{ "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": 1.6106630563735962, "learning_rate": 4.9500000000000004e-05, "loss": 0.9915, "step": 106 }, { "epoch": 1.0, "eval_LOCATION_f1": 0.0, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.0, "eval_LOCATION_recall": 0.0, "eval_ORGANIZATION_f1": 0.0, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.025157232704402517, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.125, "eval_PERSON_recall": 0.013986013986013986, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 26, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.5523906946182251, "eval_overall_accuracy": 0.8478859144358268, "eval_overall_f1": 0.010869565217391304, "eval_overall_precision": 0.06896551724137931, "eval_overall_recall": 0.0058997050147492625, "eval_runtime": 0.3726, "eval_samples_per_second": 501.919, "eval_steps_per_second": 8.052, "step": 106 }, { "epoch": 2.0, "grad_norm": 1.0314005613327026, "learning_rate": 4.9e-05, "loss": 0.5062, "step": 212 }, { "epoch": 2.0, "eval_LOCATION_f1": 0.05063291139240506, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.2857142857142857, "eval_LOCATION_recall": 0.027777777777777776, "eval_ORGANIZATION_f1": 0.0196078431372549, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.037037037037037035, "eval_ORGANIZATION_recall": 0.013333333333333334, "eval_PERSON_f1": 0.5257142857142857, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.4444444444444444, "eval_PERSON_recall": 0.6433566433566433, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.5306122448979592, "eval_TIME_number": 26, "eval_TIME_precision": 0.5652173913043478, "eval_TIME_recall": 0.5, "eval_loss": 0.3515785038471222, "eval_overall_accuracy": 0.8919189392044033, "eval_overall_f1": 0.3517915309446254, "eval_overall_precision": 0.3927272727272727, "eval_overall_recall": 0.3185840707964602, "eval_runtime": 0.3749, "eval_samples_per_second": 498.781, "eval_steps_per_second": 8.002, "step": 212 }, { "epoch": 3.0, "grad_norm": 1.118065595626831, "learning_rate": 4.85e-05, "loss": 0.325, "step": 318 }, { "epoch": 3.0, "eval_LOCATION_f1": 0.5935483870967742, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.5542168674698795, "eval_LOCATION_recall": 0.6388888888888888, "eval_ORGANIZATION_f1": 0.5517241379310344, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.48484848484848486, "eval_ORGANIZATION_recall": 0.64, "eval_PERSON_f1": 0.8269230769230769, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7633136094674556, "eval_PERSON_recall": 0.9020979020979021, "eval_QUANTITY_f1": 0.41791044776119407, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.3181818181818182, "eval_QUANTITY_recall": 0.6086956521739131, "eval_TIME_f1": 0.7272727272727274, "eval_TIME_number": 26, "eval_TIME_precision": 0.6896551724137931, "eval_TIME_recall": 0.7692307692307693, "eval_loss": 0.2219165712594986, "eval_overall_accuracy": 0.9271953965474106, "eval_overall_f1": 0.673656618610747, "eval_overall_precision": 0.6061320754716981, "eval_overall_recall": 0.7581120943952803, "eval_runtime": 0.3805, "eval_samples_per_second": 491.495, "eval_steps_per_second": 7.885, "step": 318 }, { "epoch": 4.0, "grad_norm": 1.4435498714447021, "learning_rate": 4.8e-05, "loss": 0.2281, "step": 424 }, { "epoch": 4.0, "eval_LOCATION_f1": 0.7096774193548386, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.6626506024096386, "eval_LOCATION_recall": 0.7638888888888888, "eval_ORGANIZATION_f1": 0.6022727272727274, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5247524752475248, "eval_ORGANIZATION_recall": 0.7066666666666667, "eval_PERSON_f1": 0.8525641025641025, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7869822485207101, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.3287671232876712, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.24, "eval_QUANTITY_recall": 0.5217391304347826, "eval_TIME_f1": 0.6885245901639345, "eval_TIME_number": 26, "eval_TIME_precision": 0.6, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.20335395634174347, "eval_overall_accuracy": 0.9342006504878659, "eval_overall_f1": 0.7052767052767053, "eval_overall_precision": 0.6255707762557078, "eval_overall_recall": 0.8082595870206489, "eval_runtime": 0.3781, "eval_samples_per_second": 494.548, "eval_steps_per_second": 7.934, "step": 424 }, { "epoch": 5.0, "grad_norm": 0.9061490297317505, "learning_rate": 4.75e-05, "loss": 0.1893, "step": 530 }, { "epoch": 5.0, "eval_LOCATION_f1": 0.7662337662337662, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7195121951219512, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.625, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5445544554455446, "eval_ORGANIZATION_recall": 0.7333333333333333, "eval_PERSON_f1": 0.8692810457516339, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8159509202453987, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.4838709677419355, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.38461538461538464, "eval_QUANTITY_recall": 0.6521739130434783, "eval_TIME_f1": 0.7777777777777779, "eval_TIME_number": 26, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.16108748316764832, "eval_overall_accuracy": 0.9442081561170879, "eval_overall_f1": 0.7526595744680852, "eval_overall_precision": 0.6852300242130751, "eval_overall_recall": 0.8348082595870207, "eval_runtime": 0.3842, "eval_samples_per_second": 486.665, "eval_steps_per_second": 7.807, "step": 530 }, { "epoch": 6.0, "grad_norm": 1.0410338640213013, "learning_rate": 4.7e-05, "loss": 0.1709, "step": 636 }, { "epoch": 6.0, "eval_LOCATION_f1": 0.7228915662650603, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.6382978723404256, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.6739130434782608, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5688073394495413, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.8910891089108911, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.84375, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.5517241379310345, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.45714285714285713, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.15253682434558868, "eval_overall_accuracy": 0.9482111583687766, "eval_overall_f1": 0.7692307692307694, "eval_overall_precision": 0.6892523364485982, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3762, "eval_samples_per_second": 497.072, "eval_steps_per_second": 7.974, "step": 636 }, { "epoch": 7.0, "grad_norm": 0.6735289692878723, "learning_rate": 4.6500000000000005e-05, "loss": 0.1574, "step": 742 }, { "epoch": 7.0, "eval_LOCATION_f1": 0.7564102564102564, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7023809523809523, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7052023121387283, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6224489795918368, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.8852459016393444, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8333333333333334, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.59375, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.4634146341463415, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.7777777777777779, "eval_TIME_number": 26, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.15402045845985413, "eval_overall_accuracy": 0.9489617212909682, "eval_overall_f1": 0.7845744680851063, "eval_overall_precision": 0.7142857142857143, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3789, "eval_samples_per_second": 493.535, "eval_steps_per_second": 7.918, "step": 742 }, { "epoch": 8.0, "grad_norm": 0.6694019436836243, "learning_rate": 4.600000000000001e-05, "loss": 0.1455, "step": 848 }, { "epoch": 8.0, "eval_LOCATION_f1": 0.7272727272727273, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.6829268292682927, "eval_LOCATION_recall": 0.7777777777777778, "eval_ORGANIZATION_f1": 0.7078651685393258, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6116504854368932, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8385093167701864, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6785714285714286, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5757575757575758, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.6666666666666667, "eval_TIME_number": 26, "eval_TIME_precision": 0.5882352941176471, "eval_TIME_recall": 0.7692307692307693, "eval_loss": 0.14883330464363098, "eval_overall_accuracy": 0.9479609707280461, "eval_overall_f1": 0.7792553191489361, "eval_overall_precision": 0.7094430992736077, "eval_overall_recall": 0.8643067846607669, "eval_runtime": 0.3823, "eval_samples_per_second": 489.103, "eval_steps_per_second": 7.847, "step": 848 }, { "epoch": 9.0, "grad_norm": 1.2299126386642456, "learning_rate": 4.55e-05, "loss": 0.1415, "step": 954 }, { "epoch": 9.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7071823204419889, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6037735849056604, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8874172185430464, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8427672955974843, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.7037037037037037, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6129032258064516, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.7017543859649122, "eval_TIME_number": 26, "eval_TIME_precision": 0.6451612903225806, "eval_TIME_recall": 0.7692307692307693, "eval_loss": 0.15283024311065674, "eval_overall_accuracy": 0.9472104078058544, "eval_overall_f1": 0.7951807228915664, "eval_overall_precision": 0.7279411764705882, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3784, "eval_samples_per_second": 494.225, "eval_steps_per_second": 7.929, "step": 954 }, { "epoch": 10.0, "grad_norm": 2.041289806365967, "learning_rate": 4.5e-05, "loss": 0.1317, "step": 1060 }, { "epoch": 10.0, "eval_LOCATION_f1": 0.7702702702702704, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.7916666666666666, "eval_ORGANIZATION_f1": 0.6779661016949153, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5882352941176471, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.9006622516556291, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8553459119496856, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.631578947368421, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5294117647058824, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.13493530452251434, "eval_overall_accuracy": 0.9527145359019265, "eval_overall_f1": 0.7891891891891892, "eval_overall_precision": 0.7281795511221946, "eval_overall_recall": 0.8613569321533924, "eval_runtime": 0.3777, "eval_samples_per_second": 495.125, "eval_steps_per_second": 7.943, "step": 1060 }, { "epoch": 11.0, "grad_norm": 0.6205049753189087, "learning_rate": 4.4500000000000004e-05, "loss": 0.1258, "step": 1166 }, { "epoch": 11.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7484662576687117, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6931818181818182, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.8866666666666668, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8471337579617835, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6785714285714286, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5757575757575758, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13175755739212036, "eval_overall_accuracy": 0.9572179134350763, "eval_overall_f1": 0.8104395604395604, "eval_overall_precision": 0.7583547557840618, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3786, "eval_samples_per_second": 493.972, "eval_steps_per_second": 7.925, "step": 1166 }, { "epoch": 12.0, "grad_norm": 1.5989289283752441, "learning_rate": 4.4000000000000006e-05, "loss": 0.1198, "step": 1272 }, { "epoch": 12.0, "eval_LOCATION_f1": 0.7651006711409396, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7402597402597403, "eval_LOCATION_recall": 0.7916666666666666, "eval_ORGANIZATION_f1": 0.7500000000000001, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7058823529411765, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8933333333333333, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8535031847133758, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.7547169811320754, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6666666666666666, "eval_QUANTITY_recall": 0.8695652173913043, "eval_TIME_f1": 0.830188679245283, "eval_TIME_number": 26, "eval_TIME_precision": 0.8148148148148148, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.136313334107399, "eval_overall_accuracy": 0.957968476357268, "eval_overall_f1": 0.8195804195804196, "eval_overall_precision": 0.7792553191489362, "eval_overall_recall": 0.8643067846607669, "eval_runtime": 0.3778, "eval_samples_per_second": 494.965, "eval_steps_per_second": 7.941, "step": 1272 }, { "epoch": 13.0, "grad_norm": 0.6925050020217896, "learning_rate": 4.35e-05, "loss": 0.1144, "step": 1378 }, { "epoch": 13.0, "eval_LOCATION_f1": 0.75, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7125, "eval_LOCATION_recall": 0.7916666666666666, "eval_ORGANIZATION_f1": 0.7403314917127072, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6320754716981132, "eval_ORGANIZATION_recall": 0.8933333333333333, "eval_PERSON_f1": 0.903654485049834, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8607594936708861, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.76, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.7037037037037037, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8148148148148148, "eval_TIME_number": 26, "eval_TIME_precision": 0.7857142857142857, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1362464725971222, "eval_overall_accuracy": 0.9569677257943457, "eval_overall_f1": 0.8157181571815718, "eval_overall_precision": 0.7543859649122807, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.3798, "eval_samples_per_second": 492.339, "eval_steps_per_second": 7.898, "step": 1378 }, { "epoch": 14.0, "grad_norm": 1.0199106931686401, "learning_rate": 4.3e-05, "loss": 0.1142, "step": 1484 }, { "epoch": 14.0, "eval_LOCATION_f1": 0.7837837837837838, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7631578947368421, "eval_LOCATION_recall": 0.8055555555555556, "eval_ORGANIZATION_f1": 0.7831325301204819, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7142857142857143, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.9066666666666667, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8662420382165605, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6440677966101694, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5277777777777778, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8214285714285715, "eval_TIME_number": 26, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.13535019755363464, "eval_overall_accuracy": 0.9587190392794596, "eval_overall_f1": 0.8257887517146778, "eval_overall_precision": 0.7717948717948718, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.3802, "eval_samples_per_second": 491.855, "eval_steps_per_second": 7.891, "step": 1484 }, { "epoch": 15.0, "grad_norm": 0.6930171847343445, "learning_rate": 4.25e-05, "loss": 0.1079, "step": 1590 }, { "epoch": 15.0, "eval_LOCATION_f1": 0.7671232876712328, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7567567567567568, "eval_LOCATION_recall": 0.7777777777777778, "eval_ORGANIZATION_f1": 0.785276073619632, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7272727272727273, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.9066666666666667, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8662420382165605, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.7169811320754716, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6333333333333333, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8148148148148148, "eval_TIME_number": 26, "eval_TIME_precision": 0.7857142857142857, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.12985557317733765, "eval_overall_accuracy": 0.9594696022016512, "eval_overall_f1": 0.8296089385474861, "eval_overall_precision": 0.7877984084880637, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3767, "eval_samples_per_second": 496.44, "eval_steps_per_second": 7.964, "step": 1590 }, { "epoch": 16.0, "grad_norm": 0.7586736679077148, "learning_rate": 4.2e-05, "loss": 0.1044, "step": 1696 }, { "epoch": 16.0, "eval_LOCATION_f1": 0.7947019867549668, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7683615819209039, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.9066666666666666, "eval_PERSON_f1": 0.8970099667774087, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8544303797468354, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6923076923076923, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6206896551724138, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8461538461538461, "eval_TIME_number": 26, "eval_TIME_precision": 0.8461538461538461, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.14694638550281525, "eval_overall_accuracy": 0.9547160370277709, "eval_overall_f1": 0.8267394270122784, "eval_overall_precision": 0.7690355329949239, "eval_overall_recall": 0.8938053097345132, "eval_runtime": 0.3781, "eval_samples_per_second": 494.584, "eval_steps_per_second": 7.934, "step": 1696 }, { "epoch": 17.0, "grad_norm": 0.3470544219017029, "learning_rate": 4.15e-05, "loss": 0.099, "step": 1802 }, { "epoch": 17.0, "eval_LOCATION_f1": 0.7837837837837838, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7631578947368421, "eval_LOCATION_recall": 0.8055555555555556, "eval_ORGANIZATION_f1": 0.7730061349693251, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7159090909090909, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8896321070234114, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8525641025641025, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6545454545454547, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5625, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8461538461538461, "eval_TIME_number": 26, "eval_TIME_precision": 0.8461538461538461, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1366996318101883, "eval_overall_accuracy": 0.9569677257943457, "eval_overall_f1": 0.8200836820083682, "eval_overall_precision": 0.7777777777777778, "eval_overall_recall": 0.8672566371681416, "eval_runtime": 0.3772, "eval_samples_per_second": 495.723, "eval_steps_per_second": 7.953, "step": 1802 }, { "epoch": 18.0, "grad_norm": 1.08118736743927, "learning_rate": 4.1e-05, "loss": 0.095, "step": 1908 }, { "epoch": 18.0, "eval_LOCATION_f1": 0.802721088435374, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7866666666666666, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7904191616766466, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.717391304347826, "eval_ORGANIZATION_recall": 0.88, "eval_PERSON_f1": 0.8859060402684563, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8516129032258064, "eval_PERSON_recall": 0.9230769230769231, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5806451612903226, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8148148148148148, "eval_TIME_number": 26, "eval_TIME_precision": 0.7857142857142857, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1454007923603058, "eval_overall_accuracy": 0.9574681010758068, "eval_overall_f1": 0.825, "eval_overall_precision": 0.7795275590551181, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3766, "eval_samples_per_second": 496.539, "eval_steps_per_second": 7.966, "step": 1908 }, { "epoch": 19.0, "grad_norm": 0.5193635821342468, "learning_rate": 4.05e-05, "loss": 0.0926, "step": 2014 }, { "epoch": 19.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7738095238095238, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6989247311827957, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8956228956228957, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8636363636363636, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6545454545454547, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5625, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8461538461538461, "eval_TIME_number": 26, "eval_TIME_precision": 0.8461538461538461, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13837505877017975, "eval_overall_accuracy": 0.9582186639979985, "eval_overall_f1": 0.8277777777777778, "eval_overall_precision": 0.7821522309711286, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.3785, "eval_samples_per_second": 494.12, "eval_steps_per_second": 7.927, "step": 2014 }, { "epoch": 20.0, "grad_norm": 0.9454425573348999, "learning_rate": 4e-05, "loss": 0.088, "step": 2120 }, { "epoch": 20.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7674418604651163, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6804123711340206, "eval_ORGANIZATION_recall": 0.88, "eval_PERSON_f1": 0.9060402684563759, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8709677419354839, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5588235294117647, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8076923076923077, "eval_TIME_number": 26, "eval_TIME_precision": 0.8076923076923077, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.16045436263084412, "eval_overall_accuracy": 0.9542156617463098, "eval_overall_f1": 0.8285322359396433, "eval_overall_precision": 0.7743589743589744, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.3774, "eval_samples_per_second": 495.497, "eval_steps_per_second": 7.949, "step": 2120 }, { "epoch": 21.0, "grad_norm": 0.5755162239074707, "learning_rate": 3.9500000000000005e-05, "loss": 0.0878, "step": 2226 }, { "epoch": 21.0, "eval_LOCATION_f1": 0.7972972972972973, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7763157894736842, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7555555555555555, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6476190476190476, "eval_ORGANIZATION_recall": 0.9066666666666666, "eval_PERSON_f1": 0.9060402684563759, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8709677419354839, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.7037037037037037, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6129032258064516, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8627450980392156, "eval_TIME_number": 26, "eval_TIME_precision": 0.88, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.14829762279987335, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.8290013679890561, "eval_overall_precision": 0.7729591836734694, "eval_overall_recall": 0.8938053097345132, "eval_runtime": 0.3782, "eval_samples_per_second": 494.445, "eval_steps_per_second": 7.932, "step": 2226 }, { "epoch": 22.0, "grad_norm": 0.5230295658111572, "learning_rate": 3.9000000000000006e-05, "loss": 0.089, "step": 2332 }, { "epoch": 22.0, "eval_LOCATION_f1": 0.802721088435374, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7866666666666666, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7608695652173914, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6422018348623854, "eval_ORGANIZATION_recall": 0.9333333333333333, "eval_PERSON_f1": 0.9072847682119206, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8616352201257862, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6440677966101694, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5277777777777778, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.7924528301886792, "eval_TIME_number": 26, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.15434490144252777, "eval_overall_accuracy": 0.9534650988241181, "eval_overall_f1": 0.8214765100671141, "eval_overall_precision": 0.7536945812807881, "eval_overall_recall": 0.9026548672566371, "eval_runtime": 0.3786, "eval_samples_per_second": 493.932, "eval_steps_per_second": 7.924, "step": 2332 }, { "epoch": 23.0, "grad_norm": 0.4608692526817322, "learning_rate": 3.85e-05, "loss": 0.0835, "step": 2438 }, { "epoch": 23.0, "eval_LOCATION_f1": 0.816326530612245, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7529411764705883, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6736842105263158, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.9054054054054055, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8758169934640523, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6428571428571429, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5454545454545454, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8076923076923077, "eval_TIME_number": 26, "eval_TIME_precision": 0.8076923076923077, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14608316123485565, "eval_overall_accuracy": 0.955716787590693, "eval_overall_f1": 0.8238557558945908, "eval_overall_precision": 0.7774869109947644, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3772, "eval_samples_per_second": 495.784, "eval_steps_per_second": 7.954, "step": 2438 }, { "epoch": 24.0, "grad_norm": 0.6337035298347473, "learning_rate": 3.8e-05, "loss": 0.0789, "step": 2544 }, { "epoch": 24.0, "eval_LOCATION_f1": 0.8513513513513513, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8289473684210527, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.7607361963190183, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7045454545454546, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.912751677852349, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8774193548387097, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6428571428571429, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5454545454545454, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8235294117647058, "eval_TIME_number": 26, "eval_TIME_precision": 0.84, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1453711837530136, "eval_overall_accuracy": 0.9567175381536153, "eval_overall_f1": 0.8379888268156425, "eval_overall_precision": 0.7957559681697612, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.3761, "eval_samples_per_second": 497.188, "eval_steps_per_second": 7.976, "step": 2544 }, { "epoch": 25.0, "grad_norm": 0.5838052034378052, "learning_rate": 3.7500000000000003e-05, "loss": 0.0773, "step": 2650 }, { "epoch": 25.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.84, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.7757575757575759, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7111111111111111, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.9023569023569024, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8701298701298701, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5806451612903226, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13762633502483368, "eval_overall_accuracy": 0.9589692269201902, "eval_overall_f1": 0.8372739916550764, "eval_overall_precision": 0.7921052631578948, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.378, "eval_samples_per_second": 494.698, "eval_steps_per_second": 7.936, "step": 2650 }, { "epoch": 26.0, "grad_norm": 0.6994030475616455, "learning_rate": 3.7e-05, "loss": 0.0779, "step": 2756 }, { "epoch": 26.0, "eval_LOCATION_f1": 0.8356164383561645, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8243243243243243, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7455621301775148, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6702127659574468, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.9066666666666667, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8662420382165605, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6923076923076923, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6206896551724138, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.7777777777777779, "eval_TIME_number": 26, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1366981565952301, "eval_overall_accuracy": 0.9599699774831123, "eval_overall_f1": 0.8294036061026352, "eval_overall_precision": 0.7827225130890052, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.3782, "eval_samples_per_second": 494.488, "eval_steps_per_second": 7.933, "step": 2756 }, { "epoch": 27.0, "grad_norm": 0.5041149258613586, "learning_rate": 3.65e-05, "loss": 0.0735, "step": 2862 }, { "epoch": 27.0, "eval_LOCATION_f1": 0.8493150684931507, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8378378378378378, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.759493670886076, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7228915662650602, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.9158249158249158, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8831168831168831, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6923076923076923, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6206896551724138, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.1394449919462204, "eval_overall_accuracy": 0.9629722291718789, "eval_overall_f1": 0.8470254957507082, "eval_overall_precision": 0.8147138964577657, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.3796, "eval_samples_per_second": 492.675, "eval_steps_per_second": 7.904, "step": 2862 }, { "epoch": 28.0, "grad_norm": 1.0946162939071655, "learning_rate": 3.6e-05, "loss": 0.0718, "step": 2968 }, { "epoch": 28.0, "eval_LOCATION_f1": 0.8219178082191781, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8108108108108109, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7682926829268292, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7078651685393258, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.91156462585034, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8874172185430463, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13758285343647003, "eval_overall_accuracy": 0.9604703527645734, "eval_overall_f1": 0.8330995792426367, "eval_overall_precision": 0.7941176470588235, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3787, "eval_samples_per_second": 493.744, "eval_steps_per_second": 7.921, "step": 2968 }, { "epoch": 29.0, "grad_norm": 0.6572793126106262, "learning_rate": 3.55e-05, "loss": 0.071, "step": 3074 }, { "epoch": 29.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7558139534883721, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6701030927835051, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.912751677852349, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8774193548387097, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6428571428571429, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5454545454545454, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1548575758934021, "eval_overall_accuracy": 0.9572179134350763, "eval_overall_f1": 0.8246575342465754, "eval_overall_precision": 0.7698209718670077, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.3791, "eval_samples_per_second": 493.228, "eval_steps_per_second": 7.913, "step": 3074 }, { "epoch": 30.0, "grad_norm": 0.7155618071556091, "learning_rate": 3.5e-05, "loss": 0.0717, "step": 3180 }, { "epoch": 30.0, "eval_LOCATION_f1": 0.7945205479452055, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7837837837837838, "eval_LOCATION_recall": 0.8055555555555556, "eval_ORGANIZATION_f1": 0.7664670658682634, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6956521739130435, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.9225589225589226, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8896103896103896, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.7924528301886792, "eval_TIME_number": 26, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14325742423534393, "eval_overall_accuracy": 0.9604703527645734, "eval_overall_f1": 0.8324022346368715, "eval_overall_precision": 0.7904509283819628, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.3776, "eval_samples_per_second": 495.19, "eval_steps_per_second": 7.944, "step": 3180 }, { "epoch": 31.0, "grad_norm": 0.44705238938331604, "learning_rate": 3.45e-05, "loss": 0.071, "step": 3286 }, { "epoch": 31.0, "eval_LOCATION_f1": 0.8435374149659863, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8266666666666667, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7951807228915663, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7252747252747253, "eval_ORGANIZATION_recall": 0.88, "eval_PERSON_f1": 0.9158249158249158, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8831168831168831, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.72, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6666666666666666, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8076923076923077, "eval_TIME_number": 26, "eval_TIME_precision": 0.8076923076923077, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14365795254707336, "eval_overall_accuracy": 0.9619714786089567, "eval_overall_f1": 0.8511235955056179, "eval_overall_precision": 0.8123324396782842, "eval_overall_recall": 0.8938053097345132, "eval_runtime": 0.3777, "eval_samples_per_second": 495.155, "eval_steps_per_second": 7.944, "step": 3286 }, { "epoch": 32.0, "grad_norm": 2.0400214195251465, "learning_rate": 3.4000000000000007e-05, "loss": 0.0652, "step": 3392 }, { "epoch": 32.0, "eval_LOCATION_f1": 0.8219178082191781, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8108108108108109, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.785276073619632, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7272727272727273, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8986486486486487, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.869281045751634, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6428571428571429, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.7924528301886792, "eval_TIME_number": 26, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.142520010471344, "eval_overall_accuracy": 0.9604703527645734, "eval_overall_f1": 0.8349788434414668, "eval_overall_precision": 0.8, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3788, "eval_samples_per_second": 493.644, "eval_steps_per_second": 7.919, "step": 3392 }, { "epoch": 33.0, "grad_norm": 1.2415409088134766, "learning_rate": 3.35e-05, "loss": 0.0664, "step": 3498 }, { "epoch": 33.0, "eval_LOCATION_f1": 0.8378378378378377, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8157894736842105, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7831325301204819, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7142857142857143, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.9054054054054055, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8758169934640523, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6428571428571429, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8461538461538461, "eval_TIME_number": 26, "eval_TIME_precision": 0.8461538461538461, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1492750197649002, "eval_overall_accuracy": 0.961220915686765, "eval_overall_f1": 0.8443197755960731, "eval_overall_precision": 0.8048128342245989, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.3804, "eval_samples_per_second": 491.646, "eval_steps_per_second": 7.887, "step": 3498 }, { "epoch": 34.0, "grad_norm": 1.1798769235610962, "learning_rate": 3.3e-05, "loss": 0.0623, "step": 3604 }, { "epoch": 34.0, "eval_LOCATION_f1": 0.8157894736842106, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.775, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7790697674418604, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6907216494845361, "eval_ORGANIZATION_recall": 0.8933333333333333, "eval_PERSON_f1": 0.9096989966555185, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8717948717948718, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5806451612903226, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1654369980096817, "eval_overall_accuracy": 0.9572179134350763, "eval_overall_f1": 0.829467939972715, "eval_overall_precision": 0.7715736040609137, "eval_overall_recall": 0.8967551622418879, "eval_runtime": 0.3863, "eval_samples_per_second": 484.055, "eval_steps_per_second": 7.766, "step": 3604 }, { "epoch": 35.0, "grad_norm": 1.1484782695770264, "learning_rate": 3.2500000000000004e-05, "loss": 0.0615, "step": 3710 }, { "epoch": 35.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7757575757575759, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7111111111111111, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8986486486486487, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.869281045751634, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6923076923076923, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6206896551724138, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.7777777777777779, "eval_TIME_number": 26, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1493893563747406, "eval_overall_accuracy": 0.9594696022016512, "eval_overall_f1": 0.827972027972028, "eval_overall_precision": 0.7872340425531915, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3759, "eval_samples_per_second": 497.422, "eval_steps_per_second": 7.98, "step": 3710 }, { "epoch": 36.0, "grad_norm": 1.2095956802368164, "learning_rate": 3.2000000000000005e-05, "loss": 0.0589, "step": 3816 }, { "epoch": 36.0, "eval_LOCATION_f1": 0.8322147651006712, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8051948051948052, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7738095238095238, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6989247311827957, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.9090909090909092, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8766233766233766, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6428571428571429, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8461538461538461, "eval_TIME_number": 26, "eval_TIME_precision": 0.8461538461538461, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.14943872392177582, "eval_overall_accuracy": 0.961220915686765, "eval_overall_f1": 0.8423988842398884, "eval_overall_precision": 0.798941798941799, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.3754, "eval_samples_per_second": 498.096, "eval_steps_per_second": 7.991, "step": 3816 }, { "epoch": 37.0, "grad_norm": 0.9618573784828186, "learning_rate": 3.15e-05, "loss": 0.0576, "step": 3922 }, { "epoch": 37.0, "eval_LOCATION_f1": 0.781456953642384, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7468354430379747, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7764705882352942, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6947368421052632, "eval_ORGANIZATION_recall": 0.88, "eval_PERSON_f1": 0.9096989966555185, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8717948717948718, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6428571428571429, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8461538461538461, "eval_TIME_number": 26, "eval_TIME_precision": 0.8461538461538461, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.15785393118858337, "eval_overall_accuracy": 0.9592194145609206, "eval_overall_f1": 0.8326417704011065, "eval_overall_precision": 0.7838541666666666, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.3811, "eval_samples_per_second": 490.683, "eval_steps_per_second": 7.872, "step": 3922 }, { "epoch": 38.0, "grad_norm": 0.4735202491283417, "learning_rate": 3.1e-05, "loss": 0.0586, "step": 4028 }, { "epoch": 38.0, "eval_LOCATION_f1": 0.8082191780821918, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7972972972972973, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7950310559006211, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7441860465116279, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.903654485049834, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8607594936708861, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.7924528301886792, "eval_TIME_number": 26, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.15275536477565765, "eval_overall_accuracy": 0.9589692269201902, "eval_overall_f1": 0.8347338935574229, "eval_overall_precision": 0.7946666666666666, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.3755, "eval_samples_per_second": 498.04, "eval_steps_per_second": 7.99, "step": 4028 }, { "epoch": 39.0, "grad_norm": 0.5576403141021729, "learning_rate": 3.05e-05, "loss": 0.0577, "step": 4134 }, { "epoch": 39.0, "eval_LOCATION_f1": 0.8378378378378377, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8157894736842105, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7738095238095238, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6989247311827957, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.9261744966442954, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8903225806451613, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6428571428571429, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8461538461538461, "eval_TIME_number": 26, "eval_TIME_precision": 0.8461538461538461, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.16170634329319, "eval_overall_accuracy": 0.9599699774831123, "eval_overall_f1": 0.8507670850767085, "eval_overall_precision": 0.8068783068783069, "eval_overall_recall": 0.8997050147492626, "eval_runtime": 0.3785, "eval_samples_per_second": 494.087, "eval_steps_per_second": 7.927, "step": 4134 }, { "epoch": 40.0, "grad_norm": 0.4916011393070221, "learning_rate": 3e-05, "loss": 0.0536, "step": 4240 }, { "epoch": 40.0, "eval_LOCATION_f1": 0.8421052631578948, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8888888888888888, "eval_ORGANIZATION_f1": 0.7607361963190183, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7045454545454546, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.9090909090909092, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8766233766233766, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.7777777777777779, "eval_TIME_number": 26, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.15796098113059998, "eval_overall_accuracy": 0.9602201651238429, "eval_overall_f1": 0.8344923504867873, "eval_overall_precision": 0.7894736842105263, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.3774, "eval_samples_per_second": 495.465, "eval_steps_per_second": 7.949, "step": 4240 }, { "epoch": 41.0, "grad_norm": 0.9400687217712402, "learning_rate": 2.95e-05, "loss": 0.0572, "step": 4346 }, { "epoch": 41.0, "eval_LOCATION_f1": 0.8322147651006712, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8051948051948052, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7664670658682634, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6956521739130435, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.9169435215946844, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8734177215189873, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6428571428571429, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8846153846153846, "eval_TIME_number": 26, "eval_TIME_precision": 0.8846153846153846, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.1550283432006836, "eval_overall_accuracy": 0.9597197898423818, "eval_overall_f1": 0.8472222222222222, "eval_overall_precision": 0.800524934383202, "eval_overall_recall": 0.8997050147492626, "eval_runtime": 0.3761, "eval_samples_per_second": 497.234, "eval_steps_per_second": 7.977, "step": 4346 }, { "epoch": 42.0, "grad_norm": 1.621040940284729, "learning_rate": 2.9e-05, "loss": 0.0524, "step": 4452 }, { "epoch": 42.0, "eval_LOCATION_f1": 0.8079470198675496, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7831325301204819, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7142857142857143, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.9, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8598726114649682, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.7037037037037037, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6129032258064516, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1589338332414627, "eval_overall_accuracy": 0.9589692269201902, "eval_overall_f1": 0.8319559228650136, "eval_overall_precision": 0.7803617571059431, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.3809, "eval_samples_per_second": 490.909, "eval_steps_per_second": 7.876, "step": 4452 }, { "epoch": 43.0, "grad_norm": 0.5988844037055969, "learning_rate": 2.8499999999999998e-05, "loss": 0.052, "step": 4558 }, { "epoch": 43.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.779874213836478, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7380952380952381, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.9090909090909092, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8766233766233766, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6428571428571429, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8461538461538461, "eval_TIME_number": 26, "eval_TIME_precision": 0.8461538461538461, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.15005570650100708, "eval_overall_accuracy": 0.9609707280460346, "eval_overall_f1": 0.8401697312588402, "eval_overall_precision": 0.8070652173913043, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3756, "eval_samples_per_second": 497.853, "eval_steps_per_second": 7.987, "step": 4558 }, { "epoch": 44.0, "grad_norm": 0.9367622137069702, "learning_rate": 2.8000000000000003e-05, "loss": 0.0509, "step": 4664 }, { "epoch": 44.0, "eval_LOCATION_f1": 0.8053691275167787, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7875000000000001, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7411764705882353, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.9163879598662208, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8782051282051282, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6923076923076923, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6206896551724138, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.7924528301886792, "eval_TIME_number": 26, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.15873059630393982, "eval_overall_accuracy": 0.9597197898423818, "eval_overall_f1": 0.8387096774193548, "eval_overall_precision": 0.7994652406417112, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.3749, "eval_samples_per_second": 498.817, "eval_steps_per_second": 8.002, "step": 4664 }, { "epoch": 45.0, "grad_norm": 0.6508892178535461, "learning_rate": 2.7500000000000004e-05, "loss": 0.049, "step": 4770 }, { "epoch": 45.0, "eval_LOCATION_f1": 0.8079470198675496, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7749999999999999, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7294117647058823, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.903654485049834, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8607594936708861, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.7307692307692308, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6551724137931034, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.7777777777777779, "eval_TIME_number": 26, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.15799470245838165, "eval_overall_accuracy": 0.960720540405304, "eval_overall_f1": 0.8328690807799444, "eval_overall_precision": 0.7889182058047494, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.3786, "eval_samples_per_second": 493.935, "eval_steps_per_second": 7.924, "step": 4770 }, { "epoch": 46.0, "grad_norm": 0.3828009068965912, "learning_rate": 2.7000000000000002e-05, "loss": 0.0479, "step": 4876 }, { "epoch": 46.0, "eval_LOCATION_f1": 0.8513513513513513, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8289473684210527, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.779874213836478, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7380952380952381, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.9096989966555185, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8717948717948718, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.7307692307692308, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6551724137931034, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8148148148148148, "eval_TIME_number": 26, "eval_TIME_precision": 0.7857142857142857, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1539916843175888, "eval_overall_accuracy": 0.9627220415311484, "eval_overall_f1": 0.848314606741573, "eval_overall_precision": 0.8096514745308311, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.3761, "eval_samples_per_second": 497.145, "eval_steps_per_second": 7.976, "step": 4876 }, { "epoch": 47.0, "grad_norm": 1.15745210647583, "learning_rate": 2.6500000000000004e-05, "loss": 0.0488, "step": 4982 }, { "epoch": 47.0, "eval_LOCATION_f1": 0.8378378378378377, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8157894736842105, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7484662576687117, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6931818181818182, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.8786885245901639, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8271604938271605, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6428571428571429, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.830188679245283, "eval_TIME_number": 26, "eval_TIME_precision": 0.8148148148148148, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1685992181301117, "eval_overall_accuracy": 0.9564673505128847, "eval_overall_f1": 0.825, "eval_overall_precision": 0.7795275590551181, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3774, "eval_samples_per_second": 495.517, "eval_steps_per_second": 7.949, "step": 4982 }, { "epoch": 48.0, "grad_norm": 0.9865849614143372, "learning_rate": 2.6000000000000002e-05, "loss": 0.0468, "step": 5088 }, { "epoch": 48.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.84, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.7500000000000001, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7058823529411765, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8993288590604027, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.864516129032258, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6428571428571429, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.15260353684425354, "eval_overall_accuracy": 0.9632224168126094, "eval_overall_f1": 0.840620592383639, "eval_overall_precision": 0.8054054054054054, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.3757, "eval_samples_per_second": 497.707, "eval_steps_per_second": 7.985, "step": 5088 }, { "epoch": 49.0, "grad_norm": 0.6459212303161621, "learning_rate": 2.5500000000000003e-05, "loss": 0.0474, "step": 5194 }, { "epoch": 49.0, "eval_LOCATION_f1": 0.8187919463087249, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7922077922077922, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7607361963190183, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7045454545454546, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.9169435215946844, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8734177215189873, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.6923076923076923, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6206896551724138, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8461538461538461, "eval_TIME_number": 26, "eval_TIME_precision": 0.8461538461538461, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.16667716205120087, "eval_overall_accuracy": 0.9604703527645734, "eval_overall_f1": 0.8396094839609484, "eval_overall_precision": 0.7962962962962963, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.3764, "eval_samples_per_second": 496.855, "eval_steps_per_second": 7.971, "step": 5194 }, { "epoch": 50.0, "grad_norm": 0.7612103223800659, "learning_rate": 2.5e-05, "loss": 0.0485, "step": 5300 }, { "epoch": 50.0, "eval_LOCATION_f1": 