num_sent_processes: 4 [0] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/50W100D-0.5000r/shuffled_datasets [1] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/50W100D-0.5000r/shuffled_datasets [2] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/50W100D-0.5000r/shuffled_datasets [3] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/50W100D-0.5000r/shuffled_datasets {'num_shuffle': 100, 'embed_dim': 100, 'context_len': 50, 'nworkers': 6, 'save_freq': -1, 'save_dir': '/scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/50W100D-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 [03/12/24-17:58:00] Start training [03/12/24-17:58:00] Building vocabulary [03/12/24-17:58:07] Vocabulary size is 40498 [Shuffling 1] loss 194906.8281 lr 0.5000 vocab_size 40498 (3.81s/6.47m) [Shuffling 2] loss 6461.6841 lr 0.4950 vocab_size 40498 (3.76s/6.43m) [Shuffling 3] loss 3786.0344 lr 0.4900 vocab_size 40498 (3.80s/6.44m) [Shuffling 4] loss 3182.9482 lr 0.4850 vocab_size 40498 (3.72s/6.41m) [Shuffling 5] loss 2300.9194 lr 0.4800 vocab_size 40498 (3.78s/6.41m) [Shuffling 6] loss 1650.0657 lr 0.4750 vocab_size 40498 (3.79s/6.42m) [Shuffling 7] loss 1698.4025 lr 0.4700 vocab_size 40498 (3.57s/6.37m) [Shuffling 8] loss 1291.5869 lr 0.4650 vocab_size 40498 (3.70s/6.36m) [Shuffling 9] loss 1110.5858 lr 0.4600 vocab_size 40498 (3.69s/6.35m) [Shuffling 10] loss 890.7859 lr 0.4550 vocab_size 40498 (3.70s/6.34m) [Shuffling 11] loss 982.7598 lr 0.4500 vocab_size 40498 (3.66s/6.33m) [Shuffling 12] loss 682.6500 lr 0.4450 vocab_size 40498 (3.77s/6.33m) [Shuffling 13] loss 845.9269 lr 0.4400 vocab_size 40498 (3.70s/6.33m) [Shuffling 14] loss 657.8604 lr 0.4350 vocab_size 40498 (3.73s/6.33m) [Shuffling 15] loss 703.6165 lr 0.4300 vocab_size 40498 (3.63s/6.32m) [Shuffling 16] loss 605.7755 lr 0.4250 vocab_size 40498 (3.70s/6.32m) [Shuffling 17] loss 553.2517 lr 0.4200 vocab_size 40498 (3.71s/6.32m) [Shuffling 18] loss 722.4778 lr 0.4150 vocab_size 40498 (3.61s/6.31m) [Shuffling 19] loss 462.3684 lr 0.4100 vocab_size 40498 (3.69s/6.30m) [Shuffling 20] loss 458.0803 lr 0.4050 vocab_size 40498 (3.68s/6.30m) [Shuffling 21] loss 489.8052 lr 0.4000 vocab_size 40498 (3.69s/6.30m) [Shuffling 22] loss 425.3806 lr 0.3950 vocab_size 40498 (3.63s/6.29m) [Shuffling 23] loss 526.4537 lr 0.3900 vocab_size 40498 (3.66s/6.29m) [Shuffling 24] loss 447.4605 lr 0.3850 vocab_size 40498 (3.76s/6.29m) [Shuffling 25] loss 407.5113 lr 0.3800 vocab_size 40498 (3.71s/6.29m) [Shuffling 26] loss 441.1292 lr 0.3750 vocab_size 40498 (3.57s/6.29m) [Shuffling 27] loss 441.1252 lr 0.3700 vocab_size 40498 (3.62s/6.28m) [Shuffling 28] loss 386.1376 lr 0.3650 vocab_size 40498 (3.65s/6.28m) [Shuffling 29] loss 427.8625 lr 0.3600 vocab_size 40498 (3.64s/6.28m) [Shuffling 30] loss 284.0788 lr 0.3550 vocab_size 40498 (3.71s/6.28m) [Shuffling 31] loss 339.0002 lr 0.3500 vocab_size 40498 (3.73s/6.28m) [Shuffling 32] loss 348.8190 lr 0.3450 vocab_size 40498 (3.62s/6.27m) [Shuffling 33] loss 279.0773 lr 0.3400 vocab_size 40498 (3.80s/6.28m) [Shuffling 34] loss 285.7091 lr 0.3350 vocab_size 40498 (3.65s/6.28m) [Shuffling 35] loss 315.0793 lr 0.3300 vocab_size 40498 (3.64s/6.28m) [Shuffling 36] loss 274.7918 lr 0.3250 vocab_size 40498 (3.72s/6.28m) [Shuffling 37] loss 287.3874 lr 0.3200 vocab_size 40498 (3.64s/6.27m) [Shuffling 38] loss 240.6461 lr 0.3150 vocab_size 40498 (3.73s/6.28m) [Shuffling 39] loss 311.7629 lr 0.3100 vocab_size 40498 (3.65s/6.27m) [Shuffling 40] loss 260.6060 lr 0.3050 vocab_size 40498 (3.61s/6.27m) [Shuffling 41] loss 211.3789 lr 0.3000 vocab_size 40498 (3.68s/6.27m) [Shuffling 42] loss 217.2058 lr 0.2950 vocab_size 40498 (3.70s/6.27m) [Shuffling 43] loss 270.9524 lr 0.2900 vocab_size 40498 (3.64s/6.27m) [Shuffling 44] loss 209.7313 lr 0.2850 vocab_size 40498 (3.65s/6.27m) [Shuffling 45] loss 215.2305 lr 0.2800 vocab_size 40498 (3.58s/6.26m) [Shuffling 46] loss 250.3239 lr 0.2750 vocab_size 40498 (3.81s/6.27m) [Shuffling 47] loss 251.2782 lr 0.2700 vocab_size 40498 (3.72s/6.27m) [Shuffling 48] loss 264.9336 lr 0.2650 vocab_size 40498 (3.64s/6.27m) [Shuffling 49] loss 285.2852 lr 0.2600 vocab_size 40498 (3.64s/6.27m) [Shuffling 50] loss 202.3494 lr 0.2550 vocab_size 40498 (3.73s/6.27m) [Shuffling 51] loss 229.3018 lr 0.2500 vocab_size 40498 (3.64s/6.27m) [Shuffling 52] loss 189.5716 lr 0.2451 vocab_size 40498 (3.70s/6.27m) [Shuffling 53] loss 161.4443 lr 0.2401 vocab_size 40498 (3.62s/6.26m) [Shuffling 54] loss 161.4169 lr 0.2351 vocab_size 40498 (3.68s/6.26m) [Shuffling 55] loss 196.8610 lr 0.2301 vocab_size 40498 (3.74s/6.27m) [Shuffling 56] loss 208.9587 lr 0.2251 vocab_size 40498 (3.77s/6.27m) [Shuffling 57] loss 172.1697 lr 0.2201 vocab_size 40498 (3.77s/6.27m) [Shuffling 58] loss 168.0580 lr 0.2151 vocab_size 40498 (3.64s/6.27m) [Shuffling 59] loss 186.8082 lr 0.2101 vocab_size 40498 (3.71s/6.27m) [Shuffling 60] loss 124.5560 lr 0.2051 vocab_size 40498 (3.82s/6.27m) [Shuffling 61] loss 172.2406 lr 0.2001 vocab_size 40498 (3.75s/6.27m) [Shuffling 62] loss 116.1762 lr 0.1951 vocab_size 40498 (3.60s/6.27m) [Shuffling 63] loss 109.0453 lr 0.1901 vocab_size 40498 (3.82s/6.28m) [Shuffling 64] loss 127.1724 lr 0.1851 vocab_size 40498 (3.69s/6.28m) [Shuffling 65] loss 191.9599 lr 0.1801 vocab_size 40498 (3.75s/6.28m) [Shuffling 66] loss 180.0252 lr 0.1751 vocab_size 40498 (3.72s/6.28m) [Shuffling 67] loss 166.0714 lr 0.1701 vocab_size 40498 (3.71s/6.28m) [Shuffling 68] loss 99.0425 lr 0.1651 vocab_size 40498 (3.76s/6.28m) [Shuffling 69] loss 155.0895 lr 0.1601 vocab_size 40498 (3.64s/6.28m) [Shuffling 70] loss 110.3412 lr 0.1551 vocab_size 40498 (3.70s/6.28m) [Shuffling 71] loss 153.9585 lr 0.1501 vocab_size 40498 (3.67s/6.28m) [Shuffling 72] loss 133.4181 lr 0.1451 vocab_size 40498 (3.75s/6.28m) [Shuffling 73] loss 135.3300 lr 0.1401 vocab_size 40498 (3.64s/6.28m) [Shuffling 74] loss 117.0826 lr 0.1351 vocab_size 40498 (3.70s/6.28m) [Shuffling 75] loss 121.6966 lr 0.1301 vocab_size 40498 (3.84s/6.28m) [Shuffling 76] loss 184.3780 lr 0.1251 vocab_size 40498 (3.75s/6.28m) [Shuffling 77] loss 128.0461 lr 0.1201 vocab_size 40498 (3.70s/6.28m) [Shuffling 78] loss 103.8669 lr 0.1151 vocab_size 40498 (3.68s/6.28m) [Shuffling 79] loss 116.6425 lr 0.1101 vocab_size 40498 (3.70s/6.28m) [Shuffling 80] loss 92.3694 lr 0.1051 vocab_size 40498 (3.68s/6.28m) [Shuffling 81] loss 148.0769 lr 0.1001 vocab_size 40498 (3.68s/6.28m) [Shuffling 82] loss 171.1448 lr 0.0951 vocab_size 40498 (3.65s/6.28m) [Shuffling 83] loss 106.9586 lr 0.0901 vocab_size 40498 (3.75s/6.28m) [Shuffling 84] loss 137.5220 lr 0.0851 vocab_size 40498 (3.69s/6.28m) [Shuffling 85] loss 90.4379 lr 0.0801 vocab_size 40498 (3.74s/6.28m) [Shuffling 86] loss 80.0632 lr 0.0751 vocab_size 40498 (3.71s/6.28m) [Shuffling 87] loss 112.3467 lr 0.0701 vocab_size 40498 (3.72s/6.28m) [Shuffling 88] loss 119.4233 lr 0.0651 vocab_size 40498 (3.69s/6.28m) [Shuffling 89] loss 156.9637 lr 0.0601 vocab_size 40498 (3.73s/6.28m) [Shuffling 90] loss 112.6180 lr 0.0551 vocab_size 40498 (3.70s/6.28m) [Shuffling 91] loss 110.2534 lr 0.0501 vocab_size 40498 (3.66s/6.28m) [Shuffling 92] loss 152.2552 lr 0.0451 vocab_size 40498 (3.74s/6.28m) [Shuffling 93] loss 160.3678 lr 0.0401 vocab_size 40498 (3.70s/6.28m) [Shuffling 94] loss 96.7154 lr 0.0351 vocab_size 40498 (3.73s/6.28m) [Shuffling 95] loss 124.8914 lr 0.0301 vocab_size 40498 (3.71s/6.28m) [Shuffling 96] loss 124.1078 lr 0.0251 vocab_size 40498 (3.67s/6.28m) [Shuffling 97] loss 114.9973 lr 0.0201 vocab_size 40498 (3.64s/6.28m) [Shuffling 98] loss 92.3257 lr 0.0151 vocab_size 40498 (3.68s/6.28m) [Shuffling 99] loss 109.5466 lr 0.0101 vocab_size 40498 (5.77s/6.32m) [Shuffling 100] loss 97.7188 lr 0.0051 vocab_size 40498 (4.63s/6.33m) [03/12/24-18:04:20] Training finished, training Time 6.33m