{ "best_metric": null, "best_model_checkpoint": null, "epoch": 100.0, "eval_steps": 500, "global_step": 10600, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 1.0568287372589111, "learning_rate": 4.9500000000000004e-05, "loss": 0.9528, "step": 106 }, { "epoch": 1.0, "eval_LOCATION_f1": 0.0, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.0, "eval_LOCATION_recall": 0.0, "eval_ORGANIZATION_f1": 0.0, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.012738853503184716, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.25, "eval_PERSON_recall": 0.006535947712418301, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 31, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.6222904920578003, "eval_overall_accuracy": 0.8357691354966559, "eval_overall_f1": 0.005698005698005698, "eval_overall_precision": 0.2, "eval_overall_recall": 0.002890173410404624, "eval_runtime": 0.4063, "eval_samples_per_second": 460.253, "eval_steps_per_second": 7.384, "step": 106 }, { "epoch": 2.0, "grad_norm": 1.066505789756775, "learning_rate": 4.9e-05, "loss": 0.5159, "step": 212 }, { "epoch": 2.0, "eval_LOCATION_f1": 0.45312499999999994, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.4915254237288136, "eval_LOCATION_recall": 0.42028985507246375, "eval_ORGANIZATION_f1": 0.06060606060606061, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.07894736842105263, "eval_ORGANIZATION_recall": 0.04918032786885246, "eval_PERSON_f1": 0.5912596401028277, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.4872881355932203, "eval_PERSON_recall": 0.7516339869281046, "eval_QUANTITY_f1": 0.03773584905660377, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.047619047619047616, "eval_QUANTITY_recall": 0.03125, "eval_TIME_f1": 0.5405405405405406, "eval_TIME_number": 31, "eval_TIME_precision": 0.46511627906976744, "eval_TIME_recall": 0.6451612903225806, "eval_loss": 0.36079517006874084, "eval_overall_accuracy": 0.8981917265296012, "eval_overall_f1": 0.45222072678331093, "eval_overall_precision": 0.42317380352644834, "eval_overall_recall": 0.48554913294797686, "eval_runtime": 0.4072, "eval_samples_per_second": 459.196, "eval_steps_per_second": 7.367, "step": 212 }, { "epoch": 3.0, "grad_norm": 1.205767273902893, "learning_rate": 4.85e-05, "loss": 0.297, "step": 318 }, { "epoch": 3.0, "eval_LOCATION_f1": 0.6946107784431138, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.5918367346938775, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.513888888888889, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.4457831325301205, "eval_ORGANIZATION_recall": 0.6065573770491803, "eval_PERSON_f1": 0.8414634146341464, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7885714285714286, "eval_PERSON_recall": 0.9019607843137255, "eval_QUANTITY_f1": 0.5866666666666667, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5116279069767442, "eval_QUANTITY_recall": 0.6875, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.19271065294742584, "eval_overall_accuracy": 0.940797621996532, "eval_overall_f1": 0.7249357326478149, "eval_overall_precision": 0.6527777777777778, "eval_overall_recall": 0.815028901734104, "eval_runtime": 0.4062, "eval_samples_per_second": 460.369, "eval_steps_per_second": 7.386, "step": 318 }, { "epoch": 4.0, "grad_norm": 1.6758396625518799, "learning_rate": 4.8e-05, "loss": 0.1907, "step": 424 }, { "epoch": 4.0, "eval_LOCATION_f1": 0.7142857142857143, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6060606060606061, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.624113475177305, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.55, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.8685015290519879, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8160919540229885, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.5952380952380952, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.4807692307692308, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7123287671232876, "eval_TIME_number": 31, "eval_TIME_precision": 0.6190476190476191, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.17424248158931732, "eval_overall_accuracy": 0.9437701263314342, "eval_overall_f1": 0.7490542244640607, "eval_overall_precision": 0.6644295302013423, "eval_overall_recall": 0.8583815028901735, "eval_runtime": 0.4062, "eval_samples_per_second": 460.371, "eval_steps_per_second": 7.386, "step": 424 }, { "epoch": 5.0, "grad_norm": 1.1901781558990479, "learning_rate": 4.75e-05, "loss": 0.1593, "step": 530 }, { "epoch": 5.0, "eval_LOCATION_f1": 0.728476821192053, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6707317073170732, "eval_LOCATION_recall": 0.7971014492753623, "eval_ORGANIZATION_f1": 0.6573426573426574, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.573170731707317, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8703703703703703, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8245614035087719, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8709677419354839, "eval_TIME_number": 31, "eval_TIME_precision": 0.8709677419354839, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.13567817211151123, "eval_overall_accuracy": 0.9549170175873173, "eval_overall_f1": 0.7903871829105475, "eval_overall_precision": 0.7344913151364765, "eval_overall_recall": 0.8554913294797688, "eval_runtime": 0.4057, "eval_samples_per_second": 460.888, "eval_steps_per_second": 7.394, "step": 530 }, { "epoch": 6.0, "grad_norm": 0.41255536675453186, "learning_rate": 4.7e-05, "loss": 0.1401, "step": 636 }, { "epoch": 6.0, "eval_LOCATION_f1": 0.720496894409938, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6304347826086957, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5783132530120482, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8909657320872275, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8511904761904762, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7397260273972602, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6585365853658537, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7941176470588235, "eval_TIME_number": 31, "eval_TIME_precision": 0.7297297297297297, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1358344703912735, "eval_overall_accuracy": 0.9554124349764677, "eval_overall_f1": 0.7900912646675358, "eval_overall_precision": 0.7197149643705463, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.4073, "eval_samples_per_second": 459.153, "eval_steps_per_second": 7.366, "step": 636 }, { "epoch": 7.0, "grad_norm": 0.6113700270652771, "learning_rate": 4.6500000000000005e-05, "loss": 0.1309, "step": 742 }, { "epoch": 7.0, "eval_LOCATION_f1": 0.713375796178344, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6363636363636364, "eval_LOCATION_recall": 0.8115942028985508, "eval_ORGANIZATION_f1": 0.6853146853146853, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5975609756097561, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8875000000000001, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8502994011976048, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7027027027027026, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6190476190476191, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.13016657531261444, "eval_overall_accuracy": 0.9571463958384939, "eval_overall_f1": 0.7915567282321899, "eval_overall_precision": 0.7281553398058253, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.4064, "eval_samples_per_second": 460.124, "eval_steps_per_second": 7.382, "step": 742 }, { "epoch": 8.0, "grad_norm": 0.6097145080566406, "learning_rate": 4.600000000000001e-05, "loss": 0.1197, "step": 848 }, { "epoch": 8.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6950354609929078, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6125, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8832807570977917, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8536585365853658, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7536231884057972, "eval_TIME_number": 31, "eval_TIME_precision": 0.6842105263157895, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1251688003540039, "eval_overall_accuracy": 0.9581372306167947, "eval_overall_f1": 0.8080536912751678, "eval_overall_precision": 0.7543859649122807, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.4062, "eval_samples_per_second": 460.399, "eval_steps_per_second": 7.386, "step": 848 }, { "epoch": 9.0, "grad_norm": 1.3508681058883667, "learning_rate": 4.55e-05, "loss": 0.1102, "step": 954 }, { "epoch": 9.0, "eval_LOCATION_f1": 0.7468354430379747, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6629213483146067, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6969696969696969, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.647887323943662, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8909657320872275, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8511904761904762, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.823529411764706, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7777777777777778, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.782608695652174, "eval_TIME_number": 31, "eval_TIME_precision": 0.7105263157894737, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.13306157290935516, "eval_overall_accuracy": 0.9588803567005202, "eval_overall_f1": 0.8101604278074866, "eval_overall_precision": 0.753731343283582, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.4057, "eval_samples_per_second": 460.913, "eval_steps_per_second": 7.394, "step": 954 }, { "epoch": 10.0, "grad_norm": 1.0420314073562622, "learning_rate": 4.5e-05, "loss": 0.1078, "step": 1060 }, { "epoch": 10.0, "eval_LOCATION_f1": 0.8, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7631578947368421, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6466165413533835, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5972222222222222, "eval_ORGANIZATION_recall": 0.7049180327868853, "eval_PERSON_f1": 0.9050632911392406, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8773006134969326, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.11589627712965012, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.815934065934066, "eval_overall_precision": 0.7774869109947644, "eval_overall_recall": 0.8583815028901735, "eval_runtime": 0.4069, "eval_samples_per_second": 459.57, "eval_steps_per_second": 7.373, "step": 1060 }, { "epoch": 11.0, "grad_norm": 0.47683292627334595, "learning_rate": 4.4500000000000004e-05, "loss": 0.1003, "step": 1166 }, { "epoch": 11.0, "eval_LOCATION_f1": 0.7682119205298014, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7073170731707317, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6865671641791045, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.89375, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8562874251497006, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7714285714285714, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7105263157894737, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7714285714285716, "eval_TIME_number": 31, "eval_TIME_precision": 0.6923076923076923, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.12274792045354843, "eval_overall_accuracy": 0.9591280653950953, "eval_overall_f1": 0.8080536912751678, "eval_overall_precision": 0.7543859649122807, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.4044, "eval_samples_per_second": 462.406, "eval_steps_per_second": 7.418, "step": 1166 }, { "epoch": 12.0, "grad_norm": 1.9095113277435303, "learning_rate": 4.4000000000000006e-05, "loss": 0.0953, "step": 1272 }, { "epoch": 12.0, "eval_LOCATION_f1": 0.8, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7631578947368421, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6515151515151515, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6056338028169014, "eval_ORGANIZATION_recall": 0.7049180327868853, "eval_PERSON_f1": 0.9009584664536741, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.88125, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12356565147638321, "eval_overall_accuracy": 0.9581372306167947, "eval_overall_f1": 0.8110344827586207, "eval_overall_precision": 0.7757255936675461, "eval_overall_recall": 0.8497109826589595, "eval_runtime": 0.4041, "eval_samples_per_second": 462.759, "eval_steps_per_second": 7.424, "step": 1272 }, { "epoch": 13.0, "grad_norm": 0.6649303436279297, "learning_rate": 4.35e-05, "loss": 0.0906, "step": 1378 }, { "epoch": 13.0, "eval_LOCATION_f1": 0.7549668874172186, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6951219512195121, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.7272727272727272, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6341463414634146, "eval_ORGANIZATION_recall": 0.8524590163934426, "eval_PERSON_f1": 0.9034267912772587, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8630952380952381, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8059701492537312, "eval_TIME_number": 31, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.12967564165592194, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.822429906542056, "eval_overall_precision": 0.7642679900744417, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.4045, "eval_samples_per_second": 462.351, "eval_steps_per_second": 7.417, "step": 1378 }, { "epoch": 14.0, "grad_norm": 1.123289704322815, "learning_rate": 4.3e-05, "loss": 0.0875, "step": 1484 }, { "epoch": 14.0, "eval_LOCATION_f1": 0.7891156462585034, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7435897435897436, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6928104575163399, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5760869565217391, "eval_ORGANIZATION_recall": 0.8688524590163934, "eval_PERSON_f1": 0.9090909090909091, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8734939759036144, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.75, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.675, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7222222222222222, "eval_TIME_number": 31, "eval_TIME_precision": 0.6341463414634146, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1440243422985077, "eval_overall_accuracy": 0.9546693088927422, "eval_overall_f1": 0.8099606815203145, "eval_overall_precision": 0.7410071942446043, "eval_overall_recall": 0.8930635838150289, "eval_runtime": 0.4035, "eval_samples_per_second": 463.475, "eval_steps_per_second": 7.435, "step": 1484 }, { "epoch": 15.0, "grad_norm": 0.35692471265792847, "learning_rate": 4.25e-05, "loss": 0.0851, "step": 1590 }, { "epoch": 15.0, "eval_LOCATION_f1": 0.7972972972972974, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7468354430379747, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6715328467153285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6052631578947368, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8930817610062893, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8606060606060606, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7714285714285714, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7105263157894737, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13237613439559937, "eval_overall_accuracy": 0.9573941045330691, "eval_overall_f1": 0.8130081300813009, "eval_overall_precision": 0.7653061224489796, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.4054, "eval_samples_per_second": 461.222, "eval_steps_per_second": 7.399, "step": 1590 }, { "epoch": 16.0, "grad_norm": 0.7279097437858582, "learning_rate": 4.2e-05, "loss": 0.0757, "step": 1696 }, { "epoch": 16.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7142857142857143, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6329113924050633, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7714285714285714, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7105263157894737, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1373172551393509, "eval_overall_accuracy": 0.9593757740896706, "eval_overall_f1": 0.8232118758434549, "eval_overall_precision": 0.7721518987341772, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4031, "eval_samples_per_second": 463.937, "eval_steps_per_second": 7.443, "step": 1696 }, { "epoch": 17.0, "grad_norm": 0.11543399840593338, "learning_rate": 4.15e-05, "loss": 0.0752, "step": 1802 }, { "epoch": 17.0, "eval_LOCATION_f1": 0.7483870967741935, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6744186046511628, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6811594202898551, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6103896103896104, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9015873015873016, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8765432098765432, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7826086956521738, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7297297297297297, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12998123466968536, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8118279569892471, "eval_overall_precision": 0.7587939698492462, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.4006, "eval_samples_per_second": 466.782, "eval_steps_per_second": 7.488, "step": 1802 }, { "epoch": 18.0, "grad_norm": 0.6546134948730469, "learning_rate": 4.1e-05, "loss": 0.0707, "step": 1908 }, { "epoch": 18.0, "eval_LOCATION_f1": 0.7972972972972974, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7468354430379747, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6461538461538462, "eval_ORGANIZATION_recall": 0.6885245901639344, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7826086956521738, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7297297297297297, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1343889832496643, "eval_overall_accuracy": 0.9591280653950953, "eval_overall_f1": 0.8181818181818181, "eval_overall_precision": 0.781578947368421, "eval_overall_recall": 0.8583815028901735, "eval_runtime": 0.4031, "eval_samples_per_second": 463.911, "eval_steps_per_second": 7.442, "step": 1908 }, { "epoch": 19.0, "grad_norm": 1.4081445932388306, "learning_rate": 4.05e-05, "loss": 0.0692, "step": 2014 }, { "epoch": 19.0, "eval_LOCATION_f1": 0.7945205479452054, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7532467532467533, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.7058823529411764, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.64, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8930817610062893, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8606060606060606, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.8115942028985507, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7567567567567568, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1338239461183548, "eval_overall_accuracy": 0.9601189001733961, "eval_overall_f1": 0.8228882833787465, "eval_overall_precision": 0.7783505154639175, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.4025, "eval_samples_per_second": 464.628, "eval_steps_per_second": 7.454, "step": 2014 }, { "epoch": 20.0, "grad_norm": 0.6560825705528259, "learning_rate": 4e-05, "loss": 0.0647, "step": 2120 }, { "epoch": 20.0, "eval_LOCATION_f1": 0.8082191780821918, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7662337662337663, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7058823529411764, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.64, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9056603773584905, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8727272727272727, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1284184455871582, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8333333333333334, "eval_overall_precision": 0.7901554404145078, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4032, "eval_samples_per_second": 463.739, "eval_steps_per_second": 7.44, "step": 2120 }, { "epoch": 21.0, "grad_norm": 1.2687212228775024, "learning_rate": 3.9500000000000005e-05, "loss": 0.0611, "step": 2226 }, { "epoch": 21.0, "eval_LOCATION_f1": 0.7549668874172186, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6951219512195121, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.689655172413793, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5952380952380952, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8902821316614421, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8554216867469879, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7123287671232876, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6341463414634146, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7647058823529411, "eval_TIME_number": 31, "eval_TIME_precision": 0.7027027027027027, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15563081204891205, "eval_overall_accuracy": 0.9521922219469904, "eval_overall_f1": 0.7962962962962963, "eval_overall_precision": 0.7341463414634146, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.4026, "eval_samples_per_second": 464.462, "eval_steps_per_second": 7.451, "step": 2226 }, { "epoch": 22.0, "grad_norm": 0.9706618189811707, "learning_rate": 3.9000000000000006e-05, "loss": 0.0626, "step": 2332 }, { "epoch": 22.0, "eval_LOCATION_f1": 0.7763157894736842, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7108433734939759, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7083333333333334, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6144578313253012, "eval_ORGANIZATION_recall": 0.8360655737704918, "eval_PERSON_f1": 0.9119496855345912, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8787878787878788, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7647058823529411, "eval_TIME_number": 31, "eval_TIME_precision": 0.7027027027027027, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1527089774608612, "eval_overall_accuracy": 0.9583849393113698, "eval_overall_f1": 0.8175765645805592, "eval_overall_precision": 0.7580246913580246, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.4032, "eval_samples_per_second": 463.751, "eval_steps_per_second": 7.44, "step": 2332 }, { "epoch": 23.0, "grad_norm": 0.8338723182678223, "learning_rate": 3.85e-05, "loss": 0.0588, "step": 2438 }, { "epoch": 23.0, "eval_LOCATION_f1": 0.8082191780821918, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7662337662337663, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6906474820143885, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6153846153846154, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9137380191693291, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.89375, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13671712577342987, "eval_overall_accuracy": 0.9611097349516968, "eval_overall_f1": 0.831275720164609, "eval_overall_precision": 0.7911227154046997, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.4037, "eval_samples_per_second": 463.194, "eval_steps_per_second": 7.431, "step": 2438 }, { "epoch": 24.0, "grad_norm": 1.8579022884368896, "learning_rate": 3.8e-05, "loss": 0.0549, "step": 2544 }, { "epoch": 24.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7164179104477612, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6575342465753424, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9009584664536741, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.88125, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.8358208955223881, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.8, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14114215970039368, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8324175824175825, "eval_overall_precision": 0.7931937172774869, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.4057, "eval_samples_per_second": 460.959, "eval_steps_per_second": 7.395, "step": 2544 }, { "epoch": 25.0, "grad_norm": 0.7675341963768005, "learning_rate": 3.7500000000000003e-05, "loss": 0.0524, "step": 2650 }, { "epoch": 25.0, "eval_LOCATION_f1": 0.7682119205298014, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7073170731707317, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.7050359712230215, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6282051282051282, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.9056603773584905, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8727272727272727, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1436871439218521, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8232118758434549, "eval_overall_precision": 0.7721518987341772, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4021, "eval_samples_per_second": 465.093, "eval_steps_per_second": 7.461, "step": 2650 }, { "epoch": 26.0, "grad_norm": 0.9390576481819153, "learning_rate": 3.7e-05, "loss": 0.0526, "step": 2756 }, { "epoch": 26.0, "eval_LOCATION_f1": 0.802721088435374, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7564102564102564, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6666666666666667, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6081081081081081, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9056603773584905, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8727272727272727, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.13506074249744415, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8224043715846995, "eval_overall_precision": 0.7797927461139896, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.4036, "eval_samples_per_second": 463.371, "eval_steps_per_second": 7.434, "step": 2756 }, { "epoch": 27.0, "grad_norm": 0.5190781354904175, "learning_rate": 3.65e-05, "loss": 0.0487, "step": 2862 }, { "epoch": 27.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6911764705882353, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6266666666666667, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9050632911392406, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8773006134969326, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14294296503067017, "eval_overall_accuracy": 0.9611097349516968, "eval_overall_f1": 0.8256130790190735, "eval_overall_precision": 0.7809278350515464, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.4031, "eval_samples_per_second": 463.951, "eval_steps_per_second": 7.443, "step": 2862 }, { "epoch": 28.0, "grad_norm": 1.7428516149520874, "learning_rate": 3.6e-05, "loss": 0.0476, "step": 2968 }, { "epoch": 28.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7142857142857143, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7022900763358779, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6571428571428571, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7941176470588235, "eval_TIME_number": 31, "eval_TIME_precision": 0.7297297297297297, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14721077680587769, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.8233695652173912, "eval_overall_precision": 0.7769230769230769, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.4015, "eval_samples_per_second": 465.726, "eval_steps_per_second": 7.472, "step": 2968 }, { "epoch": 29.0, "grad_norm": 1.087302803993225, "learning_rate": 3.55e-05, "loss": 0.0462, "step": 3074 }, { "epoch": 29.0, "eval_LOCATION_f1": 0.7733333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7160493827160493, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.7083333333333334, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6144578313253012, "eval_ORGANIZATION_recall": 0.8360655737704918, "eval_PERSON_f1": 0.9216300940438872, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8855421686746988, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8059701492537312, "eval_TIME_number": 31, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.16020502150058746, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8299866131191432, "eval_overall_precision": 0.773067331670823, "eval_overall_recall": 0.8959537572254336, "eval_runtime": 0.4026, "eval_samples_per_second": 464.429, "eval_steps_per_second": 7.451, "step": 3074 }, { "epoch": 30.0, "grad_norm": 0.6619191765785217, "learning_rate": 3.5e-05, "loss": 0.0444, "step": 3180 }, { "epoch": 30.0, "eval_LOCATION_f1": 0.8137931034482757, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7763157894736842, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.620253164556962, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.9216300940438872, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8855421686746988, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.15210027992725372, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8408163265306122, "eval_overall_precision": 0.794344473007712, "eval_overall_recall": 0.8930635838150289, "eval_runtime": 0.4053, "eval_samples_per_second": 461.371, "eval_steps_per_second": 7.402, "step": 3180 }, { "epoch": 31.0, "grad_norm": 0.4051073491573334, "learning_rate": 3.45e-05, "loss": 0.0446, "step": 3286 }, { "epoch": 31.0, "eval_LOCATION_f1": 0.7702702702702703, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7215189873417721, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.7, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.620253164556962, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.9119496855345912, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8787878787878788, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.15809132158756256, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.8276797829036635, "eval_overall_precision": 0.7800511508951407, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.403, "eval_samples_per_second": 464.077, "eval_steps_per_second": 7.445, "step": 3286 }, { "epoch": 32.0, "grad_norm": 0.33254846930503845, "learning_rate": 3.4000000000000007e-05, "loss": 0.0406, "step": 3392 }, { "epoch": 32.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6766917293233082, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.625, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9269841269841269, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9012345679012346, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.15239284932613373, "eval_overall_accuracy": 0.9623482784245727, "eval_overall_f1": 0.8418156808803301, "eval_overall_precision": 0.8031496062992126, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.4004, "eval_samples_per_second": 466.996, "eval_steps_per_second": 7.492, "step": 3392 }, { "epoch": 33.0, "grad_norm": 0.20717833936214447, "learning_rate": 3.35e-05, "loss": 0.0411, "step": 3498 }, { "epoch": 33.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6956521739130435, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6233766233766234, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14470325410366058, "eval_overall_accuracy": 0.9638345305920237, "eval_overall_f1": 0.8372093023255814, "eval_overall_precision": 0.7948051948051948, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.409, "eval_samples_per_second": 457.261, "eval_steps_per_second": 7.336, "step": 3498 }, { "epoch": 34.0, "grad_norm": 1.046993613243103, "learning_rate": 3.3e-05, "loss": 0.0376, "step": 3604 }, { "epoch": 34.0, "eval_LOCATION_f1": 0.7733333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7160493827160493, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.684931506849315, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5882352941176471, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9177215189873417, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8895705521472392, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.17131732404232025, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.8252688172043011, "eval_overall_precision": 0.7713567839195979, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.4026, "eval_samples_per_second": 464.46, "eval_steps_per_second": 7.451, "step": 3604 }, { "epoch": 35.0, "grad_norm": 1.2515838146209717, "learning_rate": 3.2500000000000004e-05, "loss": 0.0386, "step": 3710 }, { "epoch": 35.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6911764705882353, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6266666666666667, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.15111976861953735, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8283378746594006, "eval_overall_precision": 0.7835051546391752, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.4042, "eval_samples_per_second": 462.608, "eval_steps_per_second": 7.422, "step": 3710 }, { "epoch": 36.0, "grad_norm": 1.2548344135284424, "learning_rate": 3.2000000000000005e-05, "loss": 0.0357, "step": 3816 }, { "epoch": 36.0, "eval_LOCATION_f1": 0.8194444444444444, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7866666666666666, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7092198581560285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.625, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9182389937106918, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8848484848484849, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8484848484848485, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.8235294117647058, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1648045778274536, "eval_overall_accuracy": 0.9628436958137231, "eval_overall_f1": 0.8458390177353343, "eval_overall_precision": 0.8010335917312662, "eval_overall_recall": 0.8959537572254336, "eval_runtime": 0.4042, "eval_samples_per_second": 462.674, "eval_steps_per_second": 7.423, "step": 3816 }, { "epoch": 37.0, "grad_norm": 2.816448450088501, "learning_rate": 3.15e-05, "loss": 0.0347, "step": 3922 }, { "epoch": 37.0, "eval_LOCATION_f1": 0.7891156462585034, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7435897435897436, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.7222222222222222, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6265060240963856, "eval_ORGANIZATION_recall": 0.8524590163934426, "eval_PERSON_f1": 0.9303797468354431, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.901840490797546, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.170131117105484, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8439620081411127, "eval_overall_precision": 0.7953964194373402, "eval_overall_recall": 0.8988439306358381, "eval_runtime": 0.4012, "eval_samples_per_second": 466.072, "eval_steps_per_second": 7.477, "step": 3922 }, { "epoch": 38.0, "grad_norm": 1.0050489902496338, "learning_rate": 3.1e-05, "loss": 0.0354, "step": 4028 }, { "epoch": 38.0, "eval_LOCATION_f1": 0.7808219178082192, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7402597402597403, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6197183098591549, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.9240506329113924, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8957055214723927, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14870800077915192, "eval_overall_accuracy": 0.964082239286599, "eval_overall_f1": 0.8275862068965517, "eval_overall_precision": 0.7915567282321899, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.4006, "eval_samples_per_second": 466.802, "eval_steps_per_second": 7.489, "step": 4028 }, { "epoch": 39.0, "grad_norm": 0.5996510982513428, "learning_rate": 3.05e-05, "loss": 0.0337, "step": 4134 }, { "epoch": 39.0, "eval_LOCATION_f1": 0.8275862068965517, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7172413793103448, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6190476190476191, "eval_ORGANIZATION_recall": 0.8524590163934426, "eval_PERSON_f1": 0.9090909090909091, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8734939759036144, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.16299550235271454, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8394062078272604, "eval_overall_precision": 0.7873417721518987, "eval_overall_recall": 0.8988439306358381, "eval_runtime": 0.4063, "eval_samples_per_second": 460.239, "eval_steps_per_second": 7.384, "step": 4134 }, { "epoch": 40.0, "grad_norm": 2.1595568656921387, "learning_rate": 3e-05, "loss": 0.031, "step": 4240 }, { "epoch": 40.0, "eval_LOCATION_f1": 0.7651006711409397, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7125, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.7014925373134328, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6438356164383562, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9182389937106918, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8848484848484849, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1605391651391983, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.829467939972715, "eval_overall_precision": 0.7855297157622739, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.4029, "eval_samples_per_second": 464.118, "eval_steps_per_second": 7.446, "step": 4240 }, { "epoch": 41.0, "grad_norm": 0.07246937602758408, "learning_rate": 2.95e-05, "loss": 0.0305, "step": 4346 }, { "epoch": 41.0, "eval_LOCATION_f1": 0.7755102040816326, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7307692307692307, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.676056338028169, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5925925925925926, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9119496855345912, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8787878787878788, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1640830785036087, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8238482384823848, "eval_overall_precision": 0.7755102040816326, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.4046, "eval_samples_per_second": 462.202, "eval_steps_per_second": 7.415, "step": 4346 }, { "epoch": 42.0, "grad_norm": 1.7377935647964478, "learning_rate": 2.9e-05, "loss": 0.0292, "step": 4452 }, { "epoch": 42.0, "eval_LOCATION_f1": 0.8, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7631578947368421, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.7092198581560285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.625, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9269841269841269, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9012345679012346, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.16985991597175598, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8415300546448088, "eval_overall_precision": 0.7979274611398963, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.4032, "eval_samples_per_second": 463.799, "eval_steps_per_second": 7.441, "step": 4452 }, { "epoch": 43.0, "grad_norm": 0.08767852932214737, "learning_rate": 2.8499999999999998e-05, "loss": 0.0296, "step": 4558 }, { "epoch": 43.0, "eval_LOCATION_f1": 0.7702702702702703, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7215189873417721, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6984126984126984, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.676923076923077, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.9269841269841269, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9012345679012346, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.16103391349315643, "eval_overall_accuracy": 0.9660639088432004, "eval_overall_f1": 0.8344923504867872, "eval_overall_precision": 0.8042895442359249, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.4057, "eval_samples_per_second": 460.877, "eval_steps_per_second": 7.394, "step": 4558 }, { "epoch": 44.0, "grad_norm": 0.5797997117042542, "learning_rate": 2.8000000000000003e-05, "loss": 0.0271, "step": 4664 }, { "epoch": 44.0, "eval_LOCATION_f1": 0.802721088435374, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7564102564102564, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6969696969696969, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.647887323943662, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9182389937106918, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8848484848484849, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1736581176519394, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.837912087912088, "eval_overall_precision": 0.7984293193717278, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4141, "eval_samples_per_second": 451.532, "eval_steps_per_second": 7.244, "step": 4664 }, { "epoch": 45.0, "grad_norm": 0.5857752561569214, "learning_rate": 2.7500000000000004e-05, "loss": 0.0257, "step": 4770 }, { "epoch": 45.0, "eval_LOCATION_f1": 0.7945205479452054, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7532467532467533, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6716417910447762, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6164383561643836, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9216300940438872, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8855421686746988, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.16865137219429016, "eval_overall_accuracy": 0.964082239286599, "eval_overall_f1": 0.8340192043895747, "eval_overall_precision": 0.793733681462141, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.4037, "eval_samples_per_second": 463.213, "eval_steps_per_second": 7.431, "step": 4770 }, { "epoch": 46.0, "grad_norm": 0.6415446400642395, "learning_rate": 2.7000000000000002e-05, "loss": 0.0267, "step": 4876 }, { "epoch": 46.0, "eval_LOCATION_f1": 0.7945205479452054, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7532467532467533, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.676470588235294, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6133333333333333, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9299363057324841, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.906832298136646, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.16720764338970184, "eval_overall_accuracy": 0.9638345305920237, "eval_overall_f1": 0.8386206896551723, "eval_overall_precision": 0.8021108179419525, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.405, "eval_samples_per_second": 461.732, "eval_steps_per_second": 7.407, "step": 4876 }, { "epoch": 47.0, "grad_norm": 4.307225704193115, "learning_rate": 2.6500000000000004e-05, "loss": 0.0243, "step": 4982 }, { "epoch": 47.0, "eval_LOCATION_f1": 0.8, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7631578947368421, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.7050359712230215, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6282051282051282, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.9274447949526814, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8963414634146342, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.17239607870578766, "eval_overall_accuracy": 0.9643299479811741, "eval_overall_f1": 0.8399452804377565, "eval_overall_precision": 0.7974025974025974, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.4036, "eval_samples_per_second": 463.275, "eval_steps_per_second": 7.432, "step": 4982 }, { "epoch": 48.0, "grad_norm": 2.830711841583252, "learning_rate": 2.6000000000000002e-05, "loss": 0.0245, "step": 5088 }, { "epoch": 48.0, "eval_LOCATION_f1": 0.8082191780821918, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7662337662337663, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6814814814814815, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9240506329113924, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8957055214723927, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.17494605481624603, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.837912087912088, "eval_overall_precision": 0.7984293193717278, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4037, "eval_samples_per_second": 463.262, "eval_steps_per_second": 7.432, "step": 5088 }, { "epoch": 49.0, "grad_norm": 0.654138445854187, "learning_rate": 2.5500000000000003e-05, "loss": 0.0248, "step": 5194 }, { "epoch": 49.0, "eval_LOCATION_f1": 0.8137931034482757, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7763157894736842, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6917293233082706, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9240506329113924, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8957055214723927, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1652275174856186, "eval_overall_accuracy": 0.9643299479811741, "eval_overall_f1": 0.8386206896551723, "eval_overall_precision": 0.8021108179419525, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.4028, "eval_samples_per_second": 464.213, "eval_steps_per_second": 7.447, "step": 5194 }, { "epoch": 50.0, "grad_norm": 0.5925632119178772, "learning_rate": 2.5e-05, "loss": 0.024, "step": 5300 }, { "epoch": 50.0, "eval_LOCATION_f1": 0.7972027972027972, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7702702702702703, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6717557251908397, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6285714285714286, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1688040941953659, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8289290681502086, "eval_overall_precision": 0.7989276139410187, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.4031, "eval_samples_per_second": 463.874, "eval_steps_per_second": 7.442, "step": 5300 }, { "epoch": 51.0, "grad_norm": 0.48497816920280457, "learning_rate": 2.45e-05, "loss": 0.0218, "step": 5406 }, { "epoch": 51.0, "eval_LOCATION_f1": 0.8356164383561644, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7922077922077922, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9367088607594937, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9079754601226994, "eval_PERSON_recall": 0.9673202614379085, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1846623569726944, "eval_overall_accuracy": 0.9643299479811741, "eval_overall_f1": 0.8505434782608696, "eval_overall_precision": 0.8025641025641026, "eval_overall_recall": 0.9046242774566474, "eval_runtime": 0.4053, "eval_samples_per_second": 461.373, "eval_steps_per_second": 7.402, "step": 5406 }, { "epoch": 52.0, "grad_norm": 1.1621553897857666, "learning_rate": 2.4e-05, "loss": 0.0213, "step": 5512 }, { "epoch": 52.0, "eval_LOCATION_f1": 0.8356164383561644, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7922077922077922, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7123287671232876, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.611764705882353, "eval_ORGANIZATION_recall": 0.8524590163934426, "eval_PERSON_f1": 0.9396825396825397, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9135802469135802, "eval_PERSON_recall": 0.9673202614379085, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.180556520819664, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8486486486486486, "eval_overall_precision": 0.7969543147208121, "eval_overall_recall": 0.9075144508670521, "eval_runtime": 0.4094, "eval_samples_per_second": 456.723, "eval_steps_per_second": 7.327, "step": 5512 }, { "epoch": 53.0, "grad_norm": 0.4603475332260132, "learning_rate": 2.35e-05, "loss": 0.0201, "step": 5618 }, { "epoch": 53.0, "eval_LOCATION_f1": 0.8055555555555556, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7733333333333333, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.7375886524822695, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.65, "eval_ORGANIZATION_recall": 0.8524590163934426, "eval_PERSON_f1": 0.9245283018867925, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8909090909090909, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.18687838315963745, "eval_overall_accuracy": 0.9643299479811741, "eval_overall_f1": 0.8458390177353343, "eval_overall_precision": 0.8010335917312662, "eval_overall_recall": 0.8959537572254336, "eval_runtime": 0.4094, "eval_samples_per_second": 456.771, "eval_steps_per_second": 7.328, "step": 5618 }, { "epoch": 54.0, "grad_norm": 0.3411925733089447, "learning_rate": 2.3000000000000003e-05, "loss": 0.02, "step": 5724 }, { "epoch": 54.0, "eval_LOCATION_f1": 0.802721088435374, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7564102564102564, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.712121212121212, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6619718309859155, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.927899686520376, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.891566265060241, "eval_PERSON_recall": 0.9673202614379085, "eval_QUANTITY_f1": 0.8484848484848485, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.8235294117647058, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1793394833803177, "eval_overall_accuracy": 0.9653207827594749, "eval_overall_f1": 0.848901098901099, "eval_overall_precision": 0.8089005235602095, "eval_overall_recall": 0.8930635838150289, "eval_runtime": 0.4098, "eval_samples_per_second": 456.305, "eval_steps_per_second": 7.32, "step": 5724 }, { "epoch": 55.0, "grad_norm": 0.9535180330276489, "learning_rate": 2.25e-05, "loss": 0.0204, "step": 5830 }, { "epoch": 55.0, "eval_LOCATION_f1": 0.8055555555555556, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7733333333333333, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6715328467153285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6052631578947368, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1895986944437027, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8224043715846995, "eval_overall_precision": 0.7797927461139896, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.4065, "eval_samples_per_second": 459.994, "eval_steps_per_second": 7.38, "step": 5830 }, { "epoch": 56.0, "grad_norm": 0.5869280099868774, "learning_rate": 2.2000000000000003e-05, "loss": 0.0221, "step": 5936 }, { "epoch": 56.0, "eval_LOCATION_f1": 0.8251748251748252, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7972972972972973, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6917293233082706, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.939297124600639, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.91875, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.17885428667068481, "eval_overall_accuracy": 0.96556849145405, "eval_overall_f1": 0.85, "eval_overall_precision": 0.8181818181818182, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.4069, "eval_samples_per_second": 459.619, "eval_steps_per_second": 7.374, "step": 5936 }, { "epoch": 57.0, "grad_norm": 1.007596492767334, "learning_rate": 2.15e-05, "loss": 0.0191, "step": 6042 }, { "epoch": 57.0, "eval_LOCATION_f1": 0.8275862068965517, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6716417910447762, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6164383561643836, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9333333333333333, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9074074074074074, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.18730428814888, "eval_overall_accuracy": 0.9633391132028735, "eval_overall_f1": 0.8425414364640884, "eval_overall_precision": 0.8068783068783069, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4082, "eval_samples_per_second": 458.124, "eval_steps_per_second": 7.35, "step": 6042 }, { "epoch": 58.0, "grad_norm": 0.05349158123135567, "learning_rate": 2.1e-05, "loss": 0.0184, "step": 6148 }, { "epoch": 58.0, "eval_LOCATION_f1": 0.8, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7631578947368421, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6715328467153285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6052631578947368, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9216300940438872, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8855421686746988, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1908842921257019, "eval_overall_accuracy": 0.9623482784245727, "eval_overall_f1": 0.8344733242134064, "eval_overall_precision": 0.7922077922077922, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4093, "eval_samples_per_second": 456.924, "eval_steps_per_second": 7.33, "step": 6148 }, { "epoch": 59.0, "grad_norm": 0.5943154692649841, "learning_rate": 2.05e-05, "loss": 0.0173, "step": 6254 }, { "epoch": 59.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6617647058823529, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9211356466876972, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8902439024390244, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.19820117950439453, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8356164383561644, "eval_overall_precision": 0.7942708333333334, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4065, "eval_samples_per_second": 460.074, "eval_steps_per_second": 7.381, "step": 6254 }, { "epoch": 60.0, "grad_norm": 0.6145533323287964, "learning_rate": 2e-05, "loss": 0.018, "step": 6360 }, { "epoch": 60.0, "eval_LOCATION_f1": 0.8, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7631578947368421, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6853146853146853, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5975609756097561, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.9125, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.874251497005988, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.202591672539711, "eval_overall_accuracy": 0.9623482784245727, "eval_overall_f1": 0.8319783197831978, "eval_overall_precision": 0.7831632653061225, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.4085, "eval_samples_per_second": 457.796, "eval_steps_per_second": 7.344, "step": 6360 }, { "epoch": 61.0, "grad_norm": 1.8163769245147705, "learning_rate": 1.9500000000000003e-05, "loss": 0.0174, "step": 6466 }, { "epoch": 61.0, "eval_LOCATION_f1": 0.8028169014084506, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7808219178082192, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6929133858267716, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.9201277955271565, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.18250833451747894, "eval_overall_accuracy": 0.9653207827594749, "eval_overall_f1": 0.8387096774193549, "eval_overall_precision": 0.8147138964577657, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.4055, "eval_samples_per_second": 461.15, "eval_steps_per_second": 7.398, "step": 6466 }, { "epoch": 62.0, "grad_norm": 0.7063648104667664, "learning_rate": 1.9e-05, "loss": 0.0159, "step": 6572 }, { "epoch": 62.0, "eval_LOCATION_f1": 0.8299319727891156, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6713286713286712, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5853658536585366, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.915360501567398, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8795180722891566, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.875, "eval_TIME_number": 31, "eval_TIME_precision": 0.8484848484848485, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.20766791701316833, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8362652232746955, "eval_overall_precision": 0.7862595419847328, "eval_overall_recall": 0.8930635838150289, "eval_runtime": 0.4037, "eval_samples_per_second": 463.189, "eval_steps_per_second": 7.431, "step": 6572 }, { "epoch": 63.0, "grad_norm": 0.06240615248680115, "learning_rate": 1.85e-05, "loss": 0.0159, "step": 6678 }, { "epoch": 63.0, "eval_LOCATION_f1": 0.8251748251748252, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7972972972972973, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.676470588235294, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6133333333333333, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9274447949526814, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8963414634146342, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8484848484848486, "eval_TIME_number": 31, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.20551708340644836, "eval_overall_accuracy": 0.9623482784245727, "eval_overall_f1": 0.839506172839506, "eval_overall_precision": 0.7989556135770235, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.4048, "eval_samples_per_second": 461.929, "eval_steps_per_second": 7.411, "step": 6678 }, { "epoch": 64.0, "grad_norm": 3.2396926879882812, "learning_rate": 1.8e-05, "loss": 0.0151, "step": 6784 }, { "epoch": 64.0, "eval_LOCATION_f1": 0.8356164383561644, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7922077922077922, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6857142857142857, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6075949367088608, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9396825396825397, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9135802469135802, "eval_PERSON_recall": 0.9673202614379085, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.20788374543190002, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8485675306957707, "eval_overall_precision": 0.8036175710594315, "eval_overall_recall": 0.8988439306358381, "eval_runtime": 0.4028, "eval_samples_per_second": 464.3, "eval_steps_per_second": 7.449, "step": 6784 }, { "epoch": 65.0, "grad_norm": 0.9956832528114319, "learning_rate": 1.75e-05, "loss": 0.0162, "step": 6890 }, { "epoch": 65.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6715328467153285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6052631578947368, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9211356466876972, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8902439024390244, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.19509576261043549, "eval_overall_accuracy": 0.9643299479811741, "eval_overall_f1": 0.8383561643835618, "eval_overall_precision": 0.796875, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.4029, "eval_samples_per_second": 464.164, "eval_steps_per_second": 7.446, "step": 6890 }, { "epoch": 66.0, "grad_norm": 0.5994267463684082, "learning_rate": 1.7000000000000003e-05, "loss": 0.0149, "step": 6996 }, { "epoch": 66.0, "eval_LOCATION_f1": 0.8299319727891156, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6865671641791045, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9274447949526814, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8963414634146342, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.20032353699207306, "eval_overall_accuracy": 0.9650730740648997, "eval_overall_f1": 0.8426812585499317, "eval_overall_precision": 0.8, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.4012, "eval_samples_per_second": 466.119, "eval_steps_per_second": 7.478, "step": 6996 }, { "epoch": 67.0, "grad_norm": 0.22768262028694153, "learning_rate": 1.65e-05, "loss": 0.0155, "step": 7102 }, { "epoch": 67.0, "eval_LOCATION_f1": 0.7945205479452054, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7532467532467533, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6717557251908397, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6285714285714286, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.9337539432176657, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9024390243902439, "eval_PERSON_recall": 0.9673202614379085, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.2013421654701233, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8347107438016529, "eval_overall_precision": 0.7973684210526316, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.4059, "eval_samples_per_second": 460.723, "eval_steps_per_second": 7.391, "step": 7102 }, { "epoch": 68.0, "grad_norm": 0.4733757972717285, "learning_rate": 1.6000000000000003e-05, "loss": 0.0147, "step": 7208 }, { "epoch": 68.0, "eval_LOCATION_f1": 0.8082191780821918, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7662337662337663, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6769230769230768, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6376811594202898, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.9216300940438872, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8855421686746988, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.20686639845371246, "eval_overall_accuracy": 0.9628436958137231, "eval_overall_f1": 0.8386206896551723, "eval_overall_precision": 0.8021108179419525, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.4015, "eval_samples_per_second": 465.784, "eval_steps_per_second": 7.472, "step": 7208 }, { "epoch": 69.0, "grad_norm": 0.21161212027072906, "learning_rate": 1.55e-05, "loss": 0.0139, "step": 7314 }, { "epoch": 69.0, "eval_LOCATION_f1": 0.8275862068965517, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6917293233082706, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9269841269841269, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9012345679012346, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.19644662737846375, "eval_overall_accuracy": 0.9653207827594749, "eval_overall_f1": 0.8437067773167358, "eval_overall_precision": 0.8090185676392573, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4039, "eval_samples_per_second": 462.998, "eval_steps_per_second": 7.428, "step": 7314 }, { "epoch": 70.0, "grad_norm": 1.607442021369934, "learning_rate": 1.5e-05, "loss": 0.0141, "step": 7420 }, { "epoch": 70.0, "eval_LOCATION_f1": 0.8082191780821918, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7662337662337663, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6976744186046512, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6617647058823529, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9211356466876972, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8902439024390244, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8484848484848485, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.8235294117647058, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.20234768092632294, "eval_overall_accuracy": 0.9643299479811741, "eval_overall_f1": 0.8460471567267683, "eval_overall_precision": 0.8133333333333334, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4064, "eval_samples_per_second": 460.185, "eval_steps_per_second": 7.383, "step": 7420 }, { "epoch": 71.0, "grad_norm": 0.20785416662693024, "learning_rate": 1.45e-05, "loss": 0.0136, "step": 7526 }, { "epoch": 71.0, "eval_LOCATION_f1": 0.802721088435374, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7564102564102564, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6917293233082706, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9182389937106918, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8848484848484849, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.20758448541164398, "eval_overall_accuracy": 0.9643299479811741, "eval_overall_f1": 0.837912087912088, "eval_overall_precision": 0.7984293193717278, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4107, "eval_samples_per_second": 455.343, "eval_steps_per_second": 7.305, "step": 7526 }, { "epoch": 72.0, "grad_norm": 1.7999894618988037, "learning_rate": 1.4000000000000001e-05, "loss": 0.0135, "step": 7632 }, { "epoch": 72.0, "eval_LOCATION_f1": 0.802721088435374, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7564102564102564, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6818181818181818, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6338028169014085, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9240506329113924, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8957055214723927, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8484848484848485, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.8235294117647058, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.20112010836601257, "eval_overall_accuracy": 0.9645776566757494, "eval_overall_f1": 0.8413793103448276, "eval_overall_precision": 0.8047493403693932, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.409, "eval_samples_per_second": 457.258, "eval_steps_per_second": 7.336, "step": 7632 }, { "epoch": 73.0, "grad_norm": 0.046665601432323456, "learning_rate": 1.3500000000000001e-05, "loss": 0.0114, "step": 7738 }, { "epoch": 73.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6923076923076924, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6521739130434783, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9303797468354431, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.901840490797546, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.8484848484848485, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.8235294117647058, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.20439833402633667, "eval_overall_accuracy": 0.966807034926926, "eval_overall_f1": 0.850415512465374, "eval_overall_precision": 0.8164893617021277, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.4081, "eval_samples_per_second": 458.248, "eval_steps_per_second": 7.352, "step": 7738 }, { "epoch": 74.0, "grad_norm": 0.4319368600845337, "learning_rate": 1.3000000000000001e-05, "loss": 0.0124, "step": 7844 }, { "epoch": 74.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6766917293233082, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.625, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9303797468354431, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.901840490797546, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8615384615384616, "eval_TIME_number": 31, "eval_TIME_precision": 0.8235294117647058, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.2058665156364441, "eval_overall_accuracy": 0.9658162001486252, "eval_overall_f1": 0.8457300275482094, "eval_overall_precision": 0.8078947368421052, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.4093, "eval_samples_per_second": 456.88, "eval_steps_per_second": 7.33, "step": 7844 }, { "epoch": 75.0, "grad_norm": 0.46784916520118713, "learning_rate": 1.25e-05, "loss": 0.0113, "step": 7950 }, { "epoch": 75.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6716417910447762, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6164383561643836, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9211356466876972, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8902439024390244, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.21380963921546936, "eval_overall_accuracy": 0.9648253653703245, "eval_overall_f1": 0.8367626886145405, "eval_overall_precision": 0.7963446475195822, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4037, "eval_samples_per_second": 463.253, "eval_steps_per_second": 7.432, "step": 7950 }, { "epoch": 76.0, "grad_norm": 0.5961441397666931, "learning_rate": 1.2e-05, "loss": 0.0126, "step": 8056 }, { "epoch": 76.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6766917293233082, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.625, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9211356466876972, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8902439024390244, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8484848484848485, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.8235294117647058, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.8484848484848486, "eval_TIME_number": 31, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.21406003832817078, "eval_overall_accuracy": 0.9638345305920237, "eval_overall_f1": 0.8438356164383563, "eval_overall_precision": 0.8020833333333334, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.4046, "eval_samples_per_second": 462.204, "eval_steps_per_second": 7.415, "step": 8056 }, { "epoch": 77.0, "grad_norm": 0.5828773975372314, "learning_rate": 1.1500000000000002e-05, "loss": 0.0116, "step": 8162 }, { "epoch": 77.0, "eval_LOCATION_f1": 0.8194444444444444, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7866666666666666, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6870229007633588, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6428571428571429, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9333333333333333, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9074074074074074, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.8484848484848485, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.8235294117647058, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.21130701899528503, "eval_overall_accuracy": 0.9653207827594749, "eval_overall_f1": 0.8488210818307905, "eval_overall_precision": 0.816, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.404, "eval_samples_per_second": 462.856, "eval_steps_per_second": 7.426, "step": 8162 }, { "epoch": 78.0, "grad_norm": 0.6764857769012451, "learning_rate": 1.1000000000000001e-05, "loss": 0.0126, "step": 8268 }, { "epoch": 78.0, "eval_LOCATION_f1": 0.8356164383561644, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7922077922077922, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6962962962962963, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6351351351351351, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9245283018867925, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8909090909090909, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.8484848484848485, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.8235294117647058, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.7941176470588235, "eval_TIME_number": 31, "eval_TIME_precision": 0.7297297297297297, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.21255819499492645, "eval_overall_accuracy": 0.9653207827594749, "eval_overall_f1": 0.8458390177353343, "eval_overall_precision": 0.8010335917312662, "eval_overall_recall": 0.8959537572254336, "eval_runtime": 0.4082, "eval_samples_per_second": 458.124, "eval_steps_per_second": 7.35, "step": 8268 }, { "epoch": 79.0, "grad_norm": 0.38964611291885376, "learning_rate": 1.05e-05, "loss": 0.0123, "step": 8374 }, { "epoch": 79.0, "eval_LOCATION_f1": 0.8251748251748252, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7972972972972973, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.682170542635659, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6470588235294118, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.9303797468354431, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.901840490797546, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.8484848484848485, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.8235294117647058, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.20355309545993805, "eval_overall_accuracy": 0.966807034926926, "eval_overall_f1": 0.8495821727019499, "eval_overall_precision": 0.8198924731182796, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4033, "eval_samples_per_second": 463.657, "eval_steps_per_second": 7.438, "step": 8374 }, { "epoch": 80.0, "grad_norm": 0.3479403257369995, "learning_rate": 1e-05, "loss": 0.0121, "step": 8480 }, { "epoch": 80.0, "eval_LOCATION_f1": 0.8299319727891156, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6715328467153285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6052631578947368, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9269841269841269, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9012345679012346, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.21020622551441193, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8422496570644717, "eval_overall_precision": 0.8015665796344648, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.4048, "eval_samples_per_second": 461.968, "eval_steps_per_second": 7.411, "step": 8480 }, { "epoch": 81.0, "grad_norm": 0.370176762342453, "learning_rate": 9.5e-06, "loss": 0.0104, "step": 8586 }, { "epoch": 81.0, "eval_LOCATION_f1": 0.8356164383561644, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7922077922077922, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6766917293233082, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.625, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9269841269841269, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9012345679012346, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.21465693414211273, "eval_overall_accuracy": 0.9633391132028735, "eval_overall_f1": 0.8418156808803301, "eval_overall_precision": 0.8031496062992126, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.4029, "eval_samples_per_second": 464.107, "eval_steps_per_second": 7.446, "step": 8586 }, { "epoch": 82.0, "grad_norm": 0.28365227580070496, "learning_rate": 9e-06, "loss": 0.0108, "step": 8692 }, { "epoch": 82.0, "eval_LOCATION_f1": 0.8356164383561644, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7922077922077922, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6715328467153285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6052631578947368, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9303797468354431, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.901840490797546, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.22350215911865234, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8403819918144612, "eval_overall_precision": 0.7958656330749354, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.4037, "eval_samples_per_second": 463.167, "eval_steps_per_second": 7.43, "step": 8692 }, { "epoch": 83.0, "grad_norm": 0.8675772547721863, "learning_rate": 8.500000000000002e-06, "loss": 0.0105, "step": 8798 }, { "epoch": 83.0, "eval_LOCATION_f1": 0.8082191780821918, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7662337662337663, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6818181818181818, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6338028169014085, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9333333333333333, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9074074074074074, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.21032676100730896, "eval_overall_accuracy": 0.9645776566757494, "eval_overall_f1": 0.8437067773167358, "eval_overall_precision": 0.8090185676392573, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4035, "eval_samples_per_second": 463.458, "eval_steps_per_second": 7.435, "step": 8798 }, { "epoch": 84.0, "grad_norm": 2.7571957111358643, "learning_rate": 8.000000000000001e-06, "loss": 0.0107, "step": 8904 }, { "epoch": 84.0, "eval_LOCATION_f1": 0.8082191780821918, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7662337662337663, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6870229007633588, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6428571428571429, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9363057324840764, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9130434782608695, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.21551497280597687, "eval_overall_accuracy": 0.9648253653703245, "eval_overall_f1": 0.8425414364640884, "eval_overall_precision": 0.8068783068783069, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4034, "eval_samples_per_second": 463.566, "eval_steps_per_second": 7.437, "step": 8904 }, { "epoch": 85.0, "grad_norm": 0.0661739706993103, "learning_rate": 7.5e-06, "loss": 0.0103, "step": 9010 }, { "epoch": 85.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6818181818181818, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6338028169014085, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9240506329113924, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8957055214723927, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.2167329490184784, "eval_overall_accuracy": 0.9643299479811741, "eval_overall_f1": 0.837912087912088, "eval_overall_precision": 0.7984293193717278, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4057, "eval_samples_per_second": 460.971, "eval_steps_per_second": 7.395, "step": 9010 }, { "epoch": 86.0, "grad_norm": 1.5372931957244873, "learning_rate": 7.000000000000001e-06, "loss": 0.01, "step": 9116 }, { "epoch": 86.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.676470588235294, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6133333333333333, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9211356466876972, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8902439024390244, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8059701492537312, "eval_TIME_number": 31, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.22136247158050537, "eval_overall_accuracy": 0.964082239286599, "eval_overall_f1": 0.8365122615803814, "eval_overall_precision": 0.7912371134020618, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.4055, "eval_samples_per_second": 461.202, "eval_steps_per_second": 7.399, "step": 9116 }, { "epoch": 87.0, "grad_norm": 0.7345579266548157, "learning_rate": 6.5000000000000004e-06, "loss": 0.0101, "step": 9222 }, { "epoch": 87.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6865671641791045, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9240506329113924, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8957055214723927, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8059701492537312, "eval_TIME_number": 31, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.215372234582901, "eval_overall_accuracy": 0.964082239286599, "eval_overall_f1": 0.8399452804377565, "eval_overall_precision": 0.7974025974025974, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.4065, "eval_samples_per_second": 460.02, "eval_steps_per_second": 7.38, "step": 9222 }, { "epoch": 88.0, "grad_norm": 0.02773982100188732, "learning_rate": 6e-06, "loss": 0.0112, "step": 9328 }, { "epoch": 88.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6814814814814815, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9333333333333333, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9074074074074074, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.21471378207206726, "eval_overall_accuracy": 0.9650730740648997, "eval_overall_f1": 0.8438356164383563, "eval_overall_precision": 0.8020833333333334, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.4027, "eval_samples_per_second": 464.317, "eval_steps_per_second": 7.449, "step": 9328 }, { "epoch": 89.0, "grad_norm": 1.2374390363693237, "learning_rate": 5.500000000000001e-06, "loss": 0.0111, "step": 9434 }, { "epoch": 89.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6818181818181818, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6338028169014085, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9240506329113924, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8957055214723927, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.21400561928749084, "eval_overall_accuracy": 0.9648253653703245, "eval_overall_f1": 0.8406593406593407, "eval_overall_precision": 0.8010471204188482, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.4029, "eval_samples_per_second": 464.12, "eval_steps_per_second": 7.446, "step": 9434 }, { "epoch": 90.0, "grad_norm": 0.09918837249279022, "learning_rate": 5e-06, "loss": 0.0098, "step": 9540 }, { "epoch": 90.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7014925373134328, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6438356164383562, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9206349206349207, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8950617283950617, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.22259807586669922, "eval_overall_accuracy": 0.9638345305920237, "eval_overall_f1": 0.839506172839506, "eval_overall_precision": 0.7989556135770235, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.4017, "eval_samples_per_second": 465.48, "eval_steps_per_second": 7.468, "step": 9540 }, { "epoch": 91.0, "grad_norm": 0.10904386639595032, "learning_rate": 4.5e-06, "loss": 0.0099, "step": 9646 }, { "epoch": 91.0, "eval_LOCATION_f1": 0.8, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7631578947368421, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.712121212121212, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6619718309859155, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9333333333333333, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9074074074074074, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.21591398119926453, "eval_overall_accuracy": 0.9658162001486252, "eval_overall_f1": 0.8476454293628809, "eval_overall_precision": 0.8138297872340425, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.4022, "eval_samples_per_second": 464.95, "eval_steps_per_second": 7.459, "step": 9646 }, { "epoch": 92.0, "grad_norm": 3.4749605655670166, "learning_rate": 4.000000000000001e-06, "loss": 0.0102, "step": 9752 }, { "epoch": 92.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.712121212121212, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6619718309859155, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9303797468354431, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.901840490797546, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.22017474472522736, "eval_overall_accuracy": 0.9665593262323507, "eval_overall_f1": 0.8484848484848484, "eval_overall_precision": 0.8105263157894737, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.4038, "eval_samples_per_second": 463.073, "eval_steps_per_second": 7.429, "step": 9752 }, { "epoch": 93.0, "grad_norm": 0.8946192860603333, "learning_rate": 3.5000000000000004e-06, "loss": 0.0096, "step": 9858 }, { "epoch": 93.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6969696969696969, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.647887323943662, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9240506329113924, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8957055214723927, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.22221431136131287, "eval_overall_accuracy": 0.9650730740648997, "eval_overall_f1": 0.8418156808803301, "eval_overall_precision": 0.8031496062992126, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.4021, "eval_samples_per_second": 465.113, "eval_steps_per_second": 7.462, "step": 9858 }, { "epoch": 94.0, "grad_norm": 0.0954521968960762, "learning_rate": 3e-06, "loss": 0.0092, "step": 9964 }, { "epoch": 94.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6865671641791045, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9240506329113924, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8957055214723927, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.22241780161857605, "eval_overall_accuracy": 0.9645776566757494, "eval_overall_f1": 0.8383561643835618, "eval_overall_precision": 0.796875, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.4033, "eval_samples_per_second": 463.727, "eval_steps_per_second": 7.439, "step": 9964 }, { "epoch": 95.0, "grad_norm": 1.271582007408142, "learning_rate": 2.5e-06, "loss": 0.0087, "step": 10070 }, { "epoch": 95.0, "eval_LOCATION_f1": 0.8082191780821918, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7662337662337663, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6917293233082706, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9240506329113924, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8957055214723927, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.22204293310642242, "eval_overall_accuracy": 0.9650730740648997, "eval_overall_f1": 0.8402203856749312, "eval_overall_precision": 0.8026315789473685, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4038, "eval_samples_per_second": 463.133, "eval_steps_per_second": 7.43, "step": 10070 }, { "epoch": 96.0, "grad_norm": 0.26876676082611084, "learning_rate": 2.0000000000000003e-06, "loss": 0.0084, "step": 10176 }, { "epoch": 96.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6865671641791045, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9240506329113924, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8957055214723927, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.2239730805158615, "eval_overall_accuracy": 0.9650730740648997, "eval_overall_f1": 0.8406593406593407, "eval_overall_precision": 0.8010471204188482, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.4038, "eval_samples_per_second": 463.148, "eval_steps_per_second": 7.43, "step": 10176 }, { "epoch": 97.0, "grad_norm": 1.1765313148498535, "learning_rate": 1.5e-06, "loss": 0.0087, "step": 10282 }, { "epoch": 97.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6917293233082706, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9240506329113924, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8957055214723927, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.22398912906646729, "eval_overall_accuracy": 0.9645776566757494, "eval_overall_f1": 0.8418156808803301, "eval_overall_precision": 0.8031496062992126, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.4018, "eval_samples_per_second": 465.353, "eval_steps_per_second": 7.466, "step": 10282 }, { "epoch": 98.0, "grad_norm": 0.07008544355630875, "learning_rate": 1.0000000000000002e-06, "loss": 0.0088, "step": 10388 }, { "epoch": 98.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6917293233082706, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9240506329113924, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8957055214723927, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.2226743996143341, "eval_overall_accuracy": 0.9648253653703245, "eval_overall_f1": 0.8406593406593407, "eval_overall_precision": 0.8010471204188482, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.4033, "eval_samples_per_second": 463.678, "eval_steps_per_second": 7.439, "step": 10388 }, { "epoch": 99.0, "grad_norm": 0.22727848589420319, "learning_rate": 5.000000000000001e-07, "loss": 0.0086, "step": 10494 }, { "epoch": 99.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6865671641791045, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9240506329113924, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8957055214723927, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.22218792140483856, "eval_overall_accuracy": 0.9648253653703245, "eval_overall_f1": 0.8418156808803301, "eval_overall_precision": 0.8031496062992126, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.4019, "eval_samples_per_second": 465.321, "eval_steps_per_second": 7.465, "step": 10494 }, { "epoch": 100.0, "grad_norm": 0.21861711144447327, "learning_rate": 0.0, "loss": 0.0084, "step": 10600 }, { "epoch": 100.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6865671641791045, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9240506329113924, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8957055214723927, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.22297325730323792, "eval_overall_accuracy": 0.9650730740648997, "eval_overall_f1": 0.8418156808803301, "eval_overall_precision": 0.8031496062992126, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.4008, "eval_samples_per_second": 466.564, "eval_steps_per_second": 7.485, "step": 10600 }, { "epoch": 100.0, "step": 10600, "total_flos": 5154303869081070.0, "train_loss": 0.05378503026827326, "train_runtime": 976.0836, "train_samples_per_second": 172.834, "train_steps_per_second": 10.86 } ], "logging_steps": 500, "max_steps": 10600, "num_input_tokens_seen": 0, "num_train_epochs": 100, "save_steps": 500, "total_flos": 5154303869081070.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }