{ "best_metric": null, "best_model_checkpoint": null, "epoch": 100.0, "eval_steps": 500, "global_step": 10600, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 1.0955079793930054, "learning_rate": 4.9500000000000004e-05, "loss": 0.9897, "step": 106 }, { "epoch": 1.0, "eval_LOCATION_f1": 0.0, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.0, "eval_LOCATION_recall": 0.0, "eval_ORGANIZATION_f1": 0.0, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.03508771929824561, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.16666666666666666, "eval_PERSON_recall": 0.0196078431372549, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 31, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.5791746973991394, "eval_overall_accuracy": 0.8382462224424078, "eval_overall_f1": 0.016172506738544475, "eval_overall_precision": 0.12, "eval_overall_recall": 0.008670520231213872, "eval_runtime": 0.9785, "eval_samples_per_second": 191.103, "eval_steps_per_second": 3.066, "step": 106 }, { "epoch": 2.0, "grad_norm": 1.0362498760223389, "learning_rate": 4.9e-05, "loss": 0.4994, "step": 212 }, { "epoch": 2.0, "eval_LOCATION_f1": 0.2391304347826087, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.4782608695652174, "eval_LOCATION_recall": 0.15942028985507245, "eval_ORGANIZATION_f1": 0.022727272727272728, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.037037037037037035, "eval_ORGANIZATION_recall": 0.01639344262295082, "eval_PERSON_f1": 0.6062176165803108, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.5021459227467812, "eval_PERSON_recall": 0.7647058823529411, "eval_QUANTITY_f1": 0.12000000000000002, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.16666666666666666, "eval_QUANTITY_recall": 0.09375, "eval_TIME_f1": 0.4848484848484849, "eval_TIME_number": 31, "eval_TIME_precision": 0.45714285714285713, "eval_TIME_recall": 0.5161290322580645, "eval_loss": 0.3509860038757324, "eval_overall_accuracy": 0.8962100569729997, "eval_overall_f1": 0.43401759530791784, "eval_overall_precision": 0.44047619047619047, "eval_overall_recall": 0.4277456647398844, "eval_runtime": 1.0238, "eval_samples_per_second": 182.658, "eval_steps_per_second": 2.93, "step": 212 }, { "epoch": 3.0, "grad_norm": 1.2612115144729614, "learning_rate": 4.85e-05, "loss": 0.3081, "step": 318 }, { "epoch": 3.0, "eval_LOCATION_f1": 0.6883116883116883, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6235294117647059, "eval_LOCATION_recall": 0.7681159420289855, "eval_ORGANIZATION_f1": 0.39436619718309857, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.345679012345679, "eval_ORGANIZATION_recall": 0.45901639344262296, "eval_PERSON_f1": 0.8369230769230769, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7906976744186046, "eval_PERSON_recall": 0.8888888888888888, "eval_QUANTITY_f1": 0.6111111111111112, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.55, "eval_QUANTITY_recall": 0.6875, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.20474210381507874, "eval_overall_accuracy": 0.9380728263562051, "eval_overall_f1": 0.6982872200263505, "eval_overall_precision": 0.6416464891041163, "eval_overall_recall": 0.7658959537572254, "eval_runtime": 1.0378, "eval_samples_per_second": 180.184, "eval_steps_per_second": 2.891, "step": 318 }, { "epoch": 4.0, "grad_norm": 0.8938269019126892, "learning_rate": 4.8e-05, "loss": 0.2123, "step": 424 }, { "epoch": 4.0, "eval_LOCATION_f1": 0.6826347305389221, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.5816326530612245, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.5801526717557252, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5428571428571428, "eval_ORGANIZATION_recall": 0.6229508196721312, "eval_PERSON_f1": 0.8562874251497005, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7900552486187845, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.6046511627906976, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.48148148148148145, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.72, "eval_TIME_number": 31, "eval_TIME_precision": 0.6136363636363636, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.18629486858844757, "eval_overall_accuracy": 0.9400544959128065, "eval_overall_f1": 0.7339218158890289, "eval_overall_precision": 0.6510067114093959, "eval_overall_recall": 0.8410404624277457, "eval_runtime": 0.994, "eval_samples_per_second": 188.123, "eval_steps_per_second": 3.018, "step": 424 }, { "epoch": 5.0, "grad_norm": 1.1821776628494263, "learning_rate": 4.75e-05, "loss": 0.1737, "step": 530 }, { "epoch": 5.0, "eval_LOCATION_f1": 0.7417218543046358, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6829268292682927, "eval_LOCATION_recall": 0.8115942028985508, "eval_ORGANIZATION_f1": 0.6474820143884893, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5769230769230769, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.8693009118541033, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8125, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.6478873239436619, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5897435897435898, "eval_QUANTITY_recall": 0.71875, "eval_TIME_f1": 0.8615384615384616, "eval_TIME_number": 31, "eval_TIME_precision": 0.8235294117647058, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.14358247816562653, "eval_overall_accuracy": 0.9524399306415655, "eval_overall_f1": 0.7814569536423841, "eval_overall_precision": 0.7212713936430318, "eval_overall_recall": 0.8526011560693642, "eval_runtime": 0.9687, "eval_samples_per_second": 193.04, "eval_steps_per_second": 3.097, "step": 530 }, { "epoch": 6.0, "grad_norm": 0.5935459733009338, "learning_rate": 4.7e-05, "loss": 0.1547, "step": 636 }, { "epoch": 6.0, "eval_LOCATION_f1": 0.7388535031847134, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6590909090909091, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6666666666666667, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5617977528089888, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8827160493827161, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8362573099415205, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.684931506849315, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6097560975609756, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7714285714285716, "eval_TIME_number": 31, "eval_TIME_precision": 0.6923076923076923, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.143008753657341, "eval_overall_accuracy": 0.953183056725291, "eval_overall_f1": 0.7829457364341086, "eval_overall_precision": 0.7079439252336449, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.9772, "eval_samples_per_second": 191.367, "eval_steps_per_second": 3.07, "step": 636 }, { "epoch": 7.0, "grad_norm": 0.4739581048488617, "learning_rate": 4.6500000000000005e-05, "loss": 0.1434, "step": 742 }, { "epoch": 7.0, "eval_LOCATION_f1": 0.7142857142857144, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6470588235294118, "eval_LOCATION_recall": 0.7971014492753623, "eval_ORGANIZATION_f1": 0.6715328467153285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6052631578947368, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8800000000000001, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8313953488372093, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.6923076923076924, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5869565217391305, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8059701492537312, "eval_TIME_number": 31, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14124642312526703, "eval_overall_accuracy": 0.9529353480307159, "eval_overall_f1": 0.7831800262812089, "eval_overall_precision": 0.7180722891566265, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.998, "eval_samples_per_second": 187.368, "eval_steps_per_second": 3.006, "step": 742 }, { "epoch": 8.0, "grad_norm": 0.6086934208869934, "learning_rate": 4.600000000000001e-05, "loss": 0.1316, "step": 848 }, { "epoch": 8.0, "eval_LOCATION_f1": 0.778523489932886, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.725, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6577181208053691, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5568181818181818, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.6944444444444444, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.625, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7323943661971831, "eval_TIME_number": 31, "eval_TIME_precision": 0.65, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13939833641052246, "eval_overall_accuracy": 0.9546693088927422, "eval_overall_f1": 0.7931488801054017, "eval_overall_precision": 0.7288135593220338, "eval_overall_recall": 0.869942196531792, "eval_runtime": 1.0022, "eval_samples_per_second": 186.59, "eval_steps_per_second": 2.993, "step": 848 }, { "epoch": 9.0, "grad_norm": 1.063918113708496, "learning_rate": 4.55e-05, "loss": 0.1279, "step": 954 }, { "epoch": 9.0, "eval_LOCATION_f1": 0.763157894736842, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6987951807228916, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6518518518518518, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5945945945945946, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.897196261682243, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8571428571428571, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7397260273972602, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6585365853658537, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7222222222222222, "eval_TIME_number": 31, "eval_TIME_precision": 0.6341463414634146, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13130132853984833, "eval_overall_accuracy": 0.9564032697547684, "eval_overall_f1": 0.7941567065073042, "eval_overall_precision": 0.7346437346437347, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 1.0067, "eval_samples_per_second": 185.75, "eval_steps_per_second": 2.98, "step": 954 }, { "epoch": 10.0, "grad_norm": 0.9094120860099792, "learning_rate": 4.5e-05, "loss": 0.1211, "step": 1060 }, { "epoch": 