0.8356164383561645, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8243243243243243, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.782051282051282, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7530864197530864, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.912751677852349, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8774193548387097, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.76, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.7037037037037037, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8627450980392156, "eval_TIME_number": 26, "eval_TIME_precision": 0.88, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.15263156592845917, "eval_overall_accuracy": 0.96347260445334, "eval_overall_f1": 0.8530670470756063, "eval_overall_precision": 0.8259668508287292, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.3764, "eval_samples_per_second": 496.873, "eval_steps_per_second": 7.971, "step": 5300 }, { "epoch": 51.0, "grad_norm": 0.8503948450088501, "learning_rate": 2.45e-05, "loss": 0.0443, "step": 5406 }, { "epoch": 51.0, "eval_LOCATION_f1": 0.8435374149659863, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8266666666666667, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7784431137724551, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7065217391304348, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.9266666666666666, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8853503184713376, "eval_PERSON_recall": 0.972027972027972, "eval_QUANTITY_f1": 0.7169811320754716, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6333333333333333, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8461538461538461, "eval_TIME_number": 26, "eval_TIME_precision": 0.8461538461538461, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.16938814520835876, "eval_overall_accuracy": 0.961220915686765, "eval_overall_f1": 0.8539638386648123, "eval_overall_precision": 0.8078947368421052, "eval_overall_recall": 0.9056047197640118, "eval_runtime": 0.3772, "eval_samples_per_second": 495.786, "eval_steps_per_second": 7.954, "step": 5406 }, { "epoch": 52.0, "grad_norm": 0.4882877767086029, "learning_rate": 2.4e-05, "loss": 0.0468, "step": 5512 }, { "epoch": 52.0, "eval_LOCATION_f1": 0.8299319727891157, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8133333333333334, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7701863354037267, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7209302325581395, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.9, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8598726114649682, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6538461538461539, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5862068965517241, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7636363636363636, "eval_TIME_number": 26, "eval_TIME_precision": 0.7241379310344828, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1636158525943756, "eval_overall_accuracy": 0.9584688516387291, "eval_overall_f1": 0.827972027972028, "eval_overall_precision": 0.7872340425531915, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3772, "eval_samples_per_second": 495.701, "eval_steps_per_second": 7.952, "step": 5512 }, { "epoch": 53.0, "grad_norm": 1.0076719522476196, "learning_rate": 2.35e-05, "loss": 0.0439, "step": 5618 }, { "epoch": 53.0, "eval_LOCATION_f1": 0.8137931034482759, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8082191780821918, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.785276073619632, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7272727272727273, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.923076923076923, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8846153846153846, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.6785714285714286, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5757575757575758, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8461538461538461, "eval_TIME_number": 26, "eval_TIME_precision": 0.8461538461538461, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.16856712102890015, "eval_overall_accuracy": 0.9597197898423818, "eval_overall_f1": 0.8447552447552448, "eval_overall_precision": 0.8031914893617021, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.3748, "eval_samples_per_second": 498.942, "eval_steps_per_second": 8.004, "step": 5618 }, { "epoch": 54.0, "grad_norm": 0.4930567443370819, "learning_rate": 2.3000000000000003e-05, "loss": 0.0449, "step": 5724 }, { "epoch": 54.0, "eval_LOCATION_f1": 0.8400000000000001, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.7826086956521738, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7325581395348837, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.9169435215946844, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8734177215189873, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5806451612903226, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.830188679245283, "eval_TIME_number": 26, "eval_TIME_precision": 0.8148148148148148, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.16776379942893982, "eval_overall_accuracy": 0.9602201651238429, "eval_overall_f1": 0.8456189151599444, "eval_overall_precision": 0.8, "eval_overall_recall": 0.8967551622418879, "eval_runtime": 0.3762, "eval_samples_per_second": 497.057, "eval_steps_per_second": 7.974, "step": 5724 }, { "epoch": 55.0, "grad_norm": 1.5758038759231567, "learning_rate": 2.25e-05, "loss": 0.0428, "step": 5830 }, { "epoch": 55.0, "eval_LOCATION_f1": 0.8187919463087249, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7922077922077922, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7831325301204819, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7142857142857143, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.92, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8789808917197452, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6428571428571429, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.7931034482758621, "eval_TIME_number": 26, "eval_TIME_precision": 0.71875, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.17032887041568756, "eval_overall_accuracy": 0.9602201651238429, "eval_overall_f1": 0.8425414364640885, "eval_overall_precision": 0.7922077922077922, "eval_overall_recall": 0.8997050147492626, "eval_runtime": 0.3758, "eval_samples_per_second": 497.571, "eval_steps_per_second": 7.982, "step": 5830 }, { "epoch": 56.0, "grad_norm": 0.7785055637359619, "learning_rate": 2.2000000000000003e-05, "loss": 0.043, "step": 5936 }, { "epoch": 56.0, "eval_LOCATION_f1": 0.8211920529801324, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7848101265822784, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7710843373493976, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7032967032967034, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.9328859060402686, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.896774193548387, "eval_PERSON_recall": 0.972027972027972, "eval_QUANTITY_f1": 0.6923076923076923, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6206896551724138, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.830188679245283, "eval_TIME_number": 26, "eval_TIME_precision": 0.8148148148148148, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1670546680688858, "eval_overall_accuracy": 0.960720540405304, "eval_overall_f1": 0.8472222222222222, "eval_overall_precision": 0.800524934383202, "eval_overall_recall": 0.8997050147492626, "eval_runtime": 0.3763, "eval_samples_per_second": 496.95, "eval_steps_per_second": 7.972, "step": 5936 }, { "epoch": 57.0, "grad_norm": 0.49103009700775146, "learning_rate": 2.15e-05, "loss": 0.0405, "step": 6042 }, { "epoch": 57.0, "eval_LOCATION_f1": 0.8219178082191781, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8108108108108109, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7848101265822784, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7469879518072289, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.9225589225589226, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8896103896103896, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.7307692307692308, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6551724137931034, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8461538461538461, "eval_TIME_number": 26, "eval_TIME_precision": 0.8461538461538461, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.15890353918075562, "eval_overall_accuracy": 0.9624718538904178, "eval_overall_f1": 0.851063829787234, "eval_overall_precision": 0.819672131147541, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.3788, "eval_samples_per_second": 493.609, "eval_steps_per_second": 7.919, "step": 6042 }, { "epoch": 58.0, "grad_norm": 0.5003204345703125, "learning_rate": 2.1e-05, "loss": 0.0402, "step": 6148 }, { "epoch": 58.0, "eval_LOCATION_f1": 0.8243243243243243, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8026315789473685, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7654320987654321, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7126436781609196, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.9133333333333333, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8726114649681529, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8148148148148148, "eval_TIME_number": 26, "eval_TIME_precision": 0.7857142857142857, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.16718268394470215, "eval_overall_accuracy": 0.9609707280460346, "eval_overall_f1": 0.8368200836820084, "eval_overall_precision": 0.7936507936507936, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.3773, "eval_samples_per_second": 495.563, "eval_steps_per_second": 7.95, "step": 6148 }, { "epoch": 59.0, "grad_norm": 0.12552323937416077, "learning_rate": 2.05e-05, "loss": 0.0408, "step": 6254 }, { "epoch": 59.0, "eval_LOCATION_f1": 0.8243243243243243, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8026315789473685, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7721518987341773, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7349397590361446, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.9133333333333333, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8726114649681529, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6923076923076923, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6206896551724138, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8363636363636363, "eval_TIME_number": 26, "eval_TIME_precision": 0.7931034482758621, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.16901348531246185, "eval_overall_accuracy": 0.9627220415311484, "eval_overall_f1": 0.8415147265077138, "eval_overall_precision": 0.8021390374331551, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.3767, "eval_samples_per_second": 496.424, "eval_steps_per_second": 7.964, "step": 6254 }, { "epoch": 60.0, "grad_norm": 0.5769420266151428, "learning_rate": 2e-05, "loss": 0.0384, "step": 6360 }, { "epoch": 60.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7619047619047621, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6881720430107527, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.92, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8789808917197452, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.7307692307692308, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6551724137931034, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.7586206896551724, "eval_TIME_number": 26, "eval_TIME_precision": 0.6875, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1785995215177536, "eval_overall_accuracy": 0.9599699774831123, "eval_overall_f1": 0.8351648351648351, "eval_overall_precision": 0.781491002570694, "eval_overall_recall": 0.8967551622418879, "eval_runtime": 0.3773, "eval_samples_per_second": 495.674, "eval_steps_per_second": 7.952, "step": 6360 }, { "epoch": 61.0, "grad_norm": 0.23254899680614471, "learning_rate": 1.9500000000000003e-05, "loss": 0.0381, "step": 6466 }, { "epoch": 61.0, "eval_LOCATION_f1": 0.8226950354609929, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8405797101449275, "eval_LOCATION_recall": 0.8055555555555556, "eval_ORGANIZATION_f1": 0.763157894736842, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7532467532467533, "eval_ORGANIZATION_recall": 0.7733333333333333, "eval_PERSON_f1": 0.9023569023569024, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8701298701298701, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.7169811320754716, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6333333333333333, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8461538461538461, "eval_TIME_number": 26, "eval_TIME_precision": 0.8461538461538461, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1716317981481552, "eval_overall_accuracy": 0.9617212909682261, "eval_overall_f1": 0.8374100719424461, "eval_overall_precision": 0.8174157303370787, "eval_overall_recall": 0.8584070796460177, "eval_runtime": 0.3738, "eval_samples_per_second": 500.312, "eval_steps_per_second": 8.026, "step": 6466 }, { "epoch": 62.0, "grad_norm": 0.6055287718772888, "learning_rate": 1.9e-05, "loss": 0.0393, "step": 6572 }, { "epoch": 62.0, "eval_LOCATION_f1": 0.8299319727891157, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8133333333333334, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7662337662337663, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7468354430379747, "eval_ORGANIZATION_recall": 0.7866666666666666, "eval_PERSON_f1": 0.9163879598662208, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8782051282051282, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6428571428571429, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8461538461538461, "eval_TIME_number": 26, "eval_TIME_precision": 0.8461538461538461, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.16724902391433716, "eval_overall_accuracy": 0.9632224168126094, "eval_overall_f1": 0.844950213371266, "eval_overall_precision": 0.8159340659340659, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.376, "eval_samples_per_second": 497.38, "eval_steps_per_second": 7.979, "step": 6572 }, { "epoch": 63.0, "grad_norm": 0.6947082877159119, "learning_rate": 1.85e-05, "loss": 0.037, "step": 6678 }, { "epoch": 63.0, "eval_LOCATION_f1": 0.8356164383561645, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8243243243243243, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7435897435897435, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7160493827160493, "eval_ORGANIZATION_recall": 0.7733333333333333, "eval_PERSON_f1": 0.9163879598662208, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8782051282051282, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6923076923076923, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6206896551724138, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.16370835900306702, "eval_overall_accuracy": 0.9627220415311484, "eval_overall_f1": 0.8413597733711049, "eval_overall_precision": 0.8092643051771117, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3786, "eval_samples_per_second": 493.942, "eval_steps_per_second": 7.924, "step": 6678 }, { "epoch": 64.0, "grad_norm": 0.9311719536781311, "learning_rate": 1.8e-05, "loss": 0.0357, "step": 6784 }, { "epoch": 64.0, "eval_LOCATION_f1": 0.8456375838926175, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.7530864197530864, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7011494252873564, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.9139072847682119, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8679245283018868, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.6923076923076923, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6206896551724138, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8148148148148148, "eval_TIME_number": 26, "eval_TIME_precision": 0.7857142857142857, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1763332337141037, "eval_overall_accuracy": 0.9617212909682261, "eval_overall_f1": 0.8400556328233658, "eval_overall_precision": 0.7947368421052632, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.3767, "eval_samples_per_second": 496.439, "eval_steps_per_second": 7.964, "step": 6784 }, { "epoch": 65.0, "grad_norm": 0.061806291341781616, "learning_rate": 1.75e-05, "loss": 0.0374, "step": 6890 }, { "epoch": 65.0, "eval_LOCATION_f1": 0.8378378378378377, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8157894736842105, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7848101265822784, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7469879518072289, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.9261744966442954, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8903225806451613, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8518518518518519, "eval_TIME_number": 26, "eval_TIME_precision": 0.8214285714285714, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.17243608832359314, "eval_overall_accuracy": 0.9622216662496873, "eval_overall_f1": 0.8523206751054851, "eval_overall_precision": 0.8145161290322581, "eval_overall_recall": 0.8938053097345132, "eval_runtime": 0.3759, "eval_samples_per_second": 497.418, "eval_steps_per_second": 7.98, "step": 6890 }, { "epoch": 66.0, "grad_norm": 1.068263053894043, "learning_rate": 1.7000000000000003e-05, "loss": 0.0368, "step": 6996 }, { "epoch": 66.0, "eval_LOCATION_f1": 0.8513513513513513, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8289473684210527, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.7749999999999999, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7294117647058823, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.9133333333333333, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8726114649681529, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.7307692307692308, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6551724137931034, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8363636363636363, "eval_TIME_number": 26, "eval_TIME_precision": 0.7931034482758621, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.17702345550060272, "eval_overall_accuracy": 0.9617212909682261, "eval_overall_f1": 0.8503496503496504, "eval_overall_precision": 0.8085106382978723, "eval_overall_recall": 0.8967551622418879, "eval_runtime": 0.3774, "eval_samples_per_second": 495.511, "eval_steps_per_second": 7.949, "step": 6996 }, { "epoch": 67.0, "grad_norm": 0.35486891865730286, "learning_rate": 1.65e-05, "loss": 0.0374, "step": 7102 }, { "epoch": 67.0, "eval_LOCATION_f1": 0.8219178082191781, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8108108108108109, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7607361963190183, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7045454545454546, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.9133333333333333, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8726114649681529, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6428571428571429, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8461538461538461, "eval_TIME_number": 26, "eval_TIME_precision": 0.8461538461538461, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.17916804552078247, "eval_overall_accuracy": 0.9619714786089567, "eval_overall_f1": 0.8398876404494382, "eval_overall_precision": 0.8016085790884718, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.375, "eval_samples_per_second": 498.645, "eval_steps_per_second": 8.0, "step": 7102 }, { "epoch": 68.0, "grad_norm": 0.5311190485954285, "learning_rate": 1.6000000000000003e-05, "loss": 0.034, "step": 7208 }, { "epoch": 68.0, "eval_LOCATION_f1": 0.8243243243243243, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8026315789473685, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7421383647798742, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7023809523809523, "eval_ORGANIZATION_recall": 0.7866666666666666, "eval_PERSON_f1": 0.9139072847682119, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8679245283018868, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8148148148148148, "eval_TIME_number": 26, "eval_TIME_precision": 0.7857142857142857, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.18868251144886017, "eval_overall_accuracy": 0.9594696022016512, "eval_overall_f1": 0.8324022346368715, "eval_overall_precision": 0.7904509283819628, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.3763, "eval_samples_per_second": 496.929, "eval_steps_per_second": 7.972, "step": 7208 }, { "epoch": 69.0, "grad_norm": 1.173794150352478, "learning_rate": 1.55e-05, "loss": 0.0339, "step": 7314 }, { "epoch": 69.0, "eval_LOCATION_f1": 0.8219178082191781, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8108108108108109, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7672955974842767, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7261904761904762, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.9133333333333333, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8726114649681529, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6428571428571429, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8461538461538461, "eval_TIME_number": 26, "eval_TIME_precision": 0.8461538461538461, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.17915134131908417, "eval_overall_accuracy": 0.9614711033274956, "eval_overall_f1": 0.8418079096045198, "eval_overall_precision": 0.8075880758807588, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.3781, "eval_samples_per_second": 494.549, "eval_steps_per_second": 7.934, "step": 7314 }, { "epoch": 70.0, "grad_norm": 1.2395267486572266, "learning_rate": 1.5e-05, "loss": 0.0346, "step": 7420 }, { "epoch": 70.0, "eval_LOCATION_f1": 0.816326530612245, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7721518987341773, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7349397590361446, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.9163879598662208, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8782051282051282, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6538461538461539, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5862068965517241, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7924528301886792, "eval_TIME_number": 26, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.17411379516124725, "eval_overall_accuracy": 0.961220915686765, "eval_overall_f1": 0.8349788434414668, "eval_overall_precision": 0.8, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3765, "eval_samples_per_second": 496.729, "eval_steps_per_second": 7.969, "step": 7420 }, { "epoch": 71.0, "grad_norm": 0.5333613157272339, "learning_rate": 1.45e-05, "loss": 0.0345, "step": 7526 }, { "epoch": 71.0, "eval_LOCATION_f1": 0.8266666666666667, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7749999999999999, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7294117647058823, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.9163879598662208, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8782051282051282, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.7307692307692308, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6551724137931034, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8363636363636363, "eval_TIME_number": 26, "eval_TIME_precision": 0.7931034482758621, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.17888005077838898, "eval_overall_accuracy": 0.9627220415311484, "eval_overall_f1": 0.8463687150837987, "eval_overall_precision": 0.8037135278514589, "eval_overall_recall": 0.8938053097345132, "eval_runtime": 0.3773, "eval_samples_per_second": 495.613, "eval_steps_per_second": 7.951, "step": 7526 }, { "epoch": 72.0, "grad_norm": 0.4179161787033081, "learning_rate": 1.4000000000000001e-05, "loss": 0.0339, "step": 7632 }, { "epoch": 72.0, "eval_LOCATION_f1": 0.8243243243243243, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8026315789473685, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7721518987341773, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7349397590361446, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.9096989966555185, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8717948717948718, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5806451612903226, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8518518518518519, "eval_TIME_number": 26, "eval_TIME_precision": 0.8214285714285714, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.17914946377277374, "eval_overall_accuracy": 0.9609707280460346, "eval_overall_f1": 0.8387096774193548, "eval_overall_precision": 0.7994652406417112, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.3784, "eval_samples_per_second": 494.152, "eval_steps_per_second": 7.928, "step": 7632 }, { "epoch": 73.0, "grad_norm": 1.2512534856796265, "learning_rate": 1.3500000000000001e-05, "loss": 0.0363, "step": 7738 }, { "epoch": 73.0, "eval_LOCATION_f1": 0.8456375838926175, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.7777777777777777, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7241379310344828, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.9163879598662208, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8782051282051282, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6666666666666666, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6071428571428571, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.8461538461538461, "eval_TIME_number": 26, "eval_TIME_precision": 0.8461538461538461, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.17584359645843506, "eval_overall_accuracy": 0.9619714786089567, "eval_overall_f1": 0.847124824684432, "eval_overall_precision": 0.8074866310160428, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.3758, "eval_samples_per_second": 497.541, "eval_steps_per_second": 7.982, "step": 7738 }, { "epoch": 74.0, "grad_norm": 0.7962180972099304, "learning_rate": 1.3000000000000001e-05, "loss": 0.0309, "step": 7844 }, { "epoch": 74.0, "eval_LOCATION_f1": 0.8533333333333333, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.8888888888888888, "eval_ORGANIZATION_f1": 0.7577639751552795, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7093023255813954, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.9139072847682119, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8679245283018868, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.7307692307692308, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6551724137931034, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8363636363636363, "eval_TIME_number": 26, "eval_TIME_precision": 0.7931034482758621, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.1865181177854538, "eval_overall_accuracy": 0.9599699774831123, "eval_overall_f1": 0.8472222222222222, "eval_overall_precision": 0.800524934383202, "eval_overall_recall": 0.8997050147492626, "eval_runtime": 0.3749, "eval_samples_per_second": 498.845, "eval_steps_per_second": 8.003, "step": 7844 }, { "epoch": 75.0, "grad_norm": 0.6063715219497681, "learning_rate": 1.25e-05, "loss": 0.0337, "step": 7950 }, { "epoch": 75.0, "eval_LOCATION_f1": 0.8456375838926175, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.7625, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7176470588235294, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.9169435215946844, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8734177215189873, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.7450980392156864, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6785714285714286, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1806030422449112, "eval_overall_accuracy": 0.9609707280460346, "eval_overall_f1": 0.8451882845188284, "eval_overall_precision": 0.8015873015873016, "eval_overall_recall": 0.8938053097345132, "eval_runtime": 0.3787, "eval_samples_per_second": 493.806, "eval_steps_per_second": 7.922, "step": 7950 }, { "epoch": 76.0, "grad_norm": 0.17701131105422974, "learning_rate": 1.2e-05, "loss": 0.0329, "step": 8056 }, { "epoch": 76.0, "eval_LOCATION_f1": 0.8322147651006712, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8051948051948052, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7544910179640718, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6847826086956522, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.9096989966555185, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8717948717948718, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.7450980392156864, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6785714285714286, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.888888888888889, "eval_TIME_number": 26, "eval_TIME_precision": 0.8571428571428571, "eval_TIME_recall": 0.9230769230769231, "eval_loss": 0.1809851974248886, "eval_overall_accuracy": 0.961220915686765, "eval_overall_f1": 0.8444444444444444, "eval_overall_precision": 0.7979002624671916, "eval_overall_recall": 0.8967551622418879, "eval_runtime": 0.377, "eval_samples_per_second": 496.025, "eval_steps_per_second": 7.958, "step": 8056 }, { "epoch": 77.0, "grad_norm": 2.978839874267578, "learning_rate": 1.1500000000000002e-05, "loss": 0.0325, "step": 8162 }, { "epoch": 77.0, "eval_LOCATION_f1": 0.8243243243243243, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8026315789473685, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7407407407407408, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6896551724137931, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.9169435215946844, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8734177215189873, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6428571428571429, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.17838534712791443, "eval_overall_accuracy": 0.960720540405304, "eval_overall_f1": 0.8391608391608392, "eval_overall_precision": 0.7978723404255319, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.3767, "eval_samples_per_second": 496.446, "eval_steps_per_second": 7.964, "step": 8162 }, { "epoch": 78.0, "grad_norm": 0.9092636704444885, "learning_rate": 1.1000000000000001e-05, "loss": 0.0313, "step": 8268 }, { "epoch": 78.0, "eval_LOCATION_f1": 0.8513513513513513, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8289473684210527, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.7721518987341773, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7349397590361446, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.9066666666666667, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8662420382165605, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6428571428571429, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.17731936275959015, "eval_overall_accuracy": 0.9619714786089567, "eval_overall_f1": 0.8478873239436621, "eval_overall_precision": 0.8113207547169812, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.3766, "eval_samples_per_second": 496.56, "eval_steps_per_second": 7.966, "step": 8268 }, { "epoch": 79.0, "grad_norm": 1.61823570728302, "learning_rate": 1.05e-05, "loss": 0.0313, "step": 8374 }, { "epoch": 79.0, "eval_LOCATION_f1": 0.8243243243243243, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8026315789473685, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.779874213836478, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7380952380952381, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.9169435215946844, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8734177215189873, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.6923076923076923, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6206896551724138, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8363636363636363, "eval_TIME_number": 26, "eval_TIME_precision": 0.7931034482758621, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.17817345261573792, "eval_overall_accuracy": 0.9617212909682261, "eval_overall_f1": 0.8447552447552448, "eval_overall_precision": 0.8031914893617021, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.3768, "eval_samples_per_second": 496.276, "eval_steps_per_second": 7.962, "step": 8374 }, { "epoch": 80.0, "grad_norm": 0.3510795831680298, "learning_rate": 1e-05, "loss": 0.0302, "step": 8480 }, { "epoch": 80.0, "eval_LOCATION_f1": 0.8322147651006712, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8051948051948052, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7407407407407408, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6896551724137931, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.9169435215946844, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8734177215189873, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.7307692307692308, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6551724137931034, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8148148148148148, "eval_TIME_number": 26, "eval_TIME_precision": 0.7857142857142857, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1888643205165863, "eval_overall_accuracy": 0.9599699774831123, "eval_overall_f1": 0.8384401114206128, "eval_overall_precision": 0.7941952506596306, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.3764, "eval_samples_per_second": 496.798, "eval_steps_per_second": 7.97, "step": 8480 }, { "epoch": 81.0, "grad_norm": 0.5158957242965698, "learning_rate": 9.5e-06, "loss": 0.0307, "step": 8586 }, { "epoch": 81.0, "eval_LOCATION_f1": 0.8266666666666667, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7672955974842767, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7261904761904762, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.910299003322259, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8670886075949367, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.7169811320754716, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6333333333333333, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.1804436296224594, "eval_overall_accuracy": 0.9617212909682261, "eval_overall_f1": 0.8435754189944135, "eval_overall_precision": 0.8010610079575596, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.3776, "eval_samples_per_second": 495.235, "eval_steps_per_second": 7.945, "step": 8586 }, { "epoch": 82.0, "grad_norm": 0.9088582396507263, "learning_rate": 9e-06, "loss": 0.0289, "step": 8692 }, { "epoch": 82.0, "eval_LOCATION_f1": 0.8243243243243243, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8026315789473685, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7672955974842767, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7261904761904762, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.9066666666666667, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8662420382165605, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.7307692307692308, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6551724137931034, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.18571802973747253, "eval_overall_accuracy": 0.9609707280460346, "eval_overall_f1": 0.8375350140056023, "eval_overall_precision": 0.7973333333333333, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.3781, "eval_samples_per_second": 494.608, "eval_steps_per_second": 7.935, "step": 8692 }, { "epoch": 83.0, "grad_norm": 0.08597920835018158, "learning_rate": 8.500000000000002e-06, "loss": 0.0312, "step": 8798 }, { "epoch": 83.0, "eval_LOCATION_f1": 0.8266666666666667, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7749999999999999, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7294117647058823, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.92, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8789808917197452, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.7037037037037037, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6129032258064516, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.830188679245283, "eval_TIME_number": 26, "eval_TIME_precision": 0.8148148148148148, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.19167569279670715, "eval_overall_accuracy": 0.961220915686765, "eval_overall_f1": 0.8451882845188284, "eval_overall_precision": 0.8015873015873016, "eval_overall_recall": 0.8938053097345132, "eval_runtime": 0.3773, "eval_samples_per_second": 495.564, "eval_steps_per_second": 7.95, "step": 8798 }, { "epoch": 84.0, "grad_norm": 0.6576730608940125, "learning_rate": 8.000000000000001e-06, "loss": 0.0286, "step": 8904 }, { "epoch": 84.0, "eval_LOCATION_f1": 0.8378378378378377, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8157894736842105, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7672955974842767, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7261904761904762, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.903010033444816, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8653846153846154, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.18320870399475098, "eval_overall_accuracy": 0.960720540405304, "eval_overall_f1": 0.8398876404494382, "eval_overall_precision": 0.8016085790884718, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.3781, "eval_samples_per_second": 494.538, "eval_steps_per_second": 7.934, "step": 8904 }, { "epoch": 85.0, "grad_norm": 2.442254066467285, "learning_rate": 7.5e-06, "loss": 0.0295, "step": 9010 }, { "epoch": 85.0, "eval_LOCATION_f1": 0.8299319727891157, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8133333333333334, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.779874213836478, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7380952380952381, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.9139072847682119, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8679245283018868, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.18816226720809937, "eval_overall_accuracy": 0.960720540405304, "eval_overall_f1": 0.84593837535014, "eval_overall_precision": 0.8053333333333333, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.3775, "eval_samples_per_second": 495.33, "eval_steps_per_second": 7.946, "step": 9010 }, { "epoch": 86.0, "grad_norm": 1.4039467573165894, "learning_rate": 7.000000000000001e-06, "loss": 0.0285, "step": 9116 }, { "epoch": 86.0, "eval_LOCATION_f1": 0.8400000000000001, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.7770700636942677, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7439024390243902, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.903654485049834, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8607594936708861, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6415094339622641, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5666666666666667, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.8518518518518519, "eval_TIME_number": 26, "eval_TIME_precision": 0.8214285714285714, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.18358004093170166, "eval_overall_accuracy": 0.9617212909682261, "eval_overall_f1": 0.8391608391608392, "eval_overall_precision": 0.7978723404255319, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.378, "eval_samples_per_second": 494.765, "eval_steps_per_second": 7.937, "step": 9116 }, { "epoch": 87.0, "grad_norm": 0.6832211017608643, "learning_rate": 6.5000000000000004e-06, "loss": 0.0264, "step": 9222 }, { "epoch": 87.0, "eval_LOCATION_f1": 0.8344370860927153, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.7721518987341773, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7349397590361446, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.9, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8598726114649682, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6923076923076923, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6206896551724138, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.1859363615512848, "eval_overall_accuracy": 0.9617212909682261, "eval_overall_f1": 0.8403361344537816, "eval_overall_precision": 0.8, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.3793, "eval_samples_per_second": 492.976, "eval_steps_per_second": 7.909, "step": 9222 }, { "epoch": 88.0, "grad_norm": 0.2647896111011505, "learning_rate": 6e-06, "loss": 0.0278, "step": 9328 }, { "epoch": 88.0, "eval_LOCATION_f1": 0.8266666666666667, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7721518987341773, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7349397590361446, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.8970099667774087, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8544303797468354, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6666666666666666, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6071428571428571, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.18457496166229248, "eval_overall_accuracy": 0.9609707280460346, "eval_overall_f1": 0.8359046283309959, "eval_overall_precision": 0.7967914438502673, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.3829, "eval_samples_per_second": 488.421, "eval_steps_per_second": 7.836, "step": 9328 }, { "epoch": 89.0, "grad_norm": 0.7398730516433716, "learning_rate": 5.500000000000001e-06, "loss": 0.0275, "step": 9434 }, { "epoch": 89.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7848101265822784, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7469879518072289, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.8970099667774087, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8544303797468354, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.7307692307692308, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6551724137931034, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.18726153671741486, "eval_overall_accuracy": 0.9614711033274956, "eval_overall_f1": 0.8403361344537816, "eval_overall_precision": 0.8, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.3767, "eval_samples_per_second": 496.422, "eval_steps_per_second": 7.964, "step": 9434 }, { "epoch": 90.0, "grad_norm": 0.7052929401397705, "learning_rate": 5e-06, "loss": 0.0274, "step": 9540 }, { "epoch": 90.0, "eval_LOCATION_f1": 0.8266666666666667, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.779874213836478, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7380952380952381, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.9072847682119206, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8616352201257862, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.7169811320754716, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6333333333333333, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.18936219811439514, "eval_overall_accuracy": 0.9609707280460346, "eval_overall_f1": 0.8451882845188284, "eval_overall_precision": 0.8015873015873016, "eval_overall_recall": 0.8938053097345132, "eval_runtime": 0.3776, "eval_samples_per_second": 495.252, "eval_steps_per_second": 7.945, "step": 9540 }, { "epoch": 91.0, "grad_norm": 0.5388996005058289, "learning_rate": 4.5e-06, "loss": 0.0276, "step": 9646 }, { "epoch": 91.0, "eval_LOCATION_f1": 0.8266666666666667, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7721518987341773, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7349397590361446, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.903654485049834, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8607594936708861, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6538461538461539, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5862068965517241, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.1843438744544983, "eval_overall_accuracy": 0.9617212909682261, "eval_overall_f1": 0.8375350140056023, "eval_overall_precision": 0.7973333333333333, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.3785, "eval_samples_per_second": 494.097, "eval_steps_per_second": 7.927, "step": 9646 }, { "epoch": 92.0, "grad_norm": 1.5319263935089111, "learning_rate": 4.000000000000001e-06, "loss": 0.029, "step": 9752 }, { "epoch": 92.0, "eval_LOCATION_f1": 0.8400000000000001, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.7672955974842767, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7261904761904762, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.9066666666666667, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8662420382165605, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.7169811320754716, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6333333333333333, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.19099955260753632, "eval_overall_accuracy": 0.9604703527645734, "eval_overall_f1": 0.8447552447552448, "eval_overall_precision": 0.8031914893617021, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.3784, "eval_samples_per_second": 494.162, "eval_steps_per_second": 7.928, "step": 9752 }, { "epoch": 93.0, "grad_norm": 0.5256904363632202, "learning_rate": 3.5000000000000004e-06, "loss": 0.0272, "step": 9858 }, { "epoch": 93.0, "eval_LOCATION_f1": 0.8266666666666667, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7530864197530864, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7011494252873564, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.9066666666666667, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8662420382165605, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.18842431902885437, "eval_overall_accuracy": 0.9597197898423818, "eval_overall_f1": 0.8356545961002785, "eval_overall_precision": 0.7915567282321899, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.3765, "eval_samples_per_second": 496.635, "eval_steps_per_second": 7.967, "step": 9858 }, { "epoch": 94.0, "grad_norm": 1.0590431690216064, "learning_rate": 3e-06, "loss": 0.0282, "step": 9964 }, { "epoch": 94.0, "eval_LOCATION_f1": 0.8266666666666667, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7749999999999999, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7294117647058823, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.9169435215946844, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8734177215189873, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.6415094339622641, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5666666666666667, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.1881646066904068, "eval_overall_accuracy": 0.9609707280460346, "eval_overall_f1": 0.8423988842398884, "eval_overall_precision": 0.798941798941799, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.3776, "eval_samples_per_second": 495.181, "eval_steps_per_second": 7.944, "step": 9964 }, { "epoch": 95.0, "grad_norm": 0.05212884396314621, "learning_rate": 2.5e-06, "loss": 0.0288, "step": 10070 }, { "epoch": 95.0, "eval_LOCATION_f1": 0.8266666666666667, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7625, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7176470588235294, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.903654485049834, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8607594936708861, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.18959392607212067, "eval_overall_accuracy": 0.9599699774831123, "eval_overall_f1": 0.8368200836820084, "eval_overall_precision": 0.7936507936507936, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.3783, "eval_samples_per_second": 494.272, "eval_steps_per_second": 7.93, "step": 10070 }, { "epoch": 96.0, "grad_norm": 0.0768834576010704, "learning_rate": 2.0000000000000003e-06, "loss": 0.028, "step": 10176 }, { "epoch": 96.0, "eval_LOCATION_f1": 0.8266666666666667, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7749999999999999, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7294117647058823, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.910299003322259, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8670886075949367, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.1877508908510208, "eval_overall_accuracy": 0.9609707280460346, "eval_overall_f1": 0.8423988842398884, "eval_overall_precision": 0.798941798941799, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.3791, "eval_samples_per_second": 493.21, "eval_steps_per_second": 7.912, "step": 10176 }, { "epoch": 97.0, "grad_norm": 0.8987697958946228, "learning_rate": 1.5e-06, "loss": 0.028, "step": 10282 }, { "epoch": 97.0, "eval_LOCATION_f1": 0.8266666666666667, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7749999999999999, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7294117647058823, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.910299003322259, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8670886075949367, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.1894301176071167, "eval_overall_accuracy": 0.9604703527645734, "eval_overall_f1": 0.8423988842398884, "eval_overall_precision": 0.798941798941799, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.3799, "eval_samples_per_second": 492.219, "eval_steps_per_second": 7.897, "step": 10282 }, { "epoch": 98.0, "grad_norm": 0.4777444303035736, "learning_rate": 1.0000000000000002e-06, "loss": 0.0275, "step": 10388 }, { "epoch": 98.0, "eval_LOCATION_f1": 0.8322147651006712, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8051948051948052, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7749999999999999, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7294117647058823, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.910299003322259, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8670886075949367, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.18901941180229187, "eval_overall_accuracy": 0.9604703527645734, "eval_overall_f1": 0.8435754189944135, "eval_overall_precision": 0.8010610079575596, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.3771, "eval_samples_per_second": 495.844, "eval_steps_per_second": 7.955, "step": 10388 }, { "epoch": 99.0, "grad_norm": 1.2922275066375732, "learning_rate": 5.000000000000001e-07, "loss": 0.0269, "step": 10494 }, { "epoch": 99.0, "eval_LOCATION_f1": 0.8322147651006712, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8051948051948052, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7749999999999999, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7294117647058823, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.910299003322259, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8670886075949367, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.19013750553131104, "eval_overall_accuracy": 0.9604703527645734, "eval_overall_f1": 0.8435754189944135, "eval_overall_precision": 0.8010610079575596, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.3775, "eval_samples_per_second": 495.349, "eval_steps_per_second": 7.947, "step": 10494 }, { "epoch": 100.0, "grad_norm": 0.2882828414440155, "learning_rate": 0.0, "loss": 0.0282, "step": 10600 }, { "epoch": 100.0, "eval_LOCATION_f1": 0.8322147651006712, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.8051948051948052, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7749999999999999, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7294117647058823, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.910299003322259, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8670886075949367, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8679245283018868, "eval_TIME_number": 26, "eval_TIME_precision": 0.8518518518518519, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.18969494104385376, "eval_overall_accuracy": 0.9604703527645734, "eval_overall_f1": 0.8435754189944135, "eval_overall_precision": 0.8010610079575596, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.3767, "eval_samples_per_second": 496.362, "eval_steps_per_second": 7.963, "step": 10600 }, { "epoch": 100.0, "step": 10600, "total_flos": 5023623771566022.0, "train_loss": 0.076274028116802, "train_runtime": 633.1284, "train_samples_per_second": 266.455, "train_steps_per_second": 16.742 } ], "logging_steps": 500, "max_steps": 10600, "num_input_tokens_seen": 0, "num_train_epochs": 100, "save_steps": 500, "total_flos": 5023623771566022.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }