num_sent_processes: 4 [0] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/5W10D-0.5000r/shuffled_datasets [1] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/5W10D-0.5000r/shuffled_datasets [2] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/5W10D-0.5000r/shuffled_datasets [3] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/5W10D-0.5000r/shuffled_datasets {'num_shuffle': 100, 'embed_dim': 10, 'context_len': 5, 'nworkers': 6, 'save_freq': -1, 'save_dir': '/scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/5W10D-0.5000r', 'resume': '', 'train_alg': 'cbow', 'min_count': 5, 'neg_samples': 5, 'init_lr': 0.5, 'min_lr': 0.0001, 'lr_mode': 'linear', 'milestones': [], 'hier_softmax': False, 'update_vocab': 'once', 'seed': 0} Using cbow, negative sampling with 5 negative samples [03/12/24-17:43:38] Start training [03/12/24-17:43:38] Building vocabulary [03/12/24-17:43:46] Vocabulary size is 40498 [Shuffling 1] loss 769141.7500 lr 0.5000 vocab_size 40498 (2.74s/4.68m) [Shuffling 2] loss 12296.4844 lr 0.4950 vocab_size 40498 (2.57s/4.54m) [Shuffling 3] loss 5633.6626 lr 0.4900 vocab_size 40498 (2.56s/4.49m) [Shuffling 4] loss 3676.6416 lr 0.4850 vocab_size 40498 (2.73s/4.53m) [Shuffling 5] loss 2752.7078 lr 0.4800 vocab_size 40498 (2.54s/4.50m) [Shuffling 6] loss 1675.3407 lr 0.4750 vocab_size 40498 (2.61s/4.49m) [Shuffling 7] loss 1626.5990 lr 0.4700 vocab_size 40498 (2.65s/4.50m) [Shuffling 8] loss 1591.8950 lr 0.4650 vocab_size 40498 (2.43s/4.46m) [Shuffling 9] loss 1290.1466 lr 0.4600 vocab_size 40498 (2.57s/4.45m) [Shuffling 10] loss 1241.9896 lr 0.4550 vocab_size 40498 (2.61s/4.45m) [Shuffling 11] loss 781.8022 lr 0.4500 vocab_size 40498 (2.45s/4.43m) [Shuffling 12] loss 702.9863 lr 0.4450 vocab_size 40498 (2.63s/4.44m) [Shuffling 13] loss 1063.1892 lr 0.4400 vocab_size 40498 (2.67s/4.45m) [Shuffling 14] loss 558.8335 lr 0.4350 vocab_size 40498 (2.54s/4.44m) [Shuffling 15] loss 695.2235 lr 0.4300 vocab_size 40498 (2.59s/4.44m) [Shuffling 16] loss 487.4398 lr 0.4250 vocab_size 40498 (2.63s/4.44m) [Shuffling 17] loss 627.1163 lr 0.4200 vocab_size 40498 (2.52s/4.44m) [Shuffling 18] loss 409.4117 lr 0.4150 vocab_size 40498 (2.54s/4.43m) [Shuffling 19] loss 382.9336 lr 0.4100 vocab_size 40498 (2.59s/4.43m) [Shuffling 20] loss 466.9145 lr 0.4050 vocab_size 40498 (2.59s/4.43m) [Shuffling 21] loss 456.7705 lr 0.4000 vocab_size 40498 (2.56s/4.43m) [Shuffling 22] loss 442.5768 lr 0.3950 vocab_size 40498 (2.54s/4.43m) [Shuffling 23] loss 516.6094 lr 0.3900 vocab_size 40498 (2.56s/4.43m) [Shuffling 24] loss 405.0947 lr 0.3850 vocab_size 40498 (2.53s/4.42m) [Shuffling 25] loss 491.1031 lr 0.3800 vocab_size 40498 (2.65s/4.43m) [Shuffling 26] loss 291.6808 lr 0.3750 vocab_size 40498 (2.64s/4.43m) [Shuffling 27] loss 332.0653 lr 0.3700 vocab_size 40498 (2.62s/4.43m) [Shuffling 28] loss 419.7242 lr 0.3650 vocab_size 40498 (2.56s/4.43m) [Shuffling 29] loss 262.6374 lr 0.3600 vocab_size 40498 (2.57s/4.43m) [Shuffling 30] loss 232.6700 lr 0.3550 vocab_size 40498 (2.57s/4.43m) [Shuffling 31] loss 267.4289 lr 0.3500 vocab_size 40498 (2.55s/4.43m) [Shuffling 32] loss 189.7443 lr 0.3450 vocab_size 40498 (2.58s/4.43m) [Shuffling 33] loss 327.8373 lr 0.3400 vocab_size 40498 (2.57s/4.43m) [Shuffling 34] loss 314.3039 lr 0.3350 vocab_size 40498 (2.50s/4.42m) [Shuffling 35] loss 199.2717 lr 0.3300 vocab_size 40498 (2.53s/4.42m) [Shuffling 36] loss 239.4178 lr 0.3250 vocab_size 40498 (2.56s/4.42m) [Shuffling 37] loss 277.7159 lr 0.3200 vocab_size 40498 (2.62s/4.42m) [Shuffling 38] loss 197.3773 lr 0.3150 vocab_size 40498 (2.66s/4.42m) [Shuffling 39] loss 210.5952 lr 0.3100 vocab_size 40498 (2.67s/4.43m) [Shuffling 40] loss 205.5094 lr 0.3050 vocab_size 40498 (2.49s/4.42m) [Shuffling 41] loss 183.2366 lr 0.3000 vocab_size 40498 (2.64s/4.43m) [Shuffling 42] loss 172.9829 lr 0.2950 vocab_size 40498 (2.57s/4.43m) [Shuffling 43] loss 218.2684 lr 0.2900 vocab_size 40498 (2.61s/4.43m) [Shuffling 44] loss 209.0922 lr 0.2850 vocab_size 40498 (2.71s/4.43m) [Shuffling 45] loss 164.6657 lr 0.2800 vocab_size 40498 (2.72s/4.44m) [Shuffling 46] loss 157.6005 lr 0.2750 vocab_size 40498 (2.55s/4.44m) [Shuffling 47] loss 187.1628 lr 0.2700 vocab_size 40498 (2.71s/4.44m) [Shuffling 48] loss 129.4320 lr 0.2650 vocab_size 40498 (2.52s/4.44m) [Shuffling 49] loss 72.4340 lr 0.2600 vocab_size 40498 (2.56s/4.44m) [Shuffling 50] loss 178.0706 lr 0.2550 vocab_size 40498 (2.60s/4.44m) [Shuffling 51] loss 120.7893 lr 0.2500 vocab_size 40498 (2.50s/4.43m) [Shuffling 52] loss 182.7407 lr 0.2451 vocab_size 40498 (2.43s/4.43m) [Shuffling 53] loss 143.4489 lr 0.2401 vocab_size 40498 (2.47s/4.42m) [Shuffling 54] loss 167.3871 lr 0.2351 vocab_size 40498 (2.42s/4.42m) [Shuffling 55] loss 145.4038 lr 0.2301 vocab_size 40498 (2.48s/4.42m) [Shuffling 56] loss 129.2845 lr 0.2251 vocab_size 40498 (2.56s/4.42m) [Shuffling 57] loss 157.3617 lr 0.2201 vocab_size 40498 (2.46s/4.41m) [Shuffling 58] loss 58.0523 lr 0.2151 vocab_size 40498 (2.54s/4.41m) [Shuffling 59] loss 175.3813 lr 0.2101 vocab_size 40498 (2.51s/4.41m) [Shuffling 60] loss 161.8342 lr 0.2051 vocab_size 40498 (2.48s/4.41m) [Shuffling 61] loss 104.7973 lr 0.2001 vocab_size 40498 (2.49s/4.41m) [Shuffling 62] loss 72.4551 lr 0.1951 vocab_size 40498 (2.55s/4.40m) [Shuffling 63] loss 126.5295 lr 0.1901 vocab_size 40498 (2.47s/4.40m) [Shuffling 64] loss 159.9907 lr 0.1851 vocab_size 40498 (2.49s/4.40m) [Shuffling 65] loss 140.4784 lr 0.1801 vocab_size 40498 (2.50s/4.40m) [Shuffling 66] loss 119.8211 lr 0.1751 vocab_size 40498 (2.48s/4.40m) [Shuffling 67] loss 99.5613 lr 0.1701 vocab_size 40498 (2.52s/4.39m) [Shuffling 68] loss 168.6658 lr 0.1651 vocab_size 40498 (2.53s/4.39m) [Shuffling 69] loss 109.1367 lr 0.1601 vocab_size 40498 (2.49s/4.39m) [Shuffling 70] loss 112.2313 lr 0.1551 vocab_size 40498 (2.52s/4.39m) [Shuffling 71] loss 117.6041 lr 0.1501 vocab_size 40498 (2.52s/4.39m) [Shuffling 72] loss 86.3255 lr 0.1451 vocab_size 40498 (2.53s/4.39m) [Shuffling 73] loss 121.1357 lr 0.1401 vocab_size 40498 (2.62s/4.39m) [Shuffling 74] loss 93.9269 lr 0.1351 vocab_size 40498 (2.62s/4.39m) [Shuffling 75] loss 145.6120 lr 0.1301 vocab_size 40498 (2.50s/4.39m) [Shuffling 76] loss 132.0080 lr 0.1251 vocab_size 40498 (2.53s/4.39m) [Shuffling 77] loss 93.6608 lr 0.1201 vocab_size 40498 (2.54s/4.39m) [Shuffling 78] loss 131.4762 lr 0.1151 vocab_size 40498 (2.52s/4.39m) [Shuffling 79] loss 80.6816 lr 0.1101 vocab_size 40498 (2.51s/4.39m) [Shuffling 80] loss 80.6098 lr 0.1051 vocab_size 40498 (2.55s/4.39m) [Shuffling 81] loss 104.5260 lr 0.1001 vocab_size 40498 (2.45s/4.39m) [Shuffling 82] loss 74.6366 lr 0.0951 vocab_size 40498 (2.51s/4.38m) [Shuffling 83] loss 56.7341 lr 0.0901 vocab_size 40498 (2.50s/4.38m) [Shuffling 84] loss 121.2280 lr 0.0851 vocab_size 40498 (2.47s/4.38m) [Shuffling 85] loss 63.3178 lr 0.0801 vocab_size 40498 (2.53s/4.38m) [Shuffling 86] loss 86.5587 lr 0.0751 vocab_size 40498 (2.53s/4.38m) [Shuffling 87] loss 112.7849 lr 0.0701 vocab_size 40498 (2.48s/4.38m) [Shuffling 88] loss 111.6557 lr 0.0651 vocab_size 40498 (2.51s/4.38m) [Shuffling 89] loss 81.4617 lr 0.0601 vocab_size 40498 (2.49s/4.38m) [Shuffling 90] loss 68.8422 lr 0.0551 vocab_size 40498 (2.49s/4.38m) [Shuffling 91] loss 85.0041 lr 0.0501 vocab_size 40498 (2.53s/4.38m) [Shuffling 92] loss 92.7059 lr 0.0451 vocab_size 40498 (2.51s/4.37m) [Shuffling 93] loss 79.9454 lr 0.0401 vocab_size 40498 (2.45s/4.37m) [Shuffling 94] loss 111.9857 lr 0.0351 vocab_size 40498 (2.52s/4.37m) [Shuffling 95] loss 113.5094 lr 0.0301 vocab_size 40498 (2.47s/4.37m) [Shuffling 96] loss 116.9993 lr 0.0251 vocab_size 40498 (2.48s/4.37m) [Shuffling 97] loss 79.5952 lr 0.0201 vocab_size 40498 (2.58s/4.37m) [Shuffling 98] loss 73.2385 lr 0.0151 vocab_size 40498 (2.63s/4.37m) [Shuffling 99] loss 50.8146 lr 0.0101 vocab_size 40498 (2.48s/4.37m) [Shuffling 100] loss 80.3736 lr 0.0051 vocab_size 40498 (3.51s/4.39m) [03/12/24-17:48:02] Training finished, training Time 4.39m