10.0, "eval_LOCATION_f1": 0.7702702702702703, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7215189873417721, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6259541984732824, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5857142857142857, "eval_ORGANIZATION_recall": 0.6721311475409836, "eval_PERSON_f1": 0.9148264984227129, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8841463414634146, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8059701492537312, "eval_TIME_number": 31, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.12145308405160904, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8109589041095892, "eval_overall_precision": 0.7708333333333334, "eval_overall_recall": 0.8554913294797688, "eval_runtime": 0.9852, "eval_samples_per_second": 189.802, "eval_steps_per_second": 3.045, "step": 1060 }, { "epoch": 11.0, "grad_norm": 0.7485252022743225, "learning_rate": 4.4500000000000004e-05, "loss": 0.114, "step": 1166 }, { "epoch": 11.0, "eval_LOCATION_f1": 0.7549668874172186, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6951219512195121, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6527777777777777, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5662650602409639, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.896551724137931, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8614457831325302, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7123287671232876, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6341463414634146, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1312883496284485, "eval_overall_accuracy": 0.9571463958384939, "eval_overall_f1": 0.7941567065073042, "eval_overall_precision": 0.7346437346437347, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.9834, "eval_samples_per_second": 190.157, "eval_steps_per_second": 3.051, "step": 1166 }, { "epoch": 12.0, "grad_norm": 1.104870080947876, "learning_rate": 4.4000000000000006e-05, "loss": 0.1087, "step": 1272 }, { "epoch": 12.0, "eval_LOCATION_f1": 0.778523489932886, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.725, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6969696969696969, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.647887323943662, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7105263157894737, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6136363636363636, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.13906444609165192, "eval_overall_accuracy": 0.9561555610601932, "eval_overall_f1": 0.8146143437077131, "eval_overall_precision": 0.7659033078880407, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.9902, "eval_samples_per_second": 188.851, "eval_steps_per_second": 3.03, "step": 1272 }, { "epoch": 13.0, "grad_norm": 0.6125289797782898, "learning_rate": 4.35e-05, "loss": 0.1042, "step": 1378 }, { "epoch": 13.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6811594202898551, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6103896103896104, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7714285714285714, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7105263157894737, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13031348586082458, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.8211382113821138, "eval_overall_precision": 0.7729591836734694, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.9889, "eval_samples_per_second": 189.1, "eval_steps_per_second": 3.034, "step": 1378 }, { "epoch": 14.0, "grad_norm": 2.0589206218719482, "learning_rate": 4.3e-05, "loss": 0.1018, "step": 1484 }, { "epoch": 14.0, "eval_LOCATION_f1": 0.7945205479452054, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7532467532467533, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6911764705882353, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6266666666666667, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9056603773584905, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8727272727272727, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7012987012987012, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7428571428571428, "eval_TIME_number": 31, "eval_TIME_precision": 0.6666666666666666, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14253932237625122, "eval_overall_accuracy": 0.9561555610601932, "eval_overall_f1": 0.8085676037483266, "eval_overall_precision": 0.7531172069825436, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.9977, "eval_samples_per_second": 187.428, "eval_steps_per_second": 3.007, "step": 1484 }, { "epoch": 15.0, "grad_norm": 0.1841476559638977, "learning_rate": 4.25e-05, "loss": 0.0973, "step": 1590 }, { "epoch": 15.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6115702479338844, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6166666666666667, "eval_ORGANIZATION_recall": 0.6065573770491803, "eval_PERSON_f1": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7826086956521738, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7297297297297297, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.875, "eval_TIME_number": 31, "eval_TIME_precision": 0.8484848484848485, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1355912983417511, "eval_overall_accuracy": 0.9581372306167947, "eval_overall_f1": 0.8150208623087621, "eval_overall_precision": 0.7855227882037533, "eval_overall_recall": 0.846820809248555, "eval_runtime": 0.9803, "eval_samples_per_second": 190.757, "eval_steps_per_second": 3.06, "step": 1590 }, { "epoch": 16.0, "grad_norm": 0.4039229452610016, "learning_rate": 4.2e-05, "loss": 0.0931, "step": 1696 }, { "epoch": 16.0, "eval_LOCATION_f1": 0.7549668874172186, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6951219512195121, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6808510638297871, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9028213166144202, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8674698795180723, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1370057314634323, "eval_overall_accuracy": 0.9591280653950953, "eval_overall_f1": 0.8129205921938087, "eval_overall_precision": 0.760705289672544, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 1.0534, "eval_samples_per_second": 177.517, "eval_steps_per_second": 2.848, "step": 1696 }, { "epoch": 17.0, "grad_norm": 0.39411261677742004, "learning_rate": 4.15e-05, "loss": 0.0925, "step": 1802 }, { "epoch": 17.0, "eval_LOCATION_f1": 0.8026315789473685, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6621621621621622, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5632183908045977, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.896551724137931, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8614457831325302, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7397260273972602, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6585365853658537, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7428571428571428, "eval_TIME_number": 31, "eval_TIME_precision": 0.6666666666666666, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1501362919807434, "eval_overall_accuracy": 0.9529353480307159, "eval_overall_f1": 0.8031496062992126, "eval_overall_precision": 0.7355769230769231, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.9811, "eval_samples_per_second": 190.602, "eval_steps_per_second": 3.058, "step": 1802 }, { "epoch": 18.0, "grad_norm": 0.6146470308303833, "learning_rate": 4.1e-05, "loss": 0.0885, "step": 1908 }, { "epoch": 18.0, "eval_LOCATION_f1": 0.8299319727891156, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6451612903225806, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6349206349206349, "eval_ORGANIZATION_recall": 0.6557377049180327, "eval_PERSON_f1": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.12835608422756195, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.8210818307905687, "eval_overall_precision": 0.7893333333333333, "eval_overall_recall": 0.8554913294797688, "eval_runtime": 0.9954, "eval_samples_per_second": 187.858, "eval_steps_per_second": 3.014, "step": 1908 }, { "epoch": 19.0, "grad_norm": 0.8693987131118774, "learning_rate": 4.05e-05, "loss": 0.088, "step": 2014 }, { "epoch": 19.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6716417910447762, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6164383561643836, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7323943661971831, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6666666666666666, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.12790969014167786, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8228882833787465, "eval_overall_precision": 0.7783505154639175, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 1.0031, "eval_samples_per_second": 186.424, "eval_steps_per_second": 2.991, "step": 2014 }, { "epoch": 20.0, "grad_norm": 0.5405162572860718, "learning_rate": 4e-05, "loss": 0.0786, "step": 2120 }, { "epoch": 20.0, "eval_LOCATION_f1": 0.8079470198675496, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7323943661971831, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6666666666666666, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1476246416568756, "eval_overall_accuracy": 0.9571463958384939, "eval_overall_f1": 0.8170894526034712, "eval_overall_precision": 0.7593052109181141, "eval_overall_recall": 0.884393063583815, "eval_runtime": 1.0147, "eval_samples_per_second": 184.289, "eval_steps_per_second": 2.957, "step": 2120 }, { "epoch": 21.0, "grad_norm": 0.5259639620780945, "learning_rate": 3.9500000000000005e-05, "loss": 0.0776, "step": 2226 }, { "epoch": 21.