{ "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": 0.9931251406669617, "learning_rate": 4.9500000000000004e-05, "loss": 1.1468, "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": 58, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.0, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.0, "eval_PERSON_recall": 0.0, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 29, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.6908976435661316, "eval_overall_accuracy": 0.8396927016645327, "eval_overall_f1": 0.0, "eval_overall_precision": 0.0, "eval_overall_recall": 0.0, "eval_runtime": 0.2964, "eval_samples_per_second": 630.963, "eval_steps_per_second": 10.122, "step": 106 }, { "epoch": 2.0, "grad_norm": 1.672861933708191, "learning_rate": 4.9e-05, "loss": 0.6623, "step": 212 }, { "epoch": 2.0, "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": 58, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.08235294117647059, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.3888888888888889, "eval_PERSON_recall": 0.046052631578947366, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 29, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.5531525015830994, "eval_overall_accuracy": 0.8432778489116517, "eval_overall_f1": 0.03921568627450981, "eval_overall_precision": 0.3684210526315789, "eval_overall_recall": 0.020710059171597635, "eval_runtime": 0.2895, "eval_samples_per_second": 645.874, "eval_steps_per_second": 10.362, "step": 212 }, { "epoch": 3.0, "grad_norm": 1.7515860795974731, "learning_rate": 4.85e-05, "loss": 0.5401, "step": 318 }, { "epoch": 3.0, "eval_LOCATION_f1": 0.05263157894736841, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.2857142857142857, "eval_LOCATION_recall": 0.028985507246376812, "eval_ORGANIZATION_f1": 0.0, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.37722419928825623, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.4108527131782946, "eval_PERSON_recall": 0.34868421052631576, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.2727272727272727, "eval_TIME_number": 29, "eval_TIME_precision": 0.4, "eval_TIME_recall": 0.20689655172413793, "eval_loss": 0.4444293677806854, "eval_overall_accuracy": 0.8747759282970551, "eval_overall_f1": 0.24206349206349204, "eval_overall_precision": 0.3674698795180723, "eval_overall_recall": 0.1804733727810651, "eval_runtime": 0.2905, "eval_samples_per_second": 643.756, "eval_steps_per_second": 10.328, "step": 318 }, { "epoch": 4.0, "grad_norm": 1.807163953781128, "learning_rate": 4.8e-05, "loss": 0.4414, "step": 424 }, { "epoch": 4.0, "eval_LOCATION_f1": 0.30630630630630634, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.40476190476190477, "eval_LOCATION_recall": 0.2463768115942029, "eval_ORGANIZATION_f1": 0.022222222222222223, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.03125, "eval_ORGANIZATION_recall": 0.017241379310344827, "eval_PERSON_f1": 0.5571030640668524, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.4830917874396135, "eval_PERSON_recall": 0.6578947368421053, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.509090909090909, "eval_TIME_number": 29, "eval_TIME_precision": 0.5384615384615384, "eval_TIME_recall": 0.4827586206896552, "eval_loss": 0.35881680250167847, "eval_overall_accuracy": 0.8988476312419974, "eval_overall_f1": 0.39759036144578314, "eval_overall_precision": 0.4049079754601227, "eval_overall_recall": 0.3905325443786982, "eval_runtime": 0.2928, "eval_samples_per_second": 638.765, "eval_steps_per_second": 10.248, "step": 424 }, { "epoch": 5.0, "grad_norm": 1.5580129623413086, "learning_rate": 4.75e-05, "loss": 0.3745, "step": 530 }, { "epoch": 5.0, "eval_LOCATION_f1": 0.4671532846715329, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.47058823529411764, "eval_LOCATION_recall": 0.463768115942029, "eval_ORGANIZATION_f1": 0.16326530612244897, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.2, "eval_ORGANIZATION_recall": 0.13793103448275862, "eval_PERSON_f1": 0.6477272727272728, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.57, "eval_PERSON_recall": 0.75, "eval_QUANTITY_f1": 0.3125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.29411764705882354, "eval_QUANTITY_recall": 0.3333333333333333, "eval_TIME_f1": 0.5901639344262296, "eval_TIME_number": 29, "eval_TIME_precision": 0.5625, "eval_TIME_recall": 0.6206896551724138, "eval_loss": 0.31193920969963074, "eval_overall_accuracy": 0.9157490396927017, "eval_overall_f1": 0.5112359550561797, "eval_overall_precision": 0.48663101604278075, "eval_overall_recall": 0.5384615384615384, "eval_runtime": 0.2915, "eval_samples_per_second": 641.473, "eval_steps_per_second": 10.291, "step": 530 }, { "epoch": 6.0, "grad_norm": 1.159395694732666, "learning_rate": 4.7e-05, "loss": 0.3306, "step": 636 }, { "epoch": 6.0, "eval_LOCATION_f1": 0.576923076923077, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.5172413793103449, "eval_LOCATION_recall": 0.6521739130434783, "eval_ORGANIZATION_f1": 0.3883495145631068, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.4444444444444444, "eval_ORGANIZATION_recall": 0.3448275862068966, "eval_PERSON_f1": 0.696883852691218, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.6119402985074627, "eval_PERSON_recall": 0.8092105263157895, "eval_QUANTITY_f1": 0.4117647058823529, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.3684210526315789, "eval_QUANTITY_recall": 0.4666666666666667, "eval_TIME_f1": 0.7931034482758621, "eval_TIME_number": 29, "eval_TIME_precision": 0.7931034482758621, "eval_TIME_recall": 0.7931034482758621, "eval_loss": 0.275112509727478, "eval_overall_accuracy": 0.9270166453265045, "eval_overall_f1": 0.6097560975609756, "eval_overall_precision": 0.5625, "eval_overall_recall": 0.665680473372781, "eval_runtime": 0.2917, "eval_samples_per_second": 640.987, "eval_steps_per_second": 10.283, "step": 636 }, { "epoch": 7.0, "grad_norm": 0.7062077522277832, "learning_rate": 4.6500000000000005e-05, "loss": 0.2898, "step": 742 }, { "epoch": 7.0, "eval_LOCATION_f1": 0.6455696202531644, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.5730337078651685, "eval_LOCATION_recall": 0.7391304347826086, "eval_ORGANIZATION_f1": 0.4761904761904762, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.5319148936170213, "eval_ORGANIZATION_recall": 0.43103448275862066, "eval_PERSON_f1": 0.7624633431085044, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.6878306878306878, "eval_PERSON_recall": 0.8552631578947368, "eval_QUANTITY_f1": 0.5142857142857143, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.45, "eval_QUANTITY_recall": 0.6, "eval_TIME_f1": 0.8275862068965517, "eval_TIME_number": 29, "eval_TIME_precision": 0.8275862068965517, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.24487873911857605, "eval_overall_accuracy": 0.9346991037131882, "eval_overall_f1": 0.6775956284153006, "eval_overall_precision": 0.6294416243654822, "eval_overall_recall": 0.7337278106508875, "eval_runtime": 0.2925, "eval_samples_per_second": 639.305, "eval_steps_per_second": 10.256, "step": 742 }, { "epoch": 8.0, "grad_norm": 0.7220238447189331, "learning_rate": 4.600000000000001e-05, "loss": 0.2565, "step": 848 }, { "epoch": 8.0, "eval_LOCATION_f1": 0.6540880503144654, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.5777777777777777, "eval_LOCATION_recall": 0.7536231884057971, "eval_ORGANIZATION_f1": 0.47457627118644075, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.4666666666666667, "eval_ORGANIZATION_recall": 0.4827586206896552, "eval_PERSON_f1": 0.7751479289940829, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7043010752688172, "eval_PERSON_recall": 0.8618421052631579, "eval_QUANTITY_f1": 0.5, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.42857142857142855, "eval_QUANTITY_recall": 0.6, "eval_TIME_f1": 0.8421052631578947, "eval_TIME_number": 29, "eval_TIME_precision": 0.8571428571428571, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.22170113027095795, "eval_overall_accuracy": 0.9357234314980793, "eval_overall_f1": 0.6801075268817205, "eval_overall_precision": 0.6231527093596059, "eval_overall_recall": 0.7485207100591716, "eval_runtime": 0.2922, "eval_samples_per_second": 639.883, "eval_steps_per_second": 10.266, "step": 848 }, { "epoch": 9.0, "grad_norm": 1.7445695400238037, "learning_rate": 4.55e-05, "loss": 0.2355, "step": 954 }, { "epoch": 9.0, "eval_LOCATION_f1": 0.7051282051282052, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.632183908045977, "eval_LOCATION_recall": 0.7971014492753623, "eval_ORGANIZATION_f1": 0.4642857142857143, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.48148148148148145, "eval_ORGANIZATION_recall": 0.4482758620689655, "eval_PERSON_f1": 0.8012048192771084, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7388888888888889, "eval_PERSON_recall": 0.875, "eval_QUANTITY_f1": 0.49315068493150693, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.4186046511627907, "eval_QUANTITY_recall": 0.6, "eval_TIME_f1": 0.8421052631578947, "eval_TIME_number": 29, "eval_TIME_precision": 0.8571428571428571, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.19788858294487, "eval_overall_accuracy": 0.9413572343149808, "eval_overall_f1": 0.7013698630136985, "eval_overall_precision": 0.6530612244897959, "eval_overall_recall": 0.757396449704142, "eval_runtime": 0.2915, "eval_samples_per_second": 641.404, "eval_steps_per_second": 10.29, "step": 954 }, { "epoch": 10.0, "grad_norm": 1.1619913578033447, "learning_rate": 4.5e-05, "loss": 0.2102, "step": 1060 }, { "epoch": 10.0, "eval_LOCATION_f1": 0.7272727272727274, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6588235294117647, "eval_LOCATION_recall": 0.8115942028985508, "eval_ORGANIZATION_f1": 0.4736842105263158, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.48214285714285715, "eval_ORGANIZATION_recall": 0.46551724137931033, "eval_PERSON_f1": 0.8098159509202454, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7586206896551724, "eval_PERSON_recall": 0.868421052631579, "eval_QUANTITY_f1": 0.5142857142857143, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.45, "eval_QUANTITY_recall": 0.6, "eval_TIME_f1": 0.8421052631578947, "eval_TIME_number": 29, "eval_TIME_precision": 0.8571428571428571, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.18124544620513916, "eval_overall_accuracy": 0.9441741357234315, "eval_overall_f1": 0.7128987517337032, "eval_overall_precision": 0.6710182767624021, "eval_overall_recall": 0.7603550295857988, "eval_runtime": 0.2938, "eval_samples_per_second": 636.52, "eval_steps_per_second": 10.212, "step": 1060 }, { "epoch": 11.0, "grad_norm": 1.1275286674499512, "learning_rate": 4.4500000000000004e-05, "loss": 0.1959, "step": 1166 }, { "epoch": 11.0, "eval_LOCATION_f1": 0.7169811320754716, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6333333333333333, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.4833333333333333, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.46774193548387094, "eval_ORGANIZATION_recall": 0.5, "eval_PERSON_f1": 