DEBUG:cmd:2024-05-19 20:14:23:Popen(['git', 'rev-parse', '--show-toplevel'], cwd=/home/luyanfeng/my_code/github/pybind11-OpenKE, stdin=None, shell=False, universal_newlines=False) DEBUG:cmd:2024-05-19 20:14:23:Popen(['git', 'rev-parse', '--show-toplevel'], cwd=/home/luyanfeng/my_code/github/pybind11-OpenKE, stdin=None, shell=False, universal_newlines=False) DEBUG:connectionpool:2024-05-19 20:14:24:Starting new HTTPS connection (1): api.wandb.ai:443 DEBUG:connectionpool:2024-05-19 20:14:25:https://api.wandb.ai:443 "POST /graphql HTTP/1.1" 200 None DEBUG:connectionpool:2024-05-19 20:14:25:https://api.wandb.ai:443 "POST /graphql HTTP/1.1" 200 None wandb: Currently logged in as: 3555028709. Use `wandb login --relogin` to force relogin DEBUG:cmd:2024-05-19 20:14:25:Popen(['git', 'cat-file', '--batch-check'], cwd=/home/luyanfeng/my_code/github/pybind11-OpenKE, stdin=, shell=False, universal_newlines=False) wandb: - Waiting for wandb.init()... wandb: \ Waiting for wandb.init()... wandb: wandb version 0.17.0 is available! To upgrade, please run: wandb: $ pip install wandb --upgrade wandb: Tracking run with wandb version 0.16.6 wandb: Run data is saved locally in /home/luyanfeng/my_code/github/pybind11-OpenKE/examples/ANALOGY/wandb/run-20240519_201425-c4othhi2 wandb: Run `wandb offline` to turn off syncing. wandb: Syncing run ANALOGY-WN18RR wandb: ⭐️ View project at https://wandb.ai/3555028709/pybind11-ke wandb: 🚀 View run at https://wandb.ai/3555028709/pybind11-ke/runs/c4othhi2 INFO:Trainer:2024-05-19 20:14:29:[cuda:0] Initialization completed, start model training. INFO:Trainer:2024-05-19 20:17:52:[cuda:0] Epoch 100 | The model starts evaluation on the validation set. INFO:Trainer:2024-05-19 20:18:00:mr: 8151.436 INFO:Trainer:2024-05-19 20:18:00:mrr: 0.381 INFO:Trainer:2024-05-19 20:18:00:hits@1: 0.367 INFO:Trainer:2024-05-19 20:18:00:hits@3: 0.389 INFO:Trainer:2024-05-19 20:18:00:hits@10: 0.403 INFO:Trainer:2024-05-19 20:18:00:mr_type: 4108.788 INFO:Trainer:2024-05-19 20:18:00:mrr_type: 0.386 INFO:Trainer:2024-05-19 20:18:00:hits@1_type: 0.37 INFO:Trainer:2024-05-19 20:18:00:hits@3_type: 0.392 INFO:Trainer:2024-05-19 20:18:00:hits@10_type: 0.412 INFO:EarlyStopping:2024-05-19 20:18:00:Validation score improved (-inf --> 0.403000). Saving model ... INFO:Trainer:2024-05-19 20:18:02:[cuda:0] Epoch 100 | Training checkpoint saved at ../../checkpoint/analogy-100.pth INFO:Trainer:2024-05-19 20:18:02:[cuda:0] Epoch [ 100/2000] | Batchsize: 4096 | loss: 1.372830 | 2.03190 seconds/epoch INFO:Trainer:2024-05-19 20:21:04:[cuda:0] Epoch 200 | The model starts evaluation on the validation set. INFO:Trainer:2024-05-19 20:21:12:mr: 7038.43 INFO:Trainer:2024-05-19 20:21:12:mrr: 0.384 INFO:Trainer:2024-05-19 20:21:12:hits@1: 0.359 INFO:Trainer:2024-05-19 20:21:12:hits@3: 0.398 INFO:Trainer:2024-05-19 20:21:12:hits@10: 0.422 INFO:Trainer:2024-05-19 20:21:12:mr_type: 3427.042 INFO:Trainer:2024-05-19 20:21:12:mrr_type: 0.39 INFO:Trainer:2024-05-19 20:21:12:hits@1_type: 0.364 INFO:Trainer:2024-05-19 20:21:12:hits@3_type: 0.406 INFO:Trainer:2024-05-19 20:21:12:hits@10_type: 0.43 INFO:EarlyStopping:2024-05-19 20:21:12:Validation score improved (0.403000 --> 0.422000). Saving model ... INFO:Trainer:2024-05-19 20:21:14:[cuda:0] Epoch 200 | Training checkpoint saved at ../../checkpoint/analogy-200.pth INFO:Trainer:2024-05-19 20:21:14:[cuda:0] Epoch [ 200/2000] | Batchsize: 4096 | loss: 0.842776 | 1.97514 seconds/epoch INFO:Trainer:2024-05-19 20:24:11:[cuda:0] Epoch 300 | The model starts evaluation on the validation set. INFO:Trainer:2024-05-19 20:24:19:mr: 6630.113 INFO:Trainer:2024-05-19 20:24:19:mrr: 0.388 INFO:Trainer:2024-05-19 20:24:19:hits@1: 0.36 INFO:Trainer:2024-05-19 20:24:19:hits@3: 0.405 INFO:Trainer:2024-05-19 20:24:19:hits@10: 0.431 INFO:Trainer:2024-05-19 20:24:19:mr_type: 3176.692 INFO:Trainer:2024-05-19 20:24:19:mrr_type: 0.395 INFO:Trainer:2024-05-19 20:24:19:hits@1_type: 0.364 INFO:Trainer:2024-05-19 20:24:19:hits@3_type: 0.413 INFO:Trainer:2024-05-19 20:24:19:hits@10_type: 0.439 INFO:EarlyStopping:2024-05-19 20:24:19:EarlyStopping counter: 1 / 2 INFO:Trainer:2024-05-19 20:24:20:[cuda:0] Epoch 300 | Training checkpoint saved at ../../checkpoint/analogy-300.pth INFO:Trainer:2024-05-19 20:24:20:[cuda:0] Epoch [ 300/2000] | Batchsize: 4096 | loss: 0.702249 | 1.93839 seconds/epoch INFO:Trainer:2024-05-19 20:27:19:[cuda:0] Epoch 400 | The model starts evaluation on the validation set. INFO:Trainer:2024-05-19 20:27:27:mr: 6315.46 INFO:Trainer:2024-05-19 20:27:27:mrr: 0.393 INFO:Trainer:2024-05-19 20:27:27:hits@1: 0.363 INFO:Trainer:2024-05-19 20:27:27:hits@3: 0.411 INFO:Trainer:2024-05-19 20:27:27:hits@10: 0.44 INFO:Trainer:2024-05-19 20:27:27:mr_type: 2995.506 INFO:Trainer:2024-05-19 20:27:27:mrr_type: 0.4 INFO:Trainer:2024-05-19 20:27:27:hits@1_type: 0.367 INFO:Trainer:2024-05-19 20:27:27:hits@3_type: 0.421 INFO:Trainer:2024-05-19 20:27:27:hits@10_type: 0.448 INFO:EarlyStopping:2024-05-19 20:27:27:Validation score improved (0.422000 --> 0.440000). Saving model ... INFO:Trainer:2024-05-19 20:27:28:[cuda:0] Epoch 400 | Training checkpoint saved at ../../checkpoint/analogy-400.pth INFO:Trainer:2024-05-19 20:27:28:[cuda:0] Epoch [ 400/2000] | Batchsize: 4096 | loss: 0.654199 | 1.92449 seconds/epoch INFO:Trainer:2024-05-19 20:30:28:[cuda:0] Epoch 500 | The model starts evaluation on the validation set. INFO:Trainer:2024-05-19 20:30:37:mr: 6018.286 INFO:Trainer:2024-05-19 20:30:37:mrr: 0.399 INFO:Trainer:2024-05-19 20:30:37:hits@1: 0.369 INFO:Trainer:2024-05-19 20:30:37:hits@3: 0.414 INFO:Trainer:2024-05-19 20:30:37:hits@10: 0.445 INFO:Trainer:2024-05-19 20:30:37:mr_type: 2850.037 INFO:Trainer:2024-05-19 20:30:37:mrr_type: 0.406 INFO:Trainer:2024-05-19 20:30:37:hits@1_type: 0.374 INFO:Trainer:2024-05-19 20:30:37:hits@3_type: 0.422 INFO:Trainer:2024-05-19 20:30:37:hits@10_type: 0.456 INFO:EarlyStopping:2024-05-19 20:30:37:EarlyStopping counter: 1 / 2 INFO:Trainer:2024-05-19 20:30:38:[cuda:0] Epoch 500 | Training checkpoint saved at ../../checkpoint/analogy-500.pth INFO:Trainer:2024-05-19 20:30:38:[cuda:0] Epoch [ 500/2000] | Batchsize: 4096 | loss: 0.633198 | 1.91871 seconds/epoch INFO:Trainer:2024-05-19 20:33:37:[cuda:0] Epoch 600 | The model starts evaluation on the validation set. INFO:Trainer:2024-05-19 20:33:45:mr: 5818.697 INFO:Trainer:2024-05-19 20:33:45:mrr: 0.399 INFO:Trainer:2024-05-19 20:33:45:hits@1: 0.366 INFO:Trainer:2024-05-19 20:33:45:hits@3: 0.418 INFO:Trainer:2024-05-19 20:33:45:hits@10: 0.447 INFO:Trainer:2024-05-19 20:33:45:mr_type: 2751.707 INFO:Trainer:2024-05-19 20:33:45:mrr_type: 0.407 INFO:Trainer:2024-05-19 20:33:45:hits@1_type: 0.372 INFO:Trainer:2024-05-19 20:33:45:hits@3_type: 0.428 INFO:Trainer:2024-05-19 20:33:45:hits@10_type: 0.458 INFO:EarlyStopping:2024-05-19 20:33:45:EarlyStopping counter: 2 / 2 INFO:Trainer:2024-05-19 20:33:45:[cuda:0] Send an early stopping signal INFO:Trainer:2024-05-19 20:33:45:[cuda:0] The model training is completed, taking a total of 1148.18541 seconds. INFO:Trainer:2024-05-19 20:33:46:[cuda:0] Model saved at ../../checkpoint/analogy.pth. INFO:Trainer:2024-05-19 20:33:46:[cuda:0] The model starts evaluating in the test set. INFO:Trainer:2024-05-19 20:33:55:mr: 5930.545 INFO:Trainer:2024-05-19 20:33:55:mrr: 0.399 INFO:Trainer:2024-05-19 20:33:55:hits@1: 0.368 INFO:Trainer:2024-05-19 20:33:55:hits@3: 0.418 INFO:Trainer:2024-05-19 20:33:55:hits@10: 0.45 INFO:Trainer:2024-05-19 20:33:55:mr_type: 2838.617 INFO:Trainer:2024-05-19 20:33:55:mrr_type: 0.407 INFO:Trainer:2024-05-19 20:33:55:hits@1_type: 0.372 INFO:Trainer:2024-05-19 20:33:55:hits@3_type: 0.427 INFO:Trainer:2024-05-19 20:33:55:hits@10_type: 0.459 wandb: Network error (TransientError), entering retry loop. wandb: - 0.023 MB of 0.034 MB uploaded wandb: \ 0.024 MB of 0.036 MB uploaded wandb: | 0.026 MB of 0.036 MB uploaded wandb: / 0.036 MB of 0.036 MB uploaded wandb: wandb: Run history: wandb: duration ▁ wandb: test/hits@1 ▁ wandb: test/hits@10 ▁ wandb: test/hits@10_type ▁ wandb: test/hits@1_type ▁ wandb: test/hits@3 ▁ wandb: test/hits@3_type ▁ wandb: test/mr ▁ wandb: test/mr_type ▁ wandb: test/mrr ▁ wandb: test/mrr_type ▁ wandb: train/epoch ▁▃▅▆█ wandb: train/train_loss █▃▂▁▁ wandb: val/epoch ▁▂▄▅▇█ wandb: val/hits@1 ▇▁▂▄█▆ wandb: val/hits@10 ▁▄▅▇██ wandb: val/hits@10_type ▁▄▅▆██ wandb: val/hits@1_type ▅▁▁▃█▇ wandb: val/hits@3 ▁▃▅▆▇█ wandb: val/hits@3_type ▁▄▅▇▇█ wandb: val/mr █▅▃▂▂▁ wandb: val/mr_type █▄▃▂▂▁ wandb: val/mrr ▁▂▄▆██ wandb: val/mrr_type ▁▂▄▆██ wandb: wandb: Run summary: wandb: duration 1148.18541 wandb: test/hits@1 0.368 wandb: test/hits@10 0.45 wandb: test/hits@10_type 0.459 wandb: test/hits@1_type 0.372 wandb: test/hits@3 0.418 wandb: test/hits@3_type 0.427 wandb: test/mr 5930.545 wandb: test/mr_type 2838.617 wandb: test/mrr 0.399 wandb: test/mrr_type 0.407 wandb: train/epoch 500 wandb: train/train_loss 0.6332 wandb: val/epoch 599 wandb: val/hits@1 0.366 wandb: val/hits@10 0.447 wandb: val/hits@10_type 0.458 wandb: val/hits@1_type 0.372 wandb: val/hits@3 0.418 wandb: val/hits@3_type 0.428 wandb: val/mr 5818.697 wandb: val/mr_type 2751.707 wandb: val/mrr 0.399 wandb: val/mrr_type 0.407 wandb: wandb: 🚀 View run ANALOGY-WN18RR at: https://wandb.ai/3555028709/pybind11-ke/runs/c4othhi2 wandb: ⭐️ View project at: https://wandb.ai/3555028709/pybind11-ke wandb: Synced 5 W&B file(s), 0 media file(s), 2 artifact file(s) and 0 other file(s) wandb: Find logs at: ./wandb/run-20240519_201425-c4othhi2/logs DEBUG:connectionpool:2024-05-19 20:34:09:Starting new HTTPS connection (1): o151352.ingest.sentry.io:443 DEBUG:connectionpool:2024-05-19 20:34:10:https://o151352.ingest.sentry.io:443 "POST /api/4504800232407040/envelope/ HTTP/1.1" 200 0