num_sent_processes: 4 [0] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_tile25k/5W10D-0.0250r/shuffled_datasets [1] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_tile25k/5W10D-0.0250r/shuffled_datasets [2] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_tile25k/5W10D-0.0250r/shuffled_datasets [3] Creating shuffled datasets in /scratch/gz5hp/tfbs_region2vec_models/expr_universe_tile25k/5W10D-0.0250r/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_tile25k/5W10D-0.0250r', 'resume': '', 'train_alg': 'cbow', 'min_count': 5, 'neg_samples': 5, 'init_lr': 0.025, 'min_lr': 0.0001, 'lr_mode': 'linear', 'milestones': [], 'hier_softmax': False, 'update_vocab': 'once', 'seed': 0} Using cbow, negative sampling with 5 negative samples [03/12/24-17:09:01] Start training [03/12/24-17:09:01] Building vocabulary [03/12/24-17:09:16] Vocabulary size is 100053 [Shuffling 1] loss 5265256.0000 lr 0.0250 vocab_size 100053 (5.68s/9.71m) [Shuffling 2] loss 4256148.5000 lr 0.0248 vocab_size 100053 (5.93s/9.93m) [Shuffling 3] loss 4300851.5000 lr 0.0245 vocab_size 100053 (6.00s/10.03m) [Shuffling 4] loss 4212616.0000 lr 0.0243 vocab_size 100053 (6.04s/10.11m) [Shuffling 5] loss 4194304.0000 lr 0.0240 vocab_size 100053 (6.02s/10.14m) [Shuffling 6] loss 4070570.0000 lr 0.0238 vocab_size 100053 (6.00s/10.16m) [Shuffling 7] loss 4030954.5000 lr 0.0235 vocab_size 100053 (6.23s/10.23m) [Shuffling 8] loss 4118283.5000 lr 0.0233 vocab_size 100053 (6.08s/10.25m) [Shuffling 9] loss 4010572.2500 lr 0.0230 vocab_size 100053 (6.11s/10.28m) [Shuffling 10] loss 3892051.0000 lr 0.0228 vocab_size 100053 (6.30s/10.32m) [Shuffling 11] loss 3953252.2500 lr 0.0225 vocab_size 100053 (6.20s/10.35m) [Shuffling 12] loss 4195690.0000 lr 0.0223 vocab_size 100053 (5.95s/10.34m) [Shuffling 13] loss 4018610.2500 lr 0.0220 vocab_size 100053 (6.09s/10.34m) [Shuffling 14] loss 4070383.2500 lr 0.0218 vocab_size 100053 (6.05s/10.34m) [Shuffling 15] loss 3950116.0000 lr 0.0215 vocab_size 100053 (6.02s/10.34m) [Shuffling 16] loss 3958467.7500 lr 0.0213 vocab_size 100053 (6.02s/10.33m) [Shuffling 17] loss 3885715.5000 lr 0.0210 vocab_size 100053 (5.96s/10.33m) [Shuffling 18] loss 3924746.2500 lr 0.0208 vocab_size 100053 (6.08s/10.33m) [Shuffling 19] loss 3883372.7500 lr 0.0205 vocab_size 100053 (6.41s/10.36m) [Shuffling 20] loss 4000781.5000 lr 0.0203 vocab_size 100053 (6.03s/10.36m) [Shuffling 21] loss 3771654.7500 lr 0.0200 vocab_size 100053 (6.07s/10.36m) [Shuffling 22] loss 3829726.7500 lr 0.0198 vocab_size 100053 (6.06s/10.36m) [Shuffling 23] loss 4062453.5000 lr 0.0195 vocab_size 100053 (6.02s/10.36m) [Shuffling 24] loss 4021013.0000 lr 0.0193 vocab_size 100053 (6.03s/10.35m) [Shuffling 25] loss 3818399.2500 lr 0.0190 vocab_size 100053 (6.00s/10.35m) [Shuffling 26] loss 3709023.2500 lr 0.0188 vocab_size 100053 (6.07s/10.35m) [Shuffling 27] loss 3898738.0000 lr 0.0185 vocab_size 100053 (6.04s/10.35m) [Shuffling 28] loss 3987843.7500 lr 0.0183 vocab_size 100053 (6.05s/10.35m) [Shuffling 29] loss 3916899.5000 lr 0.0180 vocab_size 100053 (6.03s/10.35m) [Shuffling 30] loss 3932722.0000 lr 0.0178 vocab_size 100053 (6.17s/10.35m) [Shuffling 31] loss 3835917.7500 lr 0.0175 vocab_size 100053 (6.06s/10.35m) [Shuffling 32] loss 3978136.7500 lr 0.0173 vocab_size 100053 (6.03s/10.35m) [Shuffling 33] loss 3829032.2500 lr 0.0170 vocab_size 100053 (6.05s/10.35m) [Shuffling 34] loss 4016920.0000 lr 0.0168 vocab_size 100053 (6.04s/10.35m) [Shuffling 35] loss 3902797.5000 lr 0.0165 vocab_size 100053 (6.06s/10.35m) [Shuffling 36] loss 3885516.7500 lr 0.0163 vocab_size 100053 (6.08s/10.35m) [Shuffling 37] loss 4047850.2500 lr 0.0160 vocab_size 100053 (6.05s/10.35m) [Shuffling 38] loss 3766640.5000 lr 0.0158 vocab_size 100053 (6.06s/10.35m) [Shuffling 39] loss 4085181.7500 lr 0.0155 vocab_size 100053 (6.04s/10.35m) [Shuffling 40] loss 3961530.0000 lr 0.0153 vocab_size 100053 (6.06s/10.35m) [Shuffling 41] loss 3861868.0000 lr 0.0150 vocab_size 100053 (6.05s/10.35m) [Shuffling 42] loss 3835984.5000 lr 0.0148 vocab_size 100053 (6.03s/10.35m) [Shuffling 43] loss 4118862.2500 lr 0.0145 vocab_size 100053 (6.02s/10.35m) [Shuffling 44] loss 3881022.5000 lr 0.0143 vocab_size 100053 (6.06s/10.35m) [Shuffling 45] loss 3939504.7500 lr 0.0140 vocab_size 100053 (6.04s/10.35m) [Shuffling 46] loss 3852605.0000 lr 0.0138 vocab_size 100053 (6.05s/10.35m) [Shuffling 47] loss 3892580.2500 lr 0.0135 vocab_size 100053 (6.04s/10.35m) [Shuffling 48] loss 3952478.2500 lr 0.0133 vocab_size 100053 (6.06s/10.35m) [Shuffling 49] loss 3924305.2500 lr 0.0130 vocab_size 100053 (6.05s/10.35m) [Shuffling 50] loss 3931728.2500 lr 0.0128 vocab_size 100053 (6.07s/10.35m) [Shuffling 51] loss 4083141.5000 lr 0.0126 vocab_size 100053 (6.04s/10.35m) [Shuffling 52] loss 3861280.5000 lr 0.0123 vocab_size 100053 (6.05s/10.34m) [Shuffling 53] loss 3883496.0000 lr 0.0121 vocab_size 100053 (6.04s/10.34m) [Shuffling 54] loss 3976631.0000 lr 0.0118 vocab_size 100053 (6.04s/10.34m) [Shuffling 55] loss 3951486.7500 lr 0.0116 vocab_size 100053 (6.02s/10.34m) [Shuffling 56] loss 3756064.0000 lr 0.0113 vocab_size 100053 (6.05s/10.34m) [Shuffling 57] loss 3804952.5000 lr 0.0111 vocab_size 100053 (6.04s/10.34m) [Shuffling 58] loss 3909475.2500 lr 0.0108 vocab_size 100053 (6.07s/10.34m) [Shuffling 59] loss 3840283.5000 lr 0.0106 vocab_size 100053 (6.01s/10.34m) [Shuffling 60] loss 3959238.5000 lr 0.0103 vocab_size 100053 (6.05s/10.34m) [Shuffling 61] loss 3900828.7500 lr 0.0101 vocab_size 100053 (6.05s/10.34m) [Shuffling 62] loss 3898680.2500 lr 0.0098 vocab_size 100053 (6.03s/10.34m) [Shuffling 63] loss 3924320.7500 lr 0.0096 vocab_size 100053 (6.05s/10.34m) [Shuffling 64] loss 4030129.5000 lr 0.0093 vocab_size 100053 (6.05s/10.34m) [Shuffling 65] loss 3986569.0000 lr 0.0091 vocab_size 100053 (6.09s/10.34m) [Shuffling 66] loss 3858544.2500 lr 0.0088 vocab_size 100053 (6.05s/10.34m) [Shuffling 67] loss 4020886.2500 lr 0.0086 vocab_size 100053 (6.07s/10.34m) [Shuffling 68] loss 3849294.2500 lr 0.0083 vocab_size 100053 (6.02s/10.34m) [Shuffling 69] loss 3884750.5000 lr 0.0081 vocab_size 100053 (6.09s/10.34m) [Shuffling 70] loss 3841351.2500 lr 0.0078 vocab_size 100053 (6.04s/10.34m) [Shuffling 71] loss 3908735.5000 lr 0.0076 vocab_size 100053 (6.05s/10.34m) [Shuffling 72] loss 3986860.5000 lr 0.0073 vocab_size 100053 (6.09s/10.34m) [Shuffling 73] loss 4013369.5000 lr 0.0071 vocab_size 100053 (6.07s/10.34m) [Shuffling 74] loss 3998491.0000 lr 0.0068 vocab_size 100053 (6.08s/10.34m) [Shuffling 75] loss 3905153.2500 lr 0.0066 vocab_size 100053 (6.06s/10.34m) [Shuffling 76] loss 3861439.5000 lr 0.0063 vocab_size 100053 (6.09s/10.34m) [Shuffling 77] loss 3793709.7500 lr 0.0061 vocab_size 100053 (6.08s/10.35m) [Shuffling 78] loss 3872794.0000 lr 0.0058 vocab_size 100053 (6.06s/10.35m) [Shuffling 79] loss 3938289.2500 lr 0.0056 vocab_size 100053 (6.08s/10.35m) [Shuffling 80] loss 3706713.0000 lr 0.0053 vocab_size 100053 (6.13s/10.35m) [Shuffling 81] loss 3840236.5000 lr 0.0051 vocab_size 100053 (6.04s/10.35m) [Shuffling 82] loss 3841128.7500 lr 0.0048 vocab_size 100053 (6.11s/10.35m) [Shuffling 83] loss 3950271.2500 lr 0.0046 vocab_size 100053 (6.06s/10.35m) [Shuffling 84] loss 4007989.5000 lr 0.0043 vocab_size 100053 (6.09s/10.35m) [Shuffling 85] loss 3752616.2500 lr 0.0041 vocab_size 100053 (6.06s/10.35m) [Shuffling 86] loss 3886004.0000 lr 0.0038 vocab_size 100053 (6.04s/10.35m) [Shuffling 87] loss 3828232.5000 lr 0.0036 vocab_size 100053 (6.07s/10.35m) [Shuffling 88] loss 3780331.0000 lr 0.0033 vocab_size 100053 (5.95s/10.35m) [Shuffling 89] loss 3843633.0000 lr 0.0031 vocab_size 100053 (5.94s/10.34m) [Shuffling 90] loss 3762284.5000 lr 0.0028 vocab_size 100053 (6.06s/10.34m) [Shuffling 91] loss 3878988.5000 lr 0.0026 vocab_size 100053 (6.05s/10.34m) [Shuffling 92] loss 3888960.7500 lr 0.0023 vocab_size 100053 (6.10s/10.35m) [Shuffling 93] loss 3800234.2500 lr 0.0021 vocab_size 100053 (5.93s/10.34m) [Shuffling 94] loss 3896139.2500 lr 0.0018 vocab_size 100053 (5.99s/10.34m) [Shuffling 95] loss 3836220.2500 lr 0.0016 vocab_size 100053 (10.01s/10.41m) [Shuffling 96] loss 3901129.0000 lr 0.0013 vocab_size 100053 (5.96s/10.41m) [Shuffling 97] loss 3710173.5000 lr 0.0011 vocab_size 100053 (11.01s/10.49m) [Shuffling 98] loss 3735136.0000 lr 0.0008 vocab_size 100053 (6.11s/10.49m) [Shuffling 99] loss 3850358.7500 lr 0.0006 vocab_size 100053 (12.01s/10.59m) [Shuffling 100] loss 3860654.0000 lr 0.0003 vocab_size 100053 (5.82s/10.59m) [03/12/24-17:19:36] Training finished, training Time 10.59m