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6617647058823529, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.8944099378881987, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8520710059171598, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1557183563709259, "eval_overall_accuracy": 0.955907852365618, "eval_overall_f1": 0.8102288021534321, "eval_overall_precision": 0.7581863979848866, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.9938, "eval_samples_per_second": 188.167, "eval_steps_per_second": 3.019, "step": 2226 }, { "epoch": 22.0, "grad_norm": 0.4461101293563843, "learning_rate": 3.9000000000000006e-05, "loss": 0.0789, "step": 2332 }, { "epoch": 22.0, "eval_LOCATION_f1": 0.7808219178082192, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7402597402597403, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6086956521739131, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.49, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1589283049106598, "eval_overall_accuracy": 0.9497151350012385, "eval_overall_f1": 0.7941952506596306, "eval_overall_precision": 0.7305825242718447, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.993, "eval_samples_per_second": 188.313, "eval_steps_per_second": 3.021, "step": 2332 }, { "epoch": 23.0, "grad_norm": 1.1329030990600586, "learning_rate": 3.85e-05, "loss": 0.079, "step": 2438 }, { "epoch": 23.0, "eval_LOCATION_f1": 0.7702702702702703, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7215189873417721, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6818181818181818, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6338028169014085, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9113924050632911, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8834355828220859, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7222222222222223, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.65, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13774369657039642, "eval_overall_accuracy": 0.9593757740896706, "eval_overall_f1": 0.8119891008174387, "eval_overall_precision": 0.7680412371134021, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.98, "eval_samples_per_second": 190.819, "eval_steps_per_second": 3.061, "step": 2438 }, { "epoch": 24.0, "grad_norm": 1.0383950471878052, "learning_rate": 3.8e-05, "loss": 0.0728, "step": 2544 }, { "epoch": 24.0, "eval_LOCATION_f1": 0.8, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7631578947368421, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6811594202898551, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6103896103896104, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.13363541662693024, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.8262653898768809, "eval_overall_precision": 0.7844155844155845, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 1.005, "eval_samples_per_second": 186.066, "eval_steps_per_second": 2.985, "step": 2544 }, { "epoch": 25.0, "grad_norm": 0.8166852593421936, "learning_rate": 3.7500000000000003e-05, "loss": 0.071, "step": 2650 }, { "epoch": 25.0, "eval_LOCATION_f1": 0.7272727272727274, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6588235294117647, "eval_LOCATION_recall": 0.8115942028985508, "eval_ORGANIZATION_f1": 0.6623376623376623, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5483870967741935, "eval_ORGANIZATION_recall": 0.8360655737704918, "eval_PERSON_f1": 0.9028213166144202, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8674698795180723, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7222222222222223, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.65, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15092754364013672, "eval_overall_accuracy": 0.9539261828090166, "eval_overall_f1": 0.7911227154046997, "eval_overall_precision": 0.7214285714285714, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.9891, "eval_samples_per_second": 189.065, "eval_steps_per_second": 3.033, "step": 2650 }, { "epoch": 26.0, "grad_norm": 0.8139777183532715, "learning_rate": 3.7e-05, "loss": 0.072, "step": 2756 }, { "epoch": 26.0, "eval_LOCATION_f1": 0.7733333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7160493827160493, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.689655172413793, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5952380952380952, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9113924050632911, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8834355828220859, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.6756756756756757, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5952380952380952, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7647058823529411, "eval_TIME_number": 31, "eval_TIME_precision": 0.7027027027027027, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1510118842124939, "eval_overall_accuracy": 0.9549170175873173, "eval_overall_f1": 0.804780876494024, "eval_overall_precision": 0.7444717444717445, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.9975, "eval_samples_per_second": 187.468, "eval_steps_per_second": 3.008, "step": 2756 }, { "epoch": 27.0, "grad_norm": 0.325568825006485, "learning_rate": 3.65e-05, "loss": 0.068, "step": 2862 }, { "epoch": 27.0, "eval_LOCATION_f1": 0.7837837837837838, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7341772151898734, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6814814814814815, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.896551724137931, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8614457831325302, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8059701492537312, "eval_TIME_number": 31, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14145956933498383, "eval_overall_accuracy": 0.958632648005945, "eval_overall_f1": 0.8130081300813009, "eval_overall_precision": 0.7653061224489796, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.9961, "eval_samples_per_second": 187.728, "eval_steps_per_second": 3.012, "step": 2862 }, { "epoch": 28.0, "grad_norm": 0.9541507363319397, "learning_rate": 3.6e-05, "loss": 0.0668, "step": 2968 }, { "epoch": 28.0, "eval_LOCATION_f1": 0.7755102040816326, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7307692307692307, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6818181818181818, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6338028169014085, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7536231884057972, "eval_TIME_number": 31, "eval_TIME_precision": 0.6842105263157895, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1411270946264267, "eval_overall_accuracy": 0.9598711914788209, "eval_overall_f1": 0.8130968622100955, "eval_overall_precision": 0.7700258397932817, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.9842, "eval_samples_per_second": 190.009, "eval_steps_per_second": 3.048, "step": 2968 }, { "epoch": 29.0, "grad_norm": 0.8704339265823364, "learning_rate": 3.55e-05, "loss": 0.0675, "step": 3074 }, { "epoch": 29.0, "eval_LOCATION_f1": 0.8079470198675496, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6944444444444445, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6024096385542169, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.819672131147541, "eval_TIME_number": 31, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8064516129032258, "eval_loss": 0.14205148816108704, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.8243243243243245, "eval_overall_precision": 0.7741116751269036, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 1.078, "eval_samples_per_second": 173.471, "eval_steps_per_second": 2.783, "step": 3074 }, { "epoch": 30.0, "grad_norm": 0.5594027042388916, "learning_rate": 3.5e-05, "loss": 0.065, "step": 3180 }, { "epoch": 30.0, "eval_LOCATION_f1": 0.7581699346405228, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6904761904761905, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5974025974025974, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8622754491017964, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1492728590965271, "eval_overall_accuracy": 0.9583849393113698, "eval_overall_f1": 0.804289544235925, "eval_overall_precision": 0.75, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.9945, "eval_samples_per_second": 188.028, "eval_steps_per_second": 3.016, "step": 3180 }, { "epoch": 31.0, "grad_norm": 0.3202365040779114, "learning_rate": 3.45e-05, "loss": 0.0649, "step": 3286 }, { "epoch": 31.0, "eval_LOCATION_f1": 0.7837837837837838, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7341772151898734, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6865671641791045, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9044585987261147, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8819875776397516, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1405114084482193, "eval_overall_accuracy": 0.9611097349516968, "eval_overall_f1": 0.8225584594222832, "eval_overall_precision": 0.7847769028871391, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.9891, "eval_samples_per_second": 189.058, "eval_steps_per_second": 3.033, "step": 3286 }, { "epoch": 32.0, "grad_norm": 0.534267783164978, "learning_rate": 3.4000000000000007e-05, "loss": 0.0602, "step": 3392 }, { "epoch": 32.0, "eval_LOCATION_f1": 0.8187919463087248, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7625, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6865671641791045, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.875, "eval_TIME_number": 31, "eval_TIME_precision": 0.8484848484848485, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13280674815177917, "eval_overall_accuracy": 0.9628436958137231, "eval_overall_f1": 0.8290013679890561, "eval_overall_precision": 0.787012987012987, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.9944, "eval_samples_per_second": 188.059, "eval_steps_per_second": 3.017, "step": 3392 }, { "epoch": 33.0, "grad_norm": 0.28801554441452026, "learning_rate": 3.35e-05, "loss": 0.0617, "step": 3498 }, { "epoch": 33.0, "eval_LOCATION_f1": 0.7891156462585034, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7435897435897436, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6818181818181818, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6338028169014085, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9015873015873016, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8765432098765432, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1359180212020874, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8170563961485556, "eval_overall_precision": 0.7795275590551181, "eval_overall_recall": 0.8583815028901735, "eval_runtime": 0.9982, "eval_samples_per_second": 187.341, "eval_steps_per_second": 3.005, "step": 3498 }, { "epoch": 34.0, "grad_norm": 0.6007792949676514, "learning_rate": 3.3e-05, "loss": 0.0592, "step": 3604 }, { "epoch": 34.0, "eval_LOCATION_f1": 0.7483870967741935, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6744186046511628, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6754966887417219, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5666666666666667, "eval_ORGANIZATION_recall": 0.8360655737704918, "eval_PERSON_f1": 0.9125, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.874251497005988, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.6933333333333334, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6046511627906976, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7222222222222222, "eval_TIME_number": 31, "eval_TIME_precision": 0.6341463414634146, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.17786887288093567, "eval_overall_accuracy": 0.9512013871686896, "eval_overall_f1": 0.794307891332471, "eval_overall_precision": 0.7189695550351288, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 1.0067, "eval_samples_per_second": 185.754, "eval_steps_per_second": 2.98, "step": 3604 }, { "epoch": 35.0, "grad_norm": 1.0059374570846558, "learning_rate": 3.2500000000000004e-05, "loss": 0.0572, "step": 3710 }, { "epoch": 35.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6762589928057554, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6025641025641025, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8980891719745223, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8757763975155279, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8387096774193549, "eval_TIME_number": 31, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14642970263957977, "eval_overall_accuracy": 0.9591280653950953, "eval_overall_f1": 0.815825375170532, "eval_overall_precision": 0.772609819121447, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.9961, "eval_samples_per_second": 187.738, "eval_steps_per_second": 3.012, "step": 3710 }, { "epoch": 36.0, "grad_norm": 0.9360735416412354, "learning_rate": 3.2000000000000005e-05, "loss": 0.0569, "step": 3816 }, { "epoch": 36.0, "eval_LOCATION_f1": 0.7972972972972974, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7468354430379747, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6618705035971222, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5897435897435898, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9211356466876972, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8902439024390244, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8387096774193549, "eval_TIME_number": 31, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14345212280750275, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8278688524590163, "eval_overall_precision": 0.7849740932642487, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 1.0012, "eval_samples_per_second": 186.767, "eval_steps_per_second": 2.996, "step": 3816 }, { "epoch": 37.0, "grad_norm": 1.6939655542373657, "learning_rate": 3.15e-05, "loss": 0.0573, "step": 3922 }, { "epoch": 37.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6715328467153285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6052631578947368, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8524590163934426, "eval_TIME_number": 31, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14684607088565826, "eval_overall_accuracy": 0.9601189001733961, "eval_overall_f1": 0.8241758241758242, "eval_overall_precision": 0.7853403141361257, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.9892, "eval_samples_per_second": 189.05, "eval_steps_per_second": 3.033, "step": 3922 }, { "epoch": 38.0, "grad_norm": 0.7411573529243469, "learning_rate": 3.1e-05, "loss": 0.0524, "step": 4028 }, { "epoch": 38.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6714285714285714, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5949367088607594, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.89375, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8562874251497006, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7323943661971831, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6666666666666666, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15702801942825317, "eval_overall_accuracy": 0.9576418132276443, "eval_overall_f1": 0.8058902275769746, "eval_overall_precision": 0.7506234413965087, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.9832, "eval_samples_per_second": 190.205, "eval_steps_per_second": 3.051, "step": 4028 }, { "epoch": 39.0, "grad_norm": 0.9962830543518066, "learning_rate": 3.05e-05, "loss": 0.0526, "step": 4134 }, { "epoch": 39.0, "eval_LOCATION_f1": 0.7947019867549668, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7014925373134328, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6438356164383562, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9119496855345912, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8787878787878788, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14492842555046082, "eval_overall_accuracy": 0.9623482784245727, "eval_overall_f1": 0.8299319727891157, "eval_overall_precision": 0.7840616966580977, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.9833, "eval_samples_per_second": 190.175, "eval_steps_per_second": 3.051, "step": 4134 }, { "epoch": 40.0, "grad_norm": 0.8109886050224304, "learning_rate": 3e-05, "loss": 0.0525, "step": 4240 }, { "epoch": 40.0, "eval_LOCATION_f1": 0.778523489932886, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.725, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6814814814814815, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9050632911392406, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8773006134969326, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.15133674442768097, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8201634877384196, "eval_overall_precision": 0.7757731958762887, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.9893, "eval_samples_per_second": 189.014, "eval_steps_per_second": 3.032, "step": 4240 }, { "epoch": 41.0, "grad_norm": 0.10324083268642426, "learning_rate": 2.95e-05, "loss": 0.0511, "step": 4346 }, { "epoch": 41.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7142857142857143, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6666666666666667, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6081081081081081, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.909657320872274, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8690476190476191, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.157461017370224, "eval_overall_accuracy": 0.9588803567005202, "eval_overall_f1": 0.8167115902964959, "eval_overall_precision": 0.7651515151515151, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.9754, "eval_samples_per_second": 191.721, "eval_steps_per_second": 3.076, "step": 4346 }, { "epoch": 42.0, "grad_norm": 1.2128788232803345, "learning_rate": 2.9e-05, "loss": 0.0528, "step": 4452 }, { "epoch": 42.0, "eval_LOCATION_f1": 0.7733333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7160493827160493, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6619718309859155, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5802469135802469, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.915360501567398, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8795180722891566, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1547376662492752, "eval_overall_accuracy": 0.9593757740896706, "eval_overall_f1": 0.8172043010752688, "eval_overall_precision": 0.7638190954773869, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 1.0757, "eval_samples_per_second": 173.839, "eval_steps_per_second": 2.789, "step": 4452 }, { "epoch": 43.0, "grad_norm": 0.1244686096906662, "learning_rate": 2.8499999999999998e-05, "loss": 0.0499, "step": 4558 }, { "epoch": 43.0, "eval_LOCATION_f1": 0.7837837837837838, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7341772151898734, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.7014925373134328, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6438356164383562, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15334224700927734, "eval_overall_accuracy": 0.9588803567005202, "eval_overall_f1": 0.8180574555403556, "eval_overall_precision": 0.7766233766233767, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 1.1556, "eval_samples_per_second": 161.821, "eval_steps_per_second": 2.596, "step": 4558 }, { "epoch": 44.0, "grad_norm": 1.083632230758667, "learning_rate": 2.8000000000000003e-05, "loss": 0.0471, "step": 4664 }, { "epoch": 44.0, "eval_LOCATION_f1": 0.8079470198675496, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6917293233082706, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9028213166144202, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8674698795180723, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1608462631702423, "eval_overall_accuracy": 0.9591280653950953, "eval_overall_f1": 0.8211382113821138, "eval_overall_precision": 0.7729591836734694, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 1.0042, "eval_samples_per_second": 186.211, "eval_steps_per_second": 2.987, "step": 4664 }, { "epoch": 45.0, "grad_norm": 0.6506208181381226, "learning_rate": 2.7500000000000004e-05, "loss": 0.0459, "step": 4770 }, { "epoch": 45.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6865671641791045, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8819875776397514, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8402366863905325, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15545788407325745, "eval_overall_accuracy": 0.9581372306167947, "eval_overall_f1": 0.8097165991902835, "eval_overall_precision": 0.759493670886076, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.9925, "eval_samples_per_second": 188.407, "eval_steps_per_second": 3.023, "step": 4770 }, { "epoch": 46.0, "grad_norm": 0.6165773272514343, "learning_rate": 2.7000000000000002e-05, "loss": 0.0459, "step": 4876 }, { "epoch": 46.0, "eval_LOCATION_f1": 0.7549668874172186, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6951219512195121, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6616541353383459, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6111111111111112, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.8902821316614421, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8554216867469879, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.166278675198555, "eval_overall_accuracy": 0.9571463958384939, "eval_overall_f1": 0.8027210884353743, "eval_overall_precision": 0.7583547557840618, "eval_overall_recall": 0.8526011560693642, "eval_runtime": 0.9964, "eval_samples_per_second": 187.678, "eval_steps_per_second": 3.011, "step": 4876 }, { "epoch": 47.0, "grad_norm": 1.6443135738372803, "learning_rate": 2.6500000000000004e-05, "loss": 0.0457, "step": 4982 }, { "epoch": 47.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.671875, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6417910447761194, "eval_ORGANIZATION_recall": 0.7049180327868853, "eval_PERSON_f1": 0.8847352024922119, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8452380952380952, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.9180327868852459, "eval_TIME_number": 31, "eval_TIME_precision": 0.9333333333333333, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.15434302389621735, "eval_overall_accuracy": 0.9628436958137231, "eval_overall_f1": 0.8248275862068966, "eval_overall_precision": 0.7889182058047494, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 1.0099, "eval_samples_per_second": 185.163, "eval_steps_per_second": 2.971, "step": 4982 }, { "epoch": 48.0, "grad_norm": 0.7369825839996338, "learning_rate": 2.6000000000000002e-05, "loss": 0.0442, "step": 5088 }, { "epoch": 48.0, "eval_LOCATION_f1": 0.7682119205298014, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7073170731707317, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6769230769230768, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6376811594202898, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.9050632911392406, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8773006134969326, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15800130367279053, "eval_overall_accuracy": 0.9598711914788209, "eval_overall_f1": 0.8125854993160055, "eval_overall_precision": 0.7714285714285715, "eval_overall_recall": 0.8583815028901735, "eval_runtime": 0.9849, "eval_samples_per_second": 189.872, "eval_steps_per_second": 3.046, "step": 5088 }, { "epoch": 49.0, "grad_norm": 0.5814737677574158, "learning_rate": 2.5500000000000003e-05, "loss": 0.0444, "step": 5194 }, { "epoch": 49.0, "eval_LOCATION_f1": 0.778523489932886, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.725, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6962962962962963, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6351351351351351, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15717627108097076, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8235294117647058, "eval_overall_precision": 0.7818181818181819, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.993, "eval_samples_per_second": 188.327, "eval_steps_per_second": 3.021, "step": 5194 }, { "epoch": 50.0, "grad_norm": 0.585141658782959, "learning_rate": 2.5e-05, "loss": 0.0424, "step": 5300 }, { "epoch": 50.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6769230769230768, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6376811594202898, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15228819847106934, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8232044198895027, "eval_overall_precision": 0.7883597883597884, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.9899, "eval_samples_per_second": 188.901, "eval_steps_per_second": 3.031, "step": 5300 }, { "epoch": 51.0, "grad_norm": 0.8279469013214111, "learning_rate": 2.45e-05, "loss": 0.0411, "step": 5406 }, { "epoch": 51.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6714285714285714, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5949367088607594, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.897196261682243, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8571428571428571, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.15568019449710846, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8216216216216216, "eval_overall_precision": 0.7715736040609137, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.9971, "eval_samples_per_second": 187.536, "eval_steps_per_second": 3.009, "step": 5406 }, { "epoch": 52.0, "grad_norm": 0.46233218908309937, "learning_rate": 2.4e-05, "loss": 0.0424, "step": 5512 }, { "epoch": 52.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6811594202898551, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6103896103896104, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9028213166144202, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8674698795180723, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15841934084892273, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8227334235453315, "eval_overall_precision": 0.7735368956743003, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.992, "eval_samples_per_second": 188.511, "eval_steps_per_second": 3.024, "step": 5512 }, { "epoch": 53.0, "grad_norm": 0.6373240351676941, "learning_rate": 2.35e-05, "loss": 0.0408, "step": 5618 }, { "epoch": 53.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6861313868613139, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.618421052631579, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.896551724137931, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8614457831325302, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8852459016393444, "eval_TIME_number": 31, "eval_TIME_precision": 0.9, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.15928535163402557, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8278688524590163, "eval_overall_precision": 0.7849740932642487, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.989, "eval_samples_per_second": 189.088, "eval_steps_per_second": 3.034, "step": 5618 }, { "epoch": 54.0, "grad_norm": 0.2755186855792999, "learning_rate": 2.3000000000000003e-05, "loss": 0.0412, "step": 5724 }, { "epoch": 54.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6962962962962963, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6351351351351351, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.896551724137931, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8614457831325302, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.158822163939476, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.825136612021858, "eval_overall_precision": 0.7823834196891192, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.9914, "eval_samples_per_second": 188.631, "eval_steps_per_second": 3.026, "step": 5724 }, { "epoch": 55.0, "grad_norm": 2.969045639038086, "learning_rate": 2.25e-05, "loss": 0.0422, "step": 5830 }, { "epoch": 55.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6301369863013699, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5411764705882353, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1669679880142212, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.8080536912751678, "eval_overall_precision": 0.7543859649122807, "eval_overall_recall": 0.869942196531792, "eval_runtime": 1.0094, "eval_samples_per_second": 185.251, "eval_steps_per_second": 2.972, "step": 5830 }, { "epoch": 56.0, "grad_norm": 1.2709088325500488, "learning_rate": 2.2000000000000003e-05, "loss": 0.0393, "step": 5936 }, { "epoch": 56.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6917293233082706, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 31, "eval_TIME_precision": 0.8620689655172413, "eval_TIME_recall": 0.8064516129032258, "eval_loss": 0.15802454948425293, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8310249307479224, "eval_overall_precision": 0.7978723404255319, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 1.001, "eval_samples_per_second": 186.82, "eval_steps_per_second": 2.997, "step": 5936 }, { "epoch": 57.0, "grad_norm": 0.5410558581352234, "learning_rate": 2.15e-05, "loss": 0.0397, "step": 6042 }, { "epoch": 57.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6616541353383459, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6111111111111112, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.16334755718708038, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8262653898768809, "eval_overall_precision": 0.7844155844155845, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 1.0636, "eval_samples_per_second": 175.822, "eval_steps_per_second": 2.821, "step": 6042 }, { "epoch": 58.0, "grad_norm": 0.09321507066488266, "learning_rate": 2.1e-05, "loss": 0.0367, "step": 6148 }, { "epoch": 58.0, "eval_LOCATION_f1": 0.8079470198675496, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6716417910447762, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6164383561643836, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.17088571190834045, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.8212824010914053, "eval_overall_precision": 0.7777777777777778, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.9854, "eval_samples_per_second": 189.767, "eval_steps_per_second": 3.044, "step": 6148 }, { "epoch": 59.0, "grad_norm": 0.659205973148346, "learning_rate": 2.05e-05, "loss": 0.0384, "step": 6254 }, { "epoch": 59.0, "eval_LOCATION_f1": 0.8079470198675496, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6376811594202898, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5714285714285714, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8059701492537312, "eval_TIME_number": 31, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.17435206472873688, "eval_overall_accuracy": 0.9591280653950953, "eval_overall_f1": 0.8135135135135134, "eval_overall_precision": 0.7639593908629442, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.9909, "eval_samples_per_second": 188.725, "eval_steps_per_second": 3.028, "step": 6254 }, { "epoch": 60.0, "grad_norm": 0.5503810048103333, "learning_rate": 2e-05, "loss": 0.0383, "step": 6360 }, { "epoch": 60.0, "eval_LOCATION_f1": 0.7814569536423841, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7195121951219512, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6617647058823529, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8622754491017964, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1732153296470642, "eval_overall_accuracy": 0.9588803567005202, "eval_overall_f1": 0.814111261872456, "eval_overall_precision": 0.7672634271099744, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.9921, "eval_samples_per_second": 188.484, "eval_steps_per_second": 3.024, "step": 6360 }, { "epoch": 61.0, "grad_norm": 1.4769850969314575, "learning_rate": 1.9500000000000003e-05, "loss": 0.0336, "step": 6466 }, { "epoch": 61.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6917293233082706, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1649622768163681, "eval_overall_accuracy": 0.9633391132028735, "eval_overall_f1": 0.8296703296703297, "eval_overall_precision": 0.7905759162303665, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.9878, "eval_samples_per_second": 189.311, "eval_steps_per_second": 3.037, "step": 6466 }, { "epoch": 62.0, "grad_norm": 0.4070124328136444, "learning_rate": 1.9e-05, "loss": 0.0356, "step": 6572 }, { "epoch": 62.0, "eval_LOCATION_f1": 0.8026315789473685, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6521739130434783, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5844155844155844, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.897196261682243, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8571428571428571, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7826086956521738, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7297297297297297, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.18611405789852142, "eval_overall_accuracy": 0.9568986871439188, "eval_overall_f1": 0.8123324396782842, "eval_overall_precision": 0.7575, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 1.0068, "eval_samples_per_second": 185.733, "eval_steps_per_second": 2.98, "step": 6572 }, { "epoch": 63.0, "grad_norm": 0.3907913863658905, "learning_rate": 1.85e-05, "loss": 0.0344, "step": 6678 }, { "epoch": 63.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6917293233082706, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1645907610654831, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.8257887517146777, "eval_overall_precision": 0.7859007832898173, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.9932, "eval_samples_per_second": 188.281, "eval_steps_per_second": 3.021, "step": 6678 }, { "epoch": 64.0, "grad_norm": 0.682833731174469, "learning_rate": 1.8e-05, "loss": 0.0333, "step": 6784 }, { "epoch": 64.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6713286713286712, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5853658536585366, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9028213166144202, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8674698795180723, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.17704235017299652, "eval_overall_accuracy": 0.9593757740896706, "eval_overall_f1": 0.8172043010752688, "eval_overall_precision": 0.7638190954773869, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 1.0021, "eval_samples_per_second": 186.614, "eval_steps_per_second": 2.994, "step": 6784 }, { "epoch": 65.0, "grad_norm": 0.3721832036972046, "learning_rate": 1.75e-05, "loss": 0.0342, "step": 6890 }, { "epoch": 65.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6618705035971222, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5897435897435898, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9050632911392406, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8773006134969326, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1735246777534485, "eval_overall_accuracy": 0.9601189001733961, "eval_overall_f1": 0.8222523744911805, "eval_overall_precision": 0.7749360613810742, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 1.0031, "eval_samples_per_second": 186.413, "eval_steps_per_second": 2.991, "step": 6890 }, { "epoch": 66.0, "grad_norm": 0.2796691954135895, "learning_rate": 1.7000000000000003e-05, "loss": 0.0341, "step": 6996 }, { "epoch": 66.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6617647058823529, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8622754491017964, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7647058823529411, "eval_TIME_number": 31, "eval_TIME_precision": 0.7027027027027027, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1770649254322052, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.8178137651821862, "eval_overall_precision": 0.7670886075949367, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.9965, "eval_samples_per_second": 187.651, "eval_steps_per_second": 3.01, "step": 6996 }, { "epoch": 67.0, "grad_norm": 0.8784322142601013, "learning_rate": 1.65e-05, "loss": 0.0326, "step": 7102 }, { "epoch": 67.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5974025974025974, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8930817610062893, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8606060606060606, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1722780466079712, "eval_overall_accuracy": 0.9593757740896706, "eval_overall_f1": 0.8157181571815717, "eval_overall_precision": 0.7678571428571429, "eval_overall_recall": 0.869942196531792, "eval_runtime": 1.0013, "eval_samples_per_second": 186.756, "eval_steps_per_second": 2.996, "step": 7102 }, { "epoch": 68.0, "grad_norm": 0.47935327887535095, "learning_rate": 1.6000000000000003e-05, "loss": 0.0347, "step": 7208 }, { "epoch": 68.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.656934306569343, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5921052631578947, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9056603773584905, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8727272727272727, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.18066948652267456, "eval_overall_accuracy": 0.9583849393113698, "eval_overall_f1": 0.8162162162162162, "eval_overall_precision": 0.766497461928934, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.9981, "eval_samples_per_second": 187.358, "eval_steps_per_second": 3.006, "step": 7208 }, { "epoch": 69.0, "grad_norm": 0.7104108333587646, "learning_rate": 1.55e-05, "loss": 0.033, "step": 7314 }, { "epoch": 69.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5875, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9028213166144202, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8674698795180723, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1800457388162613, "eval_overall_accuracy": 0.9583849393113698, "eval_overall_f1": 0.8162162162162162, "eval_overall_precision": 0.766497461928934, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 1.0133, "eval_samples_per_second": 184.537, "eval_steps_per_second": 2.96, "step": 7314 }, { "epoch": 70.0, "grad_norm": 1.264423131942749, "learning_rate": 1.5e-05, "loss": 0.032, "step": 7420 }, { "epoch": 70.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6716417910447762, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6164383561643836, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9056603773584905, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8727272727272727, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1743316799402237, "eval_overall_accuracy": 0.9611097349516968, "eval_overall_f1": 0.8240109140518418, "eval_overall_precision": 0.7803617571059431, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.9948, "eval_samples_per_second": 187.983, "eval_steps_per_second": 3.016, "step": 7420 }, { "epoch": 71.0, "grad_norm": 0.542935848236084, "learning_rate": 1.45e-05, "loss": 0.0324, "step": 7526 }, { "epoch": 71.0, "eval_LOCATION_f1": 0.7947019867549668, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6715328467153285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6052631578947368, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.17356982827186584, "eval_overall_accuracy": 0.9601189001733961, "eval_overall_f1": 0.819047619047619, "eval_overall_precision": 0.7737789203084833, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.9929, "eval_samples_per_second": 188.343, "eval_steps_per_second": 3.022, "step": 7526 }, { "epoch": 72.0, "grad_norm": 0.2948610186576843, "learning_rate": 1.4000000000000001e-05, "loss": 0.0319, "step": 7632 }, { "epoch": 72.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6865671641791045, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1768426150083542, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.8224043715846995, "eval_overall_precision": 0.7797927461139896, "eval_overall_recall": 0.869942196531792, "eval_runtime": 1.0129, "eval_samples_per_second": 184.62, "eval_steps_per_second": 2.962, "step": 7632 }, { "epoch": 73.0, "grad_norm": 2.261873483657837, "learning_rate": 1.3500000000000001e-05, "loss": 0.0322, "step": 7738 }, { "epoch": 73.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6814814814814815, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.17177316546440125, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8262653898768809, "eval_overall_precision": 0.7844155844155845, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.9871, "eval_samples_per_second": 189.451, "eval_steps_per_second": 3.039, "step": 7738 }, { "epoch": 74.0, "grad_norm": 0.4583621025085449, "learning_rate": 1.3000000000000001e-05, "loss": 0.0299, "step": 7844 }, { "epoch": 74.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6715328467153285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6052631578947368, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8895899053627759, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8597560975609756, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1779460459947586, "eval_overall_accuracy": 0.9601189001733961, "eval_overall_f1": 0.8152173913043478, "eval_overall_precision": 0.7692307692307693, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 1.0047, "eval_samples_per_second": 186.125, "eval_steps_per_second": 2.986, "step": 7844 }, { "epoch": 75.0, "grad_norm": 0.3838861882686615, "learning_rate": 1.25e-05, "loss": 0.0291, "step": 7950 }, { "epoch": 75.0, "eval_LOCATION_f1": 0.7947019867549668, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6814814814814815, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9056603773584905, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8727272727272727, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.18026097118854523, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.8217687074829931, "eval_overall_precision": 0.7763496143958869, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.9947, "eval_samples_per_second": 187.989, "eval_steps_per_second": 3.016, "step": 7950 }, { "epoch": 76.0, "grad_norm": 0.7108933329582214, "learning_rate": 1.2e-05, "loss": 0.0295, "step": 8056 }, { "epoch": 76.0, "eval_LOCATION_f1": 0.7947019867549668, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6865671641791045, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9028213166144202, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8674698795180723, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.18334877490997314, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.8217687074829931, "eval_overall_precision": 0.7763496143958869, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.9967, "eval_samples_per_second": 187.622, "eval_steps_per_second": 3.01, "step": 8056 }, { "epoch": 77.0, "grad_norm": 0.06356514245271683, "learning_rate": 1.1500000000000002e-05, "loss": 0.0288, "step": 8162 }, { "epoch": 77.0, "eval_LOCATION_f1": 0.7894736842105263, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.676470588235294, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6133333333333333, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1836617887020111, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.814111261872456, "eval_overall_precision": 0.7672634271099744, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 1.0023, "eval_samples_per_second": 186.57, "eval_steps_per_second": 2.993, "step": 8162 }, { "epoch": 78.0, "grad_norm": 1.0761598348617554, "learning_rate": 1.1000000000000001e-05, "loss": 0.0286, "step": 8268 }, { "epoch": 78.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6969696969696969, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.647887323943662, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.18496443331241608, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.8174386920980926, "eval_overall_precision": 0.7731958762886598, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.9924, "eval_samples_per_second": 188.438, "eval_steps_per_second": 3.023, "step": 8268 }, { "epoch": 79.0, "grad_norm": 0.6377687454223633, "learning_rate": 1.05e-05, "loss": 0.0296, "step": 8374 }, { "epoch": 79.0, "eval_LOCATION_f1": 0.7947019867549668, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7022900763358779, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6571428571428571, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7826086956521738, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7297297297297297, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.18578113615512848, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.8228882833787465, "eval_overall_precision": 0.7783505154639175, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.9942, "eval_samples_per_second": 188.095, "eval_steps_per_second": 3.018, "step": 8374 }, { "epoch": 80.0, "grad_norm": 0.9133962392807007, "learning_rate": 1e-05, "loss": 0.0291, "step": 8480 }, { "epoch": 80.0, "eval_LOCATION_f1": 0.7947019867549668, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6428571428571429, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.569620253164557, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9056603773584905, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8727272727272727, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.19771257042884827, "eval_overall_accuracy": 0.9573941045330691, "eval_overall_f1": 0.8080536912751678, "eval_overall_precision": 0.7543859649122807, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.9881, "eval_samples_per_second": 189.247, "eval_steps_per_second": 3.036, "step": 8480 }, { "epoch": 81.0, "grad_norm": 0.2774830758571625, "learning_rate": 9.5e-06, "loss": 0.0286, "step": 8586 }, { "epoch": 81.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6923076923076924, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6521739130434783, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.8924050632911392, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8650306748466258, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.18613538146018982, "eval_overall_accuracy": 0.9591280653950953, "eval_overall_f1": 0.8153214774281805, "eval_overall_precision": 0.7740259740259741, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.9926, "eval_samples_per_second": 188.388, "eval_steps_per_second": 3.022, "step": 8586 }, { "epoch": 82.0, "grad_norm": 0.32229432463645935, "learning_rate": 9e-06, "loss": 0.028, "step": 8692 }, { "epoch": 82.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6962962962962963, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6351351351351351, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.19613806903362274, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.8222523744911805, "eval_overall_precision": 0.7749360613810742, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.999, "eval_samples_per_second": 187.18, "eval_steps_per_second": 3.003, "step": 8692 }, { "epoch": 83.0, "grad_norm": 0.18774951994419098, "learning_rate": 8.500000000000002e-06, "loss": 0.0268, "step": 8798 }, { "epoch": 83.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6762589928057554, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6025641025641025, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8895899053627759, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8597560975609756, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7826086956521738, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7297297297297297, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1944919377565384, "eval_overall_accuracy": 0.9588803567005202, "eval_overall_f1": 0.8124156545209177, "eval_overall_precision": 0.7620253164556962, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.9979, "eval_samples_per_second": 187.384, "eval_steps_per_second": 3.006, "step": 8798 }, { "epoch": 84.0, "grad_norm": 1.8088972568511963, "learning_rate": 8.000000000000001e-06, "loss": 0.0274, "step": 8904 }, { "epoch": 84.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6956521739130435, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6233766233766234, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8924050632911392, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8650306748466258, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1904267519712448, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.8201634877384196, "eval_overall_precision": 0.7757731958762887, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.9962, "eval_samples_per_second": 187.71, "eval_steps_per_second": 3.011, "step": 8904 }, { "epoch": 85.0, "grad_norm": 0.25640690326690674, "learning_rate": 7.5e-06, "loss": 0.0272, "step": 9010 }, { "epoch": 85.0, "eval_LOCATION_f1": 0.8187919463087248, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7625, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6818181818181818, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6338028169014085, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.8895899053627759, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8597560975609756, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.18857501447200775, "eval_overall_accuracy": 0.9611097349516968, "eval_overall_f1": 0.8241758241758242, "eval_overall_precision": 0.7853403141361257, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 1.0634, "eval_samples_per_second": 175.846, "eval_steps_per_second": 2.821, "step": 9010 }, { "epoch": 86.0, "grad_norm": 0.6918984055519104, "learning_rate": 7.000000000000001e-06, "loss": 0.0265, "step": 9116 }, { "epoch": 86.0, "eval_LOCATION_f1": 0.8187919463087248, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7625, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6716417910447762, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6164383561643836, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.8930817610062893, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8606060606060606, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.19140414893627167, "eval_overall_accuracy": 0.9601189001733961, "eval_overall_f1": 0.8201634877384196, "eval_overall_precision": 0.7757731958762887, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.9935, "eval_samples_per_second": 188.225, "eval_steps_per_second": 3.02, "step": 9116 }, { "epoch": 87.0, "grad_norm": 0.5062441229820251, "learning_rate": 6.5000000000000004e-06, "loss": 0.0264, "step": 9222 }, { "epoch": 87.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6911764705882353, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6266666666666667, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1898663192987442, "eval_overall_accuracy": 0.9611097349516968, "eval_overall_f1": 0.8283378746594006, "eval_overall_precision": 0.7835051546391752, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 1.0004, "eval_samples_per_second": 186.919, "eval_steps_per_second": 2.999, "step": 9222 }, { "epoch": 88.0, "grad_norm": 0.9881439805030823, "learning_rate": 6e-06, "loss": 0.0265, "step": 9328 }, { "epoch": 88.0, "eval_LOCATION_f1": 0.8079470198675496, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6814814814814815, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8895899053627759, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8597560975609756, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.18475988507270813, "eval_overall_accuracy": 0.9601189001733961, "eval_overall_f1": 0.8179347826086956, "eval_overall_precision": 0.7717948717948718, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.9985, "eval_samples_per_second": 187.283, "eval_steps_per_second": 3.005, "step": 9328 }, { "epoch": 89.0, "grad_norm": 0.8410730957984924, "learning_rate": 5.500000000000001e-06, "loss": 0.0272, "step": 9434 }, { "epoch": 89.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6969696969696969, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.647887323943662, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8930817610062893, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8606060606060606, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.18852190673351288, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8240109140518418, "eval_overall_precision": 0.7803617571059431, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.9938, "eval_samples_per_second": 188.167, "eval_steps_per_second": 3.019, "step": 9434 }, { "epoch": 90.0, "grad_norm": 0.46544983983039856, "learning_rate": 5e-06, "loss": 0.0247, "step": 9540 }, { "epoch": 90.0, "eval_LOCATION_f1": 0.8079470198675496, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6715328467153285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6052631578947368, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8930817610062893, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8606060606060606, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.823529411764706, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7777777777777778, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.19199509918689728, "eval_overall_accuracy": 0.9598711914788209, "eval_overall_f1": 0.8200270635994588, "eval_overall_precision": 0.7709923664122137, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 1.0076, "eval_samples_per_second": 185.591, "eval_steps_per_second": 2.977, "step": 9540 }, { "epoch": 91.0, "grad_norm": 0.5228121280670166, "learning_rate": 4.5e-06, "loss": 0.0257, "step": 9646 }, { "epoch": 91.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6814814814814815, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8895899053627759, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8597560975609756, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.18916358053684235, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.8201634877384196, "eval_overall_precision": 0.7757731958762887, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.9851, "eval_samples_per_second": 189.831, "eval_steps_per_second": 3.045, "step": 9646 }, { "epoch": 92.0, "grad_norm": 1.0351158380508423, "learning_rate": 4.000000000000001e-06, "loss": 0.0272, "step": 9752 }, { "epoch": 92.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6715328467153285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6052631578947368, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.8181818181818182, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7941176470588235, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.19310089945793152, "eval_overall_accuracy": 0.9601189001733961, "eval_overall_f1": 0.8228882833787465, "eval_overall_precision": 0.7783505154639175, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 1.0032, "eval_samples_per_second": 186.402, "eval_steps_per_second": 2.99, "step": 9752 }, { "epoch": 93.0, "grad_norm": 1.0168826580047607, "learning_rate": 3.5000000000000004e-06, "loss": 0.0264, "step": 9858 }, { "epoch": 93.0, "eval_LOCATION_f1": 0.8079470198675496, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6715328467153285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6052631578947368, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8895899053627759, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8597560975609756, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.19347640872001648, "eval_overall_accuracy": 0.9588803567005202, "eval_overall_f1": 0.8157181571815717, "eval_overall_precision": 0.7678571428571429, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.994, "eval_samples_per_second": 188.123, "eval_steps_per_second": 3.018, "step": 9858 }, { "epoch": 94.0, "grad_norm": 1.8966048955917358, "learning_rate": 3e-06, "loss": 0.025, "step": 9964 }, { "epoch": 94.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6865671641791045, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1931447982788086, "eval_overall_accuracy": 0.9601189001733961, "eval_overall_f1": 0.8244897959183674, "eval_overall_precision": 0.7789203084832905, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.9943, "eval_samples_per_second": 188.071, "eval_steps_per_second": 3.017, "step": 9964 }, { "epoch": 95.0, "grad_norm": 0.3385007679462433, "learning_rate": 2.5e-06, "loss": 0.0238, "step": 10070 }, { "epoch": 95.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6814814814814815, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9056603773584905, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8727272727272727, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.19391222298145294, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8249660786974219, "eval_overall_precision": 0.7774936061381074, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 1.0009, "eval_samples_per_second": 186.836, "eval_steps_per_second": 2.997, "step": 10070 }, { "epoch": 96.0, "grad_norm": 0.21799148619174957, "learning_rate": 2.0000000000000003e-06, "loss": 0.0253, "step": 10176 }, { "epoch": 96.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.676470588235294, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6133333333333333, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9056603773584905, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8727272727272727, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.19421541690826416, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.8265582655826559, "eval_overall_precision": 0.7780612244897959, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 1.1499, "eval_samples_per_second": 162.627, "eval_steps_per_second": 2.609, "step": 10176 }, { "epoch": 97.0, "grad_norm": 0.6869099736213684, "learning_rate": 1.5e-06, "loss": 0.0258, "step": 10282 }, { "epoch": 97.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6814814814814815, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8895899053627759, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8597560975609756, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.19163855910301208, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8217687074829931, "eval_overall_precision": 0.7763496143958869, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.9961, "eval_samples_per_second": 187.732, "eval_steps_per_second": 3.012, "step": 10282 }, { "epoch": 98.0, "grad_norm": 0.3732462525367737, "learning_rate": 1.0000000000000002e-06, "loss": 0.0237, "step": 10388 }, { "epoch": 98.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6715328467153285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6052631578947368, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8930817610062893, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8606060606060606, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.19394682347774506, "eval_overall_accuracy": 0.9601189001733961, "eval_overall_f1": 0.8211382113821138, "eval_overall_precision": 0.7729591836734694, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 1.0582, "eval_samples_per_second": 176.711, "eval_steps_per_second": 2.835, "step": 10388 }, { "epoch": 99.0, "grad_norm": 0.2899250090122223, "learning_rate": 5.000000000000001e-07, "loss": 0.0236, "step": 10494 }, { "epoch": 99.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.676470588235294, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6133333333333333, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8930817610062893, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8606060606060606, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1942683607339859, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8222523744911805, "eval_overall_precision": 0.7749360613810742, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.9864, "eval_samples_per_second": 189.57, "eval_steps_per_second": 3.041, "step": 10494 }, { "epoch": 100.0, "grad_norm": 0.24946770071983337, "learning_rate": 0.0, "loss": 0.0266, "step": 10600 }, { "epoch": 100.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.676470588235294, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6133333333333333, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8930817610062893, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8606060606060606, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.19379286468029022, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8222523744911805, "eval_overall_precision": 0.7749360613810742, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 1.0035, "eval_samples_per_second": 186.351, "eval_steps_per_second": 2.99, "step": 10600 }, { "epoch": 100.0, "step": 10600, "total_flos": 5088556202474382.0, "train_loss": 0.07152380032359429, "train_runtime": 1385.5436, "train_samples_per_second": 121.757, "train_steps_per_second": 7.65 } ], "logging_steps": 500, "max_steps": 10600, "num_input_tokens_seen": 0, "num_train_epochs": 100, "save_steps": 500, "total_flos": 5088556202474382.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }