From f6af95860a41106e91a06cbdb15fa339b89c8c7c Mon Sep 17 00:00:00 2001 From: severinsimmler Date: Wed, 25 May 2022 11:26:13 +0200 Subject: [PATCH] fix: data leakage --- examples/notebooks/ner.ipynb | 1141 ++++++++++++++++++++-------------- 1 file changed, 671 insertions(+), 470 deletions(-) diff --git a/examples/notebooks/ner.ipynb b/examples/notebooks/ner.ipynb index 8377f79..fcc2702 100755 --- a/examples/notebooks/ner.ipynb +++ b/examples/notebooks/ner.ipynb @@ -47,7 +47,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "75c6ba99733b4b318360fef82e093eff", + "model_id": "35127df3120f4ff8b098b50f703ef62b", "version_major": 2, "version_minor": 0 }, @@ -209,8 +209,8 @@ "metadata": {}, "outputs": [], "source": [ - "sentences = featurize_dataset(dataset[\"train\"])\n", - "labels = preprocess_labels(dataset[\"train\"])" + "train_sentences = featurize_dataset(dataset[\"train\"])\n", + "train_labels = preprocess_labels(dataset[\"train\"])" ] }, { @@ -242,7 +242,7 @@ } ], "source": [ - "sentences[0][0]" + "train_sentences[0][0]" ] }, { @@ -263,7 +263,7 @@ } ], "source": [ - "labels[0][0]" + "train_labels[0][0]" ] }, { @@ -281,7 +281,7 @@ "metadata": {}, "outputs": [], "source": [ - "model = chaine.train(sentences, labels, verbose=0)" + "model = chaine.train(train_sentences, train_labels, verbose=0)" ] }, { @@ -299,8 +299,8 @@ "metadata": {}, "outputs": [], "source": [ - "sentences = featurize_dataset(dataset[\"test\"])\n", - "labels = preprocess_labels(dataset[\"test\"])" + "test_sentences = featurize_dataset(dataset[\"test\"])\n", + "test_labels = preprocess_labels(dataset[\"test\"])" ] }, { @@ -328,9 +328,9 @@ } ], "source": [ - "predictions = model.predict(sentences)\n", + "predictions = model.predict(test_sentences)\n", "\n", - "print(classification_report(labels, predictions))" + "print(classification_report(test_labels, predictions))" ] }, { @@ -353,368 +353,569 @@ "name": "stdout", "output_type": "stream", "text": [ - "[2022-05-24 14:12:57,820] [INFO] Starting with arow (1/5)\n", - "[2022-05-24 14:12:57,821] [INFO] Baseline for arow\n", - "[2022-05-24 14:13:10,700] [INFO] Trial 1/10 for arow\n", - "[2022-05-24 14:13:35,112] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:13:35,113] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:13:35,115] [INFO] Trial 2/10 for arow\n", - "[2022-05-24 14:13:57,998] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:13:57,999] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:13:57,999] [INFO] Trial 3/10 for arow\n", - "[2022-05-24 14:14:22,100] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:14:22,101] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:14:22,101] [INFO] Trial 4/10 for arow\n", - "[2022-05-24 14:14:41,419] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:14:41,420] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:14:41,422] [INFO] Trial 5/10 for arow\n", - "[2022-05-24 14:15:02,888] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:15:02,889] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:15:02,890] [INFO] Trial 6/10 for arow\n", - "[2022-05-24 14:15:20,546] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:15:20,547] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:15:20,547] [INFO] Trial 7/10 for arow\n", - "[2022-05-24 14:15:39,751] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:15:39,752] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:15:39,753] [INFO] Trial 8/10 for arow\n", - "[2022-05-24 14:15:53,562] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:15:53,562] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:15:53,563] [INFO] Trial 9/10 for arow\n", - "[2022-05-24 14:16:14,962] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:16:14,963] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:16:14,964] [INFO] Trial 10/10 for arow\n", - "[2022-05-24 14:16:32,600] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:16:32,601] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:16:32,602] [INFO] Starting with ap (2/5)\n", - "[2022-05-24 14:16:32,602] [INFO] Baseline for ap\n", - "[2022-05-24 14:16:54,175] [INFO] Trial 1/10 for ap\n", - "[2022-05-24 14:17:17,903] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:17:17,905] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:17:17,906] [INFO] Trial 2/10 for ap\n", - "[2022-05-24 14:17:38,846] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:17:38,847] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:17:38,848] [INFO] Trial 3/10 for ap\n", - "[2022-05-24 14:18:03,125] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:18:03,125] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:18:03,126] [INFO] Trial 4/10 for ap\n", - "[2022-05-24 14:18:27,364] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:18:27,365] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:18:27,366] [INFO] Trial 5/10 for ap\n", - "[2022-05-24 14:18:53,926] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:18:53,927] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:18:53,928] [INFO] Trial 6/10 for ap\n", - "[2022-05-24 14:19:14,329] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:19:14,329] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:19:14,330] [INFO] Trial 7/10 for ap\n", - "[2022-05-24 14:19:35,188] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:19:35,188] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:19:35,189] [INFO] Trial 8/10 for ap\n", - "[2022-05-24 14:20:04,335] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:20:04,336] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:20:04,337] [INFO] Trial 9/10 for ap\n", - "[2022-05-24 14:20:25,747] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:20:25,747] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:20:25,748] [INFO] Trial 10/10 for ap\n", - "[2022-05-24 14:20:55,942] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:20:55,943] [INFO] Best optimized model: 0.8053851088265638\n", - "[2022-05-24 14:20:55,944] [INFO] Starting with lbfgs (3/5)\n", - "[2022-05-24 14:20:55,944] [INFO] Baseline for lbfgs\n", - "[2022-05-24 14:21:23,004] [INFO] Trial 1/10 for lbfgs\n", - "[2022-05-24 14:21:51,544] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:21:51,545] [INFO] Best optimized model: 0.8512321635171647\n", - "[2022-05-24 14:21:51,546] [INFO] Trial 2/10 for lbfgs\n", - "[2022-05-24 14:22:15,532] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:22:15,533] [INFO] Best optimized model: 0.8583669352872352\n", - "[2022-05-24 14:22:15,534] [INFO] Trial 3/10 for lbfgs\n", - "[2022-05-24 14:22:41,231] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:22:41,232] [INFO] Best optimized model: 0.8583669352872352\n", - "[2022-05-24 14:22:41,233] [INFO] Trial 4/10 for lbfgs\n", - "[2022-05-24 14:23:11,347] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:23:11,348] [INFO] Best optimized model: 0.8765343356353424\n", - "[2022-05-24 14:23:11,349] [INFO] Trial 5/10 for lbfgs\n", - "[2022-05-24 14:23:47,354] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:23:47,356] [INFO] Best optimized model: 0.8765343356353424\n", - "[2022-05-24 14:23:47,357] [INFO] Trial 6/10 for lbfgs\n", - "[2022-05-24 14:24:21,991] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:24:21,993] [INFO] Best optimized model: 0.8765343356353424\n", - "[2022-05-24 14:24:21,993] [INFO] Trial 7/10 for lbfgs\n", - "[2022-05-24 14:24:44,177] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:24:44,178] [INFO] Best optimized model: 0.8765343356353424\n", - "[2022-05-24 14:24:44,178] [INFO] Trial 8/10 for lbfgs\n", - "[2022-05-24 14:25:10,296] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:25:10,297] [INFO] Best optimized model: 0.8765343356353424\n", - "[2022-05-24 14:25:10,297] [INFO] Trial 9/10 for lbfgs\n", - "[2022-05-24 14:25:33,210] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:25:33,211] [INFO] Best optimized model: 0.8765343356353424\n", - "[2022-05-24 14:25:33,212] [INFO] Trial 10/10 for lbfgs\n", - "[2022-05-24 14:25:57,224] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:25:57,225] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:25:57,226] [INFO] Starting with l2sgd (4/5)\n", - "[2022-05-24 14:25:57,227] [INFO] Baseline for l2sgd\n", - "[2022-05-24 14:26:29,107] [INFO] Trial 1/10 for l2sgd\n", - "[2022-05-24 14:26:57,573] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:26:57,574] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:26:57,575] [INFO] Trial 2/10 for l2sgd\n", - "[2022-05-24 14:27:34,959] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:27:34,960] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:27:34,960] [INFO] Trial 3/10 for l2sgd\n", - "[2022-05-24 14:28:04,577] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:28:04,578] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:28:04,578] [INFO] Trial 4/10 for l2sgd\n", - "[2022-05-24 14:28:29,486] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:28:29,487] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:28:29,487] [INFO] Trial 5/10 for l2sgd\n", - "[2022-05-24 14:28:43,936] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:28:43,937] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:28:43,938] [INFO] Trial 6/10 for l2sgd\n", - "[2022-05-24 14:29:17,613] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:29:17,614] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:29:17,614] [INFO] Trial 7/10 for l2sgd\n", - "[2022-05-24 14:29:49,064] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:29:49,065] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:29:49,066] [INFO] Trial 8/10 for l2sgd\n", - "[2022-05-24 14:30:28,164] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:30:28,165] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:30:28,165] [INFO] Trial 9/10 for l2sgd\n", - "[2022-05-24 14:31:04,397] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:31:04,397] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:31:04,398] [INFO] Trial 10/10 for l2sgd\n", - "[2022-05-24 14:31:32,285] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:31:32,286] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:31:32,287] [INFO] Starting with pa (5/5)\n", - "[2022-05-24 14:31:32,289] [INFO] Baseline for pa\n", - "[2022-05-24 14:31:57,620] [INFO] Trial 1/10 for pa\n", - "[2022-05-24 14:32:24,894] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:32:24,895] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:32:24,895] [INFO] Trial 2/10 for pa\n", - "[2022-05-24 14:32:54,099] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:32:54,100] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:32:54,101] [INFO] Trial 3/10 for pa\n", - "[2022-05-24 14:33:17,758] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:33:17,759] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:33:17,760] [INFO] Trial 4/10 for pa\n", - "[2022-05-24 14:33:44,958] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:33:44,959] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:33:44,959] [INFO] Trial 5/10 for pa\n", - "[2022-05-24 14:34:08,806] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:34:08,807] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:34:08,808] [INFO] Trial 6/10 for pa\n", - "[2022-05-24 14:34:35,835] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:34:35,835] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:34:35,836] [INFO] Trial 7/10 for pa\n", - "[2022-05-24 14:35:02,833] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:35:02,833] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:35:02,834] [INFO] Trial 8/10 for pa\n", - "[2022-05-24 14:35:30,266] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:35:30,267] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:35:30,268] [INFO] Trial 9/10 for pa\n", - "[2022-05-24 14:35:57,715] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:35:57,716] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:35:57,717] [INFO] Trial 10/10 for pa\n", - "[2022-05-24 14:36:26,015] [INFO] Best baseline model: 0.8053851088265638\n", - "[2022-05-24 14:36:26,016] [INFO] Best optimized model: 0.8959067851139951\n", - "[2022-05-24 14:36:26,016] [INFO] Finished hyperparameter optimization\n", - "[2022-05-24 14:36:26,017] [INFO] Trained 55 models with different hyperparamters\n", - "[2022-05-24 14:36:26,018] [INFO] Loading data set\n", - "[2022-05-24 14:36:26,493] [INFO] Start training\n", - "[2022-05-24 14:36:26,494] [INFO] Processing training data\n", - "[2022-05-24 14:36:26,507] [INFO] Processed 10% of the training data\n", - "[2022-05-24 14:36:26,514] [INFO] Processed 20% of the training data\n", - "[2022-05-24 14:36:26,529] [INFO] Processed 30% of the training data\n", - "[2022-05-24 14:36:26,544] [INFO] Processed 40% of the training data\n", - "[2022-05-24 14:36:26,557] [INFO] Processed 50% of the training data\n", - "[2022-05-24 14:36:26,569] [INFO] Processed 60% of the training data\n", - "[2022-05-24 14:36:26,582] [INFO] Processed 70% of the training data\n", - "[2022-05-24 14:36:26,591] [INFO] Processed 80% of the training data\n", - "[2022-05-24 14:36:26,598] [INFO] Processed 90% of the training data\n", - "[2022-05-24 14:36:26,606] [INFO] Processed 100% of the training data\n", - "[2022-05-24 14:36:26,617] [INFO] Start training with L-BFGS\n", - "[2022-05-24 14:36:26,755] [INFO] Iteration 1, training loss: 66667.597031\n", - "[2022-05-24 14:36:26,793] [INFO] Iteration 2, training loss: 55623.925756\n", - "[2022-05-24 14:36:26,900] [INFO] Iteration 3, training loss: 41676.630126\n", - "[2022-05-24 14:36:26,936] [INFO] Iteration 4, training loss: 41402.868392\n", - "[2022-05-24 14:36:26,979] [INFO] Iteration 5, training loss: 39958.091519\n", - "[2022-05-24 14:36:27,019] [INFO] Iteration 6, training loss: 39633.105474\n", - "[2022-05-24 14:36:27,058] [INFO] Iteration 7, training loss: 39410.823374\n", - "[2022-05-24 14:36:27,096] [INFO] Iteration 8, training loss: 38754.652581\n", - "[2022-05-24 14:36:27,166] [INFO] Iteration 9, training loss: 38431.445766\n", - "[2022-05-24 14:36:27,241] [INFO] Iteration 10, training loss: 38137.852674\n", - "[2022-05-24 14:36:27,316] [INFO] Iteration 11, training loss: 37932.490149\n", - "[2022-05-24 14:36:27,393] [INFO] Iteration 12, training loss: 37656.066661\n", - "[2022-05-24 14:36:27,466] [INFO] Iteration 13, training loss: 37041.775136\n", - "[2022-05-24 14:36:27,541] [INFO] Iteration 14, training loss: 34564.163873\n", - "[2022-05-24 14:36:27,615] [INFO] Iteration 15, training loss: 29178.011268\n", - "[2022-05-24 14:36:27,689] [INFO] Iteration 16, training loss: 25701.461865\n", - "[2022-05-24 14:36:27,760] [INFO] Iteration 17, training loss: 25476.440977\n", - "[2022-05-24 14:36:27,848] [INFO] Iteration 18, training loss: 23889.822991\n", - "[2022-05-24 14:36:27,923] [INFO] Iteration 19, training loss: 23242.360239\n", - "[2022-05-24 14:36:27,998] [INFO] Iteration 20, training loss: 22419.544709\n", - "[2022-05-24 14:36:28,087] [INFO] Iteration 21, training loss: 21077.029722\n", - "[2022-05-24 14:36:28,182] [INFO] Iteration 22, training loss: 20253.875975\n", - "[2022-05-24 14:36:28,284] [INFO] Iteration 23, training loss: 19517.472648\n", - "[2022-05-24 14:36:28,359] [INFO] Iteration 24, training loss: 17391.050388\n", - "[2022-05-24 14:36:28,432] [INFO] Iteration 25, training loss: 16194.689023\n", - "[2022-05-24 14:36:28,506] [INFO] Iteration 26, training loss: 16041.706576\n", - "[2022-05-24 14:36:28,579] [INFO] Iteration 27, training loss: 14975.985721\n", - "[2022-05-24 14:36:28,661] [INFO] Iteration 28, training loss: 14545.272899\n", - "[2022-05-24 14:36:28,714] [INFO] Iteration 29, training loss: 14082.482185\n", - "[2022-05-24 14:36:28,751] [INFO] Iteration 30, training loss: 13145.371954\n", - "[2022-05-24 14:36:28,787] [INFO] Iteration 31, training loss: 12629.195146\n", - "[2022-05-24 14:36:28,827] [INFO] Iteration 32, training loss: 12032.039313\n", - "[2022-05-24 14:36:28,868] [INFO] Iteration 33, training loss: 11273.695638\n", - "[2022-05-24 14:36:28,908] [INFO] Iteration 34, training loss: 10490.230218\n", - "[2022-05-24 14:36:28,948] [INFO] Iteration 35, training loss: 10028.089928\n", - "[2022-05-24 14:36:28,986] [INFO] Iteration 36, training loss: 9620.020311\n", - "[2022-05-24 14:36:29,024] [INFO] Iteration 37, training loss: 9197.565547\n", - "[2022-05-24 14:36:29,060] [INFO] Iteration 38, training loss: 8835.211466\n", - "[2022-05-24 14:36:29,100] [INFO] Iteration 39, training loss: 8324.185003\n", - "[2022-05-24 14:36:29,138] [INFO] Iteration 40, training loss: 7813.055525\n", - "[2022-05-24 14:36:29,176] [INFO] Iteration 41, training loss: 7331.840266\n", - "[2022-05-24 14:36:29,216] [INFO] Iteration 42, training loss: 6723.739352\n", - "[2022-05-24 14:36:29,259] [INFO] Iteration 43, training loss: 6537.846199\n", - "[2022-05-24 14:36:29,295] [INFO] Iteration 44, training loss: 6297.711000\n", - "[2022-05-24 14:36:29,332] [INFO] Iteration 45, training loss: 6136.256732\n", - "[2022-05-24 14:36:29,368] [INFO] Iteration 46, training loss: 5932.489668\n", - "[2022-05-24 14:36:29,406] [INFO] Iteration 47, training loss: 5800.595526\n", - "[2022-05-24 14:36:29,442] [INFO] Iteration 48, training loss: 5610.988280\n", - "[2022-05-24 14:36:29,483] [INFO] Iteration 49, training loss: 5561.589990\n", - "[2022-05-24 14:36:29,520] [INFO] Iteration 50, training loss: 5407.647596\n", - "[2022-05-24 14:36:29,557] [INFO] Iteration 51, training loss: 5390.933736\n", - "[2022-05-24 14:36:29,593] [INFO] Iteration 52, training loss: 5245.036766\n", - "[2022-05-24 14:36:29,635] [INFO] Iteration 53, training loss: 5196.459345\n", - "[2022-05-24 14:36:29,673] [INFO] Iteration 54, training loss: 5067.404038\n", - "[2022-05-24 14:36:29,714] [INFO] Iteration 55, training loss: 5029.268875\n", - "[2022-05-24 14:36:29,761] [INFO] Iteration 56, training loss: 4961.855915\n", - "[2022-05-24 14:36:29,798] [INFO] Iteration 57, training loss: 4924.561740\n", - "[2022-05-24 14:36:29,835] [INFO] Iteration 58, training loss: 4857.772977\n", - "[2022-05-24 14:36:29,872] [INFO] Iteration 59, training loss: 4846.022914\n", - "[2022-05-24 14:36:29,920] [INFO] Iteration 60, training loss: 4808.945481\n", - "[2022-05-24 14:36:29,979] [INFO] Iteration 61, training loss: 4796.355064\n", - "[2022-05-24 14:36:30,041] [INFO] Iteration 62, training loss: 4761.780633\n", - "[2022-05-24 14:36:30,127] [INFO] Iteration 63, training loss: 4726.583580\n", - "[2022-05-24 14:36:30,169] [INFO] Iteration 64, training loss: 4710.835766\n", - "[2022-05-24 14:36:30,239] [INFO] Iteration 65, training loss: 4683.154076\n", - "[2022-05-24 14:36:30,335] [INFO] Iteration 66, training loss: 4667.099179\n", - "[2022-05-24 14:36:30,406] [INFO] Iteration 67, training loss: 4644.071842\n", - "[2022-05-24 14:36:30,484] [INFO] Iteration 68, training loss: 4625.609051\n", - "[2022-05-24 14:36:30,560] [INFO] Iteration 69, training loss: 4617.274602\n", - "[2022-05-24 14:36:30,633] [INFO] Iteration 70, training loss: 4592.817701\n", - "[2022-05-24 14:36:30,709] [INFO] Iteration 71, training loss: 4585.805803\n", - "[2022-05-24 14:36:30,785] [INFO] Iteration 72, training loss: 4569.307227\n", - "[2022-05-24 14:36:30,861] [INFO] Iteration 73, training loss: 4557.347450\n", - "[2022-05-24 14:36:30,945] [INFO] Iteration 74, training loss: 4540.827323\n", - "[2022-05-24 14:36:31,017] [INFO] Iteration 75, training loss: 4529.524746\n", - "[2022-05-24 14:36:31,090] [INFO] Iteration 76, training loss: 4512.530626\n", - "[2022-05-24 14:36:31,169] [INFO] Iteration 77, training loss: 4505.499193\n", - "[2022-05-24 14:36:31,243] [INFO] Iteration 78, training loss: 4495.679634\n", - "[2022-05-24 14:36:31,318] [INFO] Iteration 79, training loss: 4483.684821\n", - "[2022-05-24 14:36:31,395] [INFO] Iteration 80, training loss: 4468.690766\n", - "[2022-05-24 14:36:31,478] [INFO] Iteration 81, training loss: 4458.656264\n", - "[2022-05-24 14:36:31,567] [INFO] Iteration 82, training loss: 4447.938415\n", - "[2022-05-24 14:36:31,644] [INFO] Iteration 83, training loss: 4439.669589\n", - "[2022-05-24 14:36:31,722] [INFO] Iteration 84, training loss: 4429.247218\n", - "[2022-05-24 14:36:31,792] [INFO] Iteration 85, training loss: 4419.982076\n", - "[2022-05-24 14:36:31,829] [INFO] Iteration 86, training loss: 4411.021280\n", - "[2022-05-24 14:36:31,866] [INFO] Iteration 87, training loss: 4402.644481\n", - "[2022-05-24 14:36:31,904] [INFO] Iteration 88, training loss: 4399.168568\n", - "[2022-05-24 14:36:31,942] [INFO] Iteration 89, training loss: 4394.003830\n", - "[2022-05-24 14:36:31,980] [INFO] Iteration 90, training loss: 4388.713150\n", - "[2022-05-24 14:36:32,016] [INFO] Iteration 91, training loss: 4385.619733\n", - "[2022-05-24 14:36:32,053] [INFO] Iteration 92, training loss: 4381.598230\n", - "[2022-05-24 14:36:32,092] [INFO] Iteration 93, training loss: 4377.788408\n", - "[2022-05-24 14:36:32,129] [INFO] Iteration 94, training loss: 4373.437655\n", - "[2022-05-24 14:36:32,167] [INFO] Iteration 95, training loss: 4368.816208\n", - "[2022-05-24 14:36:32,205] [INFO] Iteration 96, training loss: 4365.251812\n", - "[2022-05-24 14:36:32,244] [INFO] Iteration 97, training loss: 4361.696093\n", - "[2022-05-24 14:36:32,280] [INFO] Iteration 98, training loss: 4357.857630\n", - "[2022-05-24 14:36:32,317] [INFO] Iteration 99, training loss: 4354.613360\n", - "[2022-05-24 14:36:32,357] [INFO] Iteration 100, training loss: 4350.888322\n", - "[2022-05-24 14:36:32,397] [INFO] Iteration 101, training loss: 4348.166740\n", - "[2022-05-24 14:36:32,438] [INFO] Iteration 102, training loss: 4344.833289\n", - "[2022-05-24 14:36:32,474] [INFO] Iteration 103, training loss: 4341.791561\n", - "[2022-05-24 14:36:32,520] [INFO] Iteration 104, training loss: 4338.324725\n", - "[2022-05-24 14:36:32,565] [INFO] Iteration 105, training loss: 4335.350730\n", - "[2022-05-24 14:36:32,604] [INFO] Iteration 106, training loss: 4332.347137\n", - "[2022-05-24 14:36:32,653] [INFO] Iteration 107, training loss: 4329.062501\n", - "[2022-05-24 14:36:32,696] [INFO] Iteration 108, training loss: 4326.420723\n", - "[2022-05-24 14:36:32,742] [INFO] Iteration 109, training loss: 4323.894801\n", - "[2022-05-24 14:36:32,782] [INFO] Iteration 110, training loss: 4320.632134\n", - "[2022-05-24 14:36:32,819] [INFO] Iteration 111, training loss: 4317.967978\n", - "[2022-05-24 14:36:32,857] [INFO] Iteration 112, training loss: 4315.757244\n", - "[2022-05-24 14:36:32,893] [INFO] Iteration 113, training loss: 4313.471763\n", - "[2022-05-24 14:36:32,932] [INFO] Iteration 114, training loss: 4311.927318\n", - "[2022-05-24 14:36:32,971] [INFO] Iteration 115, training loss: 4307.875027\n", - "[2022-05-24 14:36:33,008] [INFO] Iteration 116, training loss: 4305.993894\n", - "[2022-05-24 14:36:33,045] [INFO] Iteration 117, training loss: 4303.629664\n", - "[2022-05-24 14:36:33,083] [INFO] Iteration 118, training loss: 4302.472220\n", - "[2022-05-24 14:36:33,121] [INFO] Iteration 119, training loss: 4299.774125\n", - "[2022-05-24 14:36:33,179] [INFO] Iteration 120, training loss: 4298.337756\n", - "[2022-05-24 14:36:33,257] [INFO] Iteration 121, training loss: 4295.608496\n", - "[2022-05-24 14:36:33,327] [INFO] Iteration 122, training loss: 4294.142966\n", - "[2022-05-24 14:36:33,400] [INFO] Iteration 123, training loss: 4292.115642\n", - "[2022-05-24 14:36:33,491] [INFO] Iteration 124, training loss: 4291.371326\n", - "[2022-05-24 14:36:33,563] [INFO] Iteration 125, training loss: 4288.613849\n", - "[2022-05-24 14:36:33,637] [INFO] Iteration 126, training loss: 4287.839852\n", - "[2022-05-24 14:36:33,709] [INFO] Iteration 127, training loss: 4285.331459\n", - "[2022-05-24 14:36:33,782] [INFO] Iteration 128, training loss: 4284.892009\n", - "[2022-05-24 14:36:33,857] [INFO] Iteration 129, training loss: 4282.615233\n", - "[2022-05-24 14:36:33,934] [INFO] Iteration 130, training loss: 4282.102488\n", - "[2022-05-24 14:36:34,007] [INFO] Iteration 131, training loss: 4279.965314\n", - "[2022-05-24 14:36:34,081] [INFO] Iteration 132, training loss: 4279.103657\n", - "[2022-05-24 14:36:34,153] [INFO] Iteration 133, training loss: 4277.442945\n", - "[2022-05-24 14:36:34,228] [INFO] Iteration 134, training loss: 4276.815206\n", - "[2022-05-24 14:36:34,302] [INFO] Iteration 135, training loss: 4275.288222\n", - "[2022-05-24 14:36:34,375] [INFO] Iteration 136, training loss: 4274.658127\n", - "[2022-05-24 14:36:34,447] [INFO] Iteration 137, training loss: 4273.117486\n", - "[2022-05-24 14:36:34,520] [INFO] Iteration 138, training loss: 4272.456664\n", - "[2022-05-24 14:36:34,594] [INFO] Iteration 139, training loss: 4271.039188\n", - "[2022-05-24 14:36:34,667] [INFO] Iteration 140, training loss: 4270.628543\n", - "[2022-05-24 14:36:34,735] [INFO] Iteration 141, training loss: 4269.196799\n", - "[2022-05-24 14:36:34,771] [INFO] Iteration 142, training loss: 4268.917476\n", - "[2022-05-24 14:36:34,808] [INFO] Iteration 143, training loss: 4267.337330\n", - "[2022-05-24 14:36:34,852] [INFO] Iteration 144, training loss: 4267.307893\n", - "[2022-05-24 14:36:34,893] [INFO] Iteration 145, training loss: 4265.749655\n", - "[2022-05-24 14:36:34,968] [INFO] Iteration 146, training loss: 4264.680008\n", - "[2022-05-24 14:36:35,007] [INFO] Iteration 147, training loss: 4264.272858\n", - "[2022-05-24 14:36:35,046] [INFO] Iteration 148, training loss: 4262.504383\n", - "[2022-05-24 14:36:35,085] [INFO] Iteration 149, training loss: 4262.351065\n", - "[2022-05-24 14:36:35,125] [INFO] Iteration 150, training loss: 4261.240872\n", - "[2022-05-24 14:36:35,161] [INFO] Iteration 151, training loss: 4259.488339\n", - "[2022-05-24 14:36:35,198] [INFO] Iteration 152, training loss: 4258.201711\n", - "[2022-05-24 14:36:35,236] [INFO] Iteration 153, training loss: 4257.138645\n", - "[2022-05-24 14:36:35,272] [INFO] Iteration 154, training loss: 4255.885107\n", - "[2022-05-24 14:36:35,309] [INFO] Iteration 155, training loss: 4255.219267\n", - "[2022-05-24 14:36:35,344] [INFO] Iteration 156, training loss: 4254.131410\n", - "[2022-05-24 14:36:35,384] [INFO] Iteration 157, training loss: 4253.529838\n", - "[2022-05-24 14:36:35,420] [INFO] Iteration 158, training loss: 4252.574568\n", - "[2022-05-24 14:36:35,457] [INFO] Iteration 159, training loss: 4251.368121\n", - "[2022-05-24 14:36:35,492] [INFO] Iteration 160, training loss: 4250.650102\n", - "[2022-05-24 14:36:35,537] [INFO] Iteration 161, training loss: 4249.897824\n", - "[2022-05-24 14:36:35,573] [INFO] Iteration 162, training loss: 4249.316158\n", - "[2022-05-24 14:36:35,616] [INFO] Iteration 163, training loss: 4248.314410\n", - "[2022-05-24 14:36:35,653] [INFO] Iteration 164, training loss: 4247.794380\n", - "[2022-05-24 14:36:35,690] [INFO] Iteration 165, training loss: 4246.639875\n", - "[2022-05-24 14:36:35,725] [INFO] Iteration 166, training loss: 4246.142378\n", - "[2022-05-24 14:36:35,764] [INFO] Iteration 167, training loss: 4245.284106\n", - "[2022-05-24 14:36:35,800] [INFO] Iteration 168, training loss: 4244.794802\n", - "[2022-05-24 14:36:35,837] [INFO] Iteration 169, training loss: 4243.926213\n", - "[2022-05-24 14:36:35,874] [INFO] Iteration 170, training loss: 4243.502643\n", - "[2022-05-24 14:36:35,919] [INFO] Iteration 171, training loss: 4242.699617\n", - "[2022-05-24 14:36:35,963] [INFO] Iteration 172, training loss: 4242.252274\n", - "[2022-05-24 14:36:36,005] [INFO] Iteration 173, training loss: 4241.594073\n", - "[2022-05-24 14:36:36,048] [INFO] Iteration 174, training loss: 4241.395693\n", - "[2022-05-24 14:36:36,092] [INFO] Iteration 175, training loss: 4240.532660\n", - "[2022-05-24 14:36:36,136] [INFO] Iteration 176, training loss: 4240.510311\n", - "[2022-05-24 14:36:36,179] [INFO] Iteration 177, training loss: 4239.532711\n", - "[2022-05-24 14:36:36,294] [INFO] Iteration 178, training loss: 4238.947761\n", - "[2022-05-24 14:36:36,368] [INFO] Iteration 179, training loss: 4238.874127\n", - "[2022-05-24 14:36:36,370] [INFO] Terminated with the stopping criteria\n", - "[2022-05-24 14:36:36,371] [INFO] Saving model\n" + "[2022-05-25 09:23:22,872] [INFO] Starting with arow (1/5)\n", + "[2022-05-25 09:23:22,873] [INFO] Baseline for arow\n", + "[2022-05-25 09:24:20,396] [INFO] Trial 1/10 for arow\n", + "[2022-05-25 09:25:29,783] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:25:29,784] [INFO] Best optimized model: 0.8909010732379357\n", + "[2022-05-25 09:25:29,784] [INFO] Trial 2/10 for arow\n", + "[2022-05-25 09:26:37,112] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:26:37,113] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:26:37,114] [INFO] Trial 3/10 for arow\n", + "[2022-05-25 09:27:56,355] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:27:56,355] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:27:56,356] [INFO] Trial 4/10 for arow\n", + "[2022-05-25 09:29:04,767] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:29:04,768] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:29:04,769] [INFO] Trial 5/10 for arow\n", + "[2022-05-25 09:30:12,147] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:30:12,148] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:30:12,149] [INFO] Trial 6/10 for arow\n", + "[2022-05-25 09:31:50,378] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:31:50,380] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:31:50,381] [INFO] Trial 7/10 for arow\n", + "[2022-05-25 09:33:17,917] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:33:17,917] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:33:17,918] [INFO] Trial 8/10 for arow\n", + "[2022-05-25 09:34:33,506] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:34:33,506] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:34:33,507] [INFO] Trial 9/10 for arow\n", + "[2022-05-25 09:36:11,384] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:36:11,385] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:36:11,386] [INFO] Trial 10/10 for arow\n", + "[2022-05-25 09:37:42,740] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:37:42,740] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:37:42,741] [INFO] Starting with ap (2/5)\n", + "[2022-05-25 09:37:42,741] [INFO] Baseline for ap\n", + "[2022-05-25 09:39:24,452] [INFO] Trial 1/10 for ap\n", + "[2022-05-25 09:40:53,091] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:40:53,092] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:40:53,093] [INFO] Trial 2/10 for ap\n", + "[2022-05-25 09:42:21,499] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:42:21,500] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:42:21,500] [INFO] Trial 3/10 for ap\n", + "[2022-05-25 09:44:11,890] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:44:11,890] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:44:11,891] [INFO] Trial 4/10 for ap\n", + "[2022-05-25 09:46:02,012] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:46:02,014] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:46:02,014] [INFO] Trial 5/10 for ap\n", + "[2022-05-25 09:47:53,548] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:47:53,548] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:47:53,549] [INFO] Trial 6/10 for ap\n", + "[2022-05-25 09:49:20,355] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:49:20,356] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:49:20,357] [INFO] Trial 7/10 for ap\n", + "[2022-05-25 09:51:24,878] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:51:24,878] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:51:24,879] [INFO] Trial 8/10 for ap\n", + "[2022-05-25 09:52:58,025] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:52:58,026] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:52:58,027] [INFO] Trial 9/10 for ap\n", + "[2022-05-25 09:54:38,021] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:54:38,021] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:54:38,022] [INFO] Trial 10/10 for ap\n", + "[2022-05-25 09:56:20,251] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 09:56:20,252] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 09:56:20,252] [INFO] Starting with lbfgs (3/5)\n", + "[2022-05-25 09:56:20,253] [INFO] Baseline for lbfgs\n", + "[2022-05-25 09:58:15,855] [INFO] Trial 1/10 for lbfgs\n", + "[2022-05-25 10:00:05,039] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:00:05,040] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 10:00:05,041] [INFO] Trial 2/10 for lbfgs\n", + "[2022-05-25 10:02:02,479] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:02:02,481] [INFO] Best optimized model: 0.8978907390633878\n", + "[2022-05-25 10:02:02,481] [INFO] Trial 3/10 for lbfgs\n", + "[2022-05-25 10:03:47,661] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:03:47,662] [INFO] Best optimized model: 0.9058707702090455\n", + "[2022-05-25 10:03:47,663] [INFO] Trial 4/10 for lbfgs\n", + "[2022-05-25 10:05:43,615] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:05:43,617] [INFO] Best optimized model: 0.9058707702090455\n", + "[2022-05-25 10:05:43,618] [INFO] Trial 5/10 for lbfgs\n", + "[2022-05-25 10:08:31,421] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:08:31,421] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:08:31,422] [INFO] Trial 6/10 for lbfgs\n", + "[2022-05-25 10:10:20,815] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:10:20,816] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:10:20,817] [INFO] Trial 7/10 for lbfgs\n", + "[2022-05-25 10:12:38,246] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:12:38,247] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:12:38,248] [INFO] Trial 8/10 for lbfgs\n", + "[2022-05-25 10:14:49,489] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:14:49,489] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:14:49,490] [INFO] Trial 9/10 for lbfgs\n", + "[2022-05-25 10:16:57,773] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:16:57,774] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:16:57,776] [INFO] Trial 10/10 for lbfgs\n", + "[2022-05-25 10:18:55,195] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:18:55,196] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:18:55,197] [INFO] Starting with l2sgd (4/5)\n", + "[2022-05-25 10:18:55,199] [INFO] Baseline for l2sgd\n", + "[2022-05-25 10:21:23,637] [INFO] Trial 1/10 for l2sgd\n", + "[2022-05-25 10:23:20,241] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:23:20,241] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:23:20,242] [INFO] Trial 2/10 for l2sgd\n", + "[2022-05-25 10:26:09,872] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:26:09,872] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:26:09,873] [INFO] Trial 3/10 for l2sgd\n", + "[2022-05-25 10:28:42,254] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:28:42,255] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:28:42,256] [INFO] Trial 4/10 for l2sgd\n", + "[2022-05-25 10:31:16,728] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:31:16,729] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:31:16,730] [INFO] Trial 5/10 for l2sgd\n", + "[2022-05-25 10:34:19,426] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:34:19,427] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:34:19,428] [INFO] Trial 6/10 for l2sgd\n", + "[2022-05-25 10:37:00,452] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:37:00,453] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:37:00,453] [INFO] Trial 7/10 for l2sgd\n", + "[2022-05-25 10:39:40,710] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:39:40,711] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:39:40,711] [INFO] Trial 8/10 for l2sgd\n", + "[2022-05-25 10:42:25,353] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:42:25,353] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:42:25,354] [INFO] Trial 9/10 for l2sgd\n", + "[2022-05-25 10:45:11,160] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:45:11,161] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:45:11,162] [INFO] Trial 10/10 for l2sgd\n", + "[2022-05-25 10:47:33,224] [INFO] Best baseline model: 0.8538541405229366\n", + "[2022-05-25 10:47:33,225] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:47:33,225] [INFO] Starting with pa (5/5)\n", + "[2022-05-25 10:47:33,226] [INFO] Baseline for pa\n", + "[2022-05-25 10:49:37,885] [INFO] Trial 1/10 for pa\n", + "[2022-05-25 10:52:10,237] [INFO] Best baseline model: 0.8673452502903771\n", + "[2022-05-25 10:52:10,237] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:52:10,238] [INFO] Trial 2/10 for pa\n", + "[2022-05-25 10:54:10,697] [INFO] Best baseline model: 0.8673452502903771\n", + "[2022-05-25 10:54:10,698] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:54:10,699] [INFO] Trial 3/10 for pa\n", + "[2022-05-25 10:56:31,984] [INFO] Best baseline model: 0.8673452502903771\n", + "[2022-05-25 10:56:31,985] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:56:31,986] [INFO] Trial 4/10 for pa\n", + "[2022-05-25 10:59:04,346] [INFO] Best baseline model: 0.8673452502903771\n", + "[2022-05-25 10:59:04,348] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 10:59:04,349] [INFO] Trial 5/10 for pa\n", + "[2022-05-25 11:01:31,107] [INFO] Best baseline model: 0.8673452502903771\n", + "[2022-05-25 11:01:31,108] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 11:01:31,109] [INFO] Trial 6/10 for pa\n", + "[2022-05-25 11:03:38,579] [INFO] Best baseline model: 0.8673452502903771\n", + "[2022-05-25 11:03:38,579] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 11:03:38,580] [INFO] Trial 7/10 for pa\n", + "[2022-05-25 11:05:16,477] [INFO] Best baseline model: 0.8673452502903771\n", + "[2022-05-25 11:05:16,478] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 11:05:16,479] [INFO] Trial 8/10 for pa\n", + "[2022-05-25 11:06:55,920] [INFO] Best baseline model: 0.8673452502903771\n", + "[2022-05-25 11:06:55,921] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 11:06:55,922] [INFO] Trial 9/10 for pa\n", + "[2022-05-25 11:08:47,068] [INFO] Best baseline model: 0.8673452502903771\n", + "[2022-05-25 11:08:47,069] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 11:08:47,069] [INFO] Trial 10/10 for pa\n", + "[2022-05-25 11:10:34,852] [INFO] Best baseline model: 0.8673452502903771\n", + "[2022-05-25 11:10:34,853] [INFO] Best optimized model: 0.9225488624502322\n", + "[2022-05-25 11:10:34,854] [INFO] Finished hyperparameter optimization\n", + "[2022-05-25 11:10:34,854] [INFO] Trained 55 models with different hyperparamters\n", + "[2022-05-25 11:10:34,858] [INFO] Loading data set\n", + "[2022-05-25 11:10:38,048] [INFO] Start training\n", + "[2022-05-25 11:10:38,049] [INFO] Processing training data\n", + "[2022-05-25 11:10:38,437] [INFO] Processed 10% of the training data\n", + "[2022-05-25 11:10:38,900] [INFO] Processed 20% of the training data\n", + "[2022-05-25 11:10:39,269] [INFO] Processed 30% of the training data\n", + "[2022-05-25 11:10:39,888] [INFO] Processed 40% of the training data\n", + "[2022-05-25 11:10:40,625] [INFO] Processed 50% of the training data\n", + "[2022-05-25 11:10:41,142] [INFO] Processed 60% of the training data\n", + "[2022-05-25 11:10:41,607] [INFO] Processed 70% of the training data\n", + "[2022-05-25 11:10:42,068] [INFO] Processed 80% of the training data\n", + "[2022-05-25 11:10:42,818] [INFO] Processed 90% of the training data\n", + "[2022-05-25 11:10:43,789] [INFO] Processed 100% of the training data\n", + "[2022-05-25 11:10:43,917] [INFO] Start training with L-BFGS\n", + "[2022-05-25 11:10:44,773] [INFO] Iteration 1, training loss: 283388.543569\n", + "[2022-05-25 11:10:44,988] [INFO] Iteration 2, training loss: 238571.509453\n", + "[2022-05-25 11:10:45,701] [INFO] Iteration 3, training loss: 185707.832694\n", + "[2022-05-25 11:10:45,966] [INFO] Iteration 4, training loss: 182427.956479\n", + "[2022-05-25 11:10:46,242] [INFO] Iteration 5, training loss: 170732.563357\n", + "[2022-05-25 11:10:46,504] [INFO] Iteration 6, training loss: 168563.550995\n", + "[2022-05-25 11:10:46,762] [INFO] Iteration 7, training loss: 167759.381547\n", + "[2022-05-25 11:10:47,249] [INFO] Iteration 8, training loss: 166847.089946\n", + "[2022-05-25 11:10:47,767] [INFO] Iteration 9, training loss: 165213.160279\n", + "[2022-05-25 11:10:48,289] [INFO] Iteration 10, training loss: 164087.203206\n", + "[2022-05-25 11:10:48,597] [INFO] Iteration 11, training loss: 162971.724909\n", + "[2022-05-25 11:10:48,873] [INFO] Iteration 12, training loss: 162056.506561\n", + "[2022-05-25 11:10:49,163] [INFO] Iteration 13, training loss: 161139.053315\n", + "[2022-05-25 11:10:49,469] [INFO] Iteration 14, training loss: 159714.792042\n", + "[2022-05-25 11:10:49,761] [INFO] Iteration 15, training loss: 155288.977768\n", + "[2022-05-25 11:10:50,276] [INFO] Iteration 16, training loss: 138416.116654\n", + "[2022-05-25 11:10:50,831] [INFO] Iteration 17, training loss: 116236.961930\n", + "[2022-05-25 11:10:51,326] [INFO] Iteration 18, training loss: 110493.601250\n", + "[2022-05-25 11:10:51,578] [INFO] Iteration 19, training loss: 103910.508091\n", + "[2022-05-25 11:10:51,881] [INFO] Iteration 20, training loss: 99699.490169\n", + "[2022-05-25 11:10:52,178] [INFO] Iteration 21, training loss: 93898.330349\n", + "[2022-05-25 11:10:52,416] [INFO] Iteration 22, training loss: 88866.008350\n", + "[2022-05-25 11:10:52,735] [INFO] Iteration 23, training loss: 85558.046157\n", + "[2022-05-25 11:10:53,257] [INFO] Iteration 24, training loss: 80590.830862\n", + "[2022-05-25 11:10:53,727] [INFO] Iteration 25, training loss: 75842.473188\n", + "[2022-05-25 11:10:54,251] [INFO] Iteration 26, training loss: 68012.754083\n", + "[2022-05-25 11:10:54,590] [INFO] Iteration 27, training loss: 64764.757938\n", + "[2022-05-25 11:10:54,843] [INFO] Iteration 28, training loss: 62314.824031\n", + "[2022-05-25 11:10:55,097] [INFO] Iteration 29, training loss: 58789.802093\n", + "[2022-05-25 11:10:55,338] [INFO] Iteration 30, training loss: 55223.634864\n", + "[2022-05-25 11:10:55,608] [INFO] Iteration 31, training loss: 50011.445167\n", + "[2022-05-25 11:10:55,986] [INFO] Iteration 32, training loss: 47439.593282\n", + "[2022-05-25 11:10:56,462] [INFO] Iteration 33, training loss: 45114.872455\n", + "[2022-05-25 11:10:56,942] [INFO] Iteration 34, training loss: 43334.594723\n", + "[2022-05-25 11:10:57,373] [INFO] Iteration 35, training loss: 40917.298568\n", + "[2022-05-25 11:10:57,605] [INFO] Iteration 36, training loss: 37403.436755\n", + "[2022-05-25 11:10:57,844] [INFO] Iteration 37, training loss: 33566.192896\n", + "[2022-05-25 11:10:58,079] [INFO] Iteration 38, training loss: 30843.560296\n", + "[2022-05-25 11:10:58,315] [INFO] Iteration 39, training loss: 28610.647722\n", + "[2022-05-25 11:10:58,551] [INFO] Iteration 40, training loss: 26742.159269\n", + "[2022-05-25 11:10:58,932] [INFO] Iteration 41, training loss: 25288.324725\n", + "[2022-05-25 11:10:59,416] [INFO] Iteration 42, training loss: 24124.144925\n", + "[2022-05-25 11:10:59,922] [INFO] Iteration 43, training loss: 22717.594494\n", + "[2022-05-25 11:11:00,343] [INFO] Iteration 44, training loss: 21886.827148\n", + "[2022-05-25 11:11:00,583] [INFO] Iteration 45, training loss: 21315.461487\n", + "[2022-05-25 11:11:00,832] [INFO] Iteration 46, training loss: 20465.671764\n", + "[2022-05-25 11:11:01,069] [INFO] Iteration 47, training loss: 19901.275673\n", + "[2022-05-25 11:11:01,350] [INFO] Iteration 48, training loss: 19355.701731\n", + "[2022-05-25 11:11:01,597] [INFO] Iteration 49, training loss: 19108.936581\n", + "[2022-05-25 11:11:01,860] [INFO] Iteration 50, training loss: 18803.919233\n", + "[2022-05-25 11:11:02,115] [INFO] Iteration 51, training loss: 18646.107274\n", + "[2022-05-25 11:11:02,351] [INFO] Iteration 52, training loss: 18331.663189\n", + "[2022-05-25 11:11:02,593] [INFO] Iteration 53, training loss: 18143.902623\n", + "[2022-05-25 11:11:02,839] [INFO] Iteration 54, training loss: 17957.534276\n", + "[2022-05-25 11:11:03,109] [INFO] Iteration 55, training loss: 17750.491079\n", + "[2022-05-25 11:11:03,687] [INFO] Iteration 56, training loss: 17604.372531\n", + "[2022-05-25 11:11:04,192] [INFO] Iteration 57, training loss: 17497.433552\n", + "[2022-05-25 11:11:04,671] [INFO] Iteration 58, training loss: 17341.751718\n", + "[2022-05-25 11:11:05,187] [INFO] Iteration 59, training loss: 17340.657963\n", + "[2022-05-25 11:11:05,419] [INFO] Iteration 60, training loss: 17243.135538\n", + "[2022-05-25 11:11:05,675] [INFO] Iteration 61, training loss: 17195.414685\n", + "[2022-05-25 11:11:05,945] [INFO] Iteration 62, training loss: 17093.046201\n", + "[2022-05-25 11:11:06,610] [INFO] Iteration 63, training loss: 17092.643496\n", + "[2022-05-25 11:11:07,209] [INFO] Iteration 64, training loss: 17009.540950\n", + "[2022-05-25 11:11:07,761] [INFO] Iteration 65, training loss: 16972.071776\n", + "[2022-05-25 11:11:08,013] [INFO] Iteration 66, training loss: 16900.457502\n", + "[2022-05-25 11:11:08,289] [INFO] Iteration 67, training loss: 16854.607508\n", + "[2022-05-25 11:11:08,573] [INFO] Iteration 68, training loss: 16837.219296\n", + "[2022-05-25 11:11:08,855] [INFO] Iteration 69, training loss: 16822.320255\n", + "[2022-05-25 11:11:09,117] [INFO] Iteration 70, training loss: 16790.057197\n", + "[2022-05-25 11:11:09,615] [INFO] Iteration 71, training loss: 16787.026049\n", + "[2022-05-25 11:11:10,133] [INFO] Iteration 72, training loss: 16711.112918\n", + "[2022-05-25 11:11:10,628] [INFO] Iteration 73, training loss: 16701.258218\n", + "[2022-05-25 11:11:10,909] [INFO] Iteration 74, training loss: 16670.085507\n", + "[2022-05-25 11:11:11,162] [INFO] Iteration 75, training loss: 16660.311446\n", + "[2022-05-25 11:11:11,438] [INFO] Iteration 76, training loss: 16615.703561\n", + "[2022-05-25 11:11:11,692] [INFO] Iteration 77, training loss: 16600.224805\n", + "[2022-05-25 11:11:11,945] [INFO] Iteration 78, training loss: 16566.711124\n", + "[2022-05-25 11:11:12,217] [INFO] Iteration 79, training loss: 16532.851439\n", + "[2022-05-25 11:11:12,718] [INFO] Iteration 80, training loss: 16500.962605\n", + "[2022-05-25 11:11:13,254] [INFO] Iteration 81, training loss: 16480.592373\n", + "[2022-05-25 11:11:13,768] [INFO] Iteration 82, training loss: 16457.586021\n", + "[2022-05-25 11:11:14,033] [INFO] Iteration 83, training loss: 16433.056206\n", + "[2022-05-25 11:11:14,277] [INFO] Iteration 84, training loss: 16416.579562\n", + "[2022-05-25 11:11:14,536] [INFO] Iteration 85, training loss: 16386.415864\n", + "[2022-05-25 11:11:15,045] [INFO] Iteration 86, training loss: 16372.890345\n", + "[2022-05-25 11:11:15,417] [INFO] Iteration 87, training loss: 16362.095627\n", + "[2022-05-25 11:11:15,979] [INFO] Iteration 88, training loss: 16346.641446\n", + "[2022-05-25 11:11:16,470] [INFO] Iteration 89, training loss: 16334.886514\n", + "[2022-05-25 11:11:16,876] [INFO] Iteration 90, training loss: 16323.450120\n", + "[2022-05-25 11:11:17,122] [INFO] Iteration 91, training loss: 16310.605561\n", + "[2022-05-25 11:11:17,409] [INFO] Iteration 92, training loss: 16300.375583\n", + "[2022-05-25 11:11:17,687] [INFO] Iteration 93, training loss: 16289.425327\n", + "[2022-05-25 11:11:18,055] [INFO] Iteration 94, training loss: 16282.167907\n", + "[2022-05-25 11:11:18,437] [INFO] Iteration 95, training loss: 16273.891243\n", + "[2022-05-25 11:11:18,958] [INFO] Iteration 96, training loss: 16266.779198\n", + "[2022-05-25 11:11:19,461] [INFO] Iteration 97, training loss: 16259.525743\n", + "[2022-05-25 11:11:19,915] [INFO] Iteration 98, training loss: 16251.731934\n", + "[2022-05-25 11:11:20,197] [INFO] Iteration 99, training loss: 16247.832453\n", + "[2022-05-25 11:11:20,467] [INFO] Iteration 100, training loss: 16241.164852\n", + "[2022-05-25 11:11:20,695] [INFO] Iteration 101, training loss: 16236.047838\n", + "[2022-05-25 11:11:20,942] [INFO] Iteration 102, training loss: 16229.449792\n", + "[2022-05-25 11:11:21,220] [INFO] Iteration 103, training loss: 16225.793452\n", + "[2022-05-25 11:11:21,714] [INFO] Iteration 104, training loss: 16220.116846\n", + "[2022-05-25 11:11:22,208] [INFO] Iteration 105, training loss: 16217.221825\n", + "[2022-05-25 11:11:22,710] [INFO] Iteration 106, training loss: 16212.566072\n", + "[2022-05-25 11:11:23,009] [INFO] Iteration 107, training loss: 16209.496987\n", + "[2022-05-25 11:11:23,267] [INFO] Iteration 108, training loss: 16204.219403\n", + "[2022-05-25 11:11:23,531] [INFO] Iteration 109, training loss: 16202.327269\n", + "[2022-05-25 11:11:23,792] [INFO] Iteration 110, training loss: 16198.259803\n", + "[2022-05-25 11:11:24,070] [INFO] Iteration 111, training loss: 16196.294216\n", + "[2022-05-25 11:11:24,585] [INFO] Iteration 112, training loss: 16192.818622\n", + "[2022-05-25 11:11:25,127] [INFO] Iteration 113, training loss: 16190.807656\n", + "[2022-05-25 11:11:25,595] [INFO] Iteration 114, training loss: 16187.622113\n", + "[2022-05-25 11:11:25,907] [INFO] Iteration 115, training loss: 16186.063478\n", + "[2022-05-25 11:11:26,150] [INFO] Iteration 116, training loss: 16183.325785\n", + "[2022-05-25 11:11:26,389] [INFO] Iteration 117, training loss: 16181.955672\n", + "[2022-05-25 11:11:26,624] [INFO] Iteration 118, training loss: 16179.522570\n", + "[2022-05-25 11:11:26,866] [INFO] Iteration 119, training loss: 16176.955902\n", + "[2022-05-25 11:11:27,113] [INFO] Iteration 120, training loss: 16174.186865\n", + "[2022-05-25 11:11:27,503] [INFO] Iteration 121, training loss: 16173.204877\n", + "[2022-05-25 11:11:27,967] [INFO] Iteration 122, training loss: 16170.687800\n", + "[2022-05-25 11:11:28,563] [INFO] Iteration 123, training loss: 16168.023697\n", + "[2022-05-25 11:11:28,930] [INFO] Iteration 124, training loss: 16165.885510\n", + "[2022-05-25 11:11:29,182] [INFO] Iteration 125, training loss: 16163.362532\n", + "[2022-05-25 11:11:29,425] [INFO] Iteration 126, training loss: 16160.359490\n", + "[2022-05-25 11:11:29,667] [INFO] Iteration 127, training loss: 16159.116075\n", + "[2022-05-25 11:11:29,899] [INFO] Iteration 128, training loss: 16156.611033\n", + "[2022-05-25 11:11:30,135] [INFO] Iteration 129, training loss: 16154.696393\n", + "[2022-05-25 11:11:30,613] [INFO] Iteration 130, training loss: 16151.463198\n", + "[2022-05-25 11:11:31,098] [INFO] Iteration 131, training loss: 16150.244786\n", + "[2022-05-25 11:11:31,600] [INFO] Iteration 132, training loss: 16147.862274\n", + "[2022-05-25 11:11:31,917] [INFO] Iteration 133, training loss: 16146.116513\n", + "[2022-05-25 11:11:32,156] [INFO] Iteration 134, training loss: 16144.107791\n", + "[2022-05-25 11:11:32,405] [INFO] Iteration 135, training loss: 16141.972632\n", + "[2022-05-25 11:11:32,650] [INFO] Iteration 136, training loss: 16139.468005\n", + "[2022-05-25 11:11:32,884] [INFO] Iteration 137, training loss: 16137.185846\n", + "[2022-05-25 11:11:33,118] [INFO] Iteration 138, training loss: 16135.535118\n", + "[2022-05-25 11:11:33,459] [INFO] Iteration 139, training loss: 16133.390675\n", + "[2022-05-25 11:11:33,923] [INFO] Iteration 140, training loss: 16131.707915\n", + "[2022-05-25 11:11:34,387] [INFO] Iteration 141, training loss: 16129.519305\n", + "[2022-05-25 11:11:34,855] [INFO] Iteration 142, training loss: 16128.076988\n", + "[2022-05-25 11:11:35,085] [INFO] Iteration 143, training loss: 16126.042172\n", + "[2022-05-25 11:11:35,315] [INFO] Iteration 144, training loss: 16124.793203\n", + "[2022-05-25 11:11:35,545] [INFO] Iteration 145, training loss: 16123.137805\n", + "[2022-05-25 11:11:35,775] [INFO] Iteration 146, training loss: 16121.958769\n", + "[2022-05-25 11:11:36,006] [INFO] Iteration 147, training loss: 16120.250376\n", + "[2022-05-25 11:11:36,281] [INFO] Iteration 148, training loss: 16118.996159\n", + "[2022-05-25 11:11:36,741] [INFO] Iteration 149, training loss: 16117.485176\n", + "[2022-05-25 11:11:37,204] [INFO] Iteration 150, training loss: 16116.026683\n", + "[2022-05-25 11:11:37,665] [INFO] Iteration 151, training loss: 16114.215267\n", + "[2022-05-25 11:11:37,957] [INFO] Iteration 152, training loss: 16112.814582\n", + "[2022-05-25 11:11:38,187] [INFO] Iteration 153, training loss: 16111.390885\n", + "[2022-05-25 11:11:38,417] [INFO] Iteration 154, training loss: 16110.229082\n", + "[2022-05-25 11:11:38,686] [INFO] Iteration 155, training loss: 16108.276302\n", + "[2022-05-25 11:11:38,920] [INFO] Iteration 156, training loss: 16106.515369\n", + "[2022-05-25 11:11:39,193] [INFO] Iteration 157, training loss: 16105.075836\n", + "[2022-05-25 11:11:39,659] [INFO] Iteration 158, training loss: 16103.524775\n", + "[2022-05-25 11:11:40,122] [INFO] Iteration 159, training loss: 16102.039520\n", + "[2022-05-25 11:11:40,624] [INFO] Iteration 160, training loss: 16100.822599\n", + "[2022-05-25 11:11:40,938] [INFO] Iteration 161, training loss: 16099.466799\n", + "[2022-05-25 11:11:41,184] [INFO] Iteration 162, training loss: 16097.523403\n", + "[2022-05-25 11:11:41,433] [INFO] Iteration 163, training loss: 16097.064868\n", + "[2022-05-25 11:11:41,679] [INFO] Iteration 164, training loss: 16095.784258\n", + "[2022-05-25 11:11:41,928] [INFO] Iteration 165, training loss: 16094.195110\n", + "[2022-05-25 11:11:42,181] [INFO] Iteration 166, training loss: 16093.030758\n", + "[2022-05-25 11:11:42,640] [INFO] Iteration 167, training loss: 16091.249820\n", + "[2022-05-25 11:11:43,159] [INFO] Iteration 168, training loss: 16090.317491\n", + "[2022-05-25 11:11:43,697] [INFO] Iteration 169, training loss: 16088.858646\n", + "[2022-05-25 11:11:44,044] [INFO] Iteration 170, training loss: 16088.326393\n", + "[2022-05-25 11:11:44,279] [INFO] Iteration 171, training loss: 16086.235056\n", + "[2022-05-25 11:11:44,516] [INFO] Iteration 172, training loss: 16085.352039\n", + "[2022-05-25 11:11:44,747] [INFO] Iteration 173, training loss: 16083.636954\n", + "[2022-05-25 11:11:44,980] [INFO] Iteration 174, training loss: 16083.106583\n", + "[2022-05-25 11:11:45,258] [INFO] Iteration 175, training loss: 16081.574570\n", + "[2022-05-25 11:11:45,807] [INFO] Iteration 176, training loss: 16080.818812\n", + "[2022-05-25 11:11:46,365] [INFO] Iteration 177, training loss: 16079.354065\n", + "[2022-05-25 11:11:46,821] [INFO] Iteration 178, training loss: 16078.542032\n", + "[2022-05-25 11:11:47,075] [INFO] Iteration 179, training loss: 16077.231962\n", + "[2022-05-25 11:11:47,348] [INFO] Iteration 180, training loss: 16076.592644\n", + "[2022-05-25 11:11:47,627] [INFO] Iteration 181, training loss: 16075.247808\n", + "[2022-05-25 11:11:47,872] [INFO] Iteration 182, training loss: 16074.089988\n", + "[2022-05-25 11:11:48,112] [INFO] Iteration 183, training loss: 16072.644745\n", + "[2022-05-25 11:11:48,500] [INFO] Iteration 184, training loss: 16071.262353\n", + "[2022-05-25 11:11:48,991] [INFO] Iteration 185, training loss: 16069.792235\n", + "[2022-05-25 11:11:49,519] [INFO] Iteration 186, training loss: 16068.410221\n", + "[2022-05-25 11:11:49,947] [INFO] Iteration 187, training loss: 16067.163593\n", + "[2022-05-25 11:11:50,203] [INFO] Iteration 188, training loss: 16065.242429\n", + "[2022-05-25 11:11:50,447] [INFO] Iteration 189, training loss: 16063.882382\n", + "[2022-05-25 11:11:50,704] [INFO] Iteration 190, training loss: 16061.620476\n", + "[2022-05-25 11:11:50,979] [INFO] Iteration 191, training loss: 16060.515738\n", + "[2022-05-25 11:11:51,260] [INFO] Iteration 192, training loss: 16058.300741\n", + "[2022-05-25 11:11:51,745] [INFO] Iteration 193, training loss: 16057.028734\n", + "[2022-05-25 11:11:52,223] [INFO] Iteration 194, training loss: 16054.706491\n", + "[2022-05-25 11:11:52,700] [INFO] Iteration 195, training loss: 16053.582598\n", + "[2022-05-25 11:11:52,986] [INFO] Iteration 196, training loss: 16051.452814\n", + "[2022-05-25 11:11:53,231] [INFO] Iteration 197, training loss: 16050.334590\n", + "[2022-05-25 11:11:53,491] [INFO] Iteration 198, training loss: 16048.608484\n", + "[2022-05-25 11:11:53,734] [INFO] Iteration 199, training loss: 16047.133438\n", + "[2022-05-25 11:11:53,968] [INFO] Iteration 200, training loss: 16045.390393\n", + "[2022-05-25 11:11:54,287] [INFO] Iteration 201, training loss: 16044.027686\n", + "[2022-05-25 11:11:54,767] [INFO] Iteration 202, training loss: 16042.079700\n", + "[2022-05-25 11:11:55,233] [INFO] Iteration 203, training loss: 16040.807591\n", + "[2022-05-25 11:11:55,724] [INFO] Iteration 204, training loss: 16039.354837\n", + "[2022-05-25 11:11:55,961] [INFO] Iteration 205, training loss: 16037.845145\n", + "[2022-05-25 11:11:56,195] [INFO] Iteration 206, training loss: 16036.714353\n", + "[2022-05-25 11:11:56,438] [INFO] Iteration 207, training loss: 16034.999270\n", + "[2022-05-25 11:11:56,685] [INFO] Iteration 208, training loss: 16034.229970\n", + "[2022-05-25 11:11:56,951] [INFO] Iteration 209, training loss: 16032.791409\n", + "[2022-05-25 11:11:57,198] [INFO] Iteration 210, training loss: 16031.770920\n", + "[2022-05-25 11:11:57,692] [INFO] Iteration 211, training loss: 16029.886456\n", + "[2022-05-25 11:11:58,195] [INFO] Iteration 212, training loss: 16028.499115\n", + "[2022-05-25 11:11:58,704] [INFO] Iteration 213, training loss: 16027.220048\n", + "[2022-05-25 11:11:59,024] [INFO] Iteration 214, training loss: 16025.731148\n", + "[2022-05-25 11:11:59,286] [INFO] Iteration 215, training loss: 16024.217826\n", + "[2022-05-25 11:11:59,527] [INFO] Iteration 216, training loss: 16022.483510\n", + "[2022-05-25 11:11:59,774] [INFO] Iteration 217, training loss: 16021.088998\n", + "[2022-05-25 11:12:00,028] [INFO] Iteration 218, training loss: 16019.566974\n", + "[2022-05-25 11:12:00,421] [INFO] Iteration 219, training loss: 16018.074439\n", + "[2022-05-25 11:12:00,936] [INFO] Iteration 220, training loss: 16016.349677\n", + "[2022-05-25 11:12:01,466] [INFO] Iteration 221, training loss: 16015.042547\n", + "[2022-05-25 11:12:01,888] [INFO] Iteration 222, training loss: 16013.364620\n", + "[2022-05-25 11:12:02,155] [INFO] Iteration 223, training loss: 16010.716466\n", + "[2022-05-25 11:12:02,441] [INFO] Iteration 224, training loss: 16010.116564\n", + "[2022-05-25 11:12:02,679] [INFO] Iteration 225, training loss: 16007.955863\n", + "[2022-05-25 11:12:02,948] [INFO] Iteration 226, training loss: 16006.506357\n", + "[2022-05-25 11:12:03,204] [INFO] Iteration 227, training loss: 16004.629434\n", + "[2022-05-25 11:12:03,737] [INFO] Iteration 228, training loss: 16003.236044\n", + "[2022-05-25 11:12:04,204] [INFO] Iteration 229, training loss: 16001.747536\n", + "[2022-05-25 11:12:04,692] [INFO] Iteration 230, training loss: 16000.233494\n", + "[2022-05-25 11:12:05,067] [INFO] Iteration 231, training loss: 15999.037480\n", + "[2022-05-25 11:12:05,367] [INFO] Iteration 232, training loss: 15997.505407\n", + "[2022-05-25 11:12:05,607] [INFO] Iteration 233, training loss: 15996.409494\n", + "[2022-05-25 11:12:05,848] [INFO] Iteration 234, training loss: 15995.068001\n", + "[2022-05-25 11:12:06,091] [INFO] Iteration 235, training loss: 15994.169300\n", + "[2022-05-25 11:12:06,519] [INFO] Iteration 236, training loss: 15992.757029\n", + "[2022-05-25 11:12:07,041] [INFO] Iteration 237, training loss: 15992.011990\n", + "[2022-05-25 11:12:07,618] [INFO] Iteration 238, training loss: 15990.170182\n", + "[2022-05-25 11:12:08,002] [INFO] Iteration 239, training loss: 15988.520586\n", + "[2022-05-25 11:12:08,296] [INFO] Iteration 240, training loss: 15986.815254\n", + "[2022-05-25 11:12:08,534] [INFO] Iteration 241, training loss: 15986.510709\n", + "[2022-05-25 11:12:08,772] [INFO] Iteration 242, training loss: 15983.652645\n", + "[2022-05-25 11:12:09,019] [INFO] Iteration 243, training loss: 15981.683481\n", + "[2022-05-25 11:12:09,307] [INFO] Iteration 244, training loss: 15979.753516\n", + "[2022-05-25 11:12:09,625] [INFO] Iteration 245, training loss: 15978.152410\n", + "[2022-05-25 11:12:09,939] [INFO] Iteration 246, training loss: 15976.496280\n", + "[2022-05-25 11:12:10,246] [INFO] Iteration 247, training loss: 15975.191376\n", + "[2022-05-25 11:12:10,557] [INFO] Iteration 248, training loss: 15973.710700\n", + "[2022-05-25 11:12:10,898] [INFO] Iteration 249, training loss: 15972.452935\n", + "[2022-05-25 11:12:11,409] [INFO] Iteration 250, training loss: 15970.944863\n", + "[2022-05-25 11:12:11,919] [INFO] Iteration 251, training loss: 15969.265381\n", + "[2022-05-25 11:12:12,406] [INFO] Iteration 252, training loss: 15967.854511\n", + "[2022-05-25 11:12:12,679] [INFO] Iteration 253, training loss: 15966.512207\n", + "[2022-05-25 11:12:12,953] [INFO] Iteration 254, training loss: 15966.123713\n", + "[2022-05-25 11:12:13,264] [INFO] Iteration 255, training loss: 15964.258901\n", + "[2022-05-25 11:12:13,558] [INFO] Iteration 256, training loss: 15961.617960\n", + "[2022-05-25 11:12:13,923] [INFO] Iteration 257, training loss: 15960.058842\n", + "[2022-05-25 11:12:14,443] [INFO] Iteration 258, training loss: 15958.756236\n", + "[2022-05-25 11:12:14,948] [INFO] Iteration 259, training loss: 15956.748532\n", + "[2022-05-25 11:12:15,368] [INFO] Iteration 260, training loss: 15955.726445\n", + "[2022-05-25 11:12:15,616] [INFO] Iteration 261, training loss: 15953.544297\n", + "[2022-05-25 11:12:15,844] [INFO] Iteration 262, training loss: 15953.202867\n", + "[2022-05-25 11:12:16,080] [INFO] Iteration 263, training loss: 15950.784691\n", + "[2022-05-25 11:12:16,320] [INFO] Iteration 264, training loss: 15949.491400\n", + "[2022-05-25 11:12:16,568] [INFO] Iteration 265, training loss: 15948.351022\n", + "[2022-05-25 11:12:16,953] [INFO] Iteration 266, training loss: 15947.970308\n", + "[2022-05-25 11:12:17,462] [INFO] Iteration 267, training loss: 15945.165421\n", + "[2022-05-25 11:12:17,957] [INFO] Iteration 268, training loss: 15944.410272\n", + "[2022-05-25 11:12:18,358] [INFO] Iteration 269, training loss: 15942.318103\n", + "[2022-05-25 11:12:18,650] [INFO] Iteration 270, training loss: 15941.328155\n", + "[2022-05-25 11:12:18,909] [INFO] Iteration 271, training loss: 15939.837577\n", + "[2022-05-25 11:12:19,160] [INFO] Iteration 272, training loss: 15938.791373\n", + "[2022-05-25 11:12:19,391] [INFO] Iteration 273, training loss: 15937.538440\n", + "[2022-05-25 11:12:19,625] [INFO] Iteration 274, training loss: 15936.119289\n", + "[2022-05-25 11:12:19,969] [INFO] Iteration 275, training loss: 15935.164146\n", + "[2022-05-25 11:12:20,479] [INFO] Iteration 276, training loss: 15933.910733\n", + "[2022-05-25 11:12:20,960] [INFO] Iteration 277, training loss: 15933.174949\n", + "[2022-05-25 11:12:21,389] [INFO] Iteration 278, training loss: 15932.094664\n", + "[2022-05-25 11:12:21,633] [INFO] Iteration 279, training loss: 15931.261373\n", + "[2022-05-25 11:12:21,890] [INFO] Iteration 280, training loss: 15930.072220\n", + "[2022-05-25 11:12:22,141] [INFO] Iteration 281, training loss: 15929.422778\n", + "[2022-05-25 11:12:22,409] [INFO] Iteration 282, training loss: 15928.345593\n", + "[2022-05-25 11:12:22,650] [INFO] Iteration 283, training loss: 15927.626430\n", + "[2022-05-25 11:12:23,110] [INFO] Iteration 284, training loss: 15926.586786\n", + "[2022-05-25 11:12:23,599] [INFO] Iteration 285, training loss: 15925.782994\n", + "[2022-05-25 11:12:24,084] [INFO] Iteration 286, training loss: 15925.038118\n", + "[2022-05-25 11:12:24,436] [INFO] Iteration 287, training loss: 15924.102346\n", + "[2022-05-25 11:12:24,671] [INFO] Iteration 288, training loss: 15923.626276\n", + "[2022-05-25 11:12:24,901] [INFO] Iteration 289, training loss: 15922.735057\n", + "[2022-05-25 11:12:25,132] [INFO] Iteration 290, training loss: 15922.266867\n", + "[2022-05-25 11:12:25,361] [INFO] Iteration 291, training loss: 15921.451611\n", + "[2022-05-25 11:12:25,591] [INFO] Iteration 292, training loss: 15920.885878\n", + "[2022-05-25 11:12:25,820] [INFO] Iteration 293, training loss: 15919.883453\n", + "[2022-05-25 11:12:26,072] [INFO] Iteration 294, training loss: 15919.105341\n", + "[2022-05-25 11:12:26,308] [INFO] Iteration 295, training loss: 15918.347671\n", + "[2022-05-25 11:12:26,534] [INFO] Iteration 296, training loss: 15917.584495\n", + "[2022-05-25 11:12:26,763] [INFO] Iteration 297, training loss: 15916.729575\n", + "[2022-05-25 11:12:26,992] [INFO] Iteration 298, training loss: 15916.078679\n", + "[2022-05-25 11:12:27,221] [INFO] Iteration 299, training loss: 15915.453836\n", + "[2022-05-25 11:12:27,656] [INFO] Iteration 300, training loss: 15915.045246\n", + "[2022-05-25 11:12:28,156] [INFO] Iteration 301, training loss: 15914.257047\n", + "[2022-05-25 11:12:28,664] [INFO] Iteration 302, training loss: 15913.625050\n", + "[2022-05-25 11:12:29,002] [INFO] Iteration 303, training loss: 15913.040965\n", + "[2022-05-25 11:12:29,235] [INFO] Iteration 304, training loss: 15912.392620\n", + "[2022-05-25 11:12:29,467] [INFO] Iteration 305, training loss: 15911.433208\n", + "[2022-05-25 11:12:29,697] [INFO] Iteration 306, training loss: 15910.946324\n", + "[2022-05-25 11:12:29,933] [INFO] Iteration 307, training loss: 15909.998643\n", + "[2022-05-25 11:12:30,164] [INFO] Iteration 308, training loss: 15909.418334\n", + "[2022-05-25 11:12:30,586] [INFO] Iteration 309, training loss: 15908.769048\n", + "[2022-05-25 11:12:31,047] [INFO] Iteration 310, training loss: 15908.278537\n", + "[2022-05-25 11:12:31,513] [INFO] Iteration 311, training loss: 15907.283044\n", + "[2022-05-25 11:12:31,906] [INFO] Iteration 312, training loss: 15906.551210\n", + "[2022-05-25 11:12:32,143] [INFO] Iteration 313, training loss: 15905.722173\n", + "[2022-05-25 11:12:32,397] [INFO] Iteration 314, training loss: 15905.041109\n", + "[2022-05-25 11:12:32,641] [INFO] Iteration 315, training loss: 15904.277231\n", + "[2022-05-25 11:12:32,887] [INFO] Iteration 316, training loss: 15903.451508\n", + "[2022-05-25 11:12:33,121] [INFO] Iteration 317, training loss: 15902.896182\n", + "[2022-05-25 11:12:33,578] [INFO] Iteration 318, training loss: 15902.083112\n", + "[2022-05-25 11:12:34,080] [INFO] Iteration 319, training loss: 15901.583839\n", + "[2022-05-25 11:12:34,568] [INFO] Iteration 320, training loss: 15900.853213\n", + "[2022-05-25 11:12:34,895] [INFO] Iteration 321, training loss: 15900.307778\n", + "[2022-05-25 11:12:35,146] [INFO] Iteration 322, training loss: 15899.544023\n", + "[2022-05-25 11:12:35,382] [INFO] Iteration 323, training loss: 15898.924543\n", + "[2022-05-25 11:12:35,662] [INFO] Iteration 324, training loss: 15898.237670\n", + "[2022-05-25 11:12:35,911] [INFO] Iteration 325, training loss: 15897.476502\n", + "[2022-05-25 11:12:36,153] [INFO] Iteration 326, training loss: 15896.924952\n", + "[2022-05-25 11:12:36,402] [INFO] Iteration 327, training loss: 15896.019203\n", + "[2022-05-25 11:12:36,631] [INFO] Iteration 328, training loss: 15895.210599\n", + "[2022-05-25 11:12:36,880] [INFO] Iteration 329, training loss: 15894.517776\n", + "[2022-05-25 11:12:37,117] [INFO] Iteration 330, training loss: 15893.796477\n", + "[2022-05-25 11:12:37,353] [INFO] Iteration 331, training loss: 15893.038794\n", + "[2022-05-25 11:12:37,582] [INFO] Iteration 332, training loss: 15892.167991\n", + "[2022-05-25 11:12:37,823] [INFO] Iteration 333, training loss: 15891.387023\n", + "[2022-05-25 11:12:38,107] [INFO] Iteration 334, training loss: 15890.588742\n", + "[2022-05-25 11:12:38,371] [INFO] Iteration 335, training loss: 15889.826479\n", + "[2022-05-25 11:12:38,616] [INFO] Iteration 336, training loss: 15889.122733\n", + "[2022-05-25 11:12:38,845] [INFO] Iteration 337, training loss: 15888.348937\n", + "[2022-05-25 11:12:39,079] [INFO] Iteration 338, training loss: 15887.575483\n", + "[2022-05-25 11:12:39,421] [INFO] Iteration 339, training loss: 15886.804180\n", + "[2022-05-25 11:12:39,891] [INFO] Iteration 340, training loss: 15886.066320\n", + "[2022-05-25 11:12:40,353] [INFO] Iteration 341, training loss: 15885.376614\n", + "[2022-05-25 11:12:40,813] [INFO] Iteration 342, training loss: 15884.629274\n", + "[2022-05-25 11:12:41,054] [INFO] Iteration 343, training loss: 15883.936029\n", + "[2022-05-25 11:12:41,289] [INFO] Iteration 344, training loss: 15883.129301\n", + "[2022-05-25 11:12:41,539] [INFO] Iteration 345, training loss: 15882.643871\n", + "[2022-05-25 11:12:41,800] [INFO] Iteration 346, training loss: 15881.872996\n", + "[2022-05-25 11:12:42,052] [INFO] Iteration 347, training loss: 15881.236166\n", + "[2022-05-25 11:12:42,430] [INFO] Iteration 348, training loss: 15880.633027\n", + "[2022-05-25 11:12:42,931] [INFO] Iteration 349, training loss: 15880.159816\n", + "[2022-05-25 11:12:43,409] [INFO] Iteration 350, training loss: 15879.308921\n", + "[2022-05-25 11:12:43,818] [INFO] Iteration 351, training loss: 15878.756788\n", + "[2022-05-25 11:12:44,061] [INFO] Iteration 352, training loss: 15877.956870\n", + "[2022-05-25 11:12:44,310] [INFO] Iteration 353, training loss: 15877.494687\n", + "[2022-05-25 11:12:44,544] [INFO] Iteration 354, training loss: 15876.671520\n", + "[2022-05-25 11:12:44,794] [INFO] Iteration 355, training loss: 15876.254035\n", + "[2022-05-25 11:12:45,042] [INFO] Iteration 356, training loss: 15875.500097\n", + "[2022-05-25 11:12:45,322] [INFO] Iteration 357, training loss: 15874.989559\n", + "[2022-05-25 11:12:45,806] [INFO] Iteration 358, training loss: 15874.346585\n", + "[2022-05-25 11:12:46,278] [INFO] Iteration 359, training loss: 15873.863443\n", + "[2022-05-25 11:12:46,737] [INFO] Iteration 360, training loss: 15873.252417\n", + "[2022-05-25 11:12:47,055] [INFO] Iteration 361, training loss: 15872.831775\n", + "[2022-05-25 11:12:47,315] [INFO] Iteration 362, training loss: 15872.257303\n", + "[2022-05-25 11:12:47,568] [INFO] Iteration 363, training loss: 15871.862222\n", + "[2022-05-25 11:12:47,807] [INFO] Iteration 364, training loss: 15871.425272\n", + "[2022-05-25 11:12:48,097] [INFO] Iteration 365, training loss: 15871.032098\n", + "[2022-05-25 11:12:48,510] [INFO] Iteration 366, training loss: 15870.677433\n", + "[2022-05-25 11:12:48,999] [INFO] Iteration 367, training loss: 15870.325483\n", + "[2022-05-25 11:12:49,499] [INFO] Iteration 368, training loss: 15870.073440\n", + "[2022-05-25 11:12:49,877] [INFO] Iteration 369, training loss: 15869.663813\n", + "[2022-05-25 11:12:50,115] [INFO] Iteration 370, training loss: 15869.481921\n", + "[2022-05-25 11:12:50,344] [INFO] Iteration 371, training loss: 15868.824114\n", + "[2022-05-25 11:12:50,573] [INFO] Iteration 372, training loss: 15868.676411\n", + "[2022-05-25 11:12:50,801] [INFO] Iteration 373, training loss: 15868.076115\n", + "[2022-05-25 11:12:51,041] [INFO] Iteration 374, training loss: 15867.891314\n", + "[2022-05-25 11:12:51,269] [INFO] Iteration 375, training loss: 15867.282625\n", + "[2022-05-25 11:12:51,757] [INFO] Iteration 376, training loss: 15867.202255\n", + "[2022-05-25 11:12:52,292] [INFO] Iteration 377, training loss: 15866.618565\n", + "[2022-05-25 11:12:52,787] [INFO] Iteration 378, training loss: 15866.492524\n", + "[2022-05-25 11:12:53,065] [INFO] Iteration 379, training loss: 15866.017816\n", + "[2022-05-25 11:12:53,314] [INFO] Iteration 380, training loss: 15865.908283\n", + "[2022-05-25 11:12:53,321] [INFO] Terminated with the stopping criteria\n", + "[2022-05-25 11:12:53,321] [INFO] Saving model\n" ] } ], "source": [ - "model = chaine.train(sentences, labels, verbose=0, optimize_hyperparameters=True)" + "model = chaine.train(train_sentences, train_labels, verbose=0, optimize_hyperparameters=True)" ] }, { @@ -729,22 +930,22 @@ "text": [ " precision recall f1-score support\n", "\n", - " LOC 0.97 0.95 0.96 1668\n", - " MISC 0.97 0.87 0.91 702\n", - " ORG 0.94 0.93 0.94 1661\n", - " PER 0.97 0.96 0.96 1617\n", + " LOC 0.85 0.79 0.82 1668\n", + " MISC 0.80 0.70 0.75 702\n", + " ORG 0.77 0.64 0.70 1661\n", + " PER 0.80 0.84 0.82 1617\n", "\n", - " micro avg 0.96 0.94 0.95 5648\n", - " macro avg 0.96 0.93 0.94 5648\n", - "weighted avg 0.96 0.94 0.95 5648\n", + " micro avg 0.81 0.75 0.78 5648\n", + " macro avg 0.80 0.74 0.77 5648\n", + "weighted avg 0.81 0.75 0.77 5648\n", "\n" ] } ], "source": [ - "predictions = model.predict(sentences)\n", + "predictions = model.predict(test_sentences)\n", "\n", - "print(classification_report(labels, predictions))" + "print(classification_report(test_labels, predictions))" ] }, { @@ -789,64 +990,64 @@ " \n", " \n", " \n", - " 12\n", - " B-PER\n", - " I-PER\n", - " 8.318353\n", + " 6\n", + " B-ORG\n", + " I-ORG\n", + " 5.480503\n", " \n", " \n", - " 30\n", - " B-ORG\n", + " 10\n", + " O\n", + " O\n", + " 5.142529\n", + " \n", + " \n", + " 60\n", " I-ORG\n", - " 7.168033\n", + " I-ORG\n", + " 5.054006\n", + " \n", + " \n", + " 31\n", + " B-PER\n", + " I-PER\n", + " 4.621046\n", " \n", " \n", - " 22\n", + " 25\n", " B-MISC\n", " I-MISC\n", - " 6.609091\n", + " 4.454587\n", " \n", " \n", - " 26\n", - " I-MISC\n", - " I-MISC\n", - " 6.177694\n", + " 11\n", + " O\n", + " B-MISC\n", + " 4.309001\n", " \n", " \n", - " 34\n", - " I-ORG\n", - " I-ORG\n", - " 6.171870\n", + " 70\n", + " I-MISC\n", + " I-MISC\n", + " 4.072832\n", " \n", " \n", - " 0\n", - " O\n", + " 12\n", " O\n", - " 5.502018\n", + " B-PER\n", + " 3.984640\n", " \n", " \n", - " 8\n", + " 53\n", " B-LOC\n", " I-LOC\n", - " 5.196033\n", + " 3.686581\n", " \n", " \n", - " 18\n", + " 80\n", " I-LOC\n", " I-LOC\n", - " 4.680722\n", - " \n", - " \n", - " 3\n", - " O\n", - " B-MISC\n", - " 4.323212\n", - " \n", - " \n", - " 15\n", - " I-PER\n", - " I-PER\n", - " 4.204643\n", + " 3.629553\n", " \n", " \n", "\n", @@ -854,16 +1055,16 @@ ], "text/plain": [ " from to weight\n", - "12 B-PER I-PER 8.318353\n", - "30 B-ORG I-ORG 7.168033\n", - "22 B-MISC I-MISC 6.609091\n", - "26 I-MISC I-MISC 6.177694\n", - "34 I-ORG I-ORG 6.171870\n", - "0 O O 5.502018\n", - "8 B-LOC I-LOC 5.196033\n", - "18 I-LOC I-LOC 4.680722\n", - "3 O B-MISC 4.323212\n", - "15 I-PER I-PER 4.204643" + "6 B-ORG I-ORG 5.480503\n", + "10 O O 5.142529\n", + "60 I-ORG I-ORG 5.054006\n", + "31 B-PER I-PER 4.621046\n", + "25 B-MISC I-MISC 4.454587\n", + "11 O B-MISC 4.309001\n", + "70 I-MISC I-MISC 4.072832\n", + "12 O B-PER 3.984640\n", + "53 B-LOC I-LOC 3.686581\n", + "80 I-LOC I-LOC 3.629553" ] }, "execution_count": 12, @@ -910,81 +1111,81 @@ " \n", " \n", " \n", - " 4353\n", - " token[-2:]:0M\n", + " 405\n", + " EOS\n", " O\n", - " 9.405752\n", + " 4.452106\n", " \n", " \n", - " 4354\n", - " token[-2:]:5M\n", + " 58\n", + " BOS\n", " O\n", - " 8.817209\n", + " 3.263974\n", " \n", " \n", - " 216\n", - " +1:token.lower():1996-12-06\n", - " B-LOC\n", - " 5.713073\n", + " 751\n", + " token[-3:]:day\n", + " O\n", + " 2.879297\n", " \n", " \n", - " 3807\n", - " token.lower():painewebber\n", - " B-ORG\n", - " 5.619434\n", + " 142519\n", + " token[-2:]:5M\n", + " O\n", + " 2.856290\n", " \n", " \n", - " 217\n", - " +1:token.lower():1996-12-06\n", - " I-LOC\n", - " 5.243976\n", + " 142632\n", + " token[-2:]:0M\n", + " O\n", + " 2.812777\n", " \n", " \n", - " 3704\n", - " +1:token.lower():exxon\n", - " O\n", - " 5.152197\n", + " 39882\n", + " -1:token.lower():v\n", + " B-ORG\n", + " 2.672666\n", " \n", " \n", - " 1013\n", - " token.lower():italy\n", + " 4651\n", + " -1:token.lower():at\n", " B-LOC\n", - " 5.052394\n", + " 2.664489\n", " \n", " \n", - " 168\n", - " EOS\n", + " 31888\n", + " token[-2:]:I\n", " O\n", - " 4.993690\n", + " 2.658717\n", " \n", " \n", - " 1605\n", - " -1:token.lower():b\n", - " B-PER\n", - " 4.895346\n", + " 31879\n", + " token[-3:]:I\n", + " O\n", + " 2.658717\n", " \n", " \n", - " 3233\n", - " token.lower():trans-atlantic\n", - " B-MISC\n", - " 4.789043\n", + " 76909\n", + " token.lower():clinton\n", + " B-PER\n", + " 2.546819\n", " \n", " \n", "\n", "" ], "text/plain": [ - " feature label weight\n", - "4353 token[-2:]:0M O 9.405752\n", - "4354 token[-2:]:5M O 8.817209\n", - "216 +1:token.lower():1996-12-06 B-LOC 5.713073\n", - "3807 token.lower():painewebber B-ORG 5.619434\n", - "217 +1:token.lower():1996-12-06 I-LOC 5.243976\n", - "3704 +1:token.lower():exxon O 5.152197\n", - "1013 token.lower():italy B-LOC 5.052394\n", - "168 EOS O 4.993690\n", - "1605 -1:token.lower():b B-PER 4.895346\n", - "3233 token.lower():trans-atlantic B-MISC 4.789043" + " feature label weight\n", + "405 EOS O 4.452106\n", + "58 BOS O 3.263974\n", + "751 token[-3:]:day O 2.879297\n", + "142519 token[-2:]:5M O 2.856290\n", + "142632 token[-2:]:0M O 2.812777\n", + "39882 -1:token.lower():v B-ORG 2.672666\n", + "4651 -1:token.lower():at B-LOC 2.664489\n", + "31888 token[-2:]:I O 2.658717\n", + "31879 token[-3:]:I O 2.658717\n", + "76909 token.lower():clinton B-PER 2.546819" ] }, "execution_count": 13,