0.7975830815709969, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7374301675977654, "eval_PERSON_recall": 0.868421052631579, "eval_QUANTITY_f1": 0.5428571428571427, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.475, "eval_QUANTITY_recall": 0.6333333333333333, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 29, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.1784009039402008, "eval_overall_accuracy": 0.9441741357234315, "eval_overall_f1": 0.7108108108108109, "eval_overall_precision": 0.654228855721393, "eval_overall_recall": 0.7781065088757396, "eval_runtime": 0.293, "eval_samples_per_second": 638.276, "eval_steps_per_second": 10.24, "step": 1166 }, { "epoch": 12.0, "grad_norm": 2.0943050384521484, "learning_rate": 4.4000000000000006e-05, "loss": 0.1851, "step": 1272 }, { "epoch": 12.0, "eval_LOCATION_f1": 0.7549668874172186, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6951219512195121, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.5, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.5, "eval_ORGANIZATION_recall": 0.5, "eval_PERSON_f1": 0.8098159509202454, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7586206896551724, "eval_PERSON_recall": 0.868421052631579, "eval_QUANTITY_f1": 0.5428571428571427, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.475, "eval_QUANTITY_recall": 0.6333333333333333, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.1627739518880844, "eval_overall_accuracy": 0.9477592829705506, "eval_overall_f1": 0.7257617728531854, "eval_overall_precision": 0.6822916666666666, "eval_overall_recall": 0.7751479289940828, "eval_runtime": 0.2924, "eval_samples_per_second": 639.503, "eval_steps_per_second": 10.259, "step": 1272 }, { "epoch": 13.0, "grad_norm": 0.8063132166862488, "learning_rate": 4.35e-05, "loss": 0.1722, "step": 1378 }, { "epoch": 13.0, "eval_LOCATION_f1": 0.7763157894736842, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7108433734939759, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.4869565217391304, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.49122807017543857, "eval_ORGANIZATION_recall": 0.4827586206896552, "eval_PERSON_f1": 0.8024316109422492, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7457627118644068, "eval_PERSON_recall": 0.868421052631579, "eval_QUANTITY_f1": 0.6470588235294117, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.5789473684210527, "eval_QUANTITY_recall": 0.7333333333333333, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 29, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.15798519551753998, "eval_overall_accuracy": 0.9477592829705506, "eval_overall_f1": 0.7375690607734806, "eval_overall_precision": 0.6917098445595855, "eval_overall_recall": 0.7899408284023669, "eval_runtime": 0.2918, "eval_samples_per_second": 640.94, "eval_steps_per_second": 10.282, "step": 1378 }, { "epoch": 14.0, "grad_norm": 1.4455363750457764, "learning_rate": 4.3e-05, "loss": 0.1681, "step": 1484 }, { "epoch": 14.0, "eval_LOCATION_f1": 0.7581699346405228, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6904761904761905, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.5581395348837208, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.5070422535211268, "eval_ORGANIZATION_recall": 0.6206896551724138, "eval_PERSON_f1": 0.8148148148148148, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7674418604651163, "eval_PERSON_recall": 0.868421052631579, "eval_QUANTITY_f1": 0.7246376811594204, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6410256410256411, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.16039857268333435, "eval_overall_accuracy": 0.9495518565941101, "eval_overall_f1": 0.7510204081632653, "eval_overall_precision": 0.6952141057934509, "eval_overall_recall": 0.8165680473372781, "eval_runtime": 0.2865, "eval_samples_per_second": 652.766, "eval_steps_per_second": 10.472, "step": 1484 }, { "epoch": 15.0, "grad_norm": 1.1877578496932983, "learning_rate": 4.25e-05, "loss": 0.1581, "step": 1590 }, { "epoch": 15.0, "eval_LOCATION_f1": 0.7814569536423841, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7195121951219512, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.5499999999999999, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.532258064516129, "eval_ORGANIZATION_recall": 0.5689655172413793, "eval_PERSON_f1": 0.8161993769470405, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7751479289940828, "eval_PERSON_recall": 0.8618421052631579, "eval_QUANTITY_f1": 0.7164179104477612, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.1485019475221634, "eval_overall_accuracy": 0.952112676056338, "eval_overall_f1": 0.7576601671309192, "eval_overall_precision": 0.7157894736842105, "eval_overall_recall": 0.8047337278106509, "eval_runtime": 0.2924, "eval_samples_per_second": 639.644, "eval_steps_per_second": 10.262, "step": 1590 }, { "epoch": 16.0, "grad_norm": 0.9984870553016663, "learning_rate": 4.2e-05, "loss": 0.1542, "step": 1696 }, { "epoch": 16.0, "eval_LOCATION_f1": 0.802721088435374, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7564102564102564, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.5920000000000001, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.5522388059701493, "eval_ORGANIZATION_recall": 0.6379310344827587, "eval_PERSON_f1": 0.8136645962732919, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7705882352941177, "eval_PERSON_recall": 0.8618421052631579, "eval_QUANTITY_f1": 0.6363636363636365, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.5833333333333334, "eval_QUANTITY_recall": 0.7, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.14613807201385498, "eval_overall_accuracy": 0.9523687580025608, "eval_overall_f1": 0.7621696801112657, "eval_overall_precision": 0.7191601049868767, "eval_overall_recall": 0.8106508875739645, "eval_runtime": 0.2921, "eval_samples_per_second": 640.177, "eval_steps_per_second": 10.27, "step": 1696 }, { "epoch": 17.0, "grad_norm": 0.7401907444000244, "learning_rate": 4.15e-05, "loss": 0.1528, "step": 1802 }, { "epoch": 17.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7142857142857143, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.5737704918032787, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.546875, "eval_ORGANIZATION_recall": 0.603448275862069, "eval_PERSON_f1": 0.8123076923076923, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7630057803468208, "eval_PERSON_recall": 0.868421052631579, "eval_QUANTITY_f1": 0.7246376811594204, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6410256410256411, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7936507936507937, "eval_TIME_number": 29, "eval_TIME_precision": 0.7352941176470589, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.1483771950006485, "eval_overall_accuracy": 0.9518565941101153, "eval_overall_f1": 0.7568306010928961, "eval_overall_precision": 0.7030456852791879, "eval_overall_recall": 0.8195266272189349, "eval_runtime": 0.2861, "eval_samples_per_second": 653.665, "eval_steps_per_second": 10.487, "step": 1802 }, { "epoch": 18.0, "grad_norm": 2.5112438201904297, "learning_rate": 4.1e-05, "loss": 0.1498, "step": 1908 }, { "epoch": 18.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7058823529411765, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.5546218487394958, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.5409836065573771, "eval_ORGANIZATION_recall": 0.5689655172413793, "eval_PERSON_f1": 0.8159509202453987, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.764367816091954, "eval_PERSON_recall": 0.875, "eval_QUANTITY_f1": 0.6956521739130435, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6153846153846154, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.8064516129032258, "eval_TIME_number": 29, "eval_TIME_precision": 0.7575757575757576, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.14724135398864746, "eval_overall_accuracy": 0.9498079385403329, "eval_overall_f1": 0.7534246575342467, "eval_overall_precision": 0.701530612244898, "eval_overall_recall": 0.8136094674556213, "eval_runtime": 0.2864, "eval_samples_per_second": 652.903, "eval_steps_per_second": 10.474, "step": 1908 }, { "epoch": 19.0, "grad_norm": 1.1626933813095093, "learning_rate": 4.05e-05, "loss": 0.1439, "step": 2014 }, { "epoch": 19.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.5438596491228069, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.5535714285714286, "eval_ORGANIZATION_recall": 0.5344827586206896, "eval_PERSON_f1": 0.8161993769470405, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7751479289940828, "eval_PERSON_recall": 0.8618421052631579, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8524590163934426, "eval_TIME_number": 29, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.14064399898052216, "eval_overall_accuracy": 0.9526248399487837, "eval_overall_f1": 0.7647058823529411, "eval_overall_precision": 0.726063829787234, "eval_overall_recall": 0.8076923076923077, "eval_runtime": 0.2933, "eval_samples_per_second": 637.623, "eval_steps_per_second": 10.229, "step": 2014 }, { "epoch": 20.0, "grad_norm": 0.9214287996292114, "learning_rate": 4e-05, "loss": 0.141, "step": 2120 }, { "epoch": 20.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.5833333333333335, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.5645161290322581, "eval_ORGANIZATION_recall": 0.603448275862069, "eval_PERSON_f1": 0.822429906542056, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7810650887573964, "eval_PERSON_recall": 0.868421052631579, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8064516129032258, "eval_TIME_number": 29, "eval_TIME_precision": 0.7575757575757576, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.14049667119979858, "eval_overall_accuracy": 0.954673495518566, "eval_overall_f1": 0.7711511789181693, "eval_overall_precision": 0.7258485639686684, "eval_overall_recall": 0.8224852071005917, "eval_runtime": 0.2923, "eval_samples_per_second": 639.829, "eval_steps_per_second": 10.265, "step": 2120 }, { "epoch": 21.0, "grad_norm": 0.5010473132133484, "learning_rate": 3.9500000000000005e-05, "loss": 0.1371, "step": 2226 }, { "epoch": 21.0, "eval_LOCATION_f1": 0.8157894736842105, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6315789473684211, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.56, "eval_ORGANIZATION_recall": 0.7241379310344828, "eval_PERSON_f1": 0.823529411764706, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7777777777777778, "eval_PERSON_recall": 0.875, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.631578947368421, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.8196721311475409, "eval_TIME_number": 29, "eval_TIME_precision": 0.78125, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.14421436190605164, "eval_overall_accuracy": 0.9539052496798975, "eval_overall_f1": 0.7761194029850746, "eval_overall_precision": 0.7167919799498746, "eval_overall_recall": 0.8461538461538461, "eval_runtime": 0.2914, "eval_samples_per_second": 641.695, "eval_steps_per_second": 10.295, "step": 2226 }, { "epoch": 22.0, "grad_norm": 1.076838493347168, "learning_rate": 3.9000000000000006e-05, "loss": 0.1341, "step": 2332 }, { "epoch": 22.0, "eval_LOCATION_f1": 0.8211920529801324, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7560975609756098, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6046511627906976, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.5492957746478874, "eval_ORGANIZATION_recall": 0.6724137931034483, "eval_PERSON_f1": 0.825, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7857142857142857, "eval_PERSON_recall": 0.868421052631579, "eval_QUANTITY_f1": 0.7164179104477612, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.8524590163934426, "eval_TIME_number": 29, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.13648565113544464, "eval_overall_accuracy": 0.9564660691421255, "eval_overall_f1": 0.7774725274725275, "eval_overall_precision": 0.7256410256410256, "eval_overall_recall": 0.8372781065088757, "eval_runtime": 0.292, "eval_samples_per_second": 640.416, "eval_steps_per_second": 10.274, "step": 2332 }, { "epoch": 23.0, "grad_norm": 0.791005551815033, "learning_rate": 3.85e-05, "loss": 0.1304, "step": 2438 }, { "epoch": 23.0, "eval_LOCATION_f1": 0.8187919463087248, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7625, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.625, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.5714285714285714, "eval_ORGANIZATION_recall": 0.6896551724137931, "eval_PERSON_f1": 0.8297213622291022, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.783625730994152, "eval_PERSON_recall": 0.881578947368421, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8524590163934426, "eval_TIME_number": 29, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.13903699815273285, "eval_overall_accuracy": 0.9551856594110115, "eval_overall_f1": 0.7846364883401921, "eval_overall_precision": 0.731457800511509, "eval_overall_recall": 0.8461538461538461, "eval_runtime": 0.2925, "eval_samples_per_second": 639.291, "eval_steps_per_second": 10.256, "step": 2438 }, { "epoch": 24.0, "grad_norm": 1.3590947389602661, "learning_rate": 3.8e-05, "loss": 0.1318, "step": 2544 }, { "epoch": 24.0, "eval_LOCATION_f1": 0.8104575163398693, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.65625, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6, "eval_ORGANIZATION_recall": 0.7241379310344828, "eval_PERSON_f1": 0.8267477203647415, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.768361581920904, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.6956521739130435, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6153846153846154, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.75, "eval_TIME_number": 29, "eval_TIME_precision": 0.6857142857142857, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.14613154530525208, "eval_overall_accuracy": 0.9513444302176697, "eval_overall_f1": 0.775235531628533, "eval_overall_precision": 0.7111111111111111, "eval_overall_recall": 0.8520710059171598, "eval_runtime": 0.2919, "eval_samples_per_second": 640.557, "eval_steps_per_second": 10.276, "step": 2544 }, { "epoch": 25.0, "grad_norm": 1.1456764936447144, "learning_rate": 3.7500000000000003e-05, "loss": 0.1283, "step": 2650 }, { "epoch": 25.0, "eval_LOCATION_f1": 0.8266666666666668, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7654320987654321, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6511627906976745, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.5915492957746479, "eval_ORGANIZATION_recall": 0.7241379310344828, "eval_PERSON_f1": 0.8553459119496855, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8192771084337349, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.631578947368421, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7619047619047619, "eval_TIME_number": 29, "eval_TIME_precision": 0.7058823529411765, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13710016012191772, "eval_overall_accuracy": 0.9564660691421255, "eval_overall_f1": 0.7912087912087913, "eval_overall_precision": 0.7384615384615385, "eval_overall_recall": 0.8520710059171598, "eval_runtime": 0.2922, "eval_samples_per_second": 640.035, "eval_steps_per_second": 10.268, "step": 2650 }, { "epoch": 26.0, "grad_norm": 1.2503166198730469, "learning_rate": 3.7e-05, "loss": 0.1235, "step": 2756 }, { "epoch": 26.0, "eval_LOCATION_f1": 0.8266666666666668, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7654320987654321, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6614173228346457, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6086956521739131, "eval_ORGANIZATION_recall": 0.7241379310344828, "eval_PERSON_f1": 0.8430769230769231, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.791907514450867, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.75, "eval_TIME_number": 29, "eval_TIME_precision": 0.6857142857142857, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13993725180625916, "eval_overall_accuracy": 0.9554417413572344, "eval_overall_f1": 0.790190735694823, "eval_overall_precision": 0.7323232323232324, "eval_overall_recall": 0.8579881656804734, "eval_runtime": 0.2929, "eval_samples_per_second": 638.409, "eval_steps_per_second": 10.242, "step": 2756 }, { "epoch": 27.0, "grad_norm": 0.5744267702102661, "learning_rate": 3.65e-05, "loss": 0.1227, "step": 2862 }, { "epoch": 27.0, "eval_LOCATION_f1": 0.8322147651006713, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.775, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6206896551724138, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6206896551724138, "eval_ORGANIZATION_recall": 0.6206896551724138, "eval_PERSON_f1": 0.8500000000000001, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8095238095238095, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.7164179104477612, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.8196721311475409, "eval_TIME_number": 29, "eval_TIME_precision": 0.78125, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.13400302827358246, "eval_overall_accuracy": 0.9559539052496799, "eval_overall_f1": 0.79382889200561, "eval_overall_precision": 0.7546666666666667, "eval_overall_recall": 0.8372781065088757, "eval_runtime": 0.2913, "eval_samples_per_second": 642.045, "eval_steps_per_second": 10.3, "step": 2862 }, { "epoch": 28.0, "grad_norm": 2.922327995300293, "learning_rate": 3.6e-05, "loss": 0.1237, "step": 2968 }, { "epoch": 28.0, "eval_LOCATION_f1": 0.8322147651006713, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.775, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6393442622950819, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.609375, "eval_ORGANIZATION_recall": 0.6724137931034483, "eval_PERSON_f1": 0.8589341692789968, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8203592814371258, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7575757575757577, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13434159755706787, "eval_overall_accuracy": 0.9574903969270167, "eval_overall_f1": 0.7994428969359332, "eval_overall_precision": 0.7552631578947369, "eval_overall_recall": 0.849112426035503, "eval_runtime": 0.2921, "eval_samples_per_second": 640.264, "eval_steps_per_second": 10.272, "step": 2968 }, { "epoch": 29.0, "grad_norm": 0.862956702709198, "learning_rate": 3.55e-05, "loss": 0.1185, "step": 3074 }, { "epoch": 29.0, "eval_LOCATION_f1": 0.8456375838926175, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7875, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6324786324786326, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6271186440677966, "eval_ORGANIZATION_recall": 0.6379310344827587, "eval_PERSON_f1": 0.8589341692789968, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8203592814371258, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7384615384615385, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6857142857142857, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13340412080287933, "eval_overall_accuracy": 0.9574903969270167, "eval_overall_f1": 0.800561797752809, "eval_overall_precision": 0.7620320855614974, "eval_overall_recall": 0.8431952662721893, "eval_runtime": 0.2929, "eval_samples_per_second": 638.377, "eval_steps_per_second": 10.241, "step": 3074 }, { "epoch": 30.0, "grad_norm": 1.2341248989105225, "learning_rate": 3.5e-05, "loss": 0.1188, "step": 3180 }, { "epoch": 30.0, "eval_LOCATION_f1": 0.8378378378378378, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7848101265822784, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6446280991735537, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6190476190476191, "eval_ORGANIZATION_recall": 0.6724137931034483, "eval_PERSON_f1": 0.8517350157728707, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8181818181818182, "eval_PERSON_recall": 0.8881578947368421, "eval_QUANTITY_f1": 0.7384615384615385, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6857142857142857, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.8196721311475409, "eval_TIME_number": 29, "eval_TIME_precision": 0.78125, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.12923994660377502, "eval_overall_accuracy": 0.9582586427656851, "eval_overall_f1": 0.800561797752809, "eval_overall_precision": 0.7620320855614974, "eval_overall_recall": 0.8431952662721893, "eval_runtime": 0.2916, "eval_samples_per_second": 641.346, "eval_steps_per_second": 10.289, "step": 3180 }, { "epoch": 31.0, "grad_norm": 0.7088314890861511, "learning_rate": 3.45e-05, "loss": 0.1157, "step": 3286 }, { "epoch": 31.0, "eval_LOCATION_f1": 0.8322147651006713, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.775, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6050420168067226, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.5901639344262295, "eval_ORGANIZATION_recall": 0.6206896551724138, "eval_PERSON_f1": 0.8411214953271028, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7988165680473372, "eval_PERSON_recall": 0.8881578947368421, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12962517142295837, "eval_overall_accuracy": 0.9580025608194622, "eval_overall_f1": 0.787709497206704, "eval_overall_precision": 0.746031746031746, "eval_overall_recall": 0.834319526627219, "eval_runtime": 0.2921, "eval_samples_per_second": 640.291, "eval_steps_per_second": 10.272, "step": 3286 }, { "epoch": 32.0, "grad_norm": 1.4589393138885498, "learning_rate": 3.4000000000000007e-05, "loss": 0.1159, "step": 3392 }, { "epoch": 32.0, "eval_LOCATION_f1": 0.8378378378378378, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7848101265822784, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6166666666666667, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.5967741935483871, "eval_ORGANIZATION_recall": 0.6379310344827587, "eval_PERSON_f1": 0.8427672955974843, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8072289156626506, "eval_PERSON_recall": 0.881578947368421, "eval_QUANTITY_f1": 