	INFO	====> Epoch: 837852023-04-03 19:37:45,249	OUTPUT_MODEL	INFO	Train Epoch: 84 [33%]7862023-04-03 19:37:45,250	OUTPUT_MODEL	INFO	[2.294942855834961, 2.689972400665283, 9.09426498413086, 19.707487106323242, -2.4075279235839844, 1.6330012083053589, 9500, 0.00019793559857353432]7872023-04-03 19:38:42,706	OUTPUT_MODEL	INFO	====> Epoch: 847882023-04-03 19:39:02,250	OUTPUT_MODEL	INFO	Train Epoch: 85 [21%]7892023-04-03 19:39:02,251	OUTPUT_MODEL	INFO	[2.1089088916778564, 2.807429313659668, 10.57873249053955, 21.658729553222656, -7.865320682525635, 1.7409729957580566, 9600, 0.00019791085662371262]7902023-04-03 19:40:10,627	OUTPUT_MODEL	INFO	====> Epoch: 857912023-04-03 19:40:19,726	OUTPUT_MODEL	INFO	Train Epoch: 86 [9%]7922023-04-03 19:40:19,727	OUTPUT_MODEL	INFO	[2.4605777263641357, 2.6199331283569336, 9.424223899841309, 20.826648712158203, 1.9414063692092896, 1.8759279251098633, 9700, 0.00019788611776663464]7932023-04-03 19:41:36,080	OUTPUT_MODEL	INFO	Train Epoch: 86 [96%]7942023-04-03 19:41:36,081	OUTPUT_MODEL	INFO	[2.25709867477417, 2.540407180786133, 8.644290924072266, 19.772554397583008, 0.3343607187271118, 1.9784295558929443, 9800, 0.00019788611776663464]7952023-04-03 19:41:39,095	OUTPUT_MODEL	INFO	====> Epoch: 867962023-04-03 19:42:53,056	OUTPUT_MODEL	INFO	Train Epoch: 87 [84%]7972023-04-03 19:42:53,057	OUTPUT_MODEL	INFO	[2.242147922515869, 2.6610617637634277, 10.615656852722168, 21.921676635742188, -4.033838272094727, 1.651625156402588, 9900, 0.0001978613820019138]7982023-04-03 19:43:06,639	OUTPUT_MODEL	INFO	====> Epoch: 877992023-04-03 19:44:10,324	OUTPUT_MODEL	INFO	Train Epoch: 88 [72%]8002023-04-03 19:44:10,326	OUTPUT_MODEL	INFO	[2.062884569168091, 3.0218117237091064, 12.135512351989746, 23.094406127929688, -6.042035102844238, 1.7699990272521973, 10000, 0.00019783664932916355]8012023-04-03 19:44:11,764	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 88 to ././OUTPUT_MODEL/G_10000.pth8022023-04-03 19:44:12,114	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 88 to ././OUTPUT_MODEL/G_latest.pth8032023-04-03 19:44:35,762	OUTPUT_MODEL	INFO	====> Epoch: 888042023-04-03 19:45:28,997	OUTPUT_MODEL	INFO	Train Epoch: 89 [60%]8052023-04-03 19:45:28,998	OUTPUT_MODEL	INFO	[2.2025046348571777, 2.846670627593994, 9.955955505371094, 21.401071548461914, 2.107473850250244, 1.7100194692611694, 10100, 0.0001978119197479974]8062023-04-03 19:46:03,459	OUTPUT_MODEL	INFO	====> Epoch: 898072023-04-03 19:46:45,978	OUTPUT_MODEL	INFO	Train Epoch: 90 [47%]8082023-04-03 19:46:45,979	OUTPUT_MODEL	INFO	[1.9914801120758057, 3.039623498916626, 12.860808372497559, 23.9461612701416, 2.007969379425049, 1.417041301727295, 10200, 0.0001977871932580289]8092023-04-03 19:47:31,428	OUTPUT_MODEL	INFO	====> Epoch: 908102023-04-03 19:48:03,446	OUTPUT_MODEL	INFO	Train Epoch: 91 [35%]8112023-04-03 19:48:03,447	OUTPUT_MODEL	INFO	[2.270509719848633, 2.7170798778533936, 10.77274227142334, 22.01917839050293, 0.341497004032135, 1.925162672996521, 10300, 0.00019776246985887165]8122023-04-03 19:49:00,384	OUTPUT_MODEL	INFO	====> Epoch: 918132023-04-03 19:49:21,662	OUTPUT_MODEL	INFO	Train Epoch: 92 [23%]8142023-04-03 19:49:21,663	OUTPUT_MODEL	INFO	[1.9947762489318848, 2.894284963607788, 11.994261741638184, 23.310028076171875, -2.2317733764648438, 1.9493744373321533, 10400, 0.0001977377495501393]8152023-04-03 19:50:28,717	OUTPUT_MODEL	INFO	====> Epoch: 928162023-04-03 19:50:39,356	OUTPUT_MODEL	INFO	Train Epoch: 93 [11%]8172023-04-03 19:50:39,357	OUTPUT_MODEL	INFO	[2.4618051052093506, 2.2484354972839355, 9.06884479522705, 19.56756019592285, -0.019451618194580078, 1.7691856622695923, 10500, 0.0001977130323314455]8182023-04-03 19:51:55,676	OUTPUT_MODEL	INFO	Train Epoch: 93 [98%]8192023-04-03 19:51:55,677	OUTPUT_MODEL	INFO	[2.291053056716919, 2.453062057495117, 8.044502258300781, 21.095151901245117, 2.0365042686462402, 1.503006100654602, 10600, 0.0001977130323314455]8202023-04-03 19:51:57,501	OUTPUT_MODEL	INFO	====> Epoch: 938212023-04-03 19:53:13,545	OUTPUT_MODEL	INFO	Train Epoch: 94 [86%]8222023-04-03 19:53:13,547	OUTPUT_MODEL	INFO	[2.0174198150634766, 3.002519130706787, 10.744830131530762, 22.71245765686035, -1.6137800216674805, 1.5240461826324463, 10700, 0.00019768831820240408]8232023-04-03 19:53:25,617	OUTPUT_MODEL	INFO	====> Epoch: 948242023-04-03 19:54:31,163	OUTPUT_MODEL	INFO	Train Epoch: 95 [74%]8252023-04-03 19:54:31,164	OUTPUT_MODEL	INFO	[1.9791758060455322, 3.038991689682007, 12.502904891967773, 22.198877334594727, 2.010383129119873, 1.6627893447875977, 10800, 0.00019766360716262876]8262023-04-03 19:54:53,708	OUTPUT_MODEL	INFO	====> Epoch: 958272023-04-03 19:55:48,829	OUTPUT_MODEL	INFO	Train Epoch: 96 [61%]8282023-04-03 19:55:48,830	OUTPUT_MODEL	INFO	[2.4521961212158203, 2.5651869773864746, 8.860393524169922, 19.50566291809082, 2.0127437114715576, 1.9439582824707031, 10900, 0.00019763889921173343]8292023-04-03 19:56:21,888	OUTPUT_MODEL	INFO	====> Epoch: 968302023-04-03 19:57:06,454	OUTPUT_MODEL	INFO	Train Epoch: 97 [49%]8312023-04-03 19:57:06,455	OUTPUT_MODEL	INFO	[1.9950447082519531, 2.7626662254333496, 9.986225128173828, 21.833284378051758, -3.160635471343994, 1.612749457359314, 11000, 0.00019761419434933197]8322023-04-03 19:57:07,718	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 97 to ././OUTPUT_MODEL/G_11000.pth8332023-04-03 19:57:08,088	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 97 to ././OUTPUT_MODEL/G_latest.pth8342023-04-03 19:57:52,202	OUTPUT_MODEL	INFO	====> Epoch: 978352023-04-03 19:58:26,154	OUTPUT_MODEL	INFO	Train Epoch: 98 [37%]8362023-04-03 19:58:26,155	OUTPUT_MODEL	INFO	[2.3544397354125977, 2.4375946521759033, 8.922677993774414, 19.840471267700195, 2.1647486686706543, 2.0953714847564697, 11100, 0.0001975894925750383]8372023-04-03 19:59:21,212	OUTPUT_MODEL	INFO	====> Epoch: 988382023-04-03 19:59:44,810	OUTPUT_MODEL	INFO	Train Epoch: 99 [25%]8392023-04-03 19:59:44,811	OUTPUT_MODEL	INFO	[2.244258165359497, 2.810145378112793, 10.337130546569824, 21.764366149902344, 2.1804375648498535, 1.7687195539474487, 11200, 0.0001975647938884664]8402023-04-03 20:00:51,332	OUTPUT_MODEL	INFO	====> Epoch: 998412023-04-03 20:01:04,306	OUTPUT_MODEL	INFO	Train Epoch: 100 [12%]8422023-04-03 20:01:04,307	OUTPUT_MODEL	INFO	[2.4643852710723877, 2.372645378112793, 7.031031608581543, 17.890419006347656, 1.838219165802002, 1.972226619720459, 11300, 0.00019754009828923033]8432023-04-03 20:02:21,750	OUTPUT_MODEL	INFO	====> Epoch: 1008442023-04-03 20:02:23,231	OUTPUT_MODEL	INFO	Train Epoch: 101 [0%]8452023-04-03 20:02:23,232	OUTPUT_MODEL	INFO	[2.306429147720337, 2.494112014770508, 8.11408805847168, 16.018295288085938, 0.21952849626541138, 1.8010765314102173, 11400, 0.00019751540577694416]8462023-04-03 20:03:41,598	OUTPUT_MODEL	INFO	Train Epoch: 101 [88%]8472023-04-03 20:03:41,599	OUTPUT_MODEL	INFO	[2.2029073238372803, 2.7907183170318604, 11.098347663879395, 20.8450870513916, 2.0787014961242676, 2.190864324569702, 11500, 0.00019751540577694416]8482023-04-03 20:03:51,933	OUTPUT_MODEL	INFO	====> Epoch: 1018492023-04-03 20:04:59,242	OUTPUT_MODEL	INFO	Train Epoch: 102 [75%]8502023-04-03 20:04:59,243	OUTPUT_MODEL	INFO	[2.1439332962036133, 2.789710521697998, 10.518165588378906, 20.188207626342773, 1.8730192184448242, 1.634109377861023, 11600, 0.00019749071635122203]8512023-04-03 20:05:20,484	OUTPUT_MODEL	INFO	====> Epoch: 1028522023-04-03 20:06:17,120	OUTPUT_MODEL	INFO	Train Epoch: 103 [63%]8532023-04-03 20:06:17,121	OUTPUT_MODEL	INFO	[2.4488847255706787, 2.508928060531616, 8.464111328125, 20.14604377746582, 1.978141188621521, 1.763296127319336, 11700, 0.00019746603001167813]8542023-04-03 20:06:48,364	OUTPUT_MODEL	INFO	====> Epoch: 1038552023-04-03 20:07:34,384	OUTPUT_MODEL	INFO	Train Epoch: 104 [51%]8562023-04-03 20:07:34,385	OUTPUT_MODEL	INFO	[2.1589791774749756, 2.635673999786377, 12.244424819946289, 24.047082901000977, -0.31019794940948486, 2.2014617919921875, 11800, 0.00019744134675792665]8572023-04-03 20:08:16,385	OUTPUT_MODEL	INFO	====> Epoch: 1048582023-04-03 20:08:51,269	OUTPUT_MODEL	INFO	Train Epoch: 105 [39%]8592023-04-03 20:08:51,270	OUTPUT_MODEL	INFO	[2.3789772987365723, 2.558454990386963, 9.472604751586914, 19.221088409423828, 1.891870379447937, 1.9808191061019897, 11900, 0.0001974166665895819]8602023-04-03 20:09:44,672	OUTPUT_MODEL	INFO	====> Epoch: 1058612023-04-03 20:10:08,869	OUTPUT_MODEL	INFO	Train Epoch: 106 [26%]8622023-04-03 20:10:08,870	OUTPUT_MODEL	INFO	[2.2038466930389404, 2.748567819595337, 10.102746963500977, 21.396474838256836, -2.187324047088623, 2.0456013679504395, 12000, 0.0001973919895062582]8632023-04-03 20:10:10,172	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 106 to ././OUTPUT_MODEL/G_12000.pth8642023-04-03 20:10:10,567	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 106 to ././OUTPUT_MODEL/G_latest.pth8652023-04-03 20:11:13,989	OUTPUT_MODEL	INFO	====> Epoch: 1068662023-04-03 20:11:27,540	OUTPUT_MODEL	INFO	Train Epoch: 107 [14%]8672023-04-03 20:11:27,541	OUTPUT_MODEL	INFO	[2.000364303588867, 2.7178475856781006, 12.245311737060547, 22.42671775817871, -1.97821044921875, 1.7665205001831055, 12100, 0.0001973673155075699]8682023-04-03 20:12:42,204	OUTPUT_MODEL	INFO	====> Epoch: 1078692023-04-03 20:12:45,188	OUTPUT_MODEL	INFO	Train Epoch: 108 [2%]8702023-04-03 20:12:45,190	OUTPUT_MODEL	INFO	[2.102518081665039, 2.9915213584899902, 10.816621780395508, 23.42107582092285, -0.38749581575393677, 2.006298780441284, 12200, 0.00019734264459313146]8712023-04-03 20:14:01,989	OUTPUT_MODEL	INFO	Train Epoch: 108 [89%]8722023-04-03 20:14:01,990	OUTPUT_MODEL	INFO	[1.950843334197998, 2.6562395095825195, 11.05481243133545, 20.8515567779541, -2.0178306102752686, 1.7392479181289673, 12300, 0.00019734264459313146]8732023-04-03 20:14:10,839	OUTPUT_MODEL	INFO	====> Epoch: 1088742023-04-03 20:15:19,253	OUTPUT_MODEL	INFO	Train Epoch: 109 [77%]8752023-04-03 20:15:19,254	OUTPUT_MODEL	INFO	[2.022181749343872, 2.757147789001465, 10.85734748840332, 21.832143783569336, -4.788760662078857, 1.7804771661758423, 12400, 0.0001973179767625573]8762023-04-03 20:15:38,875	OUTPUT_MODEL	INFO	====> Epoch: 1098772023-04-03 20:16:37,154	OUTPUT_MODEL	INFO	Train Epoch: 110 [65%]8782023-04-03 20:16:37,155	OUTPUT_MODEL	INFO	[2.1785149574279785, 2.925473213195801, 10.536865234375, 20.716238021850586, 2.075122833251953, 1.8247686624526978, 12500, 0.00019729331201546197]8792023-04-03 20:17:07,156	OUTPUT_MODEL	INFO	====> Epoch: 1108802023-04-03 20:17:54,658	OUTPUT_MODEL	INFO	Train Epoch: 111 [53%]8812023-04-03 20:17:54,659	OUTPUT_MODEL	INFO	[1.9489551782608032, 3.2387197017669678, 11.578862190246582, 22.893863677978516, 0.4317651391029358, 1.47342848777771, 12600, 0.00019726865035146003]8822023-04-03 20:18:35,495	OUTPUT_MODEL	INFO	====> Epoch: 1118832023-04-03 20:19:12,105	OUTPUT_MODEL	INFO	Train Epoch: 112 [40%]8842023-04-03 20:19:12,106	OUTPUT_MODEL	INFO	[2.1665101051330566, 2.52164888381958, 12.002113342285156, 21.004833221435547, 1.8019821643829346, 1.4344761371612549, 12700, 0.0001972439917701661]8852023-04-03 20:20:04,332	OUTPUT_MODEL	INFO	====> Epoch: 1128862023-04-03 20:20:30,029	OUTPUT_MODEL	INFO	Train Epoch: 113 [28%]8872023-04-03 20:20:30,031	OUTPUT_MODEL	INFO	[1.9642139673233032, 2.8582119941711426, 12.304624557495117, 22.321239471435547, -2.6999270915985107, 1.4151687622070312, 12800, 0.0001972193362711948]8882023-04-03 20:21:32,090	OUTPUT_MODEL	INFO	====> Epoch: 1138892023-04-03 20:21:47,783	OUTPUT_MODEL	INFO	Train Epoch: 114 [16%]8902023-04-03 20:21:47,784	OUTPUT_MODEL	INFO	[2.368901491165161, 2.539151430130005, 8.098416328430176, 17.994552612304688, 1.9517022371292114, 1.9622920751571655, 12900, 0.0001971946838541609]8912023-04-03 20:23:01,404	OUTPUT_MODEL	INFO	====> Epoch: 1148922023-04-03 20:23:05,787	OUTPUT_MODEL	INFO	Train Epoch: 115 [4%]8932023-04-03 20:23:05,788	OUTPUT_MODEL	INFO	[2.4643006324768066, 2.572916030883789, 7.764427661895752, 20.026155471801758, 1.8621854782104492, 1.6395525932312012, 13000, 0.0001971700345186791]8942023-04-03 20:23:07,125	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 115 to ././OUTPUT_MODEL/G_13000.pth8952023-04-03 20:23:07,497	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 115 to ././OUTPUT_MODEL/G_latest.pth8962023-04-03 20:24:24,073	OUTPUT_MODEL	INFO	Train Epoch: 115 [91%]8972023-04-03 20:24:24,074	OUTPUT_MODEL	INFO	[2.1920266151428223, 2.903268337249756, 9.671224594116211, 18.11431312561035, 1.8203665018081665, 1.8684853315353394, 13100, 0.0001971700345186791]8982023-04-03 20:24:31,715	OUTPUT_MODEL	INFO	====> Epoch: 1158992023-04-03 20:25:43,003	OUTPUT_MODEL	INFO	Train Epoch: 116 [79%]9002023-04-03 20:25:43,004	OUTPUT_MODEL	INFO	[2.028818368911743, 3.0835723876953125, 10.920414924621582, 23.608930587768555, -5.291276931762695, 1.8705180883407593, 13200, 0.00019714538826436426]9012023-04-03 20:26:01,116	OUTPUT_MODEL	INFO	====> Epoch: 1169022023-04-03 20:27:01,399	OUTPUT_MODEL	INFO	Train Epoch: 117 [67%]9032023-04-03 20:27:01,400	OUTPUT_MODEL	INFO	[1.9356404542922974, 3.1410937309265137, 11.10919189453125, 22.427494049072266, -0.27776384353637695, 1.807210922241211, 13300, 0.0001971207450908312]9042023-04-03 20:27:30,074	OUTPUT_MODEL	INFO	====> Epoch: 1179052023-04-03 20:28:20,149	OUTPUT_MODEL	INFO	Train Epoch: 118 [54%]9062023-04-03 20:28:20,151	OUTPUT_MODEL	INFO	[2.2987680435180664, 2.6323108673095703, 8.480164527893066, 19.554784774780273, 2.022968292236328, 1.7360217571258545, 13400, 0.00019709610499769482]9072023-04-03 20:29:00,495	OUTPUT_MODEL	INFO	====> Epoch: 1189082023-04-03 20:29:40,279	OUTPUT_MODEL	INFO	Train Epoch: 119 [42%]9092023-04-03 20:29:40,280	OUTPUT_MODEL	INFO	[2.4278364181518555, 2.672037363052368, 8.82237720489502, 20.580907821655273, -2.0039565563201904, 2.085637092590332, 13500, 0.0001970714679845701]9102023-04-03 20:30:32,753	OUTPUT_MODEL	INFO	====> Epoch: 1199112023-04-03 20:31:01,049	OUTPUT_MODEL	INFO	Train Epoch: 120 [30%]9122023-04-03 20:31:01,050	OUTPUT_MODEL	INFO	[2.153606414794922, 2.7455084323883057, 9.443818092346191, 20.314517974853516, 1.937009572982788, 1.662386178970337, 13600, 0.000197046834051072]9132023-04-03 20:32:05,357	OUTPUT_MODEL	INFO	====> Epoch: 1209142023-04-03 20:32:22,679	OUTPUT_MODEL	INFO	Train Epoch: 121 [18%]9152023-04-03 20:32:22,681	OUTPUT_MODEL	INFO	[2.1438961029052734, 2.912036418914795, 10.571479797363281, 20.727535247802734, -2.235257863998413, 1.5111931562423706, 13700, 0.00019702220319681561]9162023-04-03 20:33:36,729	OUTPUT_MODEL	INFO	====> Epoch: 1219172023-04-03 20:33:42,871	OUTPUT_MODEL	INFO	Train Epoch: 122 [5%]9182023-04-03 20:33:42,872	OUTPUT_MODEL	INFO	[2.372283935546875, 2.7200310230255127, 9.89767837524414, 21.296384811401367, 2.0403099060058594, 1.6815271377563477, 13800, 0.000196997575421416]9192023-04-03 20:35:02,247	OUTPUT_MODEL	INFO	Train Epoch: 122 [93%]9202023-04-03 20:35:02,248	OUTPUT_MODEL	INFO	[2.383232831954956, 2.5412979125976562, 9.425552368164062, 20.085468292236328, -1.1247150897979736, 1.9377626180648804, 13900, 0.000196997575421416]9212023-04-03 20:35:08,592	OUTPUT_MODEL	INFO	====> Epoch: 1229222023-04-03 20:36:21,171	OUTPUT_MODEL	INFO	Train Epoch: 123 [81%]9232023-04-03 20:36:21,173	OUTPUT_MODEL	INFO	[2.2437853813171387, 2.5475716590881348, 10.586019515991211, 18.711729049682617, 2.0490245819091797, 1.928191065788269, 14000, 0.00019697295072448832]9242023-04-03 20:36:22,551	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 123 to ././OUTPUT_MODEL/G_14000.pth9252023-04-03 20:36:22,933	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 123 to ././OUTPUT_MODEL/G_latest.pth9262023-04-03 20:36:39,559	OUTPUT_MODEL	INFO	====> Epoch: 1239272023-04-03 20:37:41,407	OUTPUT_MODEL	INFO	Train Epoch: 124 [68%]9282023-04-03 20:37:41,408	OUTPUT_MODEL	INFO	[2.1681339740753174, 2.7286875247955322, 11.072426795959473, 22.700244903564453, -5.153722286224365, 1.4501190185546875, 14100, 0.00019694832910564775]9292023-04-03 20:38:08,809	OUTPUT_MODEL	INFO	====> Epoch: 1249302023-04-03 20:38:59,481	OUTPUT_MODEL	INFO	Train Epoch: 125 [56%]9312023-04-03 20:38:59,483	OUTPUT_MODEL	INFO	[1.9106919765472412, 3.4085562229156494, 13.267656326293945, 24.08005714416504, -4.416301727294922, 1.5308172702789307, 14200, 0.00019692371056450955]9322023-04-03 20:39:37,546	OUTPUT_MODEL	INFO	====> Epoch: 1259332023-04-03 20:40:17,353	OUTPUT_MODEL	INFO	Train Epoch: 126 [44%]9342023-04-03 20:40:17,355	OUTPUT_MODEL	INFO	[2.278599977493286, 2.7635648250579834, 10.851936340332031, 20.22602653503418, 1.8511074781417847, 2.066765308380127, 14300, 0.000196899095100689]9352023-04-03 20:41:05,899	OUTPUT_MODEL	INFO	====> Epoch: 1269362023-04-03 20:41:34,851	OUTPUT_MODEL	INFO	Train Epoch: 127 [32%]9372023-04-03 20:41:34,852	OUTPUT_MODEL	INFO	[2.2159411907196045, 2.7891409397125244, 9.02995491027832, 20.228900909423828, 2.2246286869049072, 1.8316007852554321, 14400, 0.0001968744827138014]9382023-04-03 20:42:33,826	OUTPUT_MODEL	INFO	====> Epoch: 1279392023-04-03 20:42:51,860	OUTPUT_MODEL	INFO	Train Epoch: 128 [19%]9402023-04-03 20:42:51,861	OUTPUT_MODEL	INFO	[1.9678614139556885, 3.0785176753997803, 13.865856170654297, 23.266380310058594, -3.6029129028320312, 1.7225062847137451, 14500, 0.00019684987340346216]9412023-04-03 20:44:01,679	OUTPUT_MODEL	INFO	====> Epoch: 1289422023-04-03 20:44:09,343	OUTPUT_MODEL	INFO	Train Epoch: 129 [7%]9432023-04-03 20:44:09,344	OUTPUT_MODEL	INFO	[1.9394577741622925, 2.9192569255828857, 11.641122817993164, 21.816389083862305, -8.512065887451172, 1.8343738317489624, 14600, 0.00019682526716928672]9442023-04-03 20:45:26,124	OUTPUT_MODEL	INFO	Train Epoch: 129 [95%]9452023-04-03 20:45:26,125	OUTPUT_MODEL	INFO	[2.2015953063964844, 2.5525965690612793, 10.20043659210205, 18.922805786132812, 1.710674524307251, 1.8252224922180176, 14700, 0.00019682526716928672]9462023-04-03 20:45:30,532	OUTPUT_MODEL	INFO	====> Epoch: 1299472023-04-03 20:46:43,249	OUTPUT_MODEL	INFO	Train Epoch: 130 [82%]9482023-04-03 20:46:43,251	OUTPUT_MODEL	INFO	[1.9729318618774414, 2.927025318145752, 11.511123657226562, 19.429521560668945, -1.8836040496826172, 1.7071242332458496, 14800, 0.00019680066401089056]9492023-04-03 20:46:58,378	OUTPUT_MODEL	INFO	====> Epoch: 1309502023-04-03 20:48:00,836	OUTPUT_MODEL	INFO	Train Epoch: 131 [70%]9512023-04-03 20:48:00,837	OUTPUT_MODEL	INFO	[2.2694528102874756, 2.6957292556762695, 9.386392593383789, 19.366764068603516, 1.8449735641479492, 1.7454676628112793, 14900, 0.00019677606392788917]9522023-04-03 20:48:26,541	OUTPUT_MODEL	INFO	====> Epoch: 1319532023-04-03 20:49:18,397	OUTPUT_MODEL	INFO	Train Epoch: 132 [58%]9542023-04-03 20:49:18,398	OUTPUT_MODEL	INFO	[2.684434413909912, 2.348546266555786, 7.819872856140137, 16.97273826599121, 2.1839189529418945, 1.9676790237426758, 15000, 0.00019675146691989817]9552023-04-03 20:49:19,718	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 132 to ././OUTPUT_MODEL/G_15000.pth9562023-04-03 20:49:20,086	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 132 to ././OUTPUT_MODEL/G_latest.pth9572023-04-03 20:49:55,699	OUTPUT_MODEL	INFO	====> Epoch: 1329582023-04-03 20:50:36,985	OUTPUT_MODEL	INFO	Train Epoch: 133 [46%]9592023-04-03 20:50:36,986	OUTPUT_MODEL	INFO	[2.3275346755981445, 2.6055214405059814, 9.609498977661133, 20.08955192565918, 1.7221561670303345, 2.01244854927063, 15100, 0.00019672687298653317]9602023-04-03 20:51:23,357	OUTPUT_MODEL	INFO	====> Epoch: 1339612023-04-03 20:51:53,614	OUTPUT_MODEL	INFO	Train Epoch: 134 [33%]9622023-04-03 20:51:53,615	OUTPUT_MODEL	INFO	[2.3798205852508545, 2.534238576889038, 8.05441951751709, 17.221561431884766, -2.5734972953796387, 1.7964690923690796, 15200, 0.00019670228212740986]9632023-04-03 20:52:51,343	OUTPUT_MODEL	INFO	====> Epoch: 1349642023-04-03 20:53:10,921	OUTPUT_MODEL	INFO	Train Epoch: 135 [21%]9652023-04-03 20:53:10,921	OUTPUT_MODEL	INFO	[2.1999592781066895, 2.58321213722229, 9.161837577819824, 20.334733963012695, -8.153844833374023, 1.5914881229400635, 15300, 0.00019667769434214392]9662023-04-03 20:54:19,391	OUTPUT_MODEL	INFO	====> Epoch: 1359672023-04-03 20:54:28,416	OUTPUT_MODEL	INFO	Train Epoch: 136 [9%]9682023-04-03 20:54:28,417	OUTPUT_MODEL	INFO	[2.4908292293548584, 2.390425682067871, 8.146764755249023, 19.260469436645508, 1.923396348953247, 1.7469462156295776, 15400, 0.00019665310963035113]9692023-04-03 20:55:44,981	OUTPUT_MODEL	INFO	Train Epoch: 136 [96%]9702023-04-03 20:55:44,982	OUTPUT_MODEL	INFO	[2.0234766006469727, 2.7121005058288574, 12.01541805267334, 20.340295791625977, 0.27029693126678467, 1.7634350061416626, 15500, 0.00019665310963035113]9712023-04-03 20:55:47,985	OUTPUT_MODEL	INFO	====> Epoch: 1369722023-04-03 20:57:02,366	OUTPUT_MODEL	INFO	Train Epoch: 137 [84%]9732023-04-03 20:57:02,367	OUTPUT_MODEL	INFO	[2.0544586181640625, 2.93562912940979, 13.055928230285645, 23.832008361816406, -4.052873611450195, 2.0969066619873047, 15600, 0.00019662852799164733]9742023-04-03 20:57:15,943	OUTPUT_MODEL	INFO	====> Epoch: 1379752023-04-03 20:58:19,648	OUTPUT_MODEL	INFO	Train Epoch: 138 [72%]9762023-04-03 20:58:19,648	OUTPUT_MODEL	INFO	[1.9772495031356812, 2.9134531021118164, 12.410299301147461, 23.251798629760742, -5.576955795288086, 1.7398598194122314, 15700, 0.00019660394942564837]9772023-04-03 20:58:43,596	OUTPUT_MODEL	INFO	====> Epoch: 1389782023-04-03 20:59:37,460	OUTPUT_MODEL	INFO	Train Epoch: 139 [60%]9792023-04-03 20:59:37,461	OUTPUT_MODEL	INFO	[2.352499485015869, 2.618260383605957, 8.456803321838379, 18.375272750854492, 2.074037551879883, 1.7205617427825928, 15800, 0.00019657937393197016]9802023-04-03 21:00:11,879	OUTPUT_MODEL	INFO	====> Epoch: 1399812023-04-03 21:00:54,507	OUTPUT_MODEL	INFO	Train Epoch: 140 [47%]9822023-04-03 21:00:54,508	OUTPUT_MODEL	INFO	[1.8942725658416748, 3.030506134033203, 11.410690307617188, 21.672588348388672, 1.9514493942260742, 1.6281639337539673, 15900, 0.00019655480151022865]9832023-04-03 21:01:39,608	OUTPUT_MODEL	INFO	====> Epoch: 1409842023-04-03 21:02:11,259	OUTPUT_MODEL	INFO	Train Epoch: 141 [35%]9852023-04-03 21:02:11,259	OUTPUT_MODEL	INFO	[2.2272002696990967, 2.8681039810180664, 11.0366792678833, 22.6636905670166, 0.22694194316864014, 1.860249400138855, 16000, 0.00019653023216003985]9862023-04-03 21:02:12,545	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 141 to ././OUTPUT_MODEL/G_16000.pth9872023-04-03 21:02:12,930	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 141 to ././OUTPUT_MODEL/G_latest.pth9882023-04-03 21:03:08,717	OUTPUT_MODEL	INFO	====> Epoch: 1419892023-04-03 21:03:29,826	OUTPUT_MODEL	INFO	Train Epoch: 142 [23%]9902023-04-03 21:03:29,827	OUTPUT_MODEL	INFO	[2.1813771724700928, 2.7275004386901855, 9.768020629882812, 20.441497802734375, -2.6973352432250977, 2.108966112136841, 16100, 0.00019650566588101984]9912023-04-03 21:04:36,296	OUTPUT_MODEL	INFO	====> Epoch: 1429922023-04-03 21:04:47,078	OUTPUT_MODEL	INFO	Train Epoch: 143 [11%]9932023-04-03 21:04:47,079	OUTPUT_MODEL	INFO	[2.515777826309204, 2.1156113147735596, 8.112641334533691, 19.685379028320312, 0.3286556005477905, 1.5397011041641235, 16200, 0.0001964811026727847]9942023-04-03 21:06:03,426	OUTPUT_MODEL	INFO	Train Epoch: 143 [98%]9952023-04-03 21:06:03,428	OUTPUT_MODEL	INFO	[2.3494842052459717, 2.627450466156006, 8.582590103149414, 20.778202056884766, 2.0015008449554443, 1.7245981693267822, 16300, 0.0001964811026727847]9962023-04-03 21:06:05,124	OUTPUT_MODEL	INFO	====> Epoch: 1439972023-04-03 21:07:20,749	OUTPUT_MODEL	INFO	Train Epoch: 144 [86%]9982023-04-03 21:07:20,750	OUTPUT_MODEL	INFO	[2.036226272583008, 3.1635587215423584, 12.34357738494873, 23.225910186767578, -1.8555731773376465, 1.596243977546692, 16400, 0.00019645654253495058]9992023-04-03 21:07:32,731	OUTPUT_MODEL	INFO	====> Epoch: 14410002023-04-03 21:08:37,878	OUTPUT_MODEL	INFO	Train Epoch: 145 [74%]10012023-04-03 21:08:37,879	OUTPUT_MODEL	INFO	[1.9093801975250244, 3.046074628829956, 12.131577491760254, 22.709854125976562, 1.9615952968597412, 1.424329400062561, 16500, 0.0001964319854671337]10022023-04-03 21:09:00,569	OUTPUT_MODEL	INFO	====> Epoch: 14510032023-04-03 21:09:55,354	OUTPUT_MODEL	INFO	Train Epoch: 146 [61%]10042023-04-03 21:09:55,355	OUTPUT_MODEL	INFO	[2.1518893241882324, 2.7510592937469482, 10.098980903625488, 21.654340744018555, 1.9958921670913696, 1.706437349319458, 16600, 0.0001964074314689503]10052023-04-03 21:10:28,240	OUTPUT_MODEL	INFO	====> Epoch: 14610062023-04-03 21:11:12,434	OUTPUT_MODEL	INFO	Train Epoch: 147 [49%]10072023-04-03 21:11:12,435	OUTPUT_MODEL	INFO	[2.125607490539551, 2.622837543487549, 11.29242992401123, 22.088455200195312, -3.071295738220215, 1.6613425016403198, 16700, 0.00019638288054001668]10082023-04-03 21:11:55,952	OUTPUT_MODEL	INFO	====> Epoch: 14710092023-04-03 21:12:29,357	OUTPUT_MODEL	INFO	Train Epoch: 148 [37%]10102023-04-03 21:12:29,359	OUTPUT_MODEL	INFO	[2.452683925628662, 2.4951670169830322, 10.10145378112793, 20.905094146728516, 2.119616985321045, 2.1813879013061523, 16800, 0.00019635833267994917]10112023-04-03 21:13:23,904	OUTPUT_MODEL	INFO	====> Epoch: 14810122023-04-03 21:13:46,807	OUTPUT_MODEL	INFO	Train Epoch: 149 [25%]10132023-04-03 21:13:46,808	OUTPUT_MODEL	INFO	[2.0889246463775635, 2.748607635498047, 11.926233291625977, 22.67853546142578, 2.138601541519165, 1.654150366783142, 16900, 0.00019633378788836418]10142023-04-03 21:14:51,813	OUTPUT_MODEL	INFO	====> Epoch: 14910152023-04-03 21:15:03,982	OUTPUT_MODEL	INFO	Train Epoch: 150 [12%]10162023-04-03 21:15:03,982	OUTPUT_MODEL	INFO	[2.014240264892578, 3.00461745262146, 11.656495094299316, 20.79851722717285, 1.8297853469848633, 1.9192861318588257, 17000, 0.00019630924616487812]10172023-04-03 21:15:05,282	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 150 to ././OUTPUT_MODEL/G_17000.pth10182023-04-03 21:15:05,647	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 150 to ././OUTPUT_MODEL/G_latest.pth10192023-04-03 21:16:20,776	OUTPUT_MODEL	INFO	====> Epoch: 15010202023-04-03 21:16:22,165	OUTPUT_MODEL	INFO	Train Epoch: 151 [0%]10212023-04-03 21:16:22,166	OUTPUT_MODEL	INFO	[2.299504518508911, 2.9036755561828613, 8.404783248901367, 19.345808029174805, 0.14232540130615234, 1.8701171875, 17100, 0.0001962847075091075]10222023-04-03 21:17:38,791	OUTPUT_MODEL	INFO	Train Epoch: 151 [88%]10232023-04-03 21:17:38,792	OUTPUT_MODEL	INFO	[2.2070419788360596, 2.622215509414673, 11.005857467651367, 21.670360565185547, 2.05729603767395, 2.291896104812622, 17200, 0.0001962847075091075]10242023-04-03 21:17:49,291	OUTPUT_MODEL	INFO	====> Epoch: 15110252023-04-03 21:18:56,556	OUTPUT_MODEL	INFO	Train Epoch: 152 [75%]10262023-04-03 21:18:56,557	OUTPUT_MODEL	INFO	[2.03369140625, 2.9899888038635254, 10.500231742858887, 20.34485626220703, 1.8453326225280762, 1.9871357679367065, 17300, 0.00019626017192066886]10272023-04-03 21:19:17,663	OUTPUT_MODEL	INFO	====> Epoch: 15210282023-04-03 21:20:15,643	OUTPUT_MODEL	INFO	Train Epoch: 153 [63%]10292023-04-03 21:20:15,644	OUTPUT_MODEL	INFO	[2.151749610900879, 2.6252493858337402, 8.668746948242188, 18.587596893310547, 1.9671107530593872, 1.960224986076355, 17400, 0.00019623563939917877]10302023-05-15 08:20:51,331	OUTPUT_MODEL	INFO	{'train': {'log_interval': 100, 'eval_interval': 1000, 'seed': 1234, 'epochs': 10000, 'learning_rate': 0.0002, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 16, 'fp16_run': False, 'lr_decay': 0.999875, 'segment_size': 8192, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'training_files': 'final_annotation_train.txt', 'validation_files': 'final_annotation_val.txt', 'text_cleaners': ['cjke_cleaners2'], 'max_wav_value': 32768.0, 'sampling_rate': 22050, 'filter_length': 1024, 'hop_length': 256, 'win_length': 1024, 'n_mel_channels': 80, 'mel_fmin': 0.0, 'mel_fmax': None, 'add_blank': True, 'n_speakers': 68, 'cleaned_text': True}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0.1, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [8, 8, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 256}, 'symbols': ['_', ',', '.', '!', '?', '-', '~', '…', 'A', 'E', 'I', 'N', 'O', 'Q', 'U', 'a', 'b', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'r', 's', 't', 'u', 'v', 'w', 'y', 'z', 'ʃ', 'ʧ', 'ʦ', 'ɯ', 'ɹ', 'ə', 'ɥ', '⁼', 'ʰ', '`', '→', '↓', '↑', ' '], 'speakers': {'W': 0, '仇白': 1, '令': 2, '伊芙利特': 3, '伺夜': 4, '假日威龙陈': 5, '傀影': 6, '刻俄柏': 7, '史尔特尔': 8, '号角': 9, '塞雷娅': 10, '夕': 11, '多萝西': 12, '夜莺': 13, '山': 14, '嵯峨': 15, '帕拉斯': 16, '年': 17, '异客': 18, '归溟幽灵鲨': 19, '推进之王': 20, '斥罪': 21, '斯卡蒂': 22, '早露': 23, '星熊': 24, '棘刺': 25, '森蚺': 26, '泥岩': 27, '流明': 28, '浊心斯卡蒂': 29, '温蒂': 30, '澄闪': 31, '灵知': 32, '焰尾': 33, '焰影苇草': 34, '煌': 35, '玛恩纳': 36, '琴柳': 37, '瑕光': 38, '白铁': 39, '百炼嘉维尔': 40, '空弦': 41, '缄默德克萨斯': 42, '耀骑士临光': 43, '老鲤': 44, '能天使': 45, '艾丽妮': 46, '艾雅法拉': 47, '莫斯提马': 48, '菲亚梅塔': 49, '谜图': 50, '赫拉格': 51, '远牙': 52, '迷迭香': 53, '重岳': 54, '铃兰': 55, '银灰': 56, '闪灵': 57, '阿': 58, '陈': 59, '风笛': 60, '鸿雪': 61, '麒麟X夜刀': 62, '麦哲伦': 63, '黑': 64, '黑键': 65, 'specialweek': 66, 'zhongli': 67}, 'model_dir': '././OUTPUT_MODEL', 'max_epochs': 300, 'drop_speaker_embed': True}10312023-05-15 08:20:51,332	OUTPUT_MODEL	WARNING	/root/autodl-tmp/VITS-finetune is not a git repository, therefore hash value comparison will be ignored.10322023-05-15 08:23:41,012	OUTPUT_MODEL	INFO	{'train': {'log_interval': 100, 'eval_interval': 1000, 'seed': 1234, 'epochs': 10000, 'learning_rate': 0.0002, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 16, 'fp16_run': False, 'lr_decay': 0.999875, 'segment_size': 8192, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'training_files': 'final_annotation_train.txt', 'validation_files': 'final_annotation_val.txt', 'text_cleaners': ['cjke_cleaners2'], 'max_wav_value': 32768.0, 'sampling_rate': 22050, 'filter_length': 1024, 'hop_length': 256, 'win_length': 1024, 'n_mel_channels': 80, 'mel_fmin': 0.0, 'mel_fmax': None, 'add_blank': True, 'n_speakers': 68, 'cleaned_text': True}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0.1, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [8, 8, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 256}, 'symbols': ['_', ',', '.', '!', '?', '-', '~', '…', 'A', 'E', 'I', 'N', 'O', 'Q', 'U', 'a', 'b', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'r', 's', 't', 'u', 'v', 'w', 'y', 'z', 'ʃ', 'ʧ', 'ʦ', 'ɯ', 'ɹ', 'ə', 'ɥ', '⁼', 'ʰ', '`', '→', '↓', '↑', ' '], 'speakers': {'W': 0, '仇白': 1, '令': 2, '伊芙利特': 3, '伺夜': 4, '假日威龙陈': 5, '傀影': 6, '刻俄柏': 7, '史尔特尔': 8, '号角': 9, '塞雷娅': 10, '夕': 11, '多萝西': 12, '夜莺': 13, '山': 14, '嵯峨': 15, '帕拉斯': 16, '年': 17, '异客': 18, '归溟幽灵鲨': 19, '推进之王': 20, '斥罪': 21, '斯卡蒂': 22, '早露': 23, '星熊': 24, '棘刺': 25, '森蚺': 26, '泥岩': 27, '流明': 28, '浊心斯卡蒂': 29, '温蒂': 30, '澄闪': 31, '灵知': 32, '焰尾': 33, '焰影苇草': 34, '煌': 35, '玛恩纳': 36, '琴柳': 37, '瑕光': 38, '白铁': 39, '百炼嘉维尔': 40, '空弦': 41, '缄默德克萨斯': 42, '耀骑士临光': 43, '老鲤': 44, '能天使': 45, '艾丽妮': 46, '艾雅法拉': 47, '莫斯提马': 48, '菲亚梅塔': 49, '谜图': 50, '赫拉格': 51, '远牙': 52, '迷迭香': 53, '重岳': 54, '铃兰': 55, '银灰': 56, '闪灵': 57, '阿': 58, '陈': 59, '风笛': 60, '鸿雪': 61, '麒麟X夜刀': 62, '麦哲伦': 63, '黑': 64, '黑键': 65, 'specialweek': 66, 'zhongli': 67}, 'model_dir': '././OUTPUT_MODEL', 'max_epochs': 300, 'drop_speaker_embed': True}10332023-05-15 08:23:41,013	OUTPUT_MODEL	WARNING	/root/autodl-tmp/VITS-finetune is not a git repository, therefore hash value comparison will be ignored.10342023-05-15 08:23:46,514	OUTPUT_MODEL	INFO	Loaded checkpoint './pretrained_models/G_0_.pth' (iteration None)10352023-05-15 08:23:46,761	OUTPUT_MODEL	INFO	Loaded checkpoint './pretrained_models/D_0_.pth' (iteration None)10362023-05-15 08:23:50,723	OUTPUT_MODEL	INFO	Train Epoch: 1 [0%]10372023-05-15 08:23:50,724	OUTPUT_MODEL	INFO	[2.883575677871704, 2.8500611782073975, 8.818042755126953, 28.832807540893555, 1.6273704767227173, 15.779275894165039, 0, 0.0002]10382023-05-15 08:23:52,857	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 1 to ././OUTPUT_MODEL/G_0.pth10392023-05-15 08:23:53,314	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 1 to ././OUTPUT_MODEL/G_latest.pth10402023-05-15 08:25:34,008	OUTPUT_MODEL	INFO	Train Epoch: 1 [88%]10412023-05-15 08:25:34,009	OUTPUT_MODEL	INFO	[2.1573710441589355, 2.844327926635742, 10.280744552612305, 24.20599937438965, 2.111600160598755, 3.353525400161743, 100, 0.0002]10422023-05-15 08:25:46,705	OUTPUT_MODEL	INFO	====> Epoch: 110432023-05-15 08:26:56,624	OUTPUT_MODEL	INFO	Train Epoch: 2 [75%]10442023-05-15 08:26:56,625	OUTPUT_MODEL	INFO	[2.280179977416992, 2.6554088592529297, 11.796255111694336, 23.252641677856445, 1.9046306610107422, 2.9302148818969727, 200, 0.000199975]10452023-05-15 08:27:18,427	OUTPUT_MODEL	INFO	====> Epoch: 210462023-05-15 08:28:17,247	OUTPUT_MODEL	INFO	Train Epoch: 3 [63%]10472023-05-15 08:28:17,248	OUTPUT_MODEL	INFO	[2.5086276531219482, 2.4588003158569336, 7.80949068069458, 20.061086654663086, 2.0217223167419434, 2.5374717712402344, 300, 0.000199950003125]10482023-05-15 08:28:49,725	OUTPUT_MODEL	INFO	====> Epoch: 310492023-05-15 08:29:37,934	OUTPUT_MODEL	INFO	Train Epoch: 4 [51%]10502023-05-15 08:29:37,935	OUTPUT_MODEL	INFO	[2.287137508392334, 2.720005512237549, 10.341904640197754, 25.603506088256836, -0.10357379913330078, 2.835514545440674, 400, 0.00019992500937460937]10512023-05-15 08:30:22,158	OUTPUT_MODEL	INFO	====> Epoch: 410522023-05-15 08:30:58,284	OUTPUT_MODEL	INFO	Train Epoch: 5 [39%]10532023-05-15 08:30:58,285	OUTPUT_MODEL	INFO	[2.1802754402160645, 2.8174707889556885, 11.302605628967285, 22.630441665649414, 1.940791130065918, 2.5620152950286865, 500, 0.00019990001874843754]10542023-05-15 08:31:54,328	OUTPUT_MODEL	INFO	====> Epoch: 510552023-05-15 08:32:19,424	OUTPUT_MODEL	INFO	Train Epoch: 6 [26%]10562023-05-15 08:32:19,425	OUTPUT_MODEL	INFO	[2.3132619857788086, 2.607985734939575, 9.60537052154541, 22.557619094848633, -1.9242420196533203, 2.7503998279571533, 600, 0.00019987503124609398]10572023-05-15 08:33:25,642	OUTPUT_MODEL	INFO	====> Epoch: 610582023-05-15 08:33:39,825	OUTPUT_MODEL	INFO	Train Epoch: 7 [14%]10592023-05-15 08:33:39,826	OUTPUT_MODEL	INFO	[2.2644240856170654, 2.836549758911133, 12.41378116607666, 25.12668800354004, -1.3924660682678223, 2.268775463104248, 700, 0.0001998500468671882]10602023-05-15 08:34:56,959	OUTPUT_MODEL	INFO	====> Epoch: 710612023-05-15 08:35:00,097	OUTPUT_MODEL	INFO	Train Epoch: 8 [2%]10622023-05-15 08:35:00,099	OUTPUT_MODEL	INFO	[2.315800666809082, 2.649444103240967, 11.46351432800293, 25.048734664916992, -0.19935894012451172, 2.6065094470977783, 800, 0.00019982506561132978]10632023-05-15 08:36:20,879	OUTPUT_MODEL	INFO	Train Epoch: 8 [89%]10642023-05-15 08:36:20,881	OUTPUT_MODEL	INFO	[2.275117874145508, 2.8309683799743652, 11.935769081115723, 22.91656494140625, -2.077681064605713, 2.1909730434417725, 900, 0.00019982506561132978]10652023-05-15 08:36:30,120	OUTPUT_MODEL	INFO	====> Epoch: 810662023-05-15 08:37:41,498	OUTPUT_MODEL	INFO	Train Epoch: 9 [77%]10672023-05-15 08:37:41,500	OUTPUT_MODEL	INFO	[1.925140142440796, 2.9783060550689697, 11.849682807922363, 25.20415687561035, -3.588123083114624, 2.2963902950286865, 1000, 0.00019980008747812837]10682023-05-15 08:37:43,218	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 9 to ././OUTPUT_MODEL/G_1000.pth10692023-05-15 08:37:43,627	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 9 to ././OUTPUT_MODEL/G_latest.pth10702023-05-15 08:38:03,705	OUTPUT_MODEL	INFO	====> Epoch: 910712023-05-15 08:39:04,337	OUTPUT_MODEL	INFO	Train Epoch: 10 [65%]10722023-05-15 08:39:04,338	OUTPUT_MODEL	INFO	[2.391340970993042, 2.322455644607544, 9.287607192993164, 20.03710174560547, 2.1605567932128906, 2.1346139907836914, 1100, 0.0001997751124671936]10732023-05-15 08:39:35,685	OUTPUT_MODEL	INFO	====> Epoch: 1010742023-05-15 08:40:25,147	OUTPUT_MODEL	INFO	Train Epoch: 11 [53%]10752023-05-15 08:40:25,148	OUTPUT_MODEL	INFO	[2.1332008838653564, 3.052746295928955, 10.109336853027344, 22.408096313476562, 0.6212072372436523, 1.7238134145736694, 1200, 0.00019975014057813518]10762023-05-15 08:41:07,253	OUTPUT_MODEL	INFO	====> Epoch: 1110772023-05-15 08:41:45,196	OUTPUT_MODEL	INFO	Train Epoch: 12 [40%]10782023-05-15 08:41:45,199	OUTPUT_MODEL	INFO	[2.091205596923828, 2.897787094116211, 12.444554328918457, 21.18656349182129, 1.8793288469314575, 1.9107998609542847, 1300, 0.00019972517181056292]10792023-05-15 08:42:38,965	OUTPUT_MODEL	INFO	====> Epoch: 1210802023-05-15 08:43:05,515	OUTPUT_MODEL	INFO	Train Epoch: 13 [28%]10812023-05-15 08:43:05,516	OUTPUT_MODEL	INFO	[2.1881155967712402, 2.4881961345672607, 10.956562995910645, 24.08803939819336, -2.157498598098755, 2.2954399585723877, 1400, 0.0001997002061640866]10822023-05-15 08:44:10,265	OUTPUT_MODEL	INFO	====> Epoch: 1310832023-05-15 08:44:26,021	OUTPUT_MODEL	INFO	Train Epoch: 14 [16%]10842023-05-15 08:44:26,022	OUTPUT_MODEL	INFO	[2.4517815113067627, 2.2301111221313477, 9.149811744689941, 19.15855598449707, 1.972556710243225, 2.075007915496826, 1500, 0.00019967524363831608]10852023-05-15 08:45:41,290	OUTPUT_MODEL	INFO	====> Epoch: 1410862023-05-15 08:45:45,895	OUTPUT_MODEL	INFO	Train Epoch: 15 [4%]10872023-05-15 08:45:45,897	OUTPUT_MODEL	INFO	[2.324486017227173, 2.8835017681121826, 10.233136177062988, 24.02960968017578, 1.9615873098373413, 2.0994136333465576, 1600, 0.0001996502842328613]10882023-05-15 08:47:05,383	OUTPUT_MODEL	INFO	Train Epoch: 15 [91%]10892023-05-15 08:47:05,384	OUTPUT_MODEL	INFO	[2.501518726348877, 2.6413636207580566, 8.823929786682129, 21.77501678466797, 1.915596604347229, 2.1557464599609375, 1700, 0.0001996502842328613]10902023-05-15 08:47:13,082	OUTPUT_MODEL	INFO	====> Epoch: 1510912023-05-15 08:48:25,572	OUTPUT_MODEL	INFO	Train Epoch: 16 [79%]10922023-05-15 08:48:25,573	OUTPUT_MODEL	INFO	[1.958284854888916, 2.9641308784484863, 12.263086318969727, 25.881418228149414, -5.502517223358154, 2.4551076889038086, 1800, 0.00019962532794733217]10932023-05-15 08:48:44,463	OUTPUT_MODEL	INFO	====> Epoch: 1610942023-05-15 08:49:47,297	OUTPUT_MODEL	INFO	Train Epoch: 17 [67%]10952023-05-15 08:49:47,299	OUTPUT_MODEL	INFO	[2.0367724895477295, 3.0937814712524414, 13.23363208770752, 25.615510940551758, 0.08728444576263428, 2.1325337886810303, 1900, 0.00019960037478133875]10962023-05-15 08:50:17,200	OUTPUT_MODEL	INFO	====> Epoch: 1710972023-05-15 08:51:08,351	OUTPUT_MODEL	INFO	Train Epoch: 18 [54%]10982023-05-15 08:51:08,352	OUTPUT_MODEL	INFO	[2.304152011871338, 2.9232683181762695, 9.122937202453613, 23.305646896362305, 2.1195716857910156, 1.8118478059768677, 2000, 0.00019957542473449108]10992023-05-15 08:51:09,727	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 18 to ././OUTPUT_MODEL/G_2000.pth11002023-05-15 08:51:10,130	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 18 to ././OUTPUT_MODEL/G_latest.pth11012023-05-15 08:51:50,481	OUTPUT_MODEL	INFO	====> Epoch: 1811022023-05-15 08:52:30,250	OUTPUT_MODEL	INFO	Train Epoch: 19 [42%]11032023-05-15 08:52:30,252	OUTPUT_MODEL	INFO	[2.3076906204223633, 2.4820618629455566, 9.482162475585938, 21.724037170410156, -1.6667771339416504, 2.4969019889831543, 2100, 0.00019955047780639926]11042023-05-15 08:53:22,796	OUTPUT_MODEL	INFO	====> Epoch: 1911052023-05-15 08:53:51,328	OUTPUT_MODEL	INFO	Train Epoch: 20 [30%]11062023-05-15 08:53:51,330	OUTPUT_MODEL	INFO	[2.2924201488494873, 2.5706441402435303, 9.62475872039795, 20.594863891601562, 1.966792345046997, 2.171588897705078, 2200, 0.00019952553399667344]11072023-05-15 08:54:54,487	OUTPUT_MODEL	INFO	====> Epoch: 2011082023-05-15 08:55:11,766	OUTPUT_MODEL	INFO	Train Epoch: 21 [18%]11092023-05-15 08:55:11,767	OUTPUT_MODEL	INFO	[2.5275979042053223, 2.355509042739868, 8.599774360656738, 21.193714141845703, -1.665793538093567, 2.026155710220337, 2300, 0.00019950059330492385]11102023-05-15 08:56:26,016	OUTPUT_MODEL	INFO	====> Epoch: 2111112023-05-15 08:56:32,286	OUTPUT_MODEL	INFO	Train Epoch: 22 [5%]11122023-05-15 08:56:32,287	OUTPUT_MODEL	INFO	[2.296821117401123, 2.861485481262207, 10.35749340057373, 23.287107467651367, 2.1103756427764893, 1.926958441734314, 2400, 0.00019947565573076072]11132023-05-15 08:57:52,244	OUTPUT_MODEL	INFO	Train Epoch: 22 [93%]11142023-05-15 08:57:52,245	OUTPUT_MODEL	INFO	[2.0511202812194824, 2.986746311187744, 10.679633140563965, 22.50594711303711, -0.7946839332580566, 2.061154365539551, 2500, 0.00019947565573076072]11152023-05-15 08:57:58,421	OUTPUT_MODEL	INFO	====> Epoch: 2211162023-05-15 08:59:12,806	OUTPUT_MODEL	INFO	Train Epoch: 23 [81%]11172023-05-15 08:59:12,808	OUTPUT_MODEL	INFO	[2.263258218765259, 3.0127923488616943, 10.891691207885742, 22.690906524658203, 2.1394221782684326, 1.784227728843689, 2600, 0.00019945072127379438]11182023-05-15 08:59:30,106	OUTPUT_MODEL	INFO	====> Epoch: 2311192023-05-15 09:00:33,744	OUTPUT_MODEL	INFO	Train Epoch: 24 [68%]11202023-05-15 09:00:33,745	OUTPUT_MODEL	INFO	[2.1343016624450684, 2.804497718811035, 11.5584135055542, 25.017980575561523, -4.708536148071289, 2.332347869873047, 2700, 0.00019942578993363514]11212023-05-15 09:01:01,829	OUTPUT_MODEL	INFO	====> Epoch: 2411222023-05-15 09:01:54,368	OUTPUT_MODEL	INFO	Train Epoch: 25 [56%]11232023-05-15 09:01:54,369	OUTPUT_MODEL	INFO	[2.0739078521728516, 2.7580342292785645, 10.823801040649414, 24.389009475708008, -4.069508075714111, 1.8688864707946777, 2800, 0.00019940086170989343]11242023-05-15 09:02:33,338	OUTPUT_MODEL	INFO	====> Epoch: 2511252023-05-15 09:03:14,500	OUTPUT_MODEL	INFO	Train Epoch: 26 [44%]11262023-05-15 09:03:14,502	OUTPUT_MODEL	INFO	[2.358488082885742, 2.66261887550354, 9.404172897338867, 21.32563591003418, 1.9141703844070435, 2.1128344535827637, 2900, 0.0001993759366021797]11272023-05-15 09:04:04,740	OUTPUT_MODEL	INFO	====> Epoch: 2611282023-05-15 09:04:35,028	OUTPUT_MODEL	INFO	Train Epoch: 27 [32%]11292023-05-15 09:04:35,029	OUTPUT_MODEL	INFO	[2.213637113571167, 2.77384877204895, 10.885902404785156, 19.95029640197754, 2.2733278274536133, 1.8417840003967285, 3000, 0.00019935101461010442]11302023-05-15 09:04:36,376	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 27 to ././OUTPUT_MODEL/G_3000.pth11312023-05-15 09:04:36,773	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 27 to ././OUTPUT_MODEL/G_latest.pth11322023-05-15 09:05:37,910	OUTPUT_MODEL	INFO	====> Epoch: 2711332023-05-15 09:05:56,656	OUTPUT_MODEL	INFO	Train Epoch: 28 [19%]11342023-05-15 09:05:56,657	OUTPUT_MODEL	INFO	[2.0804169178009033, 3.064420461654663, 11.470417976379395, 24.526384353637695, -3.9139604568481445, 2.057410717010498, 3100, 0.00019932609573327815]11352023-05-15 09:07:09,643	OUTPUT_MODEL	INFO	====> Epoch: 2811362023-05-15 09:07:17,344	OUTPUT_MODEL	INFO	Train Epoch: 29 [7%]11372023-05-15 09:07:17,345	OUTPUT_MODEL	INFO	[2.01894474029541, 3.131869316101074, 12.085283279418945, 22.772022247314453, -8.327593803405762, 2.1651809215545654, 3200, 0.0001993011799713115]11382023-05-15 09:08:36,474	OUTPUT_MODEL	INFO	Train Epoch: 29 [95%]11392023-05-15 09:08:36,475	OUTPUT_MODEL	INFO	[2.256652355194092, 2.966338634490967, 8.518434524536133, 20.214397430419922, 1.781857967376709, 2.026423931121826, 3300, 0.0001993011799713115]11402023-05-15 09:08:41,421	OUTPUT_MODEL	INFO	====> Epoch: 2911412023-05-15 09:09:57,836	OUTPUT_MODEL	INFO	Train Epoch: 30 [82%]11422023-05-15 09:09:57,837	OUTPUT_MODEL	INFO	[2.2298245429992676, 2.6866743564605713, 10.7785062789917, 22.844432830810547, -1.8341217041015625, 2.022649049758911, 3400, 0.00019927626732381507]11432023-05-15 09:10:13,864	OUTPUT_MODEL	INFO	====> Epoch: 3011442023-05-15 09:11:18,999	OUTPUT_MODEL	INFO	Train Epoch: 31 [70%]11452023-05-15 09:11:19,001	OUTPUT_MODEL	INFO	[2.474484920501709, 2.347720146179199, 7.804030418395996, 20.51442527770996, 1.8914880752563477, 2.2221457958221436, 3500, 0.00019925135779039958]11462023-05-15 09:11:46,055	OUTPUT_MODEL	INFO	====> Epoch: 3111472023-05-15 09:12:40,823	OUTPUT_MODEL	INFO	Train Epoch: 32 [58%]11482023-05-15 09:12:40,824	OUTPUT_MODEL	INFO	[2.4224510192871094, 2.149048089981079, 9.683818817138672, 21.558597564697266, 2.234496831893921, 2.225623846054077, 3600, 0.00019922645137067577]11492023-05-15 09:13:18,595	OUTPUT_MODEL	INFO	====> Epoch: 3211502023-05-15 09:14:01,534	OUTPUT_MODEL	INFO	Train Epoch: 33 [46%]11512023-05-15 09:14:01,535	OUTPUT_MODEL	INFO	[2.324897289276123, 2.3950281143188477, 10.593442916870117, 19.56314468383789, 1.7463090419769287, 2.0254478454589844, 3700, 0.00019920154806425444]11522023-05-15 09:14:50,424	OUTPUT_MODEL	INFO	====> Epoch: 3311532023-05-15 09:15:21,887	OUTPUT_MODEL	INFO	Train Epoch: 34 [33%]11542023-05-15 09:15:21,889	OUTPUT_MODEL	INFO	[2.34202241897583, 2.345229148864746, 9.606209754943848, 20.49749183654785, -2.444979190826416, 1.4553735256195068, 3800, 0.0001991766478707464]11552023-05-15 09:16:21,811	OUTPUT_MODEL	INFO	====> Epoch: 3411562023-05-15 09:16:42,138	OUTPUT_MODEL	INFO	Train Epoch: 35 [21%]11572023-05-15 09:16:42,139	OUTPUT_MODEL	INFO	[2.0229458808898926, 3.052290678024292, 11.751564979553223, 24.208847045898438, -8.005576133728027, 2.2388803958892822, 3900, 0.00019915175078976256]11582023-05-15 09:17:52,883	OUTPUT_MODEL	INFO	====> Epoch: 3511592023-05-15 09:18:02,362	OUTPUT_MODEL	INFO	Train Epoch: 36 [9%]11602023-05-15 09:18:02,363	OUTPUT_MODEL	INFO	[2.33034086227417, 2.6877312660217285, 10.181445121765137, 23.25379180908203, 1.976041555404663, 1.971625566482544, 4000, 0.00019912685682091382]11612023-05-15 09:18:03,751	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 36 to ././OUTPUT_MODEL/G_4000.pth11622023-05-15 09:18:04,155	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 36 to ././OUTPUT_MODEL/G_latest.pth11632023-05-15 09:19:23,521	OUTPUT_MODEL	INFO	Train Epoch: 36 [96%]11642023-05-15 09:19:23,522	OUTPUT_MODEL	INFO	[2.3052444458007812, 2.542353868484497, 8.32983112335205, 18.243999481201172, 0.2856762409210205, 1.8583269119262695, 4100, 0.00019912685682091382]11652023-05-15 09:19:26,662	OUTPUT_MODEL	INFO	====> Epoch: 3611662023-05-15 09:20:43,929	OUTPUT_MODEL	INFO	Train Epoch: 37 [84%]11672023-05-15 09:20:43,930	OUTPUT_MODEL	INFO	[2.019730567932129, 2.976344108581543, 13.960771560668945, 25.424827575683594, -3.910855770111084, 2.0867011547088623, 4200, 0.0001991019659638112]11682023-05-15 09:20:58,079	OUTPUT_MODEL	INFO	====> Epoch: 3711692023-05-15 09:22:04,300	OUTPUT_MODEL	INFO	Train Epoch: 38 [72%]11702023-05-15 09:22:04,303	OUTPUT_MODEL	INFO	[2.110328197479248, 2.6840312480926514, 11.143174171447754, 22.8408260345459, -5.805542469024658, 1.8623063564300537, 4300, 0.0001990770782180657]11712023-05-15 09:22:29,382	OUTPUT_MODEL	INFO	====> Epoch: 3811722023-05-15 09:23:25,059	OUTPUT_MODEL	INFO	Train Epoch: 39 [60%]11732023-05-15 09:23:25,060	OUTPUT_MODEL	INFO	[2.196502447128296, 2.9045543670654297, 11.285240173339844, 20.93663215637207, 2.1247804164886475, 1.8766467571258545, 4400, 0.00019905219358328844]11742023-05-15 09:24:01,227	OUTPUT_MODEL	INFO	====> Epoch: 3911752023-05-15 09:24:46,052	OUTPUT_MODEL	INFO	Train Epoch: 40 [47%]11762023-05-15 09:24:46,053	OUTPUT_MODEL	INFO	[2.0961694717407227, 2.5617763996124268, 10.149046897888184, 21.156206130981445, 2.113959789276123, 1.6261192560195923, 4500, 0.0001990273120590905]11772023-05-15 09:25:32,949	OUTPUT_MODEL	INFO	====> Epoch: 4011782023-05-15 09:26:05,927	OUTPUT_MODEL	INFO	Train Epoch: 41 [35%]11792023-05-15 09:26:05,928	OUTPUT_MODEL	INFO	[2.345233917236328, 2.383812665939331, 8.249051094055176, 21.18155860900879, 0.3124436140060425, 2.0116591453552246, 4600, 0.00019900243364508313]11802023-05-15 09:27:05,498	OUTPUT_MODEL	INFO	====> Epoch: 4111812023-05-15 09:27:27,517	OUTPUT_MODEL	INFO	Train Epoch: 42 [23%]11822023-05-15 09:27:27,518	OUTPUT_MODEL	INFO	[2.0119686126708984, 2.8317677974700928, 12.960095405578613, 24.28959846496582, 1.9706194400787354, 2.0977942943573, 4700, 0.0001989775583408775]11832023-05-15 09:28:37,220	OUTPUT_MODEL	INFO	====> Epoch: 4211842023-05-15 09:28:48,495	OUTPUT_MODEL	INFO	Train Epoch: 43 [11%]11852023-05-15 09:28:48,497	OUTPUT_MODEL	INFO	[2.2868504524230957, 2.7577972412109375, 8.69694709777832, 19.393646240234375, 2.19573974609375, 2.014125347137451, 4800, 0.00019895268614608487]11862023-05-15 09:30:07,844	OUTPUT_MODEL	INFO	Train Epoch: 43 [98%]11872023-05-15 09:30:07,845	OUTPUT_MODEL	INFO	[2.166806936264038, 2.8840389251708984, 11.337623596191406, 24.46369171142578, 2.0652577877044678, 1.7162461280822754, 4900, 0.00019895268614608487]11882023-05-15 09:30:09,588	OUTPUT_MODEL	INFO	====> Epoch: 4311892023-05-15 09:31:28,604	OUTPUT_MODEL	INFO	Train Epoch: 44 [86%]11902023-05-15 09:31:28,606	OUTPUT_MODEL	INFO	[1.9362813234329224, 3.21673321723938, 13.652947425842285, 24.75229835510254, 2.109553813934326, 1.9402551651000977, 5000, 0.0001989278170603166]11912023-05-15 09:31:30,268	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 44 to ././OUTPUT_MODEL/G_5000.pth11922023-05-15 09:31:30,656	OUTPUT_MODEL	INFO	Saving model and optimizer state at iteration 44 to ././OUTPUT_MODEL/G_latest.pth11932023-05-15 09:31:42,873	OUTPUT_MODEL	INFO	====> Epoch: 4411942023-05-15 09:32:51,212	OUTPUT_MODEL	INFO	Train Epoch: 45 [74%]11952023-05-15 09:32:51,214	OUTPUT_MODEL	INFO	[2.103963613510132, 3.116676092147827, 11.374105453491211, 24.61458396911621, 2.047689914703369, 1.7831947803497314, 5100, 0.00019890295108318404]11962023-05-15 09:33:14,988	OUTPUT_MODEL	INFO	====> Epoch: 4511972023-05-15 09:34:12,889	OUTPUT_MODEL	INFO	Train Epoch: 46 [61%]11982023-05-15 09:34:12,890	OUTPUT_MODEL	INFO	[2.119718551635742, 3.0040252208709717, 10.283185958862305, 22.897953033447266, 2.0366106033325195, 2.0922834873199463, 5200, 0.00019887808821429862]11992023-05-15 09:34:47,080	OUTPUT_MODEL	INFO	====> Epoch: 4612002023-05-15 09:35:33,192	OUTPUT_MODEL	INFO	Train Epoch: 47 [49%]
Showing the first 1,200 of 2076 lines. Download the file for the rest.