{ "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": 1.7763417959213257, "learning_rate": 4.9500000000000004e-05, "loss": 1.1469, "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": 0.0, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.0, "eval_PERSON_recall": 0.0, "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": 0.6846447587013245, "eval_overall_accuracy": 0.8448836627470603, "eval_overall_f1": 0.0, "eval_overall_precision": 0.0, "eval_overall_recall": 0.0, "eval_runtime": 0.895, "eval_samples_per_second": 208.94, "eval_steps_per_second": 3.352, "step": 106 }, { "epoch": 2.0, "grad_norm": 1.4578686952590942, "learning_rate": 4.9e-05, "loss": 0.6816, "step": 212 }, { "epoch": 2.0, "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": 0.0, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.0, "eval_PERSON_recall": 0.0, "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": 0.5663149952888489, "eval_overall_accuracy": 0.8463847885914436, "eval_overall_f1": 0.0, "eval_overall_precision": 0.0, "eval_overall_recall": 0.0, "eval_runtime": 0.9405, "eval_samples_per_second": 198.823, "eval_steps_per_second": 3.19, "step": 212 }, { "epoch": 3.0, "grad_norm": 1.51624596118927, "learning_rate": 4.85e-05, "loss": 0.5761, "step": 318 }, { "epoch": 3.0, "eval_LOCATION_f1": 0.09756097560975609, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.4, "eval_LOCATION_recall": 0.05555555555555555, "eval_ORGANIZATION_f1": 0.022222222222222223, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.06666666666666667, "eval_ORGANIZATION_recall": 0.013333333333333334, "eval_PERSON_f1": 0.18627450980392157, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.3114754098360656, "eval_PERSON_recall": 0.13286713286713286, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.23255813953488372, "eval_TIME_number": 26, "eval_TIME_precision": 0.29411764705882354, "eval_TIME_recall": 0.19230769230769232, "eval_loss": 0.4476684331893921, "eval_overall_accuracy": 0.8691518638979234, "eval_overall_f1": 0.13122171945701358, "eval_overall_precision": 0.2815533980582524, "eval_overall_recall": 0.0855457227138643, "eval_runtime": 0.9697, "eval_samples_per_second": 192.839, "eval_steps_per_second": 3.094, "step": 318 }, { "epoch": 4.0, "grad_norm": 2.4378204345703125, "learning_rate": 4.8e-05, "loss": 0.4513, "step": 424 }, { "epoch": 4.0, "eval_LOCATION_f1": 0.39999999999999997, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.5348837209302325, "eval_LOCATION_recall": 0.3194444444444444, "eval_ORGANIZATION_f1": 0.31496062992125984, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.38461538461538464, "eval_ORGANIZATION_recall": 0.26666666666666666, "eval_PERSON_f1": 0.6579804560260587, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.6158536585365854, "eval_PERSON_recall": 0.7062937062937062, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.6923076923076923, "eval_TIME_number": 26, "eval_TIME_precision": 0.6923076923076923, "eval_TIME_recall": 0.6923076923076923, "eval_loss": 0.33273494243621826, "eval_overall_accuracy": 0.9139354515886915, "eval_overall_f1": 0.5110410094637224, "eval_overall_precision": 0.5491525423728814, "eval_overall_recall": 0.4778761061946903, "eval_runtime": 0.9345, "eval_samples_per_second": 200.113, "eval_steps_per_second": 3.21, "step": 424 }, { "epoch": 5.0, "grad_norm": 1.327256441116333, "learning_rate": 4.75e-05, "loss": 0.3349, "step": 530 }, { "epoch": 5.0, "eval_LOCATION_f1": 0.6308724832214765, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.6103896103896104, "eval_LOCATION_recall": 0.6527777777777778, "eval_ORGANIZATION_f1": 0.5, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.47058823529411764, "eval_ORGANIZATION_recall": 0.5333333333333333, "eval_PERSON_f1": 0.8074534161490684, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7262569832402235, "eval_PERSON_recall": 0.9090909090909091, "eval_QUANTITY_f1": 0.3076923076923077, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.27586206896551724, "eval_QUANTITY_recall": 0.34782608695652173, "eval_TIME_f1": 0.7037037037037038, "eval_TIME_number": 26, "eval_TIME_precision": 0.6785714285714286, "eval_TIME_recall": 0.7307692307692307, "eval_loss": 0.2615293562412262, "eval_overall_accuracy": 0.932449337002752, "eval_overall_f1": 0.6621438263229307, "eval_overall_precision": 0.6130653266331658, "eval_overall_recall": 0.7197640117994101, "eval_runtime": 0.9019, "eval_samples_per_second": 207.346, "eval_steps_per_second": 3.326, "step": 530 }, { "epoch": 6.0, "grad_norm": 0.9253891706466675, "learning_rate": 4.7e-05, "loss": 0.2724, "step": 636 }, { "epoch": 6.0, "eval_LOCATION_f1": 0.7037037037037038, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.6333333333333333, "eval_LOCATION_recall": 0.7916666666666666, "eval_ORGANIZATION_f1": 0.5380116959064327, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.4791666666666667, "eval_ORGANIZATION_recall": 0.6133333333333333, "eval_PERSON_f1": 0.85, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.768361581920904, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.4, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.34375, "eval_QUANTITY_recall": 0.4782608695652174, "eval_TIME_f1": 0.7142857142857142, "eval_TIME_number": 26, "eval_TIME_precision": 0.6666666666666666, "eval_TIME_recall": 0.7692307692307693, "eval_loss": 0.22664156556129456, "eval_overall_accuracy": 0.9379534650988242, "eval_overall_f1": 0.7068062827225131, "eval_overall_precision": 0.6352941176470588, "eval_overall_recall": 0.7964601769911505, "eval_runtime": 0.8929, "eval_samples_per_second": 209.439, "eval_steps_per_second": 3.36, "step": 636 }, { "epoch": 7.0, "grad_norm": 0.9002701640129089, "learning_rate": 4.6500000000000005e-05, "loss": 0.2355, "step": 742 }, { "epoch": 7.0, "eval_LOCATION_f1": 0.7388535031847134, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.6823529411764706, "eval_LOCATION_recall": 0.8055555555555556, "eval_ORGANIZATION_f1": 0.5402298850574714, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.47474747474747475, "eval_ORGANIZATION_recall": 0.6266666666666667, "eval_PERSON_f1": 0.832807570977918, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7586206896551724, "eval_PERSON_recall": 0.9230769230769231, "eval_QUANTITY_f1": 0.3728813559322034, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.3055555555555556, "eval_QUANTITY_recall": 0.4782608695652174, "eval_TIME_f1": 0.7017543859649122, "eval_TIME_number": 26, "eval_TIME_precision": 0.6451612903225806, "eval_TIME_recall": 0.7692307692307693, "eval_loss": 0.20257450640201569, "eval_overall_accuracy": 0.937453089817363, "eval_overall_f1": 0.7015706806282723, "eval_overall_precision": 0.6305882352941177, "eval_overall_recall": 0.7905604719764012, "eval_runtime": 0.8994, "eval_samples_per_second": 207.908, "eval_steps_per_second": 3.335, "step": 742 }, { "epoch": 8.0, "grad_norm": 18.031301498413086, "learning_rate": 4.600000000000001e-05, "loss": 0.2121, "step": 848 }, { "epoch": 8.0, "eval_LOCATION_f1": 0.7547169811320755, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.6896551724137931, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.5888888888888889, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5047619047619047, "eval_ORGANIZATION_recall": 0.7066666666666667, "eval_PERSON_f1": 0.8471337579617835, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7777777777777778, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.38461538461538464, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.3448275862068966, "eval_QUANTITY_recall": 0.43478260869565216, "eval_TIME_f1": 0.7368421052631579, "eval_TIME_number": 26, "eval_TIME_precision": 0.6774193548387096, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1841818243265152, "eval_overall_accuracy": 0.9422066549912435, "eval_overall_f1": 0.727034120734908, "eval_overall_precision": 0.6548463356973995, "eval_overall_recall": 0.8171091445427728, "eval_runtime": 0.9109, "eval_samples_per_second": 205.301, "eval_steps_per_second": 3.294, "step": 848 }, { "epoch": 9.0, "grad_norm": 1.002072811126709, "learning_rate": 4.55e-05, "loss": 0.1949, "step": 954 }, { "epoch": 9.0, "eval_LOCATION_f1": 0.8076923076923077, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.6373626373626373, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5420560747663551, "eval_ORGANIZATION_recall": 0.7733333333333333, "eval_PERSON_f1": 0.8543689320388351, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7951807228915663, "eval_PERSON_recall": 0.9230769230769231, "eval_QUANTITY_f1": 0.4482758620689655, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.37142857142857144, "eval_QUANTITY_recall": 0.5652173913043478, "eval_TIME_f1": 0.7368421052631579, "eval_TIME_number": 26, "eval_TIME_precision": 0.6774193548387096, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.17754431068897247, "eval_overall_accuracy": 0.9437077808356267, "eval_overall_f1": 0.753280839895013, "eval_overall_precision": 0.6784869976359338, "eval_overall_recall": 0.8466076696165191, "eval_runtime": 0.9304, "eval_samples_per_second": 200.996, "eval_steps_per_second": 3.225, "step": 954 }, { "epoch": 10.0, "grad_norm": 2.384737968444824, "learning_rate": 4.5e-05, "loss": 0.1839, "step": 1060 }, { "epoch": 10.0, "eval_LOCATION_f1": 0.7974683544303797, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7325581395348837, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.6285714285714286, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.55, "eval_ORGANIZATION_recall": 0.7333333333333333, "eval_PERSON_f1": 0.8580645161290323, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7964071856287425, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6101694915254238, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.7241379310344829, "eval_TIME_number": 26, "eval_TIME_precision": 0.65625, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.17340479791164398, "eval_overall_accuracy": 0.9459594696022017, "eval_overall_f1": 0.7631578947368421, "eval_overall_precision": 0.6888361045130641, "eval_overall_recall": 0.855457227138643, "eval_runtime": 0.9261, "eval_samples_per_second": 201.931, "eval_steps_per_second": 3.24, "step": 1060 }, { "epoch": 11.0, "grad_norm": 1.5737191438674927, "learning_rate": 4.4500000000000004e-05, "loss": 0.1755, "step": 1166 }, { "epoch": 11.