num_sent_processes: 4 [0] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/5W100D-0.1000r/shuffled_datasets [1] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/5W100D-0.1000r/shuffled_datasets [2] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/5W100D-0.1000r/shuffled_datasets [3] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/5W100D-0.1000r/shuffled_datasets {'num_shuffle': 100, 'embed_dim': 100, 'context_len': 5, 'nworkers': 6, 'save_freq': -1, 'save_dir': '/scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/5W100D-0.1000r', 'resume': '', 'train_alg': 'cbow', 'min_count': 5, 'neg_samples': 5, 'init_lr': 0.1, 'min_lr': 0.0001, 'lr_mode': 'linear', 'milestones': [], 'hier_softmax': False, 'update_vocab': 'once', 'seed': 0} Using cbow, negative sampling with 5 negative samples [03/12/24-17:31:10] Start training [03/12/24-17:31:10] Building vocabulary [03/12/24-17:31:17] Vocabulary size is 40498 [Shuffling 1] loss 2235931.5000 lr 0.1000 vocab_size 40498 (3.05s/5.21m) [Shuffling 2] loss 2057074.7500 lr 0.0990 vocab_size 40498 (3.11s/5.26m) [Shuffling 3] loss 1952407.7500 lr 0.0980 vocab_size 40498 (3.03s/5.23m) [Shuffling 4] loss 2059733.1250 lr 0.0970 vocab_size 40498 (2.93s/5.17m) [Shuffling 5] loss 2079073.5000 lr 0.0960 vocab_size 40498 (3.00s/5.16m) [Shuffling 6] loss 2199742.5000 lr 0.0950 vocab_size 40498 (2.96s/5.15m) [Shuffling 7] loss 2082944.0000 lr 0.0940 vocab_size 40498 (2.98s/5.14m) [Shuffling 8] loss 2082506.3750 lr 0.0930 vocab_size 40498 (2.92s/5.12m) [Shuffling 9] loss 2068121.7500 lr 0.0920 vocab_size 40498 (3.01s/5.12m) [Shuffling 10] loss 2060081.0000 lr 0.0910 vocab_size 40498 (2.76s/5.08m) [Shuffling 11] loss 2105147.5000 lr 0.0900 vocab_size 40498 (2.74s/5.05m) [Shuffling 12] loss 2115034.5000 lr 0.0890 vocab_size 40498 (2.72s/5.02m) [Shuffling 13] loss 2052868.0000 lr 0.0880 vocab_size 40498 (2.70s/4.98m) [Shuffling 14] loss 2119688.0000 lr 0.0870 vocab_size 40498 (2.73s/4.96m) [Shuffling 15] loss 2105716.7500 lr 0.0860 vocab_size 40498 (2.76s/4.95m) [Shuffling 16] loss 2081536.7500 lr 0.0850 vocab_size 40498 (2.73s/4.93m) [Shuffling 17] loss 2083037.2500 lr 0.0840 vocab_size 40498 (2.76s/4.92m) [Shuffling 18] loss 2176473.5000 lr 0.0830 vocab_size 40498 (2.83s/4.91m) [Shuffling 19] loss 2137962.0000 lr 0.0820 vocab_size 40498 (2.75s/4.90m) [Shuffling 20] loss 2059810.2500 lr 0.0810 vocab_size 40498 (2.83s/4.90m) [Shuffling 21] loss 2085924.8750 lr 0.0800 vocab_size 40498 (2.86s/4.90m) [Shuffling 22] loss 2085927.2500 lr 0.0790 vocab_size 40498 (2.80s/4.90m) [Shuffling 23] loss 2159286.0000 lr 0.0780 vocab_size 40498 (2.80s/4.89m) [Shuffling 24] loss 2139250.2500 lr 0.0770 vocab_size 40498 (2.78s/4.88m) [Shuffling 25] loss 2126825.5000 lr 0.0760 vocab_size 40498 (2.74s/4.88m) [Shuffling 26] loss 2138164.2500 lr 0.0750 vocab_size 40498 (2.90s/4.88m) [Shuffling 27] loss 2105172.2500 lr 0.0740 vocab_size 40498 (2.83s/4.88m) [Shuffling 28] loss 2097182.5000 lr 0.0730 vocab_size 40498 (2.80s/4.88m) [Shuffling 29] loss 2012759.3750 lr 0.0720 vocab_size 40498 (2.85s/4.88m) [Shuffling 30] loss 2048222.0000 lr 0.0710 vocab_size 40498 (2.84s/4.87m) [Shuffling 31] loss 2052857.6250 lr 0.0700 vocab_size 40498 (2.80s/4.87m) [Shuffling 32] loss 2067552.6250 lr 0.0690 vocab_size 40498 (2.84s/4.87m) [Shuffling 33] loss 2102032.7500 lr 0.0680 vocab_size 40498 (2.81s/4.87m) [Shuffling 34] loss 2070769.8750 lr 0.0670 vocab_size 40498 (2.84s/4.87m) [Shuffling 35] loss 2062728.1250 lr 0.0660 vocab_size 40498 (2.81s/4.87m) [Shuffling 36] loss 2026052.0000 lr 0.0650 vocab_size 40498 (2.81s/4.87m) [Shuffling 37] loss 1990227.0000 lr 0.0640 vocab_size 40498 (2.92s/4.87m) [Shuffling 38] loss 2028171.5000 lr 0.0630 vocab_size 40498 (2.78s/4.87m) [Shuffling 39] loss 2105228.7500 lr 0.0620 vocab_size 40498 (2.82s/4.87m) [Shuffling 40] loss 2049154.7500 lr 0.0610 vocab_size 40498 (2.88s/4.87m) [Shuffling 41] loss 2050153.7500 lr 0.0600 vocab_size 40498 (2.84s/4.87m) [Shuffling 42] loss 2038769.3750 lr 0.0590 vocab_size 40498 (2.92s/4.87m) [Shuffling 43] loss 2031569.5000 lr 0.0580 vocab_size 40498 (2.85s/4.87m) [Shuffling 44] loss 2057116.5000 lr 0.0570 vocab_size 40498 (2.80s/4.87m) [Shuffling 45] loss 2016907.2500 lr 0.0560 vocab_size 40498 (2.87s/4.87m) [Shuffling 46] loss 1950023.1250 lr 0.0550 vocab_size 40498 (2.89s/4.87m) [Shuffling 47] loss 1994746.7500 lr 0.0540 vocab_size 40498 (2.87s/4.87m) [Shuffling 48] loss 2022465.8750 lr 0.0530 vocab_size 40498 (2.89s/4.87m) [Shuffling 49] loss 1997788.2500 lr 0.0520 vocab_size 40498 (2.80s/4.87m) [Shuffling 50] loss 2001703.6250 lr 0.0510 vocab_size 40498 (2.85s/4.87m) [Shuffling 51] loss 2019794.5000 lr 0.0500 vocab_size 40498 (2.88s/4.87m) [Shuffling 52] loss 2092462.6250 lr 0.0491 vocab_size 40498 (2.80s/4.87m) [Shuffling 53] loss 1990118.2500 lr 0.0481 vocab_size 40498 (2.91s/4.87m) [Shuffling 54] loss 2100918.0000 lr 0.0471 vocab_size 40498 (2.84s/4.87m) [Shuffling 55] loss 2058650.8750 lr 0.0461 vocab_size 40498 (2.87s/4.87m) [Shuffling 56] loss 2058260.1250 lr 0.0451 vocab_size 40498 (2.87s/4.87m) [Shuffling 57] loss 1987582.3750 lr 0.0441 vocab_size 40498 (2.84s/4.87m) [Shuffling 58] loss 2032712.7500 lr 0.0431 vocab_size 40498 (2.88s/4.87m) [Shuffling 59] loss 2001458.0000 lr 0.0421 vocab_size 40498 (2.94s/4.88m) [Shuffling 60] loss 2018539.2500 lr 0.0411 vocab_size 40498 (2.89s/4.88m) [Shuffling 61] loss 2058012.7500 lr 0.0401 vocab_size 40498 (2.93s/4.88m) [Shuffling 62] loss 1991862.1250 lr 0.0391 vocab_size 40498 (2.94s/4.88m) [Shuffling 63] loss 2009570.7500 lr 0.0381 vocab_size 40498 (2.92s/4.88m) [Shuffling 64] loss 2041687.6250 lr 0.0371 vocab_size 40498 (2.98s/4.89m) [Shuffling 65] loss 2039630.0000 lr 0.0361 vocab_size 40498 (2.96s/4.89m) [Shuffling 66] loss 2047043.3750 lr 0.0351 vocab_size 40498 (2.95s/4.89m) [Shuffling 67] loss 1975675.8750 lr 0.0341 vocab_size 40498 (2.94s/4.89m) [Shuffling 68] loss 2076252.2500 lr 0.0331 vocab_size 40498 (2.96s/4.90m) [Shuffling 69] loss 2030693.6250 lr 0.0321 vocab_size 40498 (3.06s/4.90m) [Shuffling 70] loss 2008344.8750 lr 0.0311 vocab_size 40498 (2.96s/4.90m) [Shuffling 71] loss 1990458.1250 lr 0.0301 vocab_size 40498 (2.94s/4.91m) [Shuffling 72] loss 2005970.2500 lr 0.0291 vocab_size 40498 (2.96s/4.91m) [Shuffling 73] loss 1992422.5000 lr 0.0281 vocab_size 40498 (2.93s/4.91m) [Shuffling 74] loss 1996367.7500 lr 0.0271 vocab_size 40498 (2.91s/4.91m) [Shuffling 75] loss 2001170.8750 lr 0.0261 vocab_size 40498 (3.00s/4.91m) [Shuffling 76] loss 2053532.2500 lr 0.0251 vocab_size 40498 (2.93s/4.91m) [Shuffling 77] loss 1999435.3750 lr 0.0241 vocab_size 40498 (2.92s/4.92m) [Shuffling 78] loss 2033801.2500 lr 0.0231 vocab_size 40498 (2.91s/4.92m) [Shuffling 79] loss 2008946.7500 lr 0.0221 vocab_size 40498 (2.92s/4.92m) [Shuffling 80] loss 2005335.3750 lr 0.0211 vocab_size 40498 (3.00s/4.92m) [Shuffling 81] loss 1953770.6250 lr 0.0201 vocab_size 40498 (3.06s/4.92m) [Shuffling 82] loss 1981347.0000 lr 0.0191 vocab_size 40498 (2.93s/4.93m) [Shuffling 83] loss 1918027.0000 lr 0.0181 vocab_size 40498 (3.09s/4.93m) [Shuffling 84] loss 1958648.0000 lr 0.0171 vocab_size 40498 (2.91s/4.93m) [Shuffling 85] loss 1983147.0000 lr 0.0161 vocab_size 40498 (2.96s/4.93m) [Shuffling 86] loss 2032503.7500 lr 0.0151 vocab_size 40498 (2.94s/4.93m) [Shuffling 87] loss 1942385.1250 lr 0.0141 vocab_size 40498 (2.92s/4.93m) [Shuffling 88] loss 1998361.3750 lr 0.0131 vocab_size 40498 (2.96s/4.93m) [Shuffling 89] loss 1993090.6250 lr 0.0121 vocab_size 40498 (2.94s/4.94m) [Shuffling 90] loss 1910225.6250 lr 0.0111 vocab_size 40498 (3.06s/4.94m) [Shuffling 91] loss 1999904.6250 lr 0.0101 vocab_size 40498 (3.06s/4.94m) [Shuffling 92] loss 1930397.6250 lr 0.0091 vocab_size 40498 (2.95s/4.94m) [Shuffling 93] loss 1972048.5000 lr 0.0081 vocab_size 40498 (2.93s/4.94m) [Shuffling 94] loss 1993272.0000 lr 0.0071 vocab_size 40498 (3.95s/4.96m) [Shuffling 95] loss 1920780.7500 lr 0.0061 vocab_size 40498 (2.96s/4.96m) [Shuffling 96] loss 2047136.7500 lr 0.0051 vocab_size 40498 (3.03s/4.97m) [Shuffling 97] loss 1968077.3750 lr 0.0041 vocab_size 40498 (2.93s/4.97m) [Shuffling 98] loss 1988017.7500 lr 0.0031 vocab_size 40498 (2.99s/4.97m) [Shuffling 99] loss 1972771.3750 lr 0.0021 vocab_size 40498 (2.97s/4.97m) [Shuffling 100] loss 1903471.1250 lr 0.0011 vocab_size 40498 (9.04s/5.07m) [03/12/24-17:36:14] Training finished, training Time 5.07m