DEBUG:cmd:2024-05-16 15:31:26:Popen(['git', 'rev-parse', '--show-toplevel'], cwd=/home/luyanfeng/my_code/github/pybind11-OpenKE, stdin=None, shell=False, universal_newlines=False) DEBUG:cmd:2024-05-16 15:31:26:Popen(['git', 'rev-parse', '--show-toplevel'], cwd=/home/luyanfeng/my_code/github/pybind11-OpenKE, stdin=None, shell=False, universal_newlines=False) DEBUG:connectionpool:2024-05-16 15:31:27:Starting new HTTPS connection (1): api.wandb.ai:443 DEBUG:connectionpool:2024-05-16 15:31:27:https://api.wandb.ai:443 "POST /graphql HTTP/1.1" 200 None DEBUG:connectionpool:2024-05-16 15:31:27: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:2024-05-16 15:31:28:Popen(['git', 'cat-file', '--batch-check'], cwd=/home/luyanfeng/my_code/github/pybind11-OpenKE, stdin=, shell=False, universal_newlines=False) 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/RESCAL/wandb/run-20240516_153128-yglrood1 wandb: Run `wandb offline` to turn off syncing. wandb: Syncing run RESCAL-FB15K237 wandb: ⭐️ View project at https://wandb.ai/3555028709/pybind11-ke wandb: 🚀 View run at https://wandb.ai/3555028709/pybind11-ke/runs/yglrood1 INFO:Trainer:2024-05-16 15:31:36:[cuda:0] Initialization completed, start model training. INFO:Trainer:2024-05-16 15:36:19:[cuda:0] Epoch 100 | The model starts evaluation on the validation set. INFO:Trainer:2024-05-16 15:36:35:mr: 405.744 INFO:Trainer:2024-05-16 15:36:35:mrr: 0.259 INFO:Trainer:2024-05-16 15:36:35:hits@1: 0.186 INFO:Trainer:2024-05-16 15:36:35:hits@3: 0.281 INFO:Trainer:2024-05-16 15:36:35:hits@10: 0.403 INFO:Trainer:2024-05-16 15:36:35:mr_type: 160.862 INFO:Trainer:2024-05-16 15:36:35:mrr_type: 0.291 INFO:Trainer:2024-05-16 15:36:35:hits@1_type: 0.213 INFO:Trainer:2024-05-16 15:36:35:hits@3_type: 0.312 INFO:Trainer:2024-05-16 15:36:35:hits@10_type: 0.444 INFO:EarlyStopping:2024-05-16 15:36:35:Validation score improved (-inf --> 0.403000). Saving model ... INFO:Trainer:2024-05-16 15:36:35:[cuda:0] Epoch 100 | Training checkpoint saved at ../../checkpoint/rescal-100.pth INFO:Trainer:2024-05-16 15:36:35:[cuda:0] Epoch [ 100/1000] | Batchsize: 2048 | loss: 0.206524 | 2.83429 seconds/epoch INFO:Trainer:2024-05-16 15:41:17:[cuda:0] Epoch 200 | The model starts evaluation on the validation set. INFO:Trainer:2024-05-16 15:41:32:mr: 403.897 INFO:Trainer:2024-05-16 15:41:32:mrr: 0.263 INFO:Trainer:2024-05-16 15:41:32:hits@1: 0.188 INFO:Trainer:2024-05-16 15:41:32:hits@3: 0.287 INFO:Trainer:2024-05-16 15:41:32:hits@10: 0.412 INFO:Trainer:2024-05-16 15:41:32:mr_type: 150.556 INFO:Trainer:2024-05-16 15:41:32:mrr_type: 0.295 INFO:Trainer:2024-05-16 15:41:32:hits@1_type: 0.214 INFO:Trainer:2024-05-16 15:41:32:hits@3_type: 0.319 INFO:Trainer:2024-05-16 15:41:32:hits@10_type: 0.454 INFO:EarlyStopping:2024-05-16 15:41:32:Validation score improved (0.403000 --> 0.412000). Saving model ... INFO:Trainer:2024-05-16 15:41:32:[cuda:0] Epoch 200 | Training checkpoint saved at ../../checkpoint/rescal-200.pth INFO:Trainer:2024-05-16 15:41:32:[cuda:0] Epoch [ 200/1000] | Batchsize: 2048 | loss: 0.128248 | 2.90515 seconds/epoch INFO:Trainer:2024-05-16 15:46:08:[cuda:0] Epoch 300 | The model starts evaluation on the validation set. INFO:Trainer:2024-05-16 15:46:24:mr: 406.795 INFO:Trainer:2024-05-16 15:46:24:mrr: 0.265 INFO:Trainer:2024-05-16 15:46:24:hits@1: 0.191 INFO:Trainer:2024-05-16 15:46:24:hits@3: 0.287 INFO:Trainer:2024-05-16 15:46:24:hits@10: 0.412 INFO:Trainer:2024-05-16 15:46:24:mr_type: 146.531 INFO:Trainer:2024-05-16 15:46:24:mrr_type: 0.298 INFO:Trainer:2024-05-16 15:46:24:hits@1_type: 0.218 INFO:Trainer:2024-05-16 15:46:24:hits@3_type: 0.321 INFO:Trainer:2024-05-16 15:46:24:hits@10_type: 0.456 INFO:EarlyStopping:2024-05-16 15:46:24:EarlyStopping counter: 1 / 2 INFO:Trainer:2024-05-16 15:46:24:[cuda:0] Epoch 300 | Training checkpoint saved at ../../checkpoint/rescal-300.pth INFO:Trainer:2024-05-16 15:46:24:[cuda:0] Epoch [ 300/1000] | Batchsize: 2048 | loss: 0.099204 | 2.90636 seconds/epoch INFO:Trainer:2024-05-16 15:51:05:[cuda:0] Epoch 400 | The model starts evaluation on the validation set. INFO:Trainer:2024-05-16 15:51:20:mr: 406.774 INFO:Trainer:2024-05-16 15:51:20:mrr: 0.265 INFO:Trainer:2024-05-16 15:51:20:hits@1: 0.19 INFO:Trainer:2024-05-16 15:51:20:hits@3: 0.29 INFO:Trainer:2024-05-16 15:51:20:hits@10: 0.416 INFO:Trainer:2024-05-16 15:51:20:mr_type: 144.661 INFO:Trainer:2024-05-16 15:51:20:mrr_type: 0.298 INFO:Trainer:2024-05-16 15:51:20:hits@1_type: 0.217 INFO:Trainer:2024-05-16 15:51:20:hits@3_type: 0.322 INFO:Trainer:2024-05-16 15:51:20:hits@10_type: 0.461 INFO:EarlyStopping:2024-05-16 15:51:20:Validation score improved (0.412000 --> 0.416000). Saving model ... INFO:Trainer:2024-05-16 15:51:20:[cuda:0] Epoch 400 | Training checkpoint saved at ../../checkpoint/rescal-400.pth INFO:Trainer:2024-05-16 15:51:20:[cuda:0] Epoch [ 400/1000] | Batchsize: 2048 | loss: 0.088507 | 2.92218 seconds/epoch INFO:Trainer:2024-05-16 15:56:00:[cuda:0] Epoch 500 | The model starts evaluation on the validation set. INFO:Trainer:2024-05-16 15:56:16:mr: 405.058 INFO:Trainer:2024-05-16 15:56:16:mrr: 0.267 INFO:Trainer:2024-05-16 15:56:16:hits@1: 0.191 INFO:Trainer:2024-05-16 15:56:16:hits@3: 0.291 INFO:Trainer:2024-05-16 15:56:16:hits@10: 0.416 INFO:Trainer:2024-05-16 15:56:16:mr_type: 144.149 INFO:Trainer:2024-05-16 15:56:16:mrr_type: 0.3 INFO:Trainer:2024-05-16 15:56:16:hits@1_type: 0.219 INFO:Trainer:2024-05-16 15:56:16:hits@3_type: 0.324 INFO:Trainer:2024-05-16 15:56:16:hits@10_type: 0.46 INFO:EarlyStopping:2024-05-16 15:56:16:EarlyStopping counter: 1 / 2 INFO:Trainer:2024-05-16 15:56:16:[cuda:0] Epoch 500 | Training checkpoint saved at ../../checkpoint/rescal-500.pth INFO:Trainer:2024-05-16 15:56:16:[cuda:0] Epoch [ 500/1000] | Batchsize: 2048 | loss: 0.082520 | 2.92879 seconds/epoch INFO:Trainer:2024-05-16 16:01:01:[cuda:0] Epoch 600 | The model starts evaluation on the validation set. INFO:Trainer:2024-05-16 16:01:17:mr: 403.936 INFO:Trainer:2024-05-16 16:01:17:mrr: 0.267 INFO:Trainer:2024-05-16 16:01:17:hits@1: 0.192 INFO:Trainer:2024-05-16 16:01:17:hits@3: 0.291 INFO:Trainer:2024-05-16 16:01:17:hits@10: 0.416 INFO:Trainer:2024-05-16 16:01:17:mr_type: 143.804 INFO:Trainer:2024-05-16 16:01:17:mrr_type: 0.3 INFO:Trainer:2024-05-16 16:01:17:hits@1_type: 0.219 INFO:Trainer:2024-05-16 16:01:17:hits@3_type: 0.324 INFO:Trainer:2024-05-16 16:01:17:hits@10_type: 0.46 INFO:EarlyStopping:2024-05-16 16:01:17:EarlyStopping counter: 2 / 2 INFO:Trainer:2024-05-16 16:01:17:[cuda:0] Send an early stopping signal INFO:Trainer:2024-05-16 16:01:17:[cuda:0] The model training is completed, taking a total of 1765.01537 seconds. INFO:Trainer:2024-05-16 16:01:17:[cuda:0] Model saved at ../../checkpoint/rescal.pth. INFO:Trainer:2024-05-16 16:01:17:[cuda:0] The model starts evaluating in the test set. INFO:Trainer:2024-05-16 16:01:34:mr: 415.845 INFO:Trainer:2024-05-16 16:01:34:mrr: 0.264 INFO:Trainer:2024-05-16 16:01:34:hits@1: 0.189 INFO:Trainer:2024-05-16 16:01:34:hits@3: 0.288 INFO:Trainer:2024-05-16 16:01:34:hits@10: 0.412 INFO:Trainer:2024-05-16 16:01:34:mr_type: 146.57 INFO:Trainer:2024-05-16 16:01:34:mrr_type: 0.295 INFO:Trainer:2024-05-16 16:01:34:hits@1_type: 0.215 INFO:Trainer:2024-05-16 16:01:34:hits@3_type: 0.319 INFO:Trainer:2024-05-16 16:01:34:hits@10_type: 0.455 wandb: - 0.023 MB of 0.036 MB uploaded wandb: \ 0.023 MB of 0.036 MB uploaded wandb: | 0.036 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 1765.01537 wandb: test/hits@1 0.189 wandb: test/hits@10 0.412 wandb: test/hits@10_type 0.455 wandb: test/hits@1_type 0.215 wandb: test/hits@3 0.288 wandb: test/hits@3_type 0.319 wandb: test/mr 415.845 wandb: test/mr_type 146.57 wandb: test/mrr 0.264 wandb: test/mrr_type 0.295 wandb: train/epoch 500 wandb: train/train_loss 0.08252 wandb: val/epoch 599 wandb: val/hits@1 0.192 wandb: val/hits@10 0.416 wandb: val/hits@10_type 0.46 wandb: val/hits@1_type 0.219 wandb: val/hits@3 0.291 wandb: val/hits@3_type 0.324 wandb: val/mr 403.936 wandb: val/mr_type 143.804 wandb: val/mrr 0.267 wandb: val/mrr_type 0.3 wandb: wandb: 🚀 View run RESCAL-FB15K237 at: https://wandb.ai/3555028709/pybind11-ke/runs/yglrood1 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-20240516_153128-yglrood1/logs DEBUG:connectionpool:2024-05-16 16:01:46:Starting new HTTPS connection (1): o151352.ingest.sentry.io:443 DEBUG:connectionpool:2024-05-16 16:01:47:https://o151352.ingest.sentry.io:443 "POST /api/4504800232407040/envelope/ HTTP/1.1" 200 0