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.6589595375722543, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5816326530612245, "eval_ORGANIZATION_recall": 0.76, "eval_PERSON_f1": 0.8571428571428571, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8, "eval_PERSON_recall": 0.9230769230769231, "eval_QUANTITY_f1": 0.5090909090909091, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.4375, "eval_QUANTITY_recall": 0.6086956521739131, "eval_TIME_f1": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.15954510867595673, "eval_overall_accuracy": 0.9487115336502376, "eval_overall_f1": 0.7630522088353414, "eval_overall_precision": 0.6985294117647058, "eval_overall_recall": 0.8407079646017699, "eval_runtime": 0.9153, "eval_samples_per_second": 204.313, "eval_steps_per_second": 3.278, "step": 1166 }, { "epoch": 12.0, "grad_norm": 2.4136974811553955, "learning_rate": 4.4000000000000006e-05, "loss": 0.1678, "step": 1272 }, { "epoch": 12.0, "eval_LOCATION_f1": 0.7898089171974522, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7294117647058823, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.659217877094972, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5673076923076923, "eval_ORGANIZATION_recall": 0.7866666666666666, "eval_PERSON_f1": 0.8636363636363636, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.806060606060606, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.5454545454545454, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.46875, "eval_QUANTITY_recall": 0.6521739130434783, "eval_TIME_f1": 0.7118644067796609, "eval_TIME_number": 26, "eval_TIME_precision": 0.6363636363636364, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.15768958628177643, "eval_overall_accuracy": 0.9479609707280461, "eval_overall_f1": 0.7651715039577835, "eval_overall_precision": 0.6921241050119332, "eval_overall_recall": 0.855457227138643, "eval_runtime": 0.9039, "eval_samples_per_second": 206.88, "eval_steps_per_second": 3.319, "step": 1272 }, { "epoch": 13.0, "grad_norm": 1.9186729192733765, "learning_rate": 4.35e-05, "loss": 0.162, "step": 1378 }, { "epoch": 13.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.6705202312138728, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5918367346938775, "eval_ORGANIZATION_recall": 0.7733333333333333, "eval_PERSON_f1": 0.8692810457516339, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8159509202453987, "eval_PERSON_recall": 0.9300699300699301, "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": 0.14956550300121307, "eval_overall_accuracy": 0.9509632224168126, "eval_overall_f1": 0.7806191117092866, "eval_overall_precision": 0.7178217821782178, "eval_overall_recall": 0.855457227138643, "eval_runtime": 0.9098, "eval_samples_per_second": 205.545, "eval_steps_per_second": 3.298, "step": 1378 }, { "epoch": 14.0, "grad_norm": 1.4697725772857666, "learning_rate": 4.3e-05, "loss": 0.1556, "step": 1484 }, { "epoch": 14.0, "eval_LOCATION_f1": 0.8104575163398693, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7654320987654321, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.6524064171122995, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5446428571428571, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.8758169934640523, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8220858895705522, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6909090909090908, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.59375, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.7636363636363636, "eval_TIME_number": 26, "eval_TIME_precision": 0.7241379310344828, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1513964980840683, "eval_overall_accuracy": 0.9509632224168126, "eval_overall_f1": 0.7857142857142858, "eval_overall_precision": 0.7122302158273381, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.9103, "eval_samples_per_second": 205.421, "eval_steps_per_second": 3.296, "step": 1484 }, { "epoch": 15.0, "grad_norm": 0.7057433724403381, "learning_rate": 4.25e-05, "loss": 0.1526, "step": 1590 }, { "epoch": 15.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.6815642458100559, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5865384615384616, "eval_ORGANIZATION_recall": 0.8133333333333334, "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": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.14858980476856232, "eval_overall_accuracy": 0.9522141606204654, "eval_overall_f1": 0.7994616419919246, "eval_overall_precision": 0.7351485148514851, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.9237, "eval_samples_per_second": 202.441, "eval_steps_per_second": 3.248, "step": 1590 }, { "epoch": 16.0, "grad_norm": 1.3440351486206055, "learning_rate": 4.2e-05, "loss": 0.1469, "step": 1696 }, { "epoch": 16.0, "eval_LOCATION_f1": 0.8129032258064516, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5648148148148148, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.8910891089108911, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.84375, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6909090909090908, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.59375, "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": 0.15322650969028473, "eval_overall_accuracy": 0.9509632224168126, "eval_overall_f1": 0.7957559681697612, "eval_overall_precision": 0.7228915662650602, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.9158, "eval_samples_per_second": 204.192, "eval_steps_per_second": 3.276, "step": 1696 }, { "epoch": 17.0, "grad_norm": 0.5799930095672607, "learning_rate": 4.15e-05, "loss": 0.144, "step": 1802 }, { "epoch": 17.0, "eval_LOCATION_f1": 0.7848101265822784, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7209302325581395, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.6741573033707865, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5825242718446602, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8844884488448846, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8375, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6551724137931034, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5428571428571428, "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": 0.15142452716827393, "eval_overall_accuracy": 0.9504628471353516, "eval_overall_f1": 0.7888446215139443, "eval_overall_precision": 0.717391304347826, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.9196, "eval_samples_per_second": 203.34, "eval_steps_per_second": 3.262, "step": 1802 }, { "epoch": 18.0, "grad_norm": 0.7820217609405518, "learning_rate": 4.1e-05, "loss": 0.1383, "step": 1908 }, { "epoch": 18.0, "eval_LOCATION_f1": 0.8076923076923077, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.6779661016949153, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5882352941176471, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8940397350993377, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8490566037735849, "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": 0.7719298245614036, "eval_TIME_number": 26, "eval_TIME_precision": 0.7096774193548387, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.14950262010097504, "eval_overall_accuracy": 0.9522141606204654, "eval_overall_f1": 0.7983978638184246, "eval_overall_precision": 0.7292682926829268, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.9112, "eval_samples_per_second": 205.22, "eval_steps_per_second": 3.292, "step": 1908 }, { "epoch": 19.0, "grad_norm": 1.2518548965454102, "learning_rate": 4.05e-05, "loss": 0.1377, "step": 2014 }, { "epoch": 19.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7005649717514123, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6078431372549019, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.8778877887788779, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.83125, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6551724137931034, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5428571428571428, "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": 0.1416643112897873, "eval_overall_accuracy": 0.9537152864648486, "eval_overall_f1": 0.7941176470588236, "eval_overall_precision": 0.726161369193154, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.9066, "eval_samples_per_second": 206.255, "eval_steps_per_second": 3.309, "step": 2014 }, { "epoch": 20.0, "grad_norm": 1.2376631498336792, "learning_rate": 4e-05, "loss": 0.1295, "step": 2120 }, { "epoch": 20.0, "eval_LOCATION_f1": 0.802547770700637, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7411764705882353, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.6810810810810811, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5727272727272728, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8852459016393444, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8333333333333334, "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": 0.7457627118644068, "eval_TIME_number": 26, "eval_TIME_precision": 0.6666666666666666, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.15442748367786407, "eval_overall_accuracy": 0.9492119089316988, "eval_overall_f1": 0.7926509186351707, "eval_overall_precision": 0.7139479905437353, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.9222, "eval_samples_per_second": 202.776, "eval_steps_per_second": 3.253, "step": 2120 }, { "epoch": 21.0, "grad_norm": 1.2211582660675049, "learning_rate": 3.9500000000000005e-05, "loss": 0.1322, "step": 2226 }, { "epoch": 21.0, "eval_LOCATION_f1": 0.802547770700637, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7411764705882353, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.711864406779661, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6176470588235294, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8750000000000001, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8260869565217391, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6909090909090908, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.59375, "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": 0.14581608772277832, "eval_overall_accuracy": 0.9522141606204654, "eval_overall_f1": 0.8032128514056226, "eval_overall_precision": 0.7352941176470589, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.9163, "eval_samples_per_second": 204.089, "eval_steps_per_second": 3.274, "step": 2226 }, { "epoch": 22.0, "grad_norm": 0.918321430683136, "learning_rate": 3.9000000000000006e-05, "loss": 0.1262, "step": 2332 }, { "epoch": 22.0, "eval_LOCATION_f1": 0.8129032258064516, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.7005649717514123, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6078431372549019, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.8852459016393444, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8333333333333334, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.631578947368421, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5294117647058824, "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": 0.14632713794708252, "eval_overall_accuracy": 0.9522141606204654, "eval_overall_f1": 0.8, "eval_overall_precision": 0.7299270072992701, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.9132, "eval_samples_per_second": 204.774, "eval_steps_per_second": 3.285, "step": 2332 }, { "epoch": 23.0, "grad_norm": 1.5583821535110474, "learning_rate": 3.85e-05, "loss": 0.1265, "step": 2438 }, { "epoch": 23.0, "eval_LOCATION_f1": 0.8129032258064516, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.7039106145251397, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6057692307692307, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8976897689768978, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.85, "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": 0.7719298245614036, "eval_TIME_number": 26, "eval_TIME_precision": 0.7096774193548387, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.143763929605484, "eval_overall_accuracy": 0.9534650988241181, "eval_overall_f1": 0.8053333333333332, "eval_overall_precision": 0.7347931873479319, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.923, "eval_samples_per_second": 202.593, "eval_steps_per_second": 3.25, "step": 2438 }, { "epoch": 24.0, "grad_norm": 0.9859341382980347, "learning_rate": 3.8e-05, "loss": 0.1249, "step": 2544 }, { "epoch": 24.0, "eval_LOCATION_f1": 0.7848101265822784, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7209302325581395, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.6923076923076923, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5887850467289719, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8859934853420195, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8292682926829268, "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": 0.7719298245614036, "eval_TIME_number": 26, "eval_TIME_precision": 0.7096774193548387, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.15259569883346558, "eval_overall_accuracy": 0.9492119089316988, "eval_overall_f1": 0.7910643889618922, "eval_overall_precision": 0.7132701421800948, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.9211, "eval_samples_per_second": 203.013, "eval_steps_per_second": 3.257, "step": 2544 }, { "epoch": 25.0, "grad_norm": 1.1437468528747559, "learning_rate": 3.7500000000000003e-05, "loss": 0.124, "step": 2650 }, { "epoch": 25.0, "eval_LOCATION_f1": 0.7898089171974522, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7294117647058823, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7176470588235295, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6421052631578947, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.8918032786885245, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8395061728395061, "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": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1410185694694519, "eval_overall_accuracy": 0.9549662246685013, "eval_overall_f1": 0.8026845637583893, "eval_overall_precision": 0.7364532019704434, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.9169, "eval_samples_per_second": 203.953, "eval_steps_per_second": 3.272, "step": 2650 }, { "epoch": 26.0, "grad_norm": 1.7730497121810913, "learning_rate": 3.7e-05, "loss": 0.122, "step": 2756 }, { "epoch": 26.0, "eval_LOCATION_f1": 0.8, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7283236994219654, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6428571428571429, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8888888888888888, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8343558282208589, "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": 0.7719298245614036, "eval_TIME_number": 26, "eval_TIME_precision": 0.7096774193548387, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1444074809551239, "eval_overall_accuracy": 0.9537152864648486, "eval_overall_f1": 0.8048128342245989, "eval_overall_precision": 0.7359413202933985, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.9886, "eval_samples_per_second": 189.156, "eval_steps_per_second": 3.035, "step": 2756 }, { "epoch": 27.0, "grad_norm": 1.508661150932312, "learning_rate": 3.65e-05, "loss": 0.1202, "step": 2862 }, { "epoch": 27.0, "eval_LOCATION_f1": 0.7922077922077924, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.718562874251497, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6521739130434783, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8385093167701864, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6206896551724138, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5142857142857142, "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": 0.1383628100156784, "eval_overall_accuracy": 0.9542156617463098, "eval_overall_f1": 0.8010825439783491, "eval_overall_precision": 0.74, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.9149, "eval_samples_per_second": 204.393, "eval_steps_per_second": 3.279, "step": 2862 }, { "epoch": 28.0, "grad_norm": 1.6206343173980713, "learning_rate": 3.6e-05, "loss": 0.1175, "step": 2968 }, { "epoch": 28.0, "eval_LOCATION_f1": 0.8051948051948052, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7560975609756098, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7272727272727272, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8874172185430464, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8427672955974843, "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": 0.8148148148148148, "eval_TIME_number": 26, "eval_TIME_precision": 0.7857142857142857, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13063645362854004, "eval_overall_accuracy": 0.9577182887165374, "eval_overall_f1": 0.8098495212038302, "eval_overall_precision": 0.7551020408163265, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.9182, "eval_samples_per_second": 203.651, "eval_steps_per_second": 3.267, "step": 2968 }, { "epoch": 29.0, "grad_norm": 1.3314720392227173, "learning_rate": 3.55e-05, "loss": 0.1172, "step": 3074 }, { "epoch": 29.0, "eval_LOCATION_f1": 0.8079470198675496, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7241379310344828, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6363636363636364, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8993288590604027, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.864516129032258, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13884492218494415, "eval_overall_accuracy": 0.9552164123092319, "eval_overall_f1": 0.8103683492496591, "eval_overall_precision": 0.7538071065989848, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.9267, "eval_samples_per_second": 201.801, "eval_steps_per_second": 3.237, "step": 3074 }, { "epoch": 30.0, "grad_norm": 0.5334556698799133, "learning_rate": 3.5e-05, "loss": 0.1115, "step": 3180 }, { "epoch": 30.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7411764705882353, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6631578947368421, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8963210702341137, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8589743589743589, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6545454545454547, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5625, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13577121496200562, "eval_overall_accuracy": 0.9564673505128847, "eval_overall_f1": 0.8119891008174387, "eval_overall_precision": 0.7544303797468355, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.9184, "eval_samples_per_second": 203.614, "eval_steps_per_second": 3.267, "step": 3180 }, { "epoch": 31.0, "grad_norm": 1.5126512050628662, "learning_rate": 3.45e-05, "loss": 0.1118, "step": 3286 }, { "epoch": 31.0, "eval_LOCATION_f1": 0.7922077922077924, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.718562874251497, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6521739130434783, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.9, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8598726114649682, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6545454545454547, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5625, "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": 0.1318959891796112, "eval_overall_accuracy": 0.9569677257943457, "eval_overall_f1": 0.8125854993160055, "eval_overall_precision": 0.7576530612244898, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.9794, "eval_samples_per_second": 190.938, "eval_steps_per_second": 3.063, "step": 3286 }, { "epoch": 32.0, "grad_norm": 2.184518575668335, "learning_rate": 3.4000000000000007e-05, "loss": 0.1105, "step": 3392 }, { "epoch": 32.0, "eval_LOCATION_f1": 0.7922077922077924, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7560975609756098, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6966292134831461, "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": 0.7169811320754716, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6333333333333333, "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": 0.12973971664905548, "eval_overall_accuracy": 0.9597197898423818, "eval_overall_f1": 0.8264462809917357, "eval_overall_precision": 0.7751937984496124, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.9184, "eval_samples_per_second": 203.604, "eval_steps_per_second": 3.266, "step": 3392 }, { "epoch": 33.0, "grad_norm": 1.199165940284729, "learning_rate": 3.35e-05, "loss": 0.1131, "step": 3498 }, { "epoch": 33.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.726190476190476, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6559139784946236, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8322981366459627, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.5925925925925926, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5161290322580645, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13300670683383942, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.7989130434782608, "eval_overall_precision": 0.7405541561712846, "eval_overall_recall": 0.8672566371681416, "eval_runtime": 0.9131, "eval_samples_per_second": 204.799, "eval_steps_per_second": 3.286, "step": 3498 }, { "epoch": 34.0, "grad_norm": 0.9721863865852356, "learning_rate": 3.3e-05, "loss": 0.1076, "step": 3604 }, { "epoch": 34.0, "eval_LOCATION_f1": 0.8181818181818181, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7682926829268293, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.7514450867052023, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6632653061224489, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8852459016393444, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8333333333333334, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1418086588382721, "eval_overall_accuracy": 0.955716787590693, "eval_overall_f1": 0.8140161725067384, "eval_overall_precision": 0.749379652605459, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.9094, "eval_samples_per_second": 205.631, "eval_steps_per_second": 3.299, "step": 3604 }, { "epoch": 35.0, "grad_norm": 1.8517881631851196, "learning_rate": 3.2500000000000004e-05, "loss": 0.1067, "step": 3710 }, { "epoch": 35.0, "eval_LOCATION_f1": 0.7922077922077924, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7514450867052023, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6632653061224489, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8940397350993377, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8490566037735849, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13823601603507996, "eval_overall_accuracy": 0.9567175381536153, "eval_overall_f1": 0.8119079837618404, "eval_overall_precision": 0.75, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.9205, "eval_samples_per_second": 203.16, "eval_steps_per_second": 3.259, "step": 3710 }, { "epoch": 36.0, "grad_norm": 1.0181353092193604, "learning_rate": 3.2000000000000005e-05, "loss": 0.1062, "step": 3816 }, { "epoch": 36.