0.7384615384615385, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6857142857142857, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.12884514033794403, "eval_overall_accuracy": 0.9582586427656851, "eval_overall_f1": 0.7932489451476793, "eval_overall_precision": 0.7560321715817694, "eval_overall_recall": 0.834319526627219, "eval_runtime": 0.2858, "eval_samples_per_second": 654.233, "eval_steps_per_second": 10.496, "step": 3392 }, { "epoch": 33.0, "grad_norm": 0.7174299955368042, "learning_rate": 3.35e-05, "loss": 0.1156, "step": 3498 }, { "epoch": 33.0, "eval_LOCATION_f1": 0.8513513513513514, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.628099173553719, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6031746031746031, "eval_ORGANIZATION_recall": 0.6551724137931034, "eval_PERSON_f1": 0.8417721518987342, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8109756097560976, "eval_PERSON_recall": 0.875, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7868852459016394, "eval_TIME_number": 29, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12961573898792267, "eval_overall_accuracy": 0.9582586427656851, "eval_overall_f1": 0.7960618846694796, "eval_overall_precision": 0.7587131367292225, "eval_overall_recall": 0.8372781065088757, "eval_runtime": 0.2928, "eval_samples_per_second": 638.6, "eval_steps_per_second": 10.245, "step": 3498 }, { "epoch": 34.0, "grad_norm": 1.449804663658142, "learning_rate": 3.3e-05, "loss": 0.1105, "step": 3604 }, { "epoch": 34.0, "eval_LOCATION_f1": 0.8435374149659864, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6962962962962962, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6103896103896104, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8580441640378549, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8242424242424242, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.746268656716418, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13476641476154327, "eval_overall_accuracy": 0.9587708066581306, "eval_overall_f1": 0.8076923076923076, "eval_overall_precision": 0.7538461538461538, "eval_overall_recall": 0.8698224852071006, "eval_runtime": 0.2917, "eval_samples_per_second": 641.12, "eval_steps_per_second": 10.285, "step": 3604 }, { "epoch": 35.0, "grad_norm": 1.4639244079589844, "learning_rate": 3.2500000000000004e-05, "loss": 0.1116, "step": 3710 }, { "epoch": 35.0, "eval_LOCATION_f1": 0.8513513513513514, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6440677966101694, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6333333333333333, "eval_ORGANIZATION_recall": 0.6551724137931034, "eval_PERSON_f1": 0.8500000000000001, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8095238095238095, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.6956521739130435, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6153846153846154, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.1330917477607727, "eval_overall_accuracy": 0.9572343149807938, "eval_overall_f1": 0.7949790794979079, "eval_overall_precision": 0.7519788918205804, "eval_overall_recall": 0.8431952662721893, "eval_runtime": 0.285, "eval_samples_per_second": 656.101, "eval_steps_per_second": 10.526, "step": 3710 }, { "epoch": 36.0, "grad_norm": 0.7658966183662415, "learning_rate": 3.2000000000000005e-05, "loss": 0.1115, "step": 3816 }, { "epoch": 36.0, "eval_LOCATION_f1": 0.8513513513513514, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6393442622950819, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.609375, "eval_ORGANIZATION_recall": 0.6724137931034483, "eval_PERSON_f1": 0.8454258675078864, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8121212121212121, "eval_PERSON_recall": 0.881578947368421, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.1309656947851181, "eval_overall_accuracy": 0.9574903969270167, "eval_overall_f1": 0.7949790794979079, "eval_overall_precision": 0.7519788918205804, "eval_overall_recall": 0.8431952662721893, "eval_runtime": 0.2923, "eval_samples_per_second": 639.654, "eval_steps_per_second": 10.262, "step": 3816 }, { "epoch": 37.0, "grad_norm": 0.6558132767677307, "learning_rate": 3.15e-05, "loss": 0.1102, "step": 3922 }, { "epoch": 37.0, "eval_LOCATION_f1": 0.8456375838926175, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7875, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7049180327868853, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.671875, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.8463949843260188, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8083832335329342, "eval_PERSON_recall": 0.8881578947368421, "eval_QUANTITY_f1": 0.7246376811594204, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6410256410256411, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13514076173305511, "eval_overall_accuracy": 0.9590268886043534, "eval_overall_f1": 0.8044382801664354, "eval_overall_precision": 0.7571801566579635, "eval_overall_recall": 0.8579881656804734, "eval_runtime": 0.2919, "eval_samples_per_second": 640.546, "eval_steps_per_second": 10.276, "step": 3922 }, { "epoch": 38.0, "grad_norm": 1.0988456010818481, "learning_rate": 3.1e-05, "loss": 0.1082, "step": 4028 }, { "epoch": 38.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7230769230769231, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6527777777777778, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.85625, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8154761904761905, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7246376811594204, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6410256410256411, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13633978366851807, "eval_overall_accuracy": 0.9595390524967989, "eval_overall_f1": 0.8131868131868132, "eval_overall_precision": 0.7589743589743589, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.2917, "eval_samples_per_second": 640.963, "eval_steps_per_second": 10.283, "step": 4028 }, { "epoch": 39.0, "grad_norm": 2.279130458831787, "learning_rate": 3.05e-05, "loss": 0.1055, "step": 4134 }, { "epoch": 39.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7107438016528926, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6825396825396826, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.8490566037735849, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8132530120481928, "eval_PERSON_recall": 0.8881578947368421, "eval_QUANTITY_f1": 0.746268656716418, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7868852459016394, "eval_TIME_number": 29, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.1300368756055832, "eval_overall_accuracy": 0.9600512163892445, "eval_overall_f1": 0.8123249299719889, "eval_overall_precision": 0.7712765957446809, "eval_overall_recall": 0.8579881656804734, "eval_runtime": 0.2909, "eval_samples_per_second": 642.755, "eval_steps_per_second": 10.312, "step": 4134 }, { "epoch": 40.0, "grad_norm": 1.3240655660629272, "learning_rate": 3e-05, "loss": 0.1041, "step": 4240 }, { "epoch": 40.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7107438016528926, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6825396825396826, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.8526645768025078, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8143712574850299, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.631578947368421, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.1312866359949112, "eval_overall_accuracy": 0.9595390524967989, "eval_overall_f1": 0.8089260808926082, "eval_overall_precision": 0.7651715039577837, "eval_overall_recall": 0.8579881656804734, "eval_runtime": 0.2908, "eval_samples_per_second": 643.094, "eval_steps_per_second": 10.317, "step": 4240 }, { "epoch": 41.0, "grad_norm": 0.6957283616065979, "learning_rate": 2.95e-05, "loss": 0.1046, "step": 4346 }, { "epoch": 41.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7068965517241379, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7068965517241379, "eval_ORGANIZATION_recall": 0.7068965517241379, "eval_PERSON_f1": 0.8535825545171339, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8106508875739645, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8196721311475409, "eval_TIME_number": 29, "eval_TIME_precision": 0.78125, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.12765058875083923, "eval_overall_accuracy": 0.9605633802816902, "eval_overall_f1": 0.8208744710860366, "eval_overall_precision": 0.784366576819407, "eval_overall_recall": 0.8609467455621301, "eval_runtime": 0.2916, "eval_samples_per_second": 641.373, "eval_steps_per_second": 10.289, "step": 4346 }, { "epoch": 42.0, "grad_norm": 1.2302607297897339, "learning_rate": 2.9e-05, "loss": 0.1035, "step": 4452 }, { "epoch": 42.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6610169491525424, "eval_ORGANIZATION_recall": 0.6724137931034483, "eval_PERSON_f1": 0.8589341692789968, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8203592814371258, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8196721311475409, "eval_TIME_number": 29, "eval_TIME_precision": 0.78125, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.1273678094148636, "eval_overall_accuracy": 0.9610755441741358, "eval_overall_f1": 0.8152327221438647, "eval_overall_precision": 0.7789757412398922, "eval_overall_recall": 0.8550295857988166, "eval_runtime": 0.2858, "eval_samples_per_second": 654.203, "eval_steps_per_second": 10.495, "step": 4452 }, { "epoch": 43.0, "grad_norm": 1.3074296712875366, "learning_rate": 2.8499999999999998e-05, "loss": 0.1032, "step": 4558 }, { "epoch": 43.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6984126984126984, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6470588235294118, "eval_ORGANIZATION_recall": 0.7586206896551724, "eval_PERSON_f1": 0.8509316770186336, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8058823529411765, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7164179104477612, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13292378187179565, "eval_overall_accuracy": 0.9587708066581306, "eval_overall_f1": 0.8066298342541437, "eval_overall_precision": 0.7564766839378239, "eval_overall_recall": 0.863905325443787, "eval_runtime": 0.2869, "eval_samples_per_second": 651.864, "eval_steps_per_second": 10.458, "step": 4558 }, { "epoch": 44.0, "grad_norm": 4.577354907989502, "learning_rate": 2.8000000000000003e-05, "loss": 0.1024, "step": 4664 }, { "epoch": 44.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.711864406779661, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7, "eval_ORGANIZATION_recall": 0.7241379310344828, "eval_PERSON_f1": 0.8490566037735849, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8132530120481928, "eval_PERSON_recall": 0.8881578947368421, "eval_QUANTITY_f1": 0.7272727272727272, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6666666666666666, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.8196721311475409, "eval_TIME_number": 29, "eval_TIME_precision": 0.78125, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.12674523890018463, "eval_overall_accuracy": 0.9613316261203585, "eval_overall_f1": 0.8152327221438647, "eval_overall_precision": 0.7789757412398922, "eval_overall_recall": 0.8550295857988166, "eval_runtime": 0.2861, "eval_samples_per_second": 653.585, "eval_steps_per_second": 10.485, "step": 4664 }, { "epoch": 45.0, "grad_norm": 1.4018518924713135, "learning_rate": 2.7500000000000004e-05, "loss": 0.1002, "step": 4770 }, { "epoch": 45.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7301587301587301, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6764705882352942, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.8526645768025078, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8143712574850299, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7868852459016394, "eval_TIME_number": 29, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13057196140289307, "eval_overall_accuracy": 0.9610755441741358, "eval_overall_f1": 0.8200836820083682, "eval_overall_precision": 0.7757255936675461, "eval_overall_recall": 0.8698224852071006, "eval_runtime": 0.2862, "eval_samples_per_second": 653.329, "eval_steps_per_second": 10.481, "step": 4770 }, { "epoch": 46.0, "grad_norm": 1.6696031093597412, "learning_rate": 2.7000000000000002e-05, "loss": 0.1001, "step": 4876 }, { "epoch": 46.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7580645161290323, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7121212121212122, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8526645768025078, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8143712574850299, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7868852459016394, "eval_TIME_number": 29, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12734322249889374, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8251748251748251, "eval_overall_precision": 0.7824933687002652, "eval_overall_recall": 0.8727810650887574, "eval_runtime": 0.285, "eval_samples_per_second": 656.038, "eval_steps_per_second": 10.525, "step": 4876 }, { "epoch": 47.0, "grad_norm": 1.0449410676956177, "learning_rate": 2.6500000000000004e-05, "loss": 0.0991, "step": 4982 }, { "epoch": 47.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7049180327868853, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.671875, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.8553459119496855, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8192771084337349, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.7272727272727272, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6666666666666666, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7868852459016394, "eval_TIME_number": 29, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13027527928352356, "eval_overall_accuracy": 0.9605633802816902, "eval_overall_f1": 0.8134642356241234, "eval_overall_precision": 0.7733333333333333, "eval_overall_recall": 0.8579881656804734, "eval_runtime": 0.2853, "eval_samples_per_second": 655.416, "eval_steps_per_second": 10.515, "step": 4982 }, { "epoch": 48.0, "grad_norm": 0.8292348980903625, "learning_rate": 2.6000000000000002e-05, "loss": 0.097, "step": 5088 }, { "epoch": 48.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7166666666666668, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6935483870967742, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.8553459119496855, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8192771084337349, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8196721311475409, "eval_TIME_number": 29, "eval_TIME_precision": 0.78125, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.12755466997623444, "eval_overall_accuracy": 0.9615877080665813, "eval_overall_f1": 0.8225352112676056, "eval_overall_precision": 0.7849462365591398, "eval_overall_recall": 0.863905325443787, "eval_runtime": 0.287, "eval_samples_per_second": 651.508, "eval_steps_per_second": 10.452, "step": 5088 }, { "epoch": 49.0, "grad_norm": 1.932066798210144, "learning_rate": 2.5500000000000003e-05, "loss": 0.0977, "step": 5194 }, { "epoch": 49.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7317073170731708, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6923076923076923, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.8553459119496855, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8192771084337349, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.7272727272727272, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6666666666666666, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.8196721311475409, "eval_TIME_number": 29, "eval_TIME_precision": 0.78125, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.1271757185459137, "eval_overall_accuracy": 0.9618437900128041, "eval_overall_f1": 0.8207282913165266, "eval_overall_precision": 0.7792553191489362, "eval_overall_recall": 0.8668639053254438, "eval_runtime": 0.2859, "eval_samples_per_second": 654.146, "eval_steps_per_second": 10.494, "step": 5194 }, { "epoch": 50.0, "grad_norm": 3.0932295322418213, "learning_rate": 2.5e-05, "loss": 0.0972, "step": 5300 }, { "epoch": 50.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6896551724137931, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6896551724137931, "eval_ORGANIZATION_recall": 0.6896551724137931, "eval_PERSON_f1": 0.8454258675078864, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8121212121212121, "eval_PERSON_recall": 0.881578947368421, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8135593220338982, "eval_TIME_number": 29, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12482242286205292, "eval_overall_accuracy": 0.9608194622279129, "eval_overall_f1": 0.813655761024182, "eval_overall_precision": 0.7835616438356164, "eval_overall_recall": 0.8461538461538461, "eval_runtime": 0.2852, "eval_samples_per_second": 655.67, "eval_steps_per_second": 10.519, "step": 5300 }, { "epoch": 51.0, "grad_norm": 2.206186532974243, "learning_rate": 2.45e-05, "loss": 0.096, "step": 5406 }, { "epoch": 51.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7213114754098361, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6875, "eval_ORGANIZATION_recall": 0.7586206896551724, "eval_PERSON_f1": 0.8553459119496855, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8192771084337349, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7868852459016394, "eval_TIME_number": 29, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12892574071884155, "eval_overall_accuracy": 0.9615877080665813, "eval_overall_f1": 0.8202247191011235, "eval_overall_precision": 0.7807486631016043, "eval_overall_recall": 0.863905325443787, "eval_runtime": 0.2876, "eval_samples_per_second": 650.266, "eval_steps_per_second": 10.432, "step": 5406 }, { "epoch": 52.0, "grad_norm": 1.056382179260254, "learning_rate": 2.4e-05, "loss": 0.0942, "step": 5512 }, { "epoch": 52.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7596899224806202, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6901408450704225, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.8652037617554859, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8263473053892215, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.7164179104477612, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13124997913837433, "eval_overall_accuracy": 0.9613316261203585, "eval_overall_f1": 0.8243430152143846, "eval_overall_precision": 0.7740259740259741, "eval_overall_recall": 0.8816568047337278, "eval_runtime": 0.2864, "eval_samples_per_second": 652.86, "eval_steps_per_second": 10.474, "step": 5512 }, { "epoch": 53.0, "grad_norm": 0.8895484805107117, "learning_rate": 2.35e-05, "loss": 0.096, "step": 5618 }, { "epoch": 53.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7377049180327868, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.703125, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.8526645768025078, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8143712574850299, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12694130837917328, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8230337078651686, "eval_overall_precision": 0.7834224598930482, "eval_overall_recall": 0.8668639053254438, "eval_runtime": 0.2864, "eval_samples_per_second": 652.82, "eval_steps_per_second": 10.473, "step": 5618 }, { "epoch": 54.0, "grad_norm": 0.746292769908905, "learning_rate": 2.3000000000000003e-05, "loss": 0.092, "step": 5724 }, { "epoch": 54.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7107438016528926, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6825396825396826, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.8454258675078864, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8121212121212121, "eval_PERSON_recall": 0.881578947368421, "eval_QUANTITY_f1": 0.7575757575757577, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12707680463790894, "eval_overall_accuracy": 0.9605633802816902, "eval_overall_f1": 0.8117977528089887, "eval_overall_precision": 0.7727272727272727, "eval_overall_recall": 0.8550295857988166, "eval_runtime": 0.2859, "eval_samples_per_second": 654.16, "eval_steps_per_second": 10.495, "step": 5724 }, { "epoch": 55.0, "grad_norm": 1.227086067199707, "learning_rate": 2.25e-05, "loss": 0.0937, "step": 5830 }, { "epoch": 55.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.75, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6857142857142857, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.8580441640378549, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8242424242424242, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.746268656716418, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7868852459016394, "eval_TIME_number": 29, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12925828993320465, "eval_overall_accuracy": 0.9613316261203585, "eval_overall_f1": 0.82336578581363, "eval_overall_precision": 0.7769028871391076, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.2871, "eval_samples_per_second": 651.355, "eval_steps_per_second": 10.45, "step": 5830 }, { "epoch": 56.0, "grad_norm": 0.898246169090271, "learning_rate": 2.2000000000000003e-05, "loss": 0.092, "step": 5936 }, { "epoch": 56.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6890756302521007, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6721311475409836, "eval_ORGANIZATION_recall": 0.7068965517241379, "eval_PERSON_f1": 0.8490566037735849, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8132530120481928, "eval_PERSON_recall": 0.8881578947368421, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12755441665649414, "eval_overall_accuracy": 0.9605633802816902, "eval_overall_f1": 0.8112676056338027, "eval_overall_precision": 0.7741935483870968, "eval_overall_recall": 0.8520710059171598, "eval_runtime": 0.287, "eval_samples_per_second": 651.657, "eval_steps_per_second": 10.454, "step": 5936 }, { "epoch": 57.0, "grad_norm": 0.8911055326461792, "learning_rate": 2.15e-05, "loss": 0.0908, "step": 6042 }, { "epoch": 57.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7154471544715447, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.676923076923077, "eval_ORGANIZATION_recall": 0.7586206896551724, "eval_PERSON_f1": 0.8500000000000001, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8095238095238095, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12887853384017944, "eval_overall_accuracy": 0.9605633802816902, "eval_overall_f1": 0.8156424581005586, "eval_overall_precision": 0.7724867724867724, "eval_overall_recall": 0.863905325443787, "eval_runtime": 0.2871, "eval_samples_per_second": 651.377, "eval_steps_per_second": 10.45, "step": 6042 }, { "epoch": 58.0, "grad_norm": 1.0402631759643555, "learning_rate": 2.1e-05, "loss": 0.089, "step": 6148 }, { "epoch": 58.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8500000000000001, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8095238095238095, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7868852459016394, "eval_TIME_number": 29, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12682482600212097, "eval_overall_accuracy": 0.9620998719590269, "eval_overall_f1": 0.8263305322128851, "eval_overall_precision": 0.7845744680851063, "eval_overall_recall": 0.8727810650887574, "eval_runtime": 0.2875, "eval_samples_per_second": 650.326, "eval_steps_per_second": 10.433, "step": 6148 }, { "epoch": 59.0, "grad_norm": 1.190384864807129, "learning_rate": 2.05e-05, "loss": 0.089, "step": 6254 }, { "epoch": 59.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7438016528925621, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7142857142857143, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.8490566037735849, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8132530120481928, "eval_PERSON_recall": 0.8881578947368421, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8135593220338982, "eval_TIME_number": 29, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12504172325134277, "eval_overall_accuracy": 0.9618437900128041, "eval_overall_f1": 0.8236953455571228, "eval_overall_precision": 0.7870619946091644, "eval_overall_recall": 0.863905325443787, "eval_runtime": 0.2873, "eval_samples_per_second": 650.873, "eval_steps_per_second": 10.442, "step": 6254 }, { "epoch": 60.0, "grad_norm": 1.0693303346633911, "learning_rate": 2e-05, "loss": 0.0885, "step": 6360 }, { "epoch": 60.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.736, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6865671641791045, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.8625, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8214285714285714, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.7164179104477612, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13093435764312744, "eval_overall_accuracy": 0.9600512163892445, "eval_overall_f1": 0.8194444444444444, "eval_overall_precision": 0.7722513089005235, "eval_overall_recall": 0.8727810650887574, "eval_runtime": 0.2863, "eval_samples_per_second": 653.072, "eval_steps_per_second": 10.477, "step": 6360 }, { "epoch": 61.0, "grad_norm": 1.5080128908157349, "learning_rate": 1.9500000000000003e-05, "loss": 0.0883, "step": 6466 }, { "epoch": 61.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7272727272727273, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6984126984126984, "eval_ORGANIZATION_recall": 0.7586206896551724, "eval_PERSON_f1": 0.860759493670886, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8292682926829268, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7868852459016394, "eval_TIME_number": 29, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12579382956027985, "eval_overall_accuracy": 0.9618437900128041, "eval_overall_f1": 0.8248587570621468, "eval_overall_precision": 0.7891891891891892, "eval_overall_recall": 0.863905325443787, "eval_runtime": 0.286, "eval_samples_per_second": 653.832, "eval_steps_per_second": 10.489, "step": 6466 }, { "epoch": 62.0, "grad_norm": 1.7690495252609253, "learning_rate": 1.9e-05, "loss": 0.0896, "step": 6572 }, { "epoch": 62.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7166666666666668, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6935483870967742, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.8616352201257862, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8253012048192772, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7868852459016394, "eval_TIME_number": 29, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.1268462985754013, "eval_overall_accuracy": 0.9610755441741358, "eval_overall_f1": 0.8236953455571228, "eval_overall_precision": 0.7870619946091644, "eval_overall_recall": 0.863905325443787, "eval_runtime": 0.2866, "eval_samples_per_second": 652.454, "eval_steps_per_second": 10.467, "step": 6572 }, { "epoch": 63.0, "grad_norm": 0.6065536737442017, "learning_rate": 1.85e-05, "loss": 0.0893, "step": 6678 }, { "epoch": 63.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7226890756302522, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7049180327868853, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.8643533123028391, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8303030303030303, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7575757575757577, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12584134936332703, "eval_overall_accuracy": 0.9615877080665813, "eval_overall_f1": 0.8248587570621468, "eval_overall_precision": 0.7891891891891892, "eval_overall_recall": 0.863905325443787, "eval_runtime": 0.287, "eval_samples_per_second": 651.556, "eval_steps_per_second": 10.453, "step": 6678 }, { "epoch": 64.0, "grad_norm": 1.3564276695251465, "learning_rate": 1.8e-05, "loss": 0.089, "step": 6784 }, { "epoch": 64.0, "eval_LOCATION_f1": 0.8513513513513514, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7559055118110236, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6956521739130435, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.8742138364779874, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8373493975903614, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.7164179104477612, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7419354838709677, "eval_TIME_number": 29, "eval_TIME_precision": 0.696969696969697, "eval_TIME_recall": 0.7931034482758621, "eval_loss": 0.1324695646762848, "eval_overall_accuracy": 0.9603072983354674, "eval_overall_f1": 0.8227146814404432, "eval_overall_precision": 0.7734375, "eval_overall_recall": 0.878698224852071, "eval_runtime": 0.2869, "eval_samples_per_second": 651.773, "eval_steps_per_second": 10.456, "step": 6784 }, { "epoch": 65.0, "grad_norm": 1.3449146747589111, "learning_rate": 1.75e-05, "loss": 0.0892, "step": 6890 }, { "epoch": 65.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7559055118110236, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6956521739130435, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.8742138364779874, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8373493975903614, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.7164179104477612, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7868852459016394, "eval_TIME_number": 29, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13169027864933014, "eval_overall_accuracy": 0.9613316261203585, "eval_overall_f1": 0.8277777777777778, "eval_overall_precision": 0.7801047120418848, "eval_overall_recall": 0.8816568047337278, "eval_runtime": 0.2858, "eval_samples_per_second": 654.304, "eval_steps_per_second": 10.497, "step": 6890 }, { "epoch": 66.0, "grad_norm": 1.0803149938583374, "learning_rate": 1.7000000000000003e-05, "loss": 0.0877, "step": 6996 }, { "epoch": 66.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7540983606557378, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.71875, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.8616352201257862, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8253012048192772, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7575757575757577, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7868852459016394, "eval_TIME_number": 29, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12896300852298737, "eval_overall_accuracy": 0.9620998719590269, "eval_overall_f1": 0.8274894810659188, "eval_overall_precision": 0.7866666666666666, "eval_overall_recall": 0.8727810650887574, "eval_runtime": 0.287, "eval_samples_per_second": 651.516, "eval_steps_per_second": 10.452, "step": 6996 }, { "epoch": 67.0, "grad_norm": 0.9663069248199463, "learning_rate": 1.65e-05, "loss": 0.0856, "step": 7102 }, { "epoch": 67.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7540983606557378, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.71875, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.8761904761904762, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8466257668711656, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.746268656716418, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13050326704978943, "eval_overall_accuracy": 0.9615877080665813, "eval_overall_f1": 0.8302945301542777, "eval_overall_precision": 0.7893333333333333, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.2875, "eval_samples_per_second": 650.493, "eval_steps_per_second": 10.436, "step": 7102 }, { "epoch": 68.0, "grad_norm": 0.8305689692497253, "learning_rate": 1.6000000000000003e-05, "loss": 0.0862, "step": 7208 }, { "epoch": 68.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.765625, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.8742138364779874, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8373493975903614, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.7164179104477612, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7540983606557378, "eval_TIME_number": 29, "eval_TIME_precision": 0.71875, "eval_TIME_recall": 0.7931034482758621, "eval_loss": 0.1334487646818161, "eval_overall_accuracy": 0.9610755441741358, "eval_overall_f1": 0.826629680998613, "eval_overall_precision": 0.7780678851174935, "eval_overall_recall": 0.8816568047337278, "eval_runtime": 0.2862, "eval_samples_per_second": 653.302, "eval_steps_per_second": 10.481, "step": 7208 }, { "epoch": 69.0, "grad_norm": 1.218758463859558, "learning_rate": 1.55e-05, "loss": 0.0867, "step": 7314 }, { "epoch": 69.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7419354838709677, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.696969696969697, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.8769716088328074, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8424242424242424, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7868852459016394, "eval_TIME_number": 29, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13092464208602905, "eval_overall_accuracy": 0.9620998719590269, "eval_overall_f1": 0.8319327731092437, "eval_overall_precision": 0.7898936170212766, "eval_overall_recall": 0.878698224852071, "eval_runtime": 0.2862, "eval_samples_per_second": 653.309, "eval_steps_per_second": 10.481, "step": 7314 }, { "epoch": 70.0, "grad_norm": 2.1350855827331543, "learning_rate": 1.5e-05, "loss": 0.0845, "step": 7420 }, { "epoch": 70.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7058823529411765, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6885245901639344, "eval_ORGANIZATION_recall": 0.7241379310344828, "eval_PERSON_f1": 0.8670886075949367, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8353658536585366, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.1256009340286255, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8255319148936171, "eval_overall_precision": 0.7929155313351499, "eval_overall_recall": 0.8609467455621301, "eval_runtime": 0.2864, "eval_samples_per_second": 652.871, "eval_steps_per_second": 10.474, "step": 7420 }, { "epoch": 71.0, "grad_norm": 0.7863230109214783, "learning_rate": 1.45e-05, "loss": 0.0864, "step": 7526 }, { "epoch": 71.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7377049180327868, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.703125, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.8526645768025078, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8143712574850299, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12498261779546738, "eval_overall_accuracy": 0.9620998719590269, "eval_overall_f1": 0.8253521126760562, "eval_overall_precision": 0.7876344086021505, "eval_overall_recall": 0.8668639053254438, "eval_runtime": 0.2858, "eval_samples_per_second": 654.227, "eval_steps_per_second": 10.496, "step": 7526 }, { "epoch": 72.0, "grad_norm": 0.7980266809463501, "learning_rate": 1.4000000000000001e-05, "loss": 0.0854, "step": 7632 }, { "epoch": 72.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7479674796747967, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7076923076923077, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.8761904761904762, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8466257668711656, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12747858464717865, "eval_overall_accuracy": 0.9633802816901409, "eval_overall_f1": 0.8338028169014083, "eval_overall_precision": 0.7956989247311828, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.2867, "eval_samples_per_second": 652.26, "eval_steps_per_second": 10.464, "step": 7632 }, { "epoch": 73.0, "grad_norm": 1.180917739868164, "learning_rate": 1.3500000000000001e-05, "loss": 0.0843, "step": 7738 }, { "epoch": 73.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7166666666666668, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6935483870967742, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.8670886075949367, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8353658536585366, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.761904761904762, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7272727272727273, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12380669265985489, "eval_overall_accuracy": 0.9618437900128041, "eval_overall_f1": 0.8243626062322946, "eval_overall_precision": 0.7907608695652174, "eval_overall_recall": 0.8609467455621301, "eval_runtime": 0.2872, "eval_samples_per_second": 651.041, "eval_steps_per_second": 10.445, "step": 7738 }, { "epoch": 74.0, "grad_norm": 1.4001702070236206, "learning_rate": 1.3000000000000001e-05, "loss": 0.0871, "step": 7844 }, { "epoch": 74.0, "eval_LOCATION_f1": 0.8513513513513514, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7741935483870968, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7272727272727273, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.8734177215189874, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12895327806472778, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8359046283309958, "eval_overall_precision": 0.7946666666666666, "eval_overall_recall": 0.8816568047337278, "eval_runtime": 0.2856, "eval_samples_per_second": 654.718, "eval_steps_per_second": 10.503, "step": 7844 }, { "epoch": 75.0, "grad_norm": 2.398920774459839, "learning_rate": 1.25e-05, "loss": 0.0836, "step": 7950 }, { "epoch": 75.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8698412698412699, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8404907975460123, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12761665880680084, "eval_overall_accuracy": 0.9626120358514725, "eval_overall_f1": 0.8338028169014083, "eval_overall_precision": 0.7956989247311828, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.2871, "eval_samples_per_second": 651.419, "eval_steps_per_second": 10.451, "step": 7950 }, { "epoch": 76.0, "grad_norm": 1.136534333229065, "learning_rate": 1.2e-05, "loss": 0.0825, "step": 8056 }, { "epoch": 76.0, "eval_LOCATION_f1": 0.8513513513513514, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7741935483870968, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7272727272727273, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.8734177215189874, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12773388624191284, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8359046283309958, "eval_overall_precision": 0.7946666666666666, "eval_overall_recall": 0.8816568047337278, "eval_runtime": 0.2872, "eval_samples_per_second": 651.096, "eval_steps_per_second": 10.445, "step": 8056 }, { "epoch": 77.0, "grad_norm": 0.9836848974227905, "learning_rate": 1.1500000000000002e-05, "loss": 0.0838, "step": 8162 }, { "epoch": 77.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8634920634920634, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8343558282208589, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12512867152690887, "eval_overall_accuracy": 0.9620998719590269, "eval_overall_f1": 0.8321579689703809, "eval_overall_precision": 0.7951482479784366, "eval_overall_recall": 0.8727810650887574, "eval_runtime": 0.2862, "eval_samples_per_second": 653.375, "eval_steps_per_second": 10.482, "step": 8162 }, { "epoch": 78.0, "grad_norm": 0.9845781326293945, "learning_rate": 1.1000000000000001e-05, "loss": 0.0846, "step": 8268 }, { "epoch": 78.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7580645161290323, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7121212121212122, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8698412698412699, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8404907975460123, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12692533433437347, "eval_overall_accuracy": 0.9626120358514725, "eval_overall_f1": 0.8338028169014083, "eval_overall_precision": 0.7956989247311828, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.2872, "eval_samples_per_second": 651.198, "eval_steps_per_second": 10.447, "step": 8268 }, { "epoch": 79.0, "grad_norm": 0.7519234418869019, "learning_rate": 1.05e-05, "loss": 0.0845, "step": 8374 }, { "epoch": 79.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7580645161290323, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7121212121212122, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8670886075949367, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8353658536585366, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12639828026294708, "eval_overall_accuracy": 0.9626120358514725, "eval_overall_f1": 0.8326300984528833, "eval_overall_precision": 0.7935656836461126, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.286, "eval_samples_per_second": 653.821, "eval_steps_per_second": 10.489, "step": 8374 }, { "epoch": 80.0, "grad_norm": 0.60317462682724, "learning_rate": 1e-05, "loss": 0.0816, "step": 8480 }, { "epoch": 80.0, "eval_LOCATION_f1": 0.8513513513513514, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7777777777777778, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7205882352941176, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.8643533123028391, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8303030303030303, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7540983606557378, "eval_TIME_number": 29, "eval_TIME_precision": 0.71875, "eval_TIME_recall": 0.7931034482758621, "eval_loss": 0.129006490111351, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8284518828451882, "eval_overall_precision": 0.783641160949868, "eval_overall_recall": 0.878698224852071, "eval_runtime": 0.2865, "eval_samples_per_second": 652.715, "eval_steps_per_second": 10.471, "step": 8480 }, { "epoch": 81.0, "grad_norm": 1.9326316118240356, "learning_rate": 9.5e-06, "loss": 0.0821, "step": 8586 }, { "epoch": 81.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7580645161290323, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7121212121212122, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8670886075949367, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8353658536585366, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12803098559379578, "eval_overall_accuracy": 0.9626120358514725, "eval_overall_f1": 0.8326300984528833, "eval_overall_precision": 0.7935656836461126, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.2882, "eval_samples_per_second": 648.79, "eval_steps_per_second": 10.408, "step": 8586 }, { "epoch": 82.0, "grad_norm": 0.8638326525688171, "learning_rate": 9e-06, "loss": 0.0823, "step": 8692 }, { "epoch": 82.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7777777777777778, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7205882352941176, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.8769716088328074, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8424242424242424, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7540983606557378, "eval_TIME_number": 29, "eval_TIME_precision": 0.71875, "eval_TIME_recall": 0.7931034482758621, "eval_loss": 0.13058307766914368, "eval_overall_accuracy": 0.963124199743918, "eval_overall_f1": 0.835195530726257, "eval_overall_precision": 0.791005291005291, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.2878, "eval_samples_per_second": 649.709, "eval_steps_per_second": 10.423, "step": 8692 }, { "epoch": 83.0, "grad_norm": 1.4908857345581055, "learning_rate": 8.500000000000002e-06, "loss": 0.082, "step": 8798 }, { "epoch": 83.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8634920634920634, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8343558282208589, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12721218168735504, "eval_overall_accuracy": 0.9626120358514725, "eval_overall_f1": 0.8321579689703809, "eval_overall_precision": 0.7951482479784366, "eval_overall_recall": 0.8727810650887574, "eval_runtime": 0.2865, "eval_samples_per_second": 652.793, "eval_steps_per_second": 10.473, "step": 8798 }, { "epoch": 84.0, "grad_norm": 1.9748855829238892, "learning_rate": 8.000000000000001e-06, "loss": 0.0796, "step": 8904 }, { "epoch": 84.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7580645161290323, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7121212121212122, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8698412698412699, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8404907975460123, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7666666666666667, "eval_TIME_number": 29, "eval_TIME_precision": 0.7419354838709677, "eval_TIME_recall": 0.7931034482758621, "eval_loss": 0.1286100149154663, "eval_overall_accuracy": 0.9620998719590269, "eval_overall_f1": 0.829817158931083, "eval_overall_precision": 0.7908847184986595, "eval_overall_recall": 0.8727810650887574, "eval_runtime": 0.2859, "eval_samples_per_second": 654.048, "eval_steps_per_second": 10.493, "step": 8904 }, { "epoch": 85.0, "grad_norm": 1.6315678358078003, "learning_rate": 7.5e-06, "loss": 0.082, "step": 9010 }, { "epoch": 85.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8634920634920634, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8343558282208589, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7666666666666667, "eval_TIME_number": 29, "eval_TIME_precision": 0.7419354838709677, "eval_TIME_recall": 0.7931034482758621, "eval_loss": 0.1274917721748352, "eval_overall_accuracy": 0.9618437900128041, "eval_overall_f1": 0.828169014084507, "eval_overall_precision": 0.7903225806451613, "eval_overall_recall": 0.8698224852071006, "eval_runtime": 0.2868, "eval_samples_per_second": 651.959, "eval_steps_per_second": 10.459, "step": 9010 }, { "epoch": 86.0, "grad_norm": 2.9988150596618652, "learning_rate": 7.000000000000001e-06, "loss": 0.0827, "step": 9116 }, { "epoch": 86.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8698412698412699, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8404907975460123, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12789824604988098, "eval_overall_accuracy": 0.9620998719590269, "eval_overall_f1": 0.8338028169014083, "eval_overall_precision": 0.7956989247311828, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.2874, "eval_samples_per_second": 650.709, "eval_steps_per_second": 10.439, "step": 9116 }, { "epoch": 87.0, "grad_norm": 2.0143356323242188, "learning_rate": 6.5000000000000004e-06, "loss": 0.0819, "step": 9222 }, { "epoch": 87.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8769716088328074, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8424242424242424, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12826670706272125, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8382559774964837, "eval_overall_precision": 0.7989276139410187, "eval_overall_recall": 0.8816568047337278, "eval_runtime": 0.2871, "eval_samples_per_second": 651.319, "eval_steps_per_second": 10.449, "step": 9222 }, { "epoch": 88.0, "grad_norm": 1.0121877193450928, "learning_rate": 6e-06, "loss": 0.0775, "step": 9328 }, { "epoch": 88.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8643533123028391, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8303030303030303, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12668804824352264, "eval_overall_accuracy": 0.9626120358514725, "eval_overall_f1": 0.8326300984528833, "eval_overall_precision": 0.7935656836461126, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.286, "eval_samples_per_second": 653.86, "eval_steps_per_second": 10.49, "step": 9328 }, { "epoch": 89.0, "grad_norm": 0.6306910514831543, "learning_rate": 5.500000000000001e-06, "loss": 0.0784, "step": 9434 }, { "epoch": 89.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8734177215189874, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7666666666666667, "eval_TIME_number": 29, "eval_TIME_precision": 0.7419354838709677, "eval_TIME_recall": 0.7931034482758621, "eval_loss": 0.12889203429222107, "eval_overall_accuracy": 0.9618437900128041, "eval_overall_f1": 0.8326300984528833, "eval_overall_precision": 0.7935656836461126, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.2862, "eval_samples_per_second": 653.368, "eval_steps_per_second": 10.482, "step": 9434 }, { "epoch": 90.0, "grad_norm": 1.8310757875442505, "learning_rate": 5e-06, "loss": 0.0789, "step": 9540 }, { "epoch": 90.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8634920634920634, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8343558282208589, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12754952907562256, "eval_overall_accuracy": 0.9626120358514725, "eval_overall_f1": 0.8321579689703809, "eval_overall_precision": 0.7951482479784366, "eval_overall_recall": 0.8727810650887574, "eval_runtime": 0.2868, "eval_samples_per_second": 652.02, "eval_steps_per_second": 10.46, "step": 9540 }, { "epoch": 91.0, "grad_norm": 1.1900731325149536, "learning_rate": 4.5e-06, "loss": 0.0808, "step": 9646 }, { "epoch": 91.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7741935483870968, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7272727272727273, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.8734177215189874, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.7575757575757577, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7666666666666667, "eval_TIME_number": 29, "eval_TIME_precision": 0.7419354838709677, "eval_TIME_recall": 0.7931034482758621, "eval_loss": 0.1293194442987442, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8330995792426368, "eval_overall_precision": 0.792, "eval_overall_recall": 0.878698224852071, "eval_runtime": 0.2862, "eval_samples_per_second": 653.306, "eval_steps_per_second": 10.481, "step": 9646 }, { "epoch": 92.0, "grad_norm": 1.54060959815979, "learning_rate": 4.000000000000001e-06, "loss": 0.0788, "step": 9752 }, { "epoch": 92.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8634920634920634, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8343558282208589, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12771408259868622, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8321579689703809, "eval_overall_precision": 0.7951482479784366, "eval_overall_recall": 0.8727810650887574, "eval_runtime": 0.2862, "eval_samples_per_second": 653.35, "eval_steps_per_second": 10.482, "step": 9752 }, { "epoch": 93.0, "grad_norm": 0.6988396644592285, "learning_rate": 3.5000000000000004e-06, "loss": 0.0791, "step": 9858 }, { "epoch": 93.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7741935483870968, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7272727272727273, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.8734177215189874, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.7575757575757577, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12927231192588806, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8359046283309958, "eval_overall_precision": 0.7946666666666666, "eval_overall_recall": 0.8816568047337278, "eval_runtime": 0.2858, "eval_samples_per_second": 654.3, "eval_steps_per_second": 10.497, "step": 9858 }, { "epoch": 94.0, "grad_norm": 1.71950364112854, "learning_rate": 3e-06, "loss": 0.0786, "step": 9964 }, { "epoch": 94.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8670886075949367, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8353658536585366, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12867045402526855, "eval_overall_accuracy": 0.9620998719590269, "eval_overall_f1": 0.8326300984528833, "eval_overall_precision": 0.7935656836461126, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.2924, "eval_samples_per_second": 639.556, "eval_steps_per_second": 10.26, "step": 9964 }, { "epoch": 95.0, "grad_norm": 0.9361959099769592, "learning_rate": 2.5e-06, "loss": 0.0788, "step": 10070 }, { "epoch": 95.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8698412698412699, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8404907975460123, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.1285109966993332, "eval_overall_accuracy": 0.9620998719590269, "eval_overall_f1": 0.8338028169014083, "eval_overall_precision": 0.7956989247311828, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.2879, "eval_samples_per_second": 649.541, "eval_steps_per_second": 10.42, "step": 10070 }, { "epoch": 96.0, "grad_norm": 0.82219398021698, "learning_rate": 2.0000000000000003e-06, "loss": 0.0785, "step": 10176 }, { "epoch": 96.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8769716088328074, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8424242424242424, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.7575757575757577, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12919461727142334, "eval_overall_accuracy": 0.9626120358514725, "eval_overall_f1": 0.8359046283309958, "eval_overall_precision": 0.7946666666666666, "eval_overall_recall": 0.8816568047337278, "eval_runtime": 0.2913, "eval_samples_per_second": 641.926, "eval_steps_per_second": 10.298, "step": 10176 }, { "epoch": 97.0, "grad_norm": 1.4223874807357788, "learning_rate": 1.5e-06, "loss": 0.082, "step": 10282 }, { "epoch": 97.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8698412698412699, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8404907975460123, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7575757575757577, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12852250039577484, "eval_overall_accuracy": 0.9620998719590269, "eval_overall_f1": 0.8326300984528833, "eval_overall_precision": 0.7935656836461126, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.2915, "eval_samples_per_second": 641.413, "eval_steps_per_second": 10.29, "step": 10282 }, { "epoch": 98.0, "grad_norm": 0.9472575187683105, "learning_rate": 1.0000000000000002e-06, "loss": 0.078, "step": 10388 }, { "epoch": 98.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8698412698412699, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8404907975460123, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12840475142002106, "eval_overall_accuracy": 0.9618437900128041, "eval_overall_f1": 0.8338028169014083, "eval_overall_precision": 0.7956989247311828, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.2914, "eval_samples_per_second": 641.68, "eval_steps_per_second": 10.294, "step": 10388 }, { "epoch": 99.0, "grad_norm": 0.753296971321106, "learning_rate": 5.000000000000001e-07, "loss": 0.0783, "step": 10494 }, { "epoch": 99.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8734177215189874, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12838655710220337, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8354430379746836, "eval_overall_precision": 0.7962466487935657, "eval_overall_recall": 0.878698224852071, "eval_runtime": 0.2918, "eval_samples_per_second": 640.87, "eval_steps_per_second": 10.281, "step": 10494 }, { "epoch": 100.0, "grad_norm": 0.6992992758750916, "learning_rate": 0.0, "loss": 0.0773, "step": 10600 }, { "epoch": 100.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8734177215189874, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12858808040618896, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8354430379746836, "eval_overall_precision": 0.7962466487935657, "eval_overall_recall": 0.878698224852071, "eval_runtime": 0.2908, "eval_samples_per_second": 642.981, "eval_steps_per_second": 10.315, "step": 10600 }, { "epoch": 100.0, "step": 10600, "total_flos": 4500604309905474.0, "train_loss": 0.13730014378169797, "train_runtime": 547.2904, "train_samples_per_second": 308.246, "train_steps_per_second": 19.368 } ], "logging_steps": 500, "max_steps": 10600, "num_input_tokens_seen": 0, "num_train_epochs": 100, "save_steps": 500, "total_flos": 4500604309905474.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }