num_sent_processes: 4 [0] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/5W100D-0.5000r/shuffled_datasets [1] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/5W100D-0.5000r/shuffled_datasets [2] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/5W100D-0.5000r/shuffled_datasets [3] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_Small/5W100D-0.5000r/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-0.5000r', '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 [03/12/24-17:52:55] Start training [03/12/24-17:52:55] Building vocabulary [03/12/24-17:53:02] Vocabulary size is 40498 [Shuffling 1] loss 416214.6250 lr 0.5000 vocab_size 40498 (2.81s/4.80m) [Shuffling 2] loss 9523.9717 lr 0.4950 vocab_size 40498 (2.92s/4.89m) [Shuffling 3] loss 4556.4956 lr 0.4900 vocab_size 40498 (2.80s/4.86m) [Shuffling 4] loss 3229.5547 lr 0.4850 vocab_size 40498 (2.81s/4.84m) [Shuffling 5] loss 2224.1362 lr 0.4800 vocab_size 40498 (2.93s/4.88m) [Shuffling 6] loss 1788.7794 lr 0.4750 vocab_size 40498 (2.84s/4.87m) [Shuffling 7] loss 1389.9137 lr 0.4700 vocab_size 40498 (2.86s/4.88m) [Shuffling 8] loss 1531.1799 lr 0.4650 vocab_size 40498 (2.81s/4.87m) [Shuffling 9] loss 966.7576 lr 0.4600 vocab_size 40498 (2.77s/4.85m) [Shuffling 10] loss 1039.8094 lr 0.4550 vocab_size 40498 (2.82s/4.85m) [Shuffling 11] loss 815.9439 lr 0.4500 vocab_size 40498 (2.95s/4.87m) [Shuffling 12] loss 721.6381 lr 0.4450 vocab_size 40498 (2.96s/4.88m) [Shuffling 13] loss 915.9294 lr 0.4400 vocab_size 40498 (2.87s/4.88m) [Shuffling 14] loss 658.4308 lr 0.4350 vocab_size 40498 (2.92s/4.89m) [Shuffling 15] loss 601.6989 lr 0.4300 vocab_size 40498 (2.93s/4.90m) [Shuffling 16] loss 463.9556 lr 0.4250 vocab_size 40498 (2.90s/4.90m) [Shuffling 17] loss 383.2023 lr 0.4200 vocab_size 40498 (2.98s/4.91m) [Shuffling 18] loss 461.6093 lr 0.4150 vocab_size 40498 (2.99s/4.93m) [Shuffling 19] loss 474.5841 lr 0.4100 vocab_size 40498 (2.87s/4.92m) [Shuffling 20] loss 429.4464 lr 0.4050 vocab_size 40498 (2.88s/4.92m) [Shuffling 21] loss 355.8838 lr 0.4000 vocab_size 40498 (2.99s/4.93m) [Shuffling 22] loss 326.8157 lr 0.3950 vocab_size 40498 (2.93s/4.94m) [Shuffling 23] loss 305.5783 lr 0.3900 vocab_size 40498 (3.05s/4.95m) [Shuffling 24] loss 375.6743 lr 0.3850 vocab_size 40498 (2.91s/4.95m) [Shuffling 25] loss 291.7386 lr 0.3800 vocab_size 40498 (2.94s/4.95m) [Shuffling 26] loss 273.5165 lr 0.3750 vocab_size 40498 (2.97s/4.96m) [Shuffling 27] loss 297.4984 lr 0.3700 vocab_size 40498 (2.90s/4.96m) [Shuffling 28] loss 168.1503 lr 0.3650 vocab_size 40498 (2.91s/4.96m) [Shuffling 29] loss 255.1445 lr 0.3600 vocab_size 40498 (2.93s/4.96m) [Shuffling 30] loss 226.9164 lr 0.3550 vocab_size 40498 (2.88s/4.96m) [Shuffling 31] loss 171.4989 lr 0.3500 vocab_size 40498 (2.86s/4.96m) [Shuffling 32] loss 261.8182 lr 0.3450 vocab_size 40498 (2.86s/4.95m) [Shuffling 33] loss 165.6653 lr 0.3400 vocab_size 40498 (2.95s/4.96m) [Shuffling 34] loss 190.6006 lr 0.3350 vocab_size 40498 (2.88s/4.95m) [Shuffling 35] loss 153.1448 lr 0.3300 vocab_size 40498 (2.96s/4.96m) [Shuffling 36] loss 155.8735 lr 0.3250 vocab_size 40498 (2.87s/4.96m) [Shuffling 37] loss 184.9794 lr 0.3200 vocab_size 40498 (2.86s/4.95m) [Shuffling 38] loss 209.0009 lr 0.3150 vocab_size 40498 (2.92s/4.96m) [Shuffling 39] loss 130.1955 lr 0.3100 vocab_size 40498 (2.94s/4.96m) [Shuffling 40] loss 194.8952 lr 0.3050 vocab_size 40498 (2.93s/4.96m) [Shuffling 41] loss 141.6129 lr 0.3000 vocab_size 40498 (3.06s/4.96m) [Shuffling 42] loss 174.3324 lr 0.2950 vocab_size 40498 (2.90s/4.96m) [Shuffling 43] loss 131.3840 lr 0.2900 vocab_size 40498 (2.91s/4.96m) [Shuffling 44] loss 99.8734 lr 0.2850 vocab_size 40498 (3.01s/4.97m) [Shuffling 45] loss 180.8345 lr 0.2800 vocab_size 40498 (2.90s/4.97m) [Shuffling 46] loss 168.7655 lr 0.2750 vocab_size 40498 (2.91s/4.97m) [Shuffling 47] loss 145.4126 lr 0.2700 vocab_size 40498 (2.95s/4.97m) [Shuffling 48] loss 89.5309 lr 0.2650 vocab_size 40498 (2.94s/4.97m) [Shuffling 49] loss 131.8047 lr 0.2600 vocab_size 40498 (2.85s/4.97m) [Shuffling 50] loss 140.7799 lr 0.2550 vocab_size 40498 (2.93s/4.97m) [Shuffling 51] loss 200.3288 lr 0.2500 vocab_size 40498 (2.92s/4.97m) [Shuffling 52] loss 112.0654 lr 0.2451 vocab_size 40498 (2.88s/4.97m) [Shuffling 53] loss 132.5069 lr 0.2401 vocab_size 40498 (2.89s/4.97m) [Shuffling 54] loss 128.6926 lr 0.2351 vocab_size 40498 (2.86s/4.97m) [Shuffling 55] loss 91.5606 lr 0.2301 vocab_size 40498 (2.87s/4.97m) [Shuffling 56] loss 148.5169 lr 0.2251 vocab_size 40498 (2.83s/4.96m) [Shuffling 57] loss 95.5697 lr 0.2201 vocab_size 40498 (2.85s/4.96m) [Shuffling 58] loss 135.6420 lr 0.2151 vocab_size 40498 (2.95s/4.96m) [Shuffling 59] loss 77.1113 lr 0.2101 vocab_size 40498 (2.87s/4.96m) [Shuffling 60] loss 68.6143 lr 0.2051 vocab_size 40498 (2.88s/4.96m) [Shuffling 61] loss 86.3851 lr 0.2001 vocab_size 40498 (2.91s/4.96m) [Shuffling 62] loss 95.2349 lr 0.1951 vocab_size 40498 (2.86s/4.96m) [Shuffling 63] loss 88.2235 lr 0.1901 vocab_size 40498 (2.87s/4.96m) [Shuffling 64] loss 121.0659 lr 0.1851 vocab_size 40498 (2.98s/4.96m) [Shuffling 65] loss 82.6424 lr 0.1801 vocab_size 40498 (2.84s/4.96m) [Shuffling 66] loss 90.3976 lr 0.1751 vocab_size 40498 (2.85s/4.96m) [Shuffling 67] loss 105.1483 lr 0.1701 vocab_size 40498 (2.91s/4.96m) [Shuffling 68] loss 122.0799 lr 0.1651 vocab_size 40498 (2.85s/4.96m) [Shuffling 69] loss 98.6286 lr 0.1601 vocab_size 40498 (2.84s/4.96m) [Shuffling 70] loss 119.4040 lr 0.1551 vocab_size 40498 (2.91s/4.96m) [Shuffling 71] loss 71.5784 lr 0.1501 vocab_size 40498 (2.85s/4.96m) [Shuffling 72] loss 110.3149 lr 0.1451 vocab_size 40498 (2.87s/4.96m) [Shuffling 73] loss 72.2688 lr 0.1401 vocab_size 40498 (2.89s/4.95m) [Shuffling 74] loss 116.8351 lr 0.1351 vocab_size 40498 (2.85s/4.95m) [Shuffling 75] loss 66.2086 lr 0.1301 vocab_size 40498 (2.98s/4.96m) [Shuffling 76] loss 71.4866 lr 0.1251 vocab_size 40498 (2.89s/4.96m) [Shuffling 77] loss 95.4840 lr 0.1201 vocab_size 40498 (2.84s/4.95m) [Shuffling 78] loss 100.5142 lr 0.1151 vocab_size 40498 (2.85s/4.95m) [Shuffling 79] loss 100.5468 lr 0.1101 vocab_size 40498 (2.79s/4.95m) [Shuffling 80] loss 105.9313 lr 0.1051 vocab_size 40498 (2.79s/4.95m) [Shuffling 81] loss 89.5242 lr 0.1001 vocab_size 40498 (2.86s/4.95m) [Shuffling 82] loss 132.9645 lr 0.0951 vocab_size 40498 (2.80s/4.95m) [Shuffling 83] loss 83.2057 lr 0.0901 vocab_size 40498 (2.82s/4.94m) [Shuffling 84] loss 59.6763 lr 0.0851 vocab_size 40498 (2.88s/4.94m) [Shuffling 85] loss 67.6366 lr 0.0801 vocab_size 40498 (2.82s/4.94m) [Shuffling 86] loss 86.6540 lr 0.0751 vocab_size 40498 (2.81s/4.94m) [Shuffling 87] loss 94.5861 lr 0.0701 vocab_size 40498 (2.96s/4.94m) [Shuffling 88] loss 87.2053 lr 0.0651 vocab_size 40498 (2.83s/4.94m) [Shuffling 89] loss 49.3497 lr 0.0601 vocab_size 40498 (2.90s/4.94m) [Shuffling 90] loss 107.6044 lr 0.0551 vocab_size 40498 (2.89s/4.94m) [Shuffling 91] loss 101.0116 lr 0.0501 vocab_size 40498 (2.81s/4.94m) [Shuffling 92] loss 78.0825 lr 0.0451 vocab_size 40498 (2.82s/4.94m) [Shuffling 93] loss 100.4260 lr 0.0401 vocab_size 40498 (2.89s/4.94m) [Shuffling 94] loss 78.3957 lr 0.0351 vocab_size 40498 (2.82s/4.94m) [Shuffling 95] loss 90.4046 lr 0.0301 vocab_size 40498 (2.82s/4.94m) [Shuffling 96] loss 63.5496 lr 0.0251 vocab_size 40498 (2.88s/4.94m) [Shuffling 97] loss 39.8177 lr 0.0201 vocab_size 40498 (2.91s/4.94m) [Shuffling 98] loss 102.8490 lr 0.0151 vocab_size 40498 (2.92s/4.94m) [Shuffling 99] loss 57.6864 lr 0.0101 vocab_size 40498 (2.94s/4.94m) [Shuffling 100] loss 59.5633 lr 0.0051 vocab_size 40498 (5.94s/4.99m) [03/12/24-17:57:54] Training finished, training Time 4.99m