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7590361445783131, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6923076923076923, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.880794701986755, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8364779874213837, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.5818181818181818, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.8363636363636363, "eval_TIME_number": 26, "eval_TIME_precision": 0.7931034482758621, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.12888486683368683, "eval_overall_accuracy": 0.9582186639979985, "eval_overall_f1": 0.8098495212038302, "eval_overall_precision": 0.7551020408163265, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.9138, "eval_samples_per_second": 204.646, "eval_steps_per_second": 3.283, "step": 3816 }, { "epoch": 37.0, "grad_norm": 2.295438766479492, "learning_rate": 3.15e-05, "loss": 0.1067, "step": 3922 }, { "epoch": 37.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7558139534883721, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6701030927835051, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8910891089108911, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.84375, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.631578947368421, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5294117647058824, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.7636363636363636, "eval_TIME_number": 26, "eval_TIME_precision": 0.7241379310344828, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.13770808279514313, "eval_overall_accuracy": 0.9554665999499625, "eval_overall_f1": 0.8102288021534321, "eval_overall_precision": 0.745049504950495, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.9094, "eval_samples_per_second": 205.624, "eval_steps_per_second": 3.299, "step": 3922 }, { "epoch": 38.0, "grad_norm": 1.1177865266799927, "learning_rate": 3.1e-05, "loss": 0.1035, "step": 4028 }, { "epoch": 38.0, "eval_LOCATION_f1": 0.8, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7558139534883721, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6701030927835051, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.9042904290429041, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.85625, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "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": 0.14018218219280243, "eval_overall_accuracy": 0.9559669752314236, "eval_overall_f1": 0.8162162162162162, "eval_overall_precision": 0.7531172069825436, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.9122, "eval_samples_per_second": 204.992, "eval_steps_per_second": 3.289, "step": 4028 }, { "epoch": 39.0, "grad_norm": 0.6755772829055786, "learning_rate": 3.05e-05, "loss": 0.1009, "step": 4134 }, { "epoch": 39.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7386363636363636, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6435643564356436, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8940397350993377, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8490566037735849, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.5925925925925926, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5161290322580645, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7636363636363636, "eval_TIME_number": 26, "eval_TIME_precision": 0.7241379310344828, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.13465510308742523, "eval_overall_accuracy": 0.955716787590693, "eval_overall_f1": 0.8054054054054054, "eval_overall_precision": 0.743142144638404, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.9147, "eval_samples_per_second": 204.428, "eval_steps_per_second": 3.28, "step": 4134 }, { "epoch": 40.0, "grad_norm": 1.1680387258529663, "learning_rate": 3e-05, "loss": 0.1003, "step": 4240 }, { "epoch": 40.0, "eval_LOCATION_f1": 0.7947019867549668, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7710843373493976, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7032967032967034, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8852459016393444, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8333333333333334, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.132964089512825, "eval_overall_accuracy": 0.957968476357268, "eval_overall_f1": 0.8125854993160055, "eval_overall_precision": 0.7576530612244898, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.9228, "eval_samples_per_second": 202.648, "eval_steps_per_second": 3.251, "step": 4240 }, { "epoch": 41.0, "grad_norm": 1.2968403100967407, "learning_rate": 2.95e-05, "loss": 0.0991, "step": 4346 }, { "epoch": 41.0, "eval_LOCATION_f1": 0.7922077922077924, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7439024390243902, "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": 0.8888888888888888, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8343558282208589, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.13273276388645172, "eval_overall_accuracy": 0.9577182887165374, "eval_overall_f1": 0.8075880758807586, "eval_overall_precision": 0.7468671679197995, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.9163, "eval_samples_per_second": 204.079, "eval_steps_per_second": 3.274, "step": 4346 }, { "epoch": 42.0, "grad_norm": 0.9947686195373535, "learning_rate": 2.9e-05, "loss": 0.0998, "step": 4452 }, { "epoch": 42.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7692307692307693, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6914893617021277, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8947368421052632, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.84472049689441, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.1384052336215973, "eval_overall_accuracy": 0.957968476357268, "eval_overall_f1": 0.814111261872456, "eval_overall_precision": 0.7537688442211056, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.9127, "eval_samples_per_second": 204.882, "eval_steps_per_second": 3.287, "step": 4452 }, { "epoch": 43.0, "grad_norm": 1.5766985416412354, "learning_rate": 2.8499999999999998e-05, "loss": 0.0976, "step": 4558 }, { "epoch": 43.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7647058823529413, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6842105263157895, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.9072847682119206, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8616352201257862, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.13511711359024048, "eval_overall_accuracy": 0.9589692269201902, "eval_overall_f1": 0.8201634877384195, "eval_overall_precision": 0.7620253164556962, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.9104, "eval_samples_per_second": 205.41, "eval_steps_per_second": 3.295, "step": 4558 }, { "epoch": 44.0, "grad_norm": 1.2490625381469727, "learning_rate": 2.8000000000000003e-05, "loss": 0.0983, "step": 4664 }, { "epoch": 44.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7349397590361446, "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": 0.8976897689768978, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.85, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.1334737241268158, "eval_overall_accuracy": 0.9574681010758068, "eval_overall_f1": 0.8097826086956521, "eval_overall_precision": 0.7506297229219143, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.9092, "eval_samples_per_second": 205.674, "eval_steps_per_second": 3.3, "step": 4664 }, { "epoch": 45.0, "grad_norm": 1.1862820386886597, "learning_rate": 2.7500000000000004e-05, "loss": 0.0953, "step": 4770 }, { "epoch": 45.0, "eval_LOCATION_f1": 0.8157894736842106, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.775, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7630057803468209, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.673469387755102, "eval_ORGANIZATION_recall": 0.88, "eval_PERSON_f1": 0.9042904290429041, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.85625, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.13821732997894287, "eval_overall_accuracy": 0.9559669752314236, "eval_overall_f1": 0.8222523744911804, "eval_overall_precision": 0.7613065326633166, "eval_overall_recall": 0.8938053097345132, "eval_runtime": 0.9184, "eval_samples_per_second": 203.612, "eval_steps_per_second": 3.267, "step": 4770 }, { "epoch": 46.0, "grad_norm": 0.9332220554351807, "learning_rate": 2.7000000000000002e-05, "loss": 0.0956, "step": 4876 }, { "epoch": 46.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7586206896551725, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.88, "eval_PERSON_f1": 0.9066666666666667, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8662420382165605, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.5925925925925926, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5161290322580645, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7636363636363636, "eval_TIME_number": 26, "eval_TIME_precision": 0.7241379310344828, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.13184477388858795, "eval_overall_accuracy": 0.9569677257943457, "eval_overall_f1": 0.814614343707713, "eval_overall_precision": 0.7525, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.9173, "eval_samples_per_second": 203.864, "eval_steps_per_second": 3.271, "step": 4876 }, { "epoch": 47.0, "grad_norm": 1.5982903242111206, "learning_rate": 2.6500000000000004e-05, "loss": 0.096, "step": 4982 }, { "epoch": 47.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7542857142857142, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.66, "eval_ORGANIZATION_recall": 0.88, "eval_PERSON_f1": 0.9006622516556291, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8553459119496856, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.13822437822818756, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.8140161725067384, "eval_overall_precision": 0.749379652605459, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.9171, "eval_samples_per_second": 203.909, "eval_steps_per_second": 3.271, "step": 4982 }, { "epoch": 48.0, "grad_norm": 1.2585638761520386, "learning_rate": 2.6000000000000002e-05, "loss": 0.0927, "step": 5088 }, { "epoch": 48.0, "eval_LOCATION_f1": 0.782051282051282, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7261904761904762, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.735632183908046, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6464646464646465, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.9006622516556291, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8553459119496856, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.1360795944929123, "eval_overall_accuracy": 0.9559669752314236, "eval_overall_f1": 0.8070175438596491, "eval_overall_precision": 0.7437810945273632, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.9116, "eval_samples_per_second": 205.141, "eval_steps_per_second": 3.291, "step": 5088 }, { "epoch": 49.0, "grad_norm": 1.232528805732727, "learning_rate": 2.5500000000000003e-05, "loss": 0.0937, "step": 5194 }, { "epoch": 49.0, "eval_LOCATION_f1": 0.7922077922077924, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7439024390243902, "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": 0.9042904290429041, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.85625, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6037735849056605, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5333333333333333, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7636363636363636, "eval_TIME_number": 26, "eval_TIME_precision": 0.7241379310344828, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1355244666337967, "eval_overall_accuracy": 0.9577182887165374, "eval_overall_f1": 0.8168249660786975, "eval_overall_precision": 0.7562814070351759, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.9202, "eval_samples_per_second": 203.207, "eval_steps_per_second": 3.26, "step": 5194 }, { "epoch": 50.0, "grad_norm": 1.0878721475601196, "learning_rate": 2.5e-05, "loss": 0.0929, "step": 5300 }, { "epoch": 50.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7428571428571429, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.65, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.9013157894736843, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8509316770186336, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1443309783935547, "eval_overall_accuracy": 0.9534650988241181, "eval_overall_f1": 0.8113207547169812, "eval_overall_precision": 0.7468982630272953, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.9167, "eval_samples_per_second": 203.984, "eval_steps_per_second": 3.272, "step": 5300 }, { "epoch": 51.0, "grad_norm": 1.202656865119934, "learning_rate": 2.45e-05, "loss": 0.0925, "step": 5406 }, { "epoch": 51.0, "eval_LOCATION_f1": 0.7922077922077924, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7529411764705883, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6736842105263158, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8385093167701864, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.13290907442569733, "eval_overall_accuracy": 0.957968476357268, "eval_overall_f1": 0.8086838534599728, "eval_overall_precision": 0.7487437185929648, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.9175, "eval_samples_per_second": 203.819, "eval_steps_per_second": 3.27, "step": 5406 }, { "epoch": 52.0, "grad_norm": 0.9784518480300903, "learning_rate": 2.4e-05, "loss": 0.09, "step": 5512 }, { "epoch": 52.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7283236994219654, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6428571428571429, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.9006622516556291, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8553459119496856, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6037735849056605, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5333333333333333, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13217070698738098, "eval_overall_accuracy": 0.9577182887165374, "eval_overall_f1": 0.8092016238159675, "eval_overall_precision": 0.7475, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.9087, "eval_samples_per_second": 205.785, "eval_steps_per_second": 3.301, "step": 5512 }, { "epoch": 53.0, "grad_norm": 1.721675992012024, "learning_rate": 2.35e-05, "loss": 0.0902, "step": 5618 }, { "epoch": 53.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.735632183908046, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6464646464646465, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8852459016393444, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8333333333333334, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6037735849056605, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5333333333333333, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13690826296806335, "eval_overall_accuracy": 0.9564673505128847, "eval_overall_f1": 0.8048452220726783, "eval_overall_precision": 0.7400990099009901, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.9136, "eval_samples_per_second": 204.686, "eval_steps_per_second": 3.284, "step": 5618 }, { "epoch": 54.0, "grad_norm": 1.8446025848388672, "learning_rate": 2.3000000000000003e-05, "loss": 0.0903, "step": 5724 }, { "epoch": 54.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7514450867052023, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6632653061224489, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.9006622516556291, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8553459119496856, "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": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13621099293231964, "eval_overall_accuracy": 0.957968476357268, "eval_overall_f1": 0.817320703653586, "eval_overall_precision": 0.755, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.9166, "eval_samples_per_second": 204.014, "eval_steps_per_second": 3.273, "step": 5724 }, { "epoch": 55.0, "grad_norm": 1.4813069105148315, "learning_rate": 2.25e-05, "loss": 0.0884, "step": 5830 }, { "epoch": 55.0, "eval_LOCATION_f1": 0.8076923076923077, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.7362637362637362, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6261682242990654, "eval_ORGANIZATION_recall": 0.8933333333333333, "eval_PERSON_f1": 0.9139072847682119, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8679245283018868, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.6071428571428571, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5151515151515151, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1463117152452469, "eval_overall_accuracy": 0.9532149111833875, "eval_overall_f1": 0.8138297872340426, "eval_overall_precision": 0.7409200968523002, "eval_overall_recall": 0.9026548672566371, "eval_runtime": 0.925, "eval_samples_per_second": 202.169, "eval_steps_per_second": 3.243, "step": 5830 }, { "epoch": 56.0, "grad_norm": 1.3962222337722778, "learning_rate": 2.2000000000000003e-05, "loss": 0.0876, "step": 5936 }, { "epoch": 56.0, "eval_LOCATION_f1": 0.8129032258064516, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.736842105263158, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.65625, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8888888888888888, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8343558282208589, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.13651299476623535, "eval_overall_accuracy": 0.9564673505128847, "eval_overall_f1": 0.8097165991902835, "eval_overall_precision": 0.746268656716418, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.9185, "eval_samples_per_second": 203.594, "eval_steps_per_second": 3.266, "step": 5936 }, { "epoch": 57.0, "grad_norm": 1.3669453859329224, "learning_rate": 2.15e-05, "loss": 0.0866, "step": 6042 }, { "epoch": 57.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7380952380952381, "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": 0.8918032786885245, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8395061728395061, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.5925925925925926, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5161290322580645, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7636363636363636, "eval_TIME_number": 26, "eval_TIME_precision": 0.7241379310344828, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1323753148317337, "eval_overall_accuracy": 0.9574681010758068, "eval_overall_f1": 0.8086838534599728, "eval_overall_precision": 0.7487437185929648, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.916, "eval_samples_per_second": 204.14, "eval_steps_per_second": 3.275, "step": 6042 }, { "epoch": 58.0, "grad_norm": 0.734471321105957, "learning_rate": 2.1e-05, "loss": 0.0859, "step": 6148 }, { "epoch": 58.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7647058823529413, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6842105263157895, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.9078947368421052, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8571428571428571, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.1391240656375885, "eval_overall_accuracy": 0.9559669752314236, "eval_overall_f1": 0.8200270635994586, "eval_overall_precision": 0.7575, "eval_overall_recall": 0.8938053097345132, "eval_runtime": 0.912, "eval_samples_per_second": 205.044, "eval_steps_per_second": 3.289, "step": 6148 }, { "epoch": 59.0, "grad_norm": 0.7517756819725037, "learning_rate": 2.05e-05, "loss": 0.084, "step": 6254 }, { "epoch": 59.0, "eval_LOCATION_f1": 0.8129032258064516, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.875, "eval_ORGANIZATION_f1": 0.7630057803468209, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.673469387755102, "eval_ORGANIZATION_recall": 0.88, "eval_PERSON_f1": 0.9042904290429041, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.85625, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.1424020528793335, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.8216216216216216, "eval_overall_precision": 0.7581047381546134, "eval_overall_recall": 0.8967551622418879, "eval_runtime": 0.9134, "eval_samples_per_second": 204.73, "eval_steps_per_second": 3.284, "step": 6254 }, { "epoch": 60.0, "grad_norm": 0.7630839943885803, "learning_rate": 2e-05, "loss": 0.0846, "step": 6360 }, { "epoch": 60.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7647058823529413, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6842105263157895, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8983606557377047, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.845679012345679, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.14165633916854858, "eval_overall_accuracy": 0.9552164123092319, "eval_overall_f1": 0.814614343707713, "eval_overall_precision": 0.7525, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.9969, "eval_samples_per_second": 187.574, "eval_steps_per_second": 3.009, "step": 6360 }, { "epoch": 61.0, "grad_norm": 0.882446825504303, "learning_rate": 1.9500000000000003e-05, "loss": 0.0861, "step": 6466 }, { "epoch": 61.0, "eval_LOCATION_f1": 0.7922077922077924, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7457627118644068, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6470588235294118, "eval_ORGANIZATION_recall": 0.88, "eval_PERSON_f1": 0.9078947368421052, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8571428571428571, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.14782929420471191, "eval_overall_accuracy": 0.9524643482611959, "eval_overall_f1": 0.814516129032258, "eval_overall_precision": 0.7481481481481481, "eval_overall_recall": 0.8938053097345132, "eval_runtime": 0.9085, "eval_samples_per_second": 205.843, "eval_steps_per_second": 3.302, "step": 6466 }, { "epoch": 62.0, "grad_norm": 0.8927095532417297, "learning_rate": 1.9e-05, "loss": 0.0842, "step": 6572 }, { "epoch": 62.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7602339181286549, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6770833333333334, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.9006622516556291, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8553459119496856, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.13655085861682892, "eval_overall_accuracy": 0.9574681010758068, "eval_overall_f1": 0.8163265306122449, "eval_overall_precision": 0.7575757575757576, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.9099, "eval_samples_per_second": 205.519, "eval_steps_per_second": 3.297, "step": 6572 }, { "epoch": 63.0, "grad_norm": 0.5297817587852478, "learning_rate": 1.85e-05, "loss": 0.0827, "step": 6678 }, { "epoch": 63.0, "eval_LOCATION_f1": 0.8051948051948052, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7560975609756098, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7647058823529413, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6842105263157895, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8947368421052632, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.84472049689441, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.1402578353881836, "eval_overall_accuracy": 0.9554665999499625, "eval_overall_f1": 0.8168249660786975, "eval_overall_precision": 0.7562814070351759, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.9123, "eval_samples_per_second": 204.97, "eval_steps_per_second": 3.288, "step": 6678 }, { "epoch": 64.0, "grad_norm": 0.9679049253463745, "learning_rate": 1.8e-05, "loss": 0.0843, "step": 6784 }, { "epoch": 64.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7555555555555555, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6476190476190476, "eval_ORGANIZATION_recall": 0.9066666666666666, "eval_PERSON_f1": 0.9108910891089109, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8625, "eval_PERSON_recall": 0.965034965034965, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.15152409672737122, "eval_overall_accuracy": 0.9522141606204654, "eval_overall_f1": 0.8165997322623828, "eval_overall_precision": 0.7475490196078431, "eval_overall_recall": 0.8997050147492626, "eval_runtime": 0.9107, "eval_samples_per_second": 205.337, "eval_steps_per_second": 3.294, "step": 6784 }, { "epoch": 65.0, "grad_norm": 0.6541423797607422, "learning_rate": 1.75e-05, "loss": 0.0834, "step": 6890 }, { "epoch": 65.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7630057803468209, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.673469387755102, "eval_ORGANIZATION_recall": 0.88, "eval_PERSON_f1": 0.9072847682119206, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8616352201257862, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6415094339622641, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5666666666666667, "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": 0.139739528298378, "eval_overall_accuracy": 0.9564673505128847, "eval_overall_f1": 0.8184281842818428, "eval_overall_precision": 0.7568922305764411, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.9101, "eval_samples_per_second": 205.463, "eval_steps_per_second": 3.296, "step": 6890 }, { "epoch": 66.0, "grad_norm": 0.8754425048828125, "learning_rate": 1.7000000000000003e-05, "loss": 0.0839, "step": 6996 }, { "epoch": 66.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7719298245614036, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6875, "eval_ORGANIZATION_recall": 0.88, "eval_PERSON_f1": 0.8947368421052632, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.84472049689441, "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": 0.7636363636363636, "eval_TIME_number": 26, "eval_TIME_precision": 0.7241379310344828, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14074495434761047, "eval_overall_accuracy": 0.9567175381536153, "eval_overall_f1": 0.8157181571815718, "eval_overall_precision": 0.7543859649122807, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.9064, "eval_samples_per_second": 206.308, "eval_steps_per_second": 3.31, "step": 6996 }, { "epoch": 67.0, "grad_norm": 0.7492014169692993, "learning_rate": 1.65e-05, "loss": 0.0815, "step": 7102 }, { "epoch": 67.0, "eval_LOCATION_f1": 0.8051948051948052, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7560975609756098, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7719298245614036, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6875, "eval_ORGANIZATION_recall": 0.88, "eval_PERSON_f1": 0.8947368421052632, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.84472049689441, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.13906767964363098, "eval_overall_accuracy": 0.9569677257943457, "eval_overall_f1": 0.8184281842818428, "eval_overall_precision": 0.7568922305764411, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.9162, "eval_samples_per_second": 204.102, "eval_steps_per_second": 3.274, "step": 7102 }, { "epoch": 68.0, "grad_norm": 1.0627390146255493, "learning_rate": 1.6000000000000003e-05, "loss": 0.0829, "step": 7208 }, { "epoch": 68.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7738095238095238, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6989247311827957, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.9013157894736843, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8509316770186336, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6071428571428571, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5151515151515151, "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": 0.13949720561504364, "eval_overall_accuracy": 0.9572179134350763, "eval_overall_f1": 0.8157181571815718, "eval_overall_precision": 0.7543859649122807, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.9115, "eval_samples_per_second": 205.152, "eval_steps_per_second": 3.291, "step": 7208 }, { "epoch": 69.0, "grad_norm": 1.1830741167068481, "learning_rate": 1.55e-05, "loss": 0.0807, "step": 7314 }, { "epoch": 69.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7745664739884393, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6836734693877551, "eval_ORGANIZATION_recall": 0.8933333333333333, "eval_PERSON_f1": 0.9078947368421052, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8571428571428571, "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": 0.7636363636363636, "eval_TIME_number": 26, "eval_TIME_precision": 0.7241379310344828, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1431589275598526, "eval_overall_accuracy": 0.9559669752314236, "eval_overall_f1": 0.8216216216216216, "eval_overall_precision": 0.7581047381546134, "eval_overall_recall": 0.8967551622418879, "eval_runtime": 0.9156, "eval_samples_per_second": 204.239, "eval_steps_per_second": 3.277, "step": 7314 }, { "epoch": 70.0, "grad_norm": 0.7310447692871094, "learning_rate": 1.5e-05, "loss": 0.0818, "step": 7420 }, { "epoch": 70.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7349397590361446, "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": 0.8881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8385093167701864, "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": 0.7636363636363636, "eval_TIME_number": 26, "eval_TIME_precision": 0.7241379310344828, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.13888637721538544, "eval_overall_accuracy": 0.9572179134350763, "eval_overall_f1": 0.814614343707713, "eval_overall_precision": 0.7525, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.9137, "eval_samples_per_second": 204.651, "eval_steps_per_second": 3.283, "step": 7420 }, { "epoch": 71.0, "grad_norm": 0.9271581768989563, "learning_rate": 1.45e-05, "loss": 0.0822, "step": 7526 }, { "epoch": 71.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7558139534883721, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6701030927835051, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8918032786885245, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8395061728395061, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.14012862741947174, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.8097165991902835, "eval_overall_precision": 0.746268656716418, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.9209, "eval_samples_per_second": 203.059, "eval_steps_per_second": 3.258, "step": 7526 }, { "epoch": 72.0, "grad_norm": 1.0138612985610962, "learning_rate": 1.4000000000000001e-05, "loss": 0.0808, "step": 7632 }, { "epoch": 72.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7349397590361446, "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": 0.8918032786885245, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8395061728395061, "eval_PERSON_recall": 0.951048951048951, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "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": 0.1410142481327057, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.8124156545209177, "eval_overall_precision": 0.7487562189054726, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.915, "eval_samples_per_second": 204.377, "eval_steps_per_second": 3.279, "step": 7632 }, { "epoch": 73.0, "grad_norm": 1.7626816034317017, "learning_rate": 1.3500000000000001e-05, "loss": 0.0809, "step": 7738 }, { "epoch": 73.0, "eval_LOCATION_f1": 0.7712418300653595, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7647058823529413, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6842105263157895, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8385093167701864, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6415094339622641, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5666666666666667, "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": 0.13809551298618317, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.8081632653061224, "eval_overall_precision": 0.75, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.9143, "eval_samples_per_second": 204.522, "eval_steps_per_second": 3.281, "step": 7738 }, { "epoch": 74.0, "grad_norm": 2.8185625076293945, "learning_rate": 1.3000000000000001e-05, "loss": 0.0799, "step": 7844 }, { "epoch": 74.0, "eval_LOCATION_f1": 0.7848101265822784, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7209302325581395, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7657142857142857, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.67, "eval_ORGANIZATION_recall": 0.8933333333333333, "eval_PERSON_f1": 0.8983606557377047, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.845679012345679, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "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": 0.14839713275432587, "eval_overall_accuracy": 0.9539654741055792, "eval_overall_f1": 0.8128342245989304, "eval_overall_precision": 0.7432762836185819, "eval_overall_recall": 0.8967551622418879, "eval_runtime": 0.9191, "eval_samples_per_second": 203.465, "eval_steps_per_second": 3.264, "step": 7844 }, { "epoch": 75.0, "grad_norm": 1.3576046228408813, "learning_rate": 1.25e-05, "loss": 0.0783, "step": 7950 }, { "epoch": 75.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7764705882352942, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6947368421052632, "eval_ORGANIZATION_recall": 0.88, "eval_PERSON_f1": 0.8947368421052632, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.84472049689441, "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": 0.7636363636363636, "eval_TIME_number": 26, "eval_TIME_precision": 0.7241379310344828, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14130501449108124, "eval_overall_accuracy": 0.9559669752314236, "eval_overall_f1": 0.814111261872456, "eval_overall_precision": 0.7537688442211056, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.9938, "eval_samples_per_second": 188.158, "eval_steps_per_second": 3.019, "step": 7950 }, { "epoch": 76.0, "grad_norm": 1.2748137712478638, "learning_rate": 1.2e-05, "loss": 0.0787, "step": 8056 }, { "epoch": 76.0, "eval_LOCATION_f1": 0.782051282051282, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7261904761904762, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7771428571428572, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.68, "eval_ORGANIZATION_recall": 0.9066666666666666, "eval_PERSON_f1": 0.8888888888888888, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8343558282208589, "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": 0.7636363636363636, "eval_TIME_number": 26, "eval_TIME_precision": 0.7241379310344828, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14577369391918182, "eval_overall_accuracy": 0.9547160370277709, "eval_overall_f1": 0.8134228187919462, "eval_overall_precision": 0.7463054187192119, "eval_overall_recall": 0.8938053097345132, "eval_runtime": 0.9101, "eval_samples_per_second": 205.463, "eval_steps_per_second": 3.296, "step": 8056 }, { "epoch": 77.0, "grad_norm": 0.8947278261184692, "learning_rate": 1.1500000000000002e-05, "loss": 0.0782, "step": 8162 }, { "epoch": 77.0, "eval_LOCATION_f1": 0.782051282051282, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7261904761904762, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7790697674418604, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6907216494845361, "eval_ORGANIZATION_recall": 0.8933333333333333, "eval_PERSON_f1": 0.9013157894736843, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8509316770186336, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6415094339622641, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5666666666666667, "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": 0.14258120954036713, "eval_overall_accuracy": 0.9554665999499625, "eval_overall_f1": 0.8189189189189189, "eval_overall_precision": 0.7556109725685786, "eval_overall_recall": 0.8938053097345132, "eval_runtime": 0.9125, "eval_samples_per_second": 204.921, "eval_steps_per_second": 3.287, "step": 8162 }, { "epoch": 78.0, "grad_norm": 1.4929758310317993, "learning_rate": 1.1000000000000001e-05, "loss": 0.0789, "step": 8268 }, { "epoch": 78.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7692307692307693, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6914893617021277, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8947368421052632, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.84472049689441, "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": 0.7636363636363636, "eval_TIME_number": 26, "eval_TIME_precision": 0.7241379310344828, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14018741250038147, "eval_overall_accuracy": 0.9559669752314236, "eval_overall_f1": 0.8125000000000001, "eval_overall_precision": 0.7531486146095718, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.9168, "eval_samples_per_second": 203.978, "eval_steps_per_second": 3.272, "step": 8268 }, { "epoch": 79.0, "grad_norm": 1.9485721588134766, "learning_rate": 1.05e-05, "loss": 0.0777, "step": 8374 }, { "epoch": 79.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7745664739884393, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6836734693877551, "eval_ORGANIZATION_recall": 0.8933333333333333, "eval_PERSON_f1": 0.8976897689768978, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.85, "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": 0.7636363636363636, "eval_TIME_number": 26, "eval_TIME_precision": 0.7241379310344828, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14088545739650726, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.814614343707713, "eval_overall_precision": 0.7525, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.9198, "eval_samples_per_second": 203.311, "eval_steps_per_second": 3.262, "step": 8374 }, { "epoch": 80.0, "grad_norm": 0.9733961820602417, "learning_rate": 1e-05, "loss": 0.0766, "step": 8480 }, { "epoch": 80.0, "eval_LOCATION_f1": 0.7612903225806451, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7108433734939759, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7683615819209039, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.9066666666666666, "eval_PERSON_f1": 0.9013157894736843, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8509316770186336, "eval_PERSON_recall": 0.958041958041958, "eval_QUANTITY_f1": 0.6415094339622641, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5666666666666667, "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": 0.14972136914730072, "eval_overall_accuracy": 0.952964723542657, "eval_overall_f1": 0.8118279569892473, "eval_overall_precision": 0.745679012345679, "eval_overall_recall": 0.8908554572271387, "eval_runtime": 0.9946, "eval_samples_per_second": 188.024, "eval_steps_per_second": 3.016, "step": 8480 }, { "epoch": 81.0, "grad_norm": 1.994262456893921, "learning_rate": 9.5e-06, "loss": 0.078, "step": 8586 }, { "epoch": 81.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7602339181286549, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6770833333333334, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8918032786885245, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8395061728395061, "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": 0.7636363636363636, "eval_TIME_number": 26, "eval_TIME_precision": 0.7241379310344828, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14083416759967804, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.8092016238159675, "eval_overall_precision": 0.7475, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.9107, "eval_samples_per_second": 205.34, "eval_steps_per_second": 3.294, "step": 8586 }, { "epoch": 82.0, "grad_norm": 1.8665719032287598, "learning_rate": 9e-06, "loss": 0.0762, "step": 8692 }, { "epoch": 82.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7619047619047621, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6881720430107527, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8947368421052632, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.84472049689441, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.13929150998592377, "eval_overall_accuracy": 0.9574681010758068, "eval_overall_f1": 0.8119891008174387, "eval_overall_precision": 0.7544303797468355, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.9151, "eval_samples_per_second": 204.346, "eval_steps_per_second": 3.278, "step": 8692 }, { "epoch": 83.0, "grad_norm": 2.8703787326812744, "learning_rate": 8.500000000000002e-06, "loss": 0.0768, "step": 8798 }, { "epoch": 83.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "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": 0.8947368421052632, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.84472049689441, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14202933013439178, "eval_overall_accuracy": 0.9552164123092319, "eval_overall_f1": 0.8075880758807586, "eval_overall_precision": 0.7468671679197995, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.9727, "eval_samples_per_second": 192.248, "eval_steps_per_second": 3.084, "step": 8798 }, { "epoch": 84.0, "grad_norm": 1.1315829753875732, "learning_rate": 8.000000000000001e-06, "loss": 0.076, "step": 8904 }, { "epoch": 84.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7514450867052023, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6632653061224489, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8976897689768978, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.85, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14301645755767822, "eval_overall_accuracy": 0.9554665999499625, "eval_overall_f1": 0.8092016238159675, "eval_overall_precision": 0.7475, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.9165, "eval_samples_per_second": 204.042, "eval_steps_per_second": 3.273, "step": 8904 }, { "epoch": 85.0, "grad_norm": 2.2398879528045654, "learning_rate": 7.5e-06, "loss": 0.0799, "step": 9010 }, { "epoch": 85.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7602339181286549, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6770833333333334, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8976897689768978, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.85, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1421351134777069, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.8113975576662144, "eval_overall_precision": 0.7512562814070352, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.9592, "eval_samples_per_second": 194.953, "eval_steps_per_second": 3.128, "step": 9010 }, { "epoch": 86.0, "grad_norm": 2.19338059425354, "learning_rate": 7.000000000000001e-06, "loss": 0.0782, "step": 9116 }, { "epoch": 86.0, "eval_LOCATION_f1": 0.782051282051282, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7261904761904762, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7647058823529413, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6842105263157895, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8918032786885245, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8395061728395061, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14250795543193817, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.8108108108108109, "eval_overall_precision": 0.7481296758104738, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.9096, "eval_samples_per_second": 205.578, "eval_steps_per_second": 3.298, "step": 9116 }, { "epoch": 87.0, "grad_norm": 1.4476428031921387, "learning_rate": 6.5000000000000004e-06, "loss": 0.0745, "step": 9222 }, { "epoch": 87.0, "eval_LOCATION_f1": 0.7612903225806451, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7108433734939759, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7647058823529413, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6842105263157895, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8918032786885245, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8395061728395061, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14125750958919525, "eval_overall_accuracy": 0.9554665999499625, "eval_overall_f1": 0.8064952638700948, "eval_overall_precision": 0.745, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.9247, "eval_samples_per_second": 202.234, "eval_steps_per_second": 3.244, "step": 9222 }, { "epoch": 88.0, "grad_norm": 0.9746472835540771, "learning_rate": 6e-06, "loss": 0.0761, "step": 9328 }, { "epoch": 88.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7692307692307693, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6914893617021277, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8918032786885245, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8395061728395061, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14156818389892578, "eval_overall_accuracy": 0.9559669752314236, "eval_overall_f1": 0.8113975576662144, "eval_overall_precision": 0.7512562814070352, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.918, "eval_samples_per_second": 203.695, "eval_steps_per_second": 3.268, "step": 9328 }, { "epoch": 89.0, "grad_norm": 1.442697525024414, "learning_rate": 5.500000000000001e-06, "loss": 0.077, "step": 9434 }, { "epoch": 89.0, "eval_LOCATION_f1": 0.7662337662337662, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7195121951219512, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7647058823529413, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6842105263157895, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8947368421052632, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.84472049689441, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14453893899917603, "eval_overall_accuracy": 0.9544658493870403, "eval_overall_f1": 0.8086838534599728, "eval_overall_precision": 0.7487437185929648, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.9168, "eval_samples_per_second": 203.963, "eval_steps_per_second": 3.272, "step": 9434 }, { "epoch": 90.0, "grad_norm": 1.2341150045394897, "learning_rate": 5e-06, "loss": 0.0736, "step": 9540 }, { "epoch": 90.0, "eval_LOCATION_f1": 0.7662337662337662, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7195121951219512, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7647058823529413, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6842105263157895, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8947368421052632, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.84472049689441, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1449405997991562, "eval_overall_accuracy": 0.9547160370277709, "eval_overall_f1": 0.8086838534599728, "eval_overall_precision": 0.7487437185929648, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.9126, "eval_samples_per_second": 204.9, "eval_steps_per_second": 3.287, "step": 9540 }, { "epoch": 91.0, "grad_norm": 0.9457686543464661, "learning_rate": 4.5e-06, "loss": 0.0751, "step": 9646 }, { "epoch": 91.0, "eval_LOCATION_f1": 0.782051282051282, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7261904761904762, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7692307692307693, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6914893617021277, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8918032786885245, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8395061728395061, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14425554871559143, "eval_overall_accuracy": 0.9554665999499625, "eval_overall_f1": 0.8119079837618404, "eval_overall_precision": 0.75, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.9133, "eval_samples_per_second": 204.753, "eval_steps_per_second": 3.285, "step": 9646 }, { "epoch": 92.0, "grad_norm": 2.3483853340148926, "learning_rate": 4.000000000000001e-06, "loss": 0.0786, "step": 9752 }, { "epoch": 92.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7647058823529413, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6842105263157895, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8918032786885245, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8395061728395061, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14525118470191956, "eval_overall_accuracy": 0.9547160370277709, "eval_overall_f1": 0.8102981029810299, "eval_overall_precision": 0.7493734335839599, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.9237, "eval_samples_per_second": 202.447, "eval_steps_per_second": 3.248, "step": 9752 }, { "epoch": 93.0, "grad_norm": 0.5804659724235535, "learning_rate": 3.5000000000000004e-06, "loss": 0.074, "step": 9858 }, { "epoch": 93.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7701149425287357, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6767676767676768, "eval_ORGANIZATION_recall": 0.8933333333333333, "eval_PERSON_f1": 0.8918032786885245, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8395061728395061, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1493208408355713, "eval_overall_accuracy": 0.9532149111833875, "eval_overall_f1": 0.8102288021534321, "eval_overall_precision": 0.745049504950495, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.9189, "eval_samples_per_second": 203.504, "eval_steps_per_second": 3.265, "step": 9858 }, { "epoch": 94.0, "grad_norm": 0.7812560796737671, "learning_rate": 3e-06, "loss": 0.0752, "step": 9964 }, { "epoch": 94.0, "eval_LOCATION_f1": 0.7712418300653595, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7586206896551725, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.88, "eval_PERSON_f1": 0.8918032786885245, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8395061728395061, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14663609862327576, "eval_overall_accuracy": 0.9534650988241181, "eval_overall_f1": 0.8070175438596491, "eval_overall_precision": 0.7437810945273632, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.913, "eval_samples_per_second": 204.821, "eval_steps_per_second": 3.286, "step": 9964 }, { "epoch": 95.0, "grad_norm": 0.8495714068412781, "learning_rate": 2.5e-06, "loss": 0.0745, "step": 10070 }, { "epoch": 95.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.783625730994152, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6979166666666666, "eval_ORGANIZATION_recall": 0.8933333333333333, "eval_PERSON_f1": 0.8888888888888888, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8343558282208589, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14591553807258606, "eval_overall_accuracy": 0.955716787590693, "eval_overall_f1": 0.8135135135135134, "eval_overall_precision": 0.7506234413965087, "eval_overall_recall": 0.887905604719764, "eval_runtime": 0.9201, "eval_samples_per_second": 203.239, "eval_steps_per_second": 3.261, "step": 10070 }, { "epoch": 96.0, "grad_norm": 0.3554103374481201, "learning_rate": 2.0000000000000003e-06, "loss": 0.0777, "step": 10176 }, { "epoch": 96.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7810650887573964, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7021276595744681, "eval_ORGANIZATION_recall": 0.88, "eval_PERSON_f1": 0.8888888888888888, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8343558282208589, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14481669664382935, "eval_overall_accuracy": 0.955716787590693, "eval_overall_f1": 0.8130081300813008, "eval_overall_precision": 0.7518796992481203, "eval_overall_recall": 0.8849557522123894, "eval_runtime": 0.9164, "eval_samples_per_second": 204.064, "eval_steps_per_second": 3.274, "step": 10176 }, { "epoch": 97.0, "grad_norm": 0.6766789555549622, "learning_rate": 1.5e-06, "loss": 0.0757, "step": 10282 }, { "epoch": 97.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7647058823529413, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6842105263157895, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8888888888888888, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8343558282208589, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14305640757083893, "eval_overall_accuracy": 0.9559669752314236, "eval_overall_f1": 0.8092016238159675, "eval_overall_precision": 0.7475, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.9169, "eval_samples_per_second": 203.956, "eval_steps_per_second": 3.272, "step": 10282 }, { "epoch": 98.0, "grad_norm": 0.7809789180755615, "learning_rate": 1.0000000000000002e-06, "loss": 0.0733, "step": 10388 }, { "epoch": 98.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7692307692307693, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6914893617021277, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8888888888888888, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8343558282208589, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14303794503211975, "eval_overall_accuracy": 0.955716787590693, "eval_overall_f1": 0.8102981029810299, "eval_overall_precision": 0.7493734335839599, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.9207, "eval_samples_per_second": 203.11, "eval_steps_per_second": 3.258, "step": 10388 }, { "epoch": 99.0, "grad_norm": 0.6889355778694153, "learning_rate": 5.000000000000001e-07, "loss": 0.0735, "step": 10494 }, { "epoch": 99.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7692307692307693, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6914893617021277, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8888888888888888, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8343558282208589, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14303508400917053, "eval_overall_accuracy": 0.955716787590693, "eval_overall_f1": 0.8102981029810299, "eval_overall_precision": 0.7493734335839599, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.9116, "eval_samples_per_second": 205.136, "eval_steps_per_second": 3.291, "step": 10494 }, { "epoch": 100.0, "grad_norm": 0.5818679332733154, "learning_rate": 0.0, "loss": 0.0758, "step": 10600 }, { "epoch": 100.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7692307692307693, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6914893617021277, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8888888888888888, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8343558282208589, "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": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14349789917469025, "eval_overall_accuracy": 0.955716787590693, "eval_overall_f1": 0.8102981029810299, "eval_overall_precision": 0.7493734335839599, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.9177, "eval_samples_per_second": 203.777, "eval_steps_per_second": 3.269, "step": 10600 }, { "epoch": 100.0, "step": 10600, "total_flos": 4533533359897542.0, "train_loss": 0.13073445756480379, "train_runtime": 1224.6081, "train_samples_per_second": 137.758, "train_steps_per_second": 8.656 } ], "logging_steps": 500, "max_steps": 10600, "num_input_tokens_seen": 0, "num_train_epochs": 100, "save_steps": 500, "total_flos": 4533533359897542.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }