{ "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": 1.5585302114486694, "learning_rate": 4.9500000000000004e-05, "loss": 1.0106, "step": 106 }, { "epoch": 1.0, "eval_LOCATION_f1": 0.0, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.0, "eval_LOCATION_recall": 0.0, "eval_ORGANIZATION_f1": 0.0, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.02366863905325444, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.10526315789473684, "eval_PERSON_recall": 0.013333333333333334, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 34, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.584353506565094, "eval_overall_accuracy": 0.840265813438346, "eval_overall_f1": 0.010416666666666668, "eval_overall_precision": 0.06060606060606061, "eval_overall_recall": 0.005698005698005698, "eval_runtime": 0.3862, "eval_samples_per_second": 484.243, "eval_steps_per_second": 7.769, "step": 106 }, { "epoch": 2.0, "grad_norm": 1.2475420236587524, "learning_rate": 4.9e-05, "loss": 0.4994, "step": 212 }, { "epoch": 2.0, "eval_LOCATION_f1": 0.2476190476190476, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.40625, "eval_LOCATION_recall": 0.1780821917808219, "eval_ORGANIZATION_f1": 0.05309734513274336, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.0625, "eval_ORGANIZATION_recall": 0.046153846153846156, "eval_PERSON_f1": 0.6495726495726495, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.5671641791044776, "eval_PERSON_recall": 0.76, "eval_QUANTITY_f1": 0.11764705882352941, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.13636363636363635, "eval_QUANTITY_recall": 0.10344827586206896, "eval_TIME_f1": 0.5454545454545455, "eval_TIME_number": 34, "eval_TIME_precision": 0.5625, "eval_TIME_recall": 0.5294117647058824, "eval_loss": 0.3691530227661133, "eval_overall_accuracy": 0.8973664779719419, "eval_overall_f1": 0.4402332361516035, "eval_overall_precision": 0.4507462686567164, "eval_overall_recall": 0.4301994301994302, "eval_runtime": 0.3854, "eval_samples_per_second": 485.184, "eval_steps_per_second": 7.784, "step": 212 }, { "epoch": 3.0, "grad_norm": 1.0947109460830688, "learning_rate": 4.85e-05, "loss": 0.3195, "step": 318 }, { "epoch": 3.0, "eval_LOCATION_f1": 0.6257668711656442, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.5666666666666667, "eval_LOCATION_recall": 0.6986301369863014, "eval_ORGANIZATION_f1": 0.3464566929133858, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.3548387096774194, "eval_ORGANIZATION_recall": 0.3384615384615385, "eval_PERSON_f1": 0.8220858895705522, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7613636363636364, "eval_PERSON_recall": 0.8933333333333333, "eval_QUANTITY_f1": 0.5396825396825397, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.5862068965517241, "eval_TIME_f1": 0.8285714285714286, "eval_TIME_number": 34, "eval_TIME_precision": 0.8055555555555556, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.2105339616537094, "eval_overall_accuracy": 0.9308392813192222, "eval_overall_f1": 0.6755674232309746, "eval_overall_precision": 0.635678391959799, "eval_overall_recall": 0.7207977207977208, "eval_runtime": 0.3874, "eval_samples_per_second": 482.736, "eval_steps_per_second": 7.744, "step": 318 }, { "epoch": 4.0, "grad_norm": 1.0842955112457275, "learning_rate": 4.8e-05, "loss": 0.2206, "step": 424 }, { "epoch": 4.0, "eval_LOCATION_f1": 0.7204968944099379, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6590909090909091, "eval_LOCATION_recall": 0.7945205479452054, "eval_ORGANIZATION_f1": 0.5889570552147239, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.4897959183673469, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.8553459119496856, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8095238095238095, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.5753424657534246, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.4772727272727273, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.9014084507042254, "eval_TIME_number": 34, "eval_TIME_precision": 0.8648648648648649, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.17346060276031494, "eval_overall_accuracy": 0.9428993354664041, "eval_overall_f1": 0.7506361323155216, "eval_overall_precision": 0.6781609195402298, "eval_overall_recall": 0.8404558404558404, "eval_runtime": 0.386, "eval_samples_per_second": 484.418, "eval_steps_per_second": 7.771, "step": 424 }, { "epoch": 5.0, "grad_norm": 1.0773650407791138, "learning_rate": 4.75e-05, "loss": 0.1791, "step": 530 }, { "epoch": 5.0, "eval_LOCATION_f1": 0.7151515151515151, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6413043478260869, "eval_LOCATION_recall": 0.8082191780821918, "eval_ORGANIZATION_f1": 0.6103896103896104, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5280898876404494, "eval_ORGANIZATION_recall": 0.7230769230769231, "eval_PERSON_f1": 0.8643533123028392, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8203592814371258, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.591549295774648, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.7848101265822784, "eval_TIME_number": 34, "eval_TIME_precision": 0.6888888888888889, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1583884358406067, "eval_overall_accuracy": 0.9456066945606695, "eval_overall_f1": 0.7506361323155216, "eval_overall_precision": 0.6781609195402298, "eval_overall_recall": 0.8404558404558404, "eval_runtime": 0.3888, "eval_samples_per_second": 480.92, "eval_steps_per_second": 7.715, "step": 530 }, { "epoch": 6.0, "grad_norm": 1.4482425451278687, "learning_rate": 4.7e-05, "loss": 0.1602, "step": 636 }, { "epoch": 6.0, "eval_LOCATION_f1": 0.7407407407407406, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6741573033707865, "eval_LOCATION_recall": 0.821917808219178, "eval_ORGANIZATION_f1": 0.6787878787878788, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.56, "eval_ORGANIZATION_recall": 0.8615384615384616, "eval_PERSON_f1": 0.8633540372670808, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8081395348837209, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6153846153846154, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.4897959183673469, "eval_QUANTITY_recall": 0.8275862068965517, "eval_TIME_f1": 0.7435897435897436, "eval_TIME_number": 34, "eval_TIME_precision": 0.6590909090909091, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.18004342913627625, "eval_overall_accuracy": 0.9416687176962836, "eval_overall_f1": 0.7652173913043478, "eval_overall_precision": 0.6784140969162996, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3887, "eval_samples_per_second": 481.105, "eval_steps_per_second": 7.718, "step": 636 }, { "epoch": 7.0, "grad_norm": 0.84205162525177, "learning_rate": 4.6500000000000005e-05, "loss": 0.1484, "step": 742 }, { "epoch": 7.0, "eval_LOCATION_f1": 0.779874213836478, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7209302325581395, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6887417218543046, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6046511627906976, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.879746835443038, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8373493975903614, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6857142857142856, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5853658536585366, "eval_QUANTITY_recall": 0.8275862068965517, "eval_TIME_f1": 0.8108108108108107, "eval_TIME_number": 34, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14192061126232147, "eval_overall_accuracy": 0.9549593896135861, "eval_overall_f1": 0.7974025974025974, "eval_overall_precision": 0.7326968973747017, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.3888, "eval_samples_per_second": 481.015, "eval_steps_per_second": 7.717, "step": 742 }, { "epoch": 8.0, "grad_norm": 1.116653561592102, "learning_rate": 4.600000000000001e-05, "loss": 0.1372, "step": 848 }, { "epoch": 8.0, "eval_LOCATION_f1": 0.7439024390243901, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6703296703296703, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.6887417218543046, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6046511627906976, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8853503184713376, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8475609756097561, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6857142857142856, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5853658536585366, "eval_QUANTITY_recall": 0.8275862068965517, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.14389163255691528, "eval_overall_accuracy": 0.9527442776273689, "eval_overall_f1": 0.7943078913324709, "eval_overall_precision": 0.7274881516587678, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.3896, "eval_samples_per_second": 479.969, "eval_steps_per_second": 7.7, "step": 848 }, { "epoch": 9.0, "grad_norm": 1.8104156255722046, "learning_rate": 4.55e-05, "loss": 0.1271, "step": 954 }, { "epoch": 9.0, "eval_LOCATION_f1": 0.8129032258064516, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7682926829268293, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6838709677419356, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5888888888888889, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.9061488673139159, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8805031446540881, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8767123287671232, "eval_TIME_number": 34, "eval_TIME_precision": 0.8205128205128205, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.12979353964328766, "eval_overall_accuracy": 0.9584051193699237, "eval_overall_f1": 0.8269484808454426, "eval_overall_precision": 0.770935960591133, "eval_overall_recall": 0.8917378917378918, "eval_runtime": 0.3907, "eval_samples_per_second": 478.642, "eval_steps_per_second": 7.679, "step": 954 }, { "epoch": 10.0, "grad_norm": 0.966005802154541, "learning_rate": 4.5e-05, "loss": 0.1255, "step": 1060 }, { "epoch": 10.0, "eval_LOCATION_f1": 0.8235294117647058, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7875, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6986301369863014, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6296296296296297, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.9025974025974027, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.879746835443038, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6410256410256411, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8732394366197184, "eval_TIME_number": 34, "eval_TIME_precision": 0.8378378378378378, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.12757907807826996, "eval_overall_accuracy": 0.9601279842480925, "eval_overall_f1": 0.8284182305630027, "eval_overall_precision": 0.7822784810126582, "eval_overall_recall": 0.8803418803418803, "eval_runtime": 0.3875, "eval_samples_per_second": 482.56, "eval_steps_per_second": 7.742, "step": 1060 }, { "epoch": 11.0, "grad_norm": 0.9226321578025818, "learning_rate": 4.4500000000000004e-05, "loss": 0.118, "step": 1166 }, { "epoch": 11.0, "eval_LOCATION_f1": 0.8051948051948052, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7654320987654321, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.697986577181208, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6190476190476191, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8867313915857605, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8616352201257862, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6410256410256411, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.13041509687900543, "eval_overall_accuracy": 0.9584051193699237, "eval_overall_f1": 0.8138297872340426, "eval_overall_precision": 0.7630922693266833, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.3856, "eval_samples_per_second": 484.897, "eval_steps_per_second": 7.779, "step": 1166 }, { "epoch": 12.0, "grad_norm": 0.9765021800994873, "learning_rate": 4.4000000000000006e-05, "loss": 0.1125, "step": 1272 }, { "epoch": 12.0, "eval_LOCATION_f1": 0.7848101265822783, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7294117647058823, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.738255033557047, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6547619047619048, "eval_ORGANIZATION_recall": 0.8461538461538461, "eval_PERSON_f1": 0.8860759493670886, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8433734939759037, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6410256410256411, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14262500405311584, "eval_overall_accuracy": 0.9559438838296825, "eval_overall_f1": 0.8146214099216709, "eval_overall_precision": 0.7518072289156627, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.3856, "eval_samples_per_second": 484.965, "eval_steps_per_second": 7.78, "step": 1272 }, { "epoch": 13.0, "grad_norm": 0.696005642414093, "learning_rate": 4.35e-05, "loss": 0.1032, "step": 1378 }, { "epoch": 13.0, "eval_LOCATION_f1": 0.8079470198675496, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.713375796178344, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6086956521739131, "eval_ORGANIZATION_recall": 0.8615384615384616, "eval_PERSON_f1": 0.896103896103896, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8734177215189873, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.746268656716418, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8823529411764706, "eval_TIME_number": 34, "eval_TIME_precision": 0.8823529411764706, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.13183027505874634, "eval_overall_accuracy": 0.9593896135860202, "eval_overall_f1": 0.8255659121171771, "eval_overall_precision": 0.775, "eval_overall_recall": 0.8831908831908832, "eval_runtime": 0.3838, "eval_samples_per_second": 487.205, "eval_steps_per_second": 7.816, "step": 1378 }, { "epoch": 14.0, "grad_norm": 0.6964078545570374, "learning_rate": 4.3e-05, "loss": 0.1046, "step": 1484 }, { "epoch": 14.0, "eval_LOCATION_f1": 0.7848101265822783, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7294117647058823, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7105263157894737, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6206896551724138, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.86875, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.7536231884057972, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.65, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.7368421052631577, "eval_TIME_number": 34, "eval_TIME_precision": 0.6666666666666666, "eval_TIME_recall": 0.8235294117647058, "eval_loss": 0.1450473964214325, "eval_overall_accuracy": 0.9564361309377307, "eval_overall_f1": 0.807843137254902, "eval_overall_precision": 0.7463768115942029, "eval_overall_recall": 0.8803418803418803, "eval_runtime": 0.3863, "eval_samples_per_second": 484.097, "eval_steps_per_second": 7.766, "step": 1484 }, { "epoch": 15.0, "grad_norm": 1.2660812139511108, "learning_rate": 4.25e-05, "loss": 0.0969, "step": 1590 }, { "epoch": 15.0, "eval_LOCATION_f1": 0.8129032258064516, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7682926829268293, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7162162162162162, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6385542168674698, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8925081433224756, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8726114649681529, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8732394366197184, "eval_TIME_number": 34, "eval_TIME_precision": 0.8378378378378378, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13275112211704254, "eval_overall_accuracy": 0.9618508491262614, "eval_overall_f1": 0.8284182305630027, "eval_overall_precision": 0.7822784810126582, "eval_overall_recall": 0.8803418803418803, "eval_runtime": 0.3835, "eval_samples_per_second": 487.585, "eval_steps_per_second": 7.822, "step": 1590 }, { "epoch": 16.0, "grad_norm": 1.0079460144042969, "learning_rate": 4.2e-05, "loss": 0.0916, "step": 1696 }, { "epoch": 16.0, "eval_LOCATION_f1": 0.8366013071895425, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.7323943661971831, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6753246753246753, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8974358974358974, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8641975308641975, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.7575757575757576, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8169014084507041, "eval_TIME_number": 34, "eval_TIME_precision": 0.7837837837837838, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.1358853280544281, "eval_overall_accuracy": 0.9625892197883338, "eval_overall_f1": 0.8333333333333334, "eval_overall_precision": 0.7888040712468194, "eval_overall_recall": 0.8831908831908832, "eval_runtime": 0.3837, "eval_samples_per_second": 487.337, "eval_steps_per_second": 7.818, "step": 1696 }, { "epoch": 17.0, "grad_norm": 2.586317539215088, "learning_rate": 4.15e-05, "loss": 0.0915, "step": 1802 }, { "epoch": 17.0, "eval_LOCATION_f1": 0.8076923076923077, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7310344827586207, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6625, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.875, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.8064516129032258, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8857142857142858, "eval_TIME_number": 34, "eval_TIME_precision": 0.8611111111111112, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1329522430896759, "eval_overall_accuracy": 0.9623430962343096, "eval_overall_f1": 0.8398384925975775, "eval_overall_precision": 0.7959183673469388, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.3851, "eval_samples_per_second": 485.53, "eval_steps_per_second": 7.789, "step": 1802 }, { "epoch": 18.0, "grad_norm": 0.9525734782218933, "learning_rate": 4.1e-05, "loss": 0.0917, "step": 1908 }, { "epoch": 18.0, "eval_LOCATION_f1": 0.8289473684210525, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7310344827586207, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6625, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8903225806451613, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8625, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.716417910447761, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.631578947368421, "eval_QUANTITY_recall": 0.8275862068965517, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 34, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14254941046237946, "eval_overall_accuracy": 0.9591434900319961, "eval_overall_f1": 0.8279569892473119, "eval_overall_precision": 0.7837150127226463, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3852, "eval_samples_per_second": 485.425, "eval_steps_per_second": 7.788, "step": 1908 }, { "epoch": 19.0, "grad_norm": 0.7584782242774963, "learning_rate": 4.05e-05, "loss": 0.0883, "step": 2014 }, { "epoch": 19.0, "eval_LOCATION_f1": 0.8289473684210525, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7586206896551724, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6875, "eval_ORGANIZATION_recall": 0.8461538461538461, "eval_PERSON_f1": 0.8903225806451613, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8625, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.8125, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8055555555555555, "eval_TIME_number": 34, "eval_TIME_precision": 0.7631578947368421, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.13237319886684418, "eval_overall_accuracy": 0.963081466896382, "eval_overall_f1": 0.8371467025572006, "eval_overall_precision": 0.7933673469387755, "eval_overall_recall": 0.886039886039886, "eval_runtime": 0.3833, "eval_samples_per_second": 487.824, "eval_steps_per_second": 7.826, "step": 2014 }, { "epoch": 20.0, "grad_norm": 0.6288883090019226, "learning_rate": 4e-05, "loss": 0.0838, "step": 2120 }, { "epoch": 20.0, "eval_LOCATION_f1": 0.8311688311688312, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.75, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6835443037974683, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8996763754045306, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8742138364779874, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6857142857142856, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5853658536585366, "eval_QUANTITY_recall": 0.8275862068965517, "eval_TIME_f1": 0.8985507246376812, "eval_TIME_number": 34, "eval_TIME_precision": 0.8857142857142857, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1400074064731598, "eval_overall_accuracy": 0.9613586020182131, "eval_overall_f1": 0.8364611260053618, "eval_overall_precision": 0.789873417721519, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.3837, "eval_samples_per_second": 487.366, "eval_steps_per_second": 7.819, "step": 2120 }, { "epoch": 21.0, "grad_norm": 2.4087135791778564, "learning_rate": 3.9500000000000005e-05, "loss": 0.0809, "step": 2226 }, { "epoch": 21.0, "eval_LOCATION_f1": 0.8289473684210525, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7466666666666668, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6588235294117647, "eval_ORGANIZATION_recall": 0.8615384615384616, "eval_PERSON_f1": 0.8846153846153846, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8518518518518519, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7419354838709677, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.696969696969697, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.8985507246376812, "eval_TIME_number": 34, "eval_TIME_precision": 0.8857142857142857, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13903410732746124, "eval_overall_accuracy": 0.9628353433423579, "eval_overall_f1": 0.8348993288590604, "eval_overall_precision": 0.7893401015228426, "eval_overall_recall": 0.886039886039886, "eval_runtime": 0.3836, "eval_samples_per_second": 487.45, "eval_steps_per_second": 7.82, "step": 2226 }, { "epoch": 22.0, "grad_norm": 1.5907405614852905, "learning_rate": 3.9000000000000006e-05, "loss": 0.0795, "step": 2332 }, { "epoch": 22.0, "eval_LOCATION_f1": 0.8421052631578948, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.7448275862068966, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.675, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.9025974025974027, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.879746835443038, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.75, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6857142857142857, "eval_QUANTITY_recall": 0.8275862068965517, "eval_TIME_f1": 0.8169014084507041, "eval_TIME_number": 34, "eval_TIME_precision": 0.7837837837837838, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.13828279078006744, "eval_overall_accuracy": 0.9613586020182131, "eval_overall_f1": 0.8378378378378378, "eval_overall_precision": 0.7969151670951157, "eval_overall_recall": 0.8831908831908832, "eval_runtime": 0.3851, "eval_samples_per_second": 485.564, "eval_steps_per_second": 7.79, "step": 2332 }, { "epoch": 23.0, "grad_norm": 1.1399990320205688, "learning_rate": 3.85e-05, "loss": 0.0778, "step": 2438 }, { "epoch": 23.0, "eval_LOCATION_f1": 0.8441558441558442, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8024691358024691, "eval_LOCATION_recall": 0.8904109589041096, "eval_ORGANIZATION_f1": 0.7448275862068966, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.675, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.875, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 34, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1377546340227127, "eval_overall_accuracy": 0.9645582082205267, "eval_overall_f1": 0.8502024291497975, "eval_overall_precision": 0.8076923076923077, "eval_overall_recall": 0.8974358974358975, "eval_runtime": 0.3866, "eval_samples_per_second": 483.721, "eval_steps_per_second": 7.76, "step": 2438 }, { "epoch": 24.0, "grad_norm": 0.7097505331039429, "learning_rate": 3.8e-05, "loss": 0.0731, "step": 2544 }, { "epoch": 24.0, "eval_LOCATION_f1": 0.8311688311688312, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.7417218543046358, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6511627906976745, "eval_ORGANIZATION_recall": 0.8615384615384616, "eval_PERSON_f1": 0.90032154340836, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8695652173913043, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.8253968253968255, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8695652173913043, "eval_TIME_number": 34, "eval_TIME_precision": 0.8571428571428571, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14163164794445038, "eval_overall_accuracy": 0.9625892197883338, "eval_overall_f1": 0.8449197860962567, "eval_overall_precision": 0.7959697732997482, "eval_overall_recall": 0.9002849002849003, "eval_runtime": 0.3896, "eval_samples_per_second": 479.933, "eval_steps_per_second": 7.699, "step": 2544 }, { "epoch": 25.0, "grad_norm": 0.6983250379562378, "learning_rate": 3.7500000000000003e-05, "loss": 0.0729, "step": 2650 }, { "epoch": 25.0, "eval_LOCATION_f1": 0.8289473684210525, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7586206896551724, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6875, "eval_ORGANIZATION_recall": 0.8461538461538461, "eval_PERSON_f1": 0.8910256410256411, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8580246913580247, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6956521739130435, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.8275862068965517, "eval_TIME_f1": 0.8055555555555555, "eval_TIME_number": 34, "eval_TIME_precision": 0.7631578947368421, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.15113840997219086, "eval_overall_accuracy": 0.9608663549101649, "eval_overall_f1": 0.8266666666666667, "eval_overall_precision": 0.7769423558897243, "eval_overall_recall": 0.8831908831908832, "eval_runtime": 0.3874, "eval_samples_per_second": 482.751, "eval_steps_per_second": 7.745, "step": 2650 }, { "epoch": 26.0, "grad_norm": 0.6798135638237, "learning_rate": 3.7e-05, "loss": 0.0724, "step": 2756 }, { "epoch": 26.0, "eval_LOCATION_f1": 0.8211920529801324, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7714285714285715, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.72, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8896103896103896, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8670886075949367, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.676056338028169, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5714285714285714, "eval_QUANTITY_recall": 0.8275862068965517, "eval_TIME_f1": 0.7837837837837837, "eval_TIME_number": 34, "eval_TIME_precision": 0.725, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.14874529838562012, "eval_overall_accuracy": 0.958897366477972, "eval_overall_f1": 0.8225806451612903, "eval_overall_precision": 0.7786259541984732, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.3851, "eval_samples_per_second": 485.534, "eval_steps_per_second": 7.789, "step": 2756 }, { "epoch": 27.0, "grad_norm": 1.0639210939407349, "learning_rate": 3.65e-05, "loss": 0.0699, "step": 2862 }, { "epoch": 27.0, "eval_LOCATION_f1": 0.802547770700637, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7724137931034483, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.7, "eval_ORGANIZATION_recall": 0.8615384615384616, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.875, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.6666666666666666, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5581395348837209, "eval_QUANTITY_recall": 0.8275862068965517, "eval_TIME_f1": 0.8055555555555555, "eval_TIME_number": 34, "eval_TIME_precision": 0.7631578947368421, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.14704443514347076, "eval_overall_accuracy": 0.9601279842480925, "eval_overall_f1": 0.8253968253968255, "eval_overall_precision": 0.7703703703703704, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.3833, "eval_samples_per_second": 487.887, "eval_steps_per_second": 7.827, "step": 2862 }, { "epoch": 28.0, "grad_norm": 1.30838942527771, "learning_rate": 3.6e-05, "loss": 0.0669, "step": 2968 }, { "epoch": 28.0, "eval_LOCATION_f1": 0.8243243243243243, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8133333333333334, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.702290076335878, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.696969696969697, "eval_ORGANIZATION_recall": 0.7076923076923077, "eval_PERSON_f1": 0.8996763754045306, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8742138364779874, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.75, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6857142857142857, "eval_QUANTITY_recall": 0.8275862068965517, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.136509507894516, "eval_overall_accuracy": 0.9633275904504061, "eval_overall_f1": 0.8287292817679558, "eval_overall_precision": 0.8042895442359249, "eval_overall_recall": 0.8547008547008547, "eval_runtime": 0.3862, "eval_samples_per_second": 484.155, "eval_steps_per_second": 7.767, "step": 2968 }, { "epoch": 29.0, "grad_norm": 3.5960898399353027, "learning_rate": 3.55e-05, "loss": 0.0671, "step": 3074 }, { "epoch": 29.0, "eval_LOCATION_f1": 0.847682119205298, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.7746478873239436, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.7142857142857143, "eval_ORGANIZATION_recall": 0.8461538461538461, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.8253968253968255, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8695652173913043, "eval_TIME_number": 34, "eval_TIME_precision": 0.8571428571428571, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.13075676560401917, "eval_overall_accuracy": 0.9667733202067438, "eval_overall_f1": 0.8532608695652173, "eval_overall_precision": 0.8155844155844156, "eval_overall_recall": 0.8945868945868946, "eval_runtime": 0.3854, "eval_samples_per_second": 485.171, "eval_steps_per_second": 7.783, "step": 3074 }, { "epoch": 30.0, "grad_norm": 1.5083116292953491, "learning_rate": 3.5e-05, "loss": 0.0645, "step": 3180 }, { "epoch": 30.0, "eval_LOCATION_f1": 0.8187919463087249, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8026315789473685, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.75, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6835443037974683, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.875, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8169014084507041, "eval_TIME_number": 34, "eval_TIME_precision": 0.7837837837837838, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.1309884488582611, "eval_overall_accuracy": 0.9657888259906473, "eval_overall_f1": 0.8423913043478262, "eval_overall_precision": 0.8051948051948052, "eval_overall_recall": 0.8831908831908832, "eval_runtime": 0.3861, "eval_samples_per_second": 484.356, "eval_steps_per_second": 7.77, "step": 3180 }, { "epoch": 31.0, "grad_norm": 0.48864850401878357, "learning_rate": 3.45e-05, "loss": 0.0598, "step": 3286 }, { "epoch": 31.0, "eval_LOCATION_f1": 0.8101265822784809, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7529411764705882, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.7517730496453899, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6973684210526315, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.9025974025974027, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.879746835443038, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.7812500000000001, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8285714285714286, "eval_TIME_number": 34, "eval_TIME_precision": 0.8055555555555556, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.13982480764389038, "eval_overall_accuracy": 0.9635737140044303, "eval_overall_f1": 0.8367071524966261, "eval_overall_precision": 0.7948717948717948, "eval_overall_recall": 0.8831908831908832, "eval_runtime": 0.3844, "eval_samples_per_second": 486.52, "eval_steps_per_second": 7.805, "step": 3286 }, { "epoch": 32.0, "grad_norm": 0.22911441326141357, "learning_rate": 3.4000000000000007e-05, "loss": 0.0598, "step": 3392 }, { "epoch": 32.0, "eval_LOCATION_f1": 0.802547770700637, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7534246575342466, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6790123456790124, "eval_ORGANIZATION_recall": 0.8461538461538461, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.7272727272727273, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.8275862068965517, "eval_TIME_f1": 0.8055555555555555, "eval_TIME_number": 34, "eval_TIME_precision": 0.7631578947368421, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.14981552958488464, "eval_overall_accuracy": 0.9608663549101649, "eval_overall_f1": 0.824468085106383, "eval_overall_precision": 0.773067331670823, "eval_overall_recall": 0.8831908831908832, "eval_runtime": 0.3854, "eval_samples_per_second": 485.203, "eval_steps_per_second": 7.784, "step": 3392 }, { "epoch": 33.0, "grad_norm": 0.9966171979904175, "learning_rate": 3.35e-05, "loss": 0.0607, "step": 3498 }, { "epoch": 33.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7922077922077922, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.76056338028169, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.7012987012987013, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8910256410256411, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8580246913580247, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.8253968253968255, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14727307856082916, "eval_overall_accuracy": 0.9625892197883338, "eval_overall_f1": 0.8389715832205684, "eval_overall_precision": 0.7989690721649485, "eval_overall_recall": 0.8831908831908832, "eval_runtime": 0.3862, "eval_samples_per_second": 484.264, "eval_steps_per_second": 7.769, "step": 3498 }, { "epoch": 34.0, "grad_norm": 1.1382331848144531, "learning_rate": 3.3e-05, "loss": 0.0583, "step": 3604 }, { "epoch": 34.0, "eval_LOCATION_f1": 0.8400000000000001, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7659574468085107, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.7105263157894737, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.887459807073955, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8571428571428571, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.8253968253968255, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.861111111111111, "eval_TIME_number": 34, "eval_TIME_precision": 0.8157894736842105, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.14073994755744934, "eval_overall_accuracy": 0.9670194437607679, "eval_overall_f1": 0.8466757123473541, "eval_overall_precision": 0.8082901554404145, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.3852, "eval_samples_per_second": 485.414, "eval_steps_per_second": 7.787, "step": 3604 }, { "epoch": 35.0, "grad_norm": 0.9959651231765747, "learning_rate": 3.2500000000000004e-05, "loss": 0.0558, "step": 3710 }, { "epoch": 35.0, "eval_LOCATION_f1": 0.8051948051948052, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7654320987654321, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.757142857142857, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.7066666666666667, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8838709677419355, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.85625, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.7812500000000001, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8857142857142858, "eval_TIME_number": 34, "eval_TIME_precision": 0.8611111111111112, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.14661699533462524, "eval_overall_accuracy": 0.9635737140044303, "eval_overall_f1": 0.8346883468834689, "eval_overall_precision": 0.7958656330749354, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3862, "eval_samples_per_second": 484.19, "eval_steps_per_second": 7.768, "step": 3710 }, { "epoch": 36.0, "grad_norm": 1.7864693403244019, "learning_rate": 3.2000000000000005e-05, "loss": 0.0562, "step": 3816 }, { "epoch": 36.0, "eval_LOCATION_f1": 0.8026315789473685, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.7482993197278912, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6707317073170732, "eval_ORGANIZATION_recall": 0.8461538461538461, "eval_PERSON_f1": 0.8838709677419355, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.85625, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.7999999999999999, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8219178082191781, "eval_TIME_number": 34, "eval_TIME_precision": 0.7692307692307693, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1466834545135498, "eval_overall_accuracy": 0.9625892197883338, "eval_overall_f1": 0.8273092369477911, "eval_overall_precision": 0.7803030303030303, "eval_overall_recall": 0.8803418803418803, "eval_runtime": 0.3864, "eval_samples_per_second": 483.938, "eval_steps_per_second": 7.764, "step": 3816 }, { "epoch": 37.0, "grad_norm": 0.5526124238967896, "learning_rate": 3.15e-05, "loss": 0.0548, "step": 3922 }, { "epoch": 37.0, "eval_LOCATION_f1": 0.8051948051948052, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7654320987654321, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7346938775510204, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6585365853658537, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8932038834951457, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8679245283018868, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7812500000000001, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8285714285714286, "eval_TIME_number": 34, "eval_TIME_precision": 0.8055555555555556, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.15039868652820587, "eval_overall_accuracy": 0.9613586020182131, "eval_overall_f1": 0.8279569892473119, "eval_overall_precision": 0.7837150127226463, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3877, "eval_samples_per_second": 482.325, "eval_steps_per_second": 7.738, "step": 3922 }, { "epoch": 38.0, "grad_norm": 0.6235684156417847, "learning_rate": 3.1e-05, "loss": 0.0528, "step": 4028 }, { "epoch": 38.0, "eval_LOCATION_f1": 0.8435374149659863, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8378378378378378, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7313432835820897, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.7101449275362319, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8867313915857605, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8616352201257862, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.75, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6857142857142857, "eval_QUANTITY_recall": 0.8275862068965517, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 34, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14205525815486908, "eval_overall_accuracy": 0.9638198375584544, "eval_overall_f1": 0.8342541436464089, "eval_overall_precision": 0.8096514745308311, "eval_overall_recall": 0.8603988603988604, "eval_runtime": 0.3858, "eval_samples_per_second": 484.723, "eval_steps_per_second": 7.776, "step": 4028 }, { "epoch": 39.0, "grad_norm": 0.9376897811889648, "learning_rate": 3.05e-05, "loss": 0.0504, "step": 4134 }, { "epoch": 39.0, "eval_LOCATION_f1": 0.8496732026143791, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8125, "eval_LOCATION_recall": 0.8904109589041096, "eval_ORGANIZATION_f1": 0.76056338028169, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.7012987012987013, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8903225806451613, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8625, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.71875, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6571428571428571, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.8219178082191781, "eval_TIME_number": 34, "eval_TIME_precision": 0.7692307692307693, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1570240557193756, "eval_overall_accuracy": 0.9628353433423579, "eval_overall_f1": 0.8355795148247979, "eval_overall_precision": 0.7928388746803069, "eval_overall_recall": 0.8831908831908832, "eval_runtime": 0.394, "eval_samples_per_second": 474.609, "eval_steps_per_second": 7.614, "step": 4134 }, { "epoch": 40.0, "grad_norm": 0.5903038382530212, "learning_rate": 3e-05, "loss": 0.053, "step": 4240 }, { "epoch": 40.0, "eval_LOCATION_f1": 0.8366013071895425, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.7236842105263158, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.632183908045977, "eval_ORGANIZATION_recall": 0.8461538461538461, "eval_PERSON_f1": 0.8802588996763754, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8553459119496856, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.7812500000000001, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8732394366197184, "eval_TIME_number": 34, "eval_TIME_precision": 0.8378378378378378, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.15270885825157166, "eval_overall_accuracy": 0.9613586020182131, "eval_overall_f1": 0.8304405874499333, "eval_overall_precision": 0.7814070351758794, "eval_overall_recall": 0.886039886039886, "eval_runtime": 0.3873, "eval_samples_per_second": 482.792, "eval_steps_per_second": 7.745, "step": 4240 }, { "epoch": 41.0, "grad_norm": 0.2513221204280853, "learning_rate": 2.95e-05, "loss": 0.0469, "step": 4346 }, { "epoch": 41.0, "eval_LOCATION_f1": 0.8516129032258065, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8048780487804879, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.75, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6835443037974683, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8774193548387097, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.85, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.6956521739130435, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.8275862068965517, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.15680240094661713, "eval_overall_accuracy": 0.9593896135860202, "eval_overall_f1": 0.8266666666666667, "eval_overall_precision": 0.7769423558897243, "eval_overall_recall": 0.8831908831908832, "eval_runtime": 0.3855, "eval_samples_per_second": 485.071, "eval_steps_per_second": 7.782, "step": 4346 }, { "epoch": 42.0, "grad_norm": 0.4710911512374878, "learning_rate": 2.9e-05, "loss": 0.0487, "step": 4452 }, { "epoch": 42.0, "eval_LOCATION_f1": 0.8666666666666666, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8441558441558441, "eval_LOCATION_recall": 0.8904109589041096, "eval_ORGANIZATION_f1": 0.7517730496453899, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6973684210526315, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8896103896103896, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8670886075949367, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.696969696969697, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6216216216216216, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.861111111111111, "eval_TIME_number": 34, "eval_TIME_precision": 0.8157894736842105, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.14796730875968933, "eval_overall_accuracy": 0.9628353433423579, "eval_overall_f1": 0.8385345997286296, "eval_overall_precision": 0.8005181347150259, "eval_overall_recall": 0.8803418803418803, "eval_runtime": 0.3852, "eval_samples_per_second": 485.429, "eval_steps_per_second": 7.788, "step": 4452 }, { "epoch": 43.0, "grad_norm": 0.774330198764801, "learning_rate": 2.8499999999999998e-05, "loss": 0.0463, "step": 4558 }, { "epoch": 43.0, "eval_LOCATION_f1": 0.8400000000000001, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7310344827586207, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6625, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8838709677419355, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.85625, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.8450704225352113, "eval_TIME_number": 34, "eval_TIME_precision": 0.8108108108108109, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.154840350151062, "eval_overall_accuracy": 0.9618508491262614, "eval_overall_f1": 0.8259109311740892, "eval_overall_precision": 0.7846153846153846, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.3873, "eval_samples_per_second": 482.887, "eval_steps_per_second": 7.747, "step": 4558 }, { "epoch": 44.0, "grad_norm": 0.41449031233787537, "learning_rate": 2.8000000000000003e-05, "loss": 0.0459, "step": 4664 }, { "epoch": 44.0, "eval_LOCATION_f1": 0.8456375838926175, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8289473684210527, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7692307692307693, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.7051282051282052, "eval_ORGANIZATION_recall": 0.8461538461538461, "eval_PERSON_f1": 0.8996763754045306, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8742138364779874, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.7868852459016394, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.8275862068965517, "eval_TIME_f1": 0.8732394366197184, "eval_TIME_number": 34, "eval_TIME_precision": 0.8378378378378378, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.15145742893218994, "eval_overall_accuracy": 0.9662810730986956, "eval_overall_f1": 0.8512960436562074, "eval_overall_precision": 0.8167539267015707, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.3853, "eval_samples_per_second": 485.335, "eval_steps_per_second": 7.786, "step": 4664 }, { "epoch": 45.0, "grad_norm": 2.1948015689849854, "learning_rate": 2.7500000000000004e-05, "loss": 0.0454, "step": 4770 }, { "epoch": 45.0, "eval_LOCATION_f1": 0.8609271523178808, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8333333333333334, "eval_LOCATION_recall": 0.8904109589041096, "eval_ORGANIZATION_f1": 0.702290076335878, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.696969696969697, "eval_ORGANIZATION_recall": 0.7076923076923077, "eval_PERSON_f1": 0.9025974025974027, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.879746835443038, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.8524590163934426, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8732394366197184, "eval_TIME_number": 34, "eval_TIME_precision": 0.8378378378378378, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1515069454908371, "eval_overall_accuracy": 0.9657888259906473, "eval_overall_f1": 0.850415512465374, "eval_overall_precision": 0.8274932614555256, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.3871, "eval_samples_per_second": 483.034, "eval_steps_per_second": 7.749, "step": 4770 }, { "epoch": 46.0, "grad_norm": 0.26949745416641235, "learning_rate": 2.7000000000000002e-05, "loss": 0.0455, "step": 4876 }, { "epoch": 46.0, "eval_LOCATION_f1": 0.8627450980392157, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.825, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7681159420289856, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.726027397260274, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8990228013029316, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8789808917197452, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.8524590163934426, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8732394366197184, "eval_TIME_number": 34, "eval_TIME_precision": 0.8378378378378378, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.14826659858226776, "eval_overall_accuracy": 0.9672655673147921, "eval_overall_f1": 0.8602739726027397, "eval_overall_precision": 0.8284960422163589, "eval_overall_recall": 0.8945868945868946, "eval_runtime": 0.3856, "eval_samples_per_second": 484.938, "eval_steps_per_second": 7.78, "step": 4876 }, { "epoch": 47.0, "grad_norm": 1.137783408164978, "learning_rate": 2.6500000000000004e-05, "loss": 0.0424, "step": 4982 }, { "epoch": 47.0, "eval_LOCATION_f1": 0.8684210526315789, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8354430379746836, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7534246575342466, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6790123456790124, "eval_ORGANIZATION_recall": 0.8461538461538461, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.8524590163934426, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 34, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.15139973163604736, "eval_overall_accuracy": 0.9655427024366232, "eval_overall_f1": 0.8540540540540541, "eval_overall_precision": 0.8123393316195373, "eval_overall_recall": 0.9002849002849003, "eval_runtime": 0.3872, "eval_samples_per_second": 482.907, "eval_steps_per_second": 7.747, "step": 4982 }, { "epoch": 48.0, "grad_norm": 2.368671178817749, "learning_rate": 2.6000000000000002e-05, "loss": 0.0444, "step": 5088 }, { "epoch": 48.0, "eval_LOCATION_f1": 0.8741721854304636, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8461538461538461, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7611940298507462, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.7391304347826086, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8932038834951457, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8679245283018868, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7272727272727273, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.8275862068965517, "eval_TIME_f1": 0.8055555555555555, "eval_TIME_number": 34, "eval_TIME_precision": 0.7631578947368421, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.15529875457286835, "eval_overall_accuracy": 0.965296578882599, "eval_overall_f1": 0.8415300546448087, "eval_overall_precision": 0.8083989501312336, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3834, "eval_samples_per_second": 487.749, "eval_steps_per_second": 7.825, "step": 5088 }, { "epoch": 49.0, "grad_norm": 0.1998334676027298, "learning_rate": 2.5500000000000003e-05, "loss": 0.0427, "step": 5194 }, { "epoch": 49.0, "eval_LOCATION_f1": 0.88, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8571428571428571, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7972027972027972, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.7307692307692307, "eval_ORGANIZATION_recall": 0.8769230769230769, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.86875, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.8064516129032258, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.15635553002357483, "eval_overall_accuracy": 0.965296578882599, "eval_overall_f1": 0.8602442333785618, "eval_overall_precision": 0.8212435233160622, "eval_overall_recall": 0.9031339031339032, "eval_runtime": 0.3863, "eval_samples_per_second": 484.136, "eval_steps_per_second": 7.767, "step": 5194 }, { "epoch": 50.0, "grad_norm": 0.9808441996574402, "learning_rate": 2.5e-05, "loss": 0.041, "step": 5300 }, { "epoch": 50.0, "eval_LOCATION_f1": 0.855263157894737, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8227848101265823, "eval_LOCATION_recall": 0.8904109589041096, "eval_ORGANIZATION_f1": 0.7857142857142856, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.7333333333333333, "eval_ORGANIZATION_recall": 0.8461538461538461, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.875, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.8196721311475409, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.78125, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.15144038200378418, "eval_overall_accuracy": 0.9660349495446714, "eval_overall_f1": 0.8571428571428573, "eval_overall_precision": 0.8203125, "eval_overall_recall": 0.8974358974358975, "eval_runtime": 0.3897, "eval_samples_per_second": 479.861, "eval_steps_per_second": 7.698, "step": 5300 }, { "epoch": 51.0, "grad_norm": 0.43952253460884094, "learning_rate": 2.45e-05, "loss": 0.0416, "step": 5406 }, { "epoch": 51.0, "eval_LOCATION_f1": 0.858974358974359, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8072289156626506, "eval_LOCATION_recall": 0.9178082191780822, "eval_ORGANIZATION_f1": 0.7246376811594203, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.684931506849315, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.8524590163934426, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1590029001235962, "eval_overall_accuracy": 0.9650504553285749, "eval_overall_f1": 0.8405405405405405, "eval_overall_precision": 0.7994858611825193, "eval_overall_recall": 0.886039886039886, "eval_runtime": 0.3875, "eval_samples_per_second": 482.58, "eval_steps_per_second": 7.742, "step": 5406 }, { "epoch": 52.0, "grad_norm": 0.5576232075691223, "learning_rate": 2.4e-05, "loss": 0.0398, "step": 5512 }, { "epoch": 52.0, "eval_LOCATION_f1": 0.8741721854304636, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8461538461538461, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7516778523489933, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8615384615384616, "eval_PERSON_f1": 0.8910256410256411, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8580246913580247, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.16141797602176666, "eval_overall_accuracy": 0.9648043317745508, "eval_overall_f1": 0.8498659517426275, "eval_overall_precision": 0.8025316455696202, "eval_overall_recall": 0.9031339031339032, "eval_runtime": 0.3872, "eval_samples_per_second": 483.005, "eval_steps_per_second": 7.749, "step": 5512 }, { "epoch": 53.0, "grad_norm": 0.973469078540802, "learning_rate": 2.35e-05, "loss": 0.0404, "step": 5618 }, { "epoch": 53.0, "eval_LOCATION_f1": 0.8684210526315789, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8354430379746836, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7552447552447553, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6923076923076923, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.9067524115755627, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8757763975155279, "eval_PERSON_recall": 0.94, "eval_QUANTITY_f1": 0.7812500000000001, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1627216637134552, "eval_overall_accuracy": 0.963081466896382, "eval_overall_f1": 0.8517520215633424, "eval_overall_precision": 0.8081841432225064, "eval_overall_recall": 0.9002849002849003, "eval_runtime": 0.387, "eval_samples_per_second": 483.151, "eval_steps_per_second": 7.751, "step": 5618 }, { "epoch": 54.0, "grad_norm": 0.923568606376648, "learning_rate": 2.3000000000000003e-05, "loss": 0.0405, "step": 5724 }, { "epoch": 54.0, "eval_LOCATION_f1": 0.8684210526315789, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8354430379746836, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7361111111111112, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6708860759493671, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8996763754045306, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8742138364779874, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.15863551199436188, "eval_overall_accuracy": 0.9660349495446714, "eval_overall_f1": 0.8497970230040596, "eval_overall_precision": 0.8092783505154639, "eval_overall_recall": 0.8945868945868946, "eval_runtime": 0.385, "eval_samples_per_second": 485.707, "eval_steps_per_second": 7.792, "step": 5724 }, { "epoch": 55.0, "grad_norm": 0.5156478881835938, "learning_rate": 2.25e-05, "loss": 0.037, "step": 5830 }, { "epoch": 55.0, "eval_LOCATION_f1": 0.8441558441558442, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8024691358024691, "eval_LOCATION_recall": 0.8904109589041096, "eval_ORGANIZATION_f1": 0.7338129496402878, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6891891891891891, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8810289389067525, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8509316770186336, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.16379383206367493, "eval_overall_accuracy": 0.9618508491262614, "eval_overall_f1": 0.8313090418353576, "eval_overall_precision": 0.7897435897435897, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3857, "eval_samples_per_second": 484.839, "eval_steps_per_second": 7.778, "step": 5830 }, { "epoch": 56.0, "grad_norm": 1.4201856851577759, "learning_rate": 2.2000000000000003e-05, "loss": 0.0367, "step": 5936 }, { "epoch": 56.0, "eval_LOCATION_f1": 0.8513513513513513, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.84, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7391304347826088, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6986301369863014, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8846153846153846, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8518518518518519, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7936507936507937, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.861111111111111, "eval_TIME_number": 34, "eval_TIME_precision": 0.8157894736842105, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.15849658846855164, "eval_overall_accuracy": 0.9648043317745508, "eval_overall_f1": 0.840381991814461, "eval_overall_precision": 0.806282722513089, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3861, "eval_samples_per_second": 484.373, "eval_steps_per_second": 7.771, "step": 5936 }, { "epoch": 57.0, "grad_norm": 0.06779062002897263, "learning_rate": 2.15e-05, "loss": 0.0387, "step": 6042 }, { "epoch": 57.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8513513513513513, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7482014388489208, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.7027027027027027, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8932038834951457, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8679245283018868, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.8253968253968255, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8857142857142858, "eval_TIME_number": 34, "eval_TIME_precision": 0.8611111111111112, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.15448686480522156, "eval_overall_accuracy": 0.9662810730986956, "eval_overall_f1": 0.8516483516483517, "eval_overall_precision": 0.8222811671087533, "eval_overall_recall": 0.8831908831908832, "eval_runtime": 0.3872, "eval_samples_per_second": 482.965, "eval_steps_per_second": 7.748, "step": 6042 }, { "epoch": 58.0, "grad_norm": 0.30816060304641724, "learning_rate": 2.1e-05, "loss": 0.0371, "step": 6148 }, { "epoch": 58.0, "eval_LOCATION_f1": 0.8741721854304636, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8461538461538461, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8774193548387097, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.85, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.7936507936507937, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8450704225352113, "eval_TIME_number": 34, "eval_TIME_precision": 0.8108108108108109, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.16250932216644287, "eval_overall_accuracy": 0.963081466896382, "eval_overall_f1": 0.8358208955223881, "eval_overall_precision": 0.7979274611398963, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3844, "eval_samples_per_second": 486.46, "eval_steps_per_second": 7.804, "step": 6148 }, { "epoch": 59.0, "grad_norm": 0.8676481246948242, "learning_rate": 2.05e-05, "loss": 0.0354, "step": 6254 }, { "epoch": 59.0, "eval_LOCATION_f1": 0.8741721854304636, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8461538461538461, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7391304347826088, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6986301369863014, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8810289389067525, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8509316770186336, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.8253968253968255, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8732394366197184, "eval_TIME_number": 34, "eval_TIME_precision": 0.8378378378378378, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.16529938578605652, "eval_overall_accuracy": 0.965296578882599, "eval_overall_f1": 0.8474114441416893, "eval_overall_precision": 0.8120104438642297, "eval_overall_recall": 0.886039886039886, "eval_runtime": 0.3865, "eval_samples_per_second": 483.887, "eval_steps_per_second": 7.763, "step": 6254 }, { "epoch": 60.0, "grad_norm": 0.16957683861255646, "learning_rate": 2e-05, "loss": 0.0363, "step": 6360 }, { "epoch": 60.0, "eval_LOCATION_f1": 0.88, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8571428571428571, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7375886524822695, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6842105263157895, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8846153846153846, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8518518518518519, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.8524590163934426, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8857142857142858, "eval_TIME_number": 34, "eval_TIME_precision": 0.8611111111111112, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.16163839399814606, "eval_overall_accuracy": 0.9655427024366232, "eval_overall_f1": 0.8528610354223433, "eval_overall_precision": 0.8172323759791122, "eval_overall_recall": 0.8917378917378918, "eval_runtime": 0.3845, "eval_samples_per_second": 486.366, "eval_steps_per_second": 7.803, "step": 6360 }, { "epoch": 61.0, "grad_norm": 0.5314693450927734, "learning_rate": 1.9500000000000003e-05, "loss": 0.0333, "step": 6466 }, { "epoch": 61.0, "eval_LOCATION_f1": 0.847682119205298, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.7027027027027027, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6265060240963856, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.887459807073955, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8571428571428571, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.8253968253968255, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.17665402591228485, "eval_overall_accuracy": 0.9623430962343096, "eval_overall_f1": 0.8322147651006713, "eval_overall_precision": 0.7868020304568528, "eval_overall_recall": 0.8831908831908832, "eval_runtime": 0.3866, "eval_samples_per_second": 483.688, "eval_steps_per_second": 7.76, "step": 6466 }, { "epoch": 62.0, "grad_norm": 0.8911972641944885, "learning_rate": 1.9e-05, "loss": 0.0324, "step": 6572 }, { "epoch": 62.0, "eval_LOCATION_f1": 0.8456375838926175, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8289473684210527, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7464788732394366, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6883116883116883, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.9090909090909091, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8450704225352113, "eval_TIME_number": 34, "eval_TIME_precision": 0.8108108108108109, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.16479013860225677, "eval_overall_accuracy": 0.965296578882599, "eval_overall_f1": 0.8524590163934426, "eval_overall_precision": 0.8188976377952756, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.3851, "eval_samples_per_second": 485.634, "eval_steps_per_second": 7.791, "step": 6572 }, { "epoch": 63.0, "grad_norm": 1.928049087524414, "learning_rate": 1.85e-05, "loss": 0.0364, "step": 6678 }, { "epoch": 63.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8533333333333334, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.7586206896551724, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6875, "eval_ORGANIZATION_recall": 0.8461538461538461, "eval_PERSON_f1": 0.8903225806451613, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8625, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.8524590163934426, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8857142857142858, "eval_TIME_number": 34, "eval_TIME_precision": 0.8611111111111112, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.16289159655570984, "eval_overall_accuracy": 0.9650504553285749, "eval_overall_f1": 0.8555858310626703, "eval_overall_precision": 0.8198433420365535, "eval_overall_recall": 0.8945868945868946, "eval_runtime": 0.3875, "eval_samples_per_second": 482.637, "eval_steps_per_second": 7.743, "step": 6678 }, { "epoch": 64.0, "grad_norm": 0.33195340633392334, "learning_rate": 1.8e-05, "loss": 0.034, "step": 6784 }, { "epoch": 64.0, "eval_LOCATION_f1": 0.8571428571428571, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8148148148148148, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.6616541353383458, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6470588235294118, "eval_ORGANIZATION_recall": 0.676923076923077, "eval_PERSON_f1": 0.8802588996763754, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8553459119496856, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8857142857142858, "eval_TIME_number": 34, "eval_TIME_precision": 0.8611111111111112, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1654130518436432, "eval_overall_accuracy": 0.9638198375584544, "eval_overall_f1": 0.8324175824175825, "eval_overall_precision": 0.8037135278514589, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.3842, "eval_samples_per_second": 486.754, "eval_steps_per_second": 7.809, "step": 6784 }, { "epoch": 65.0, "grad_norm": 0.7465774416923523, "learning_rate": 1.75e-05, "loss": 0.0325, "step": 6890 }, { "epoch": 65.0, "eval_LOCATION_f1": 0.8724832214765101, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8552631578947368, "eval_LOCATION_recall": 0.8904109589041096, "eval_ORGANIZATION_f1": 0.7428571428571429, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6933333333333334, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.887459807073955, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8571428571428571, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.8064516129032258, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8219178082191781, "eval_TIME_number": 34, "eval_TIME_precision": 0.7692307692307693, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1645297259092331, "eval_overall_accuracy": 0.9665271966527197, "eval_overall_f1": 0.8435374149659863, "eval_overall_precision": 0.8072916666666666, "eval_overall_recall": 0.8831908831908832, "eval_runtime": 0.3854, "eval_samples_per_second": 485.217, "eval_steps_per_second": 7.784, "step": 6890 }, { "epoch": 66.0, "grad_norm": 2.1847379207611084, "learning_rate": 1.7000000000000003e-05, "loss": 0.0322, "step": 6996 }, { "epoch": 66.0, "eval_LOCATION_f1": 0.8571428571428571, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8148148148148148, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7272727272727272, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.86875, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.8524590163934426, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1727007031440735, "eval_overall_accuracy": 0.9645582082205267, "eval_overall_f1": 0.845945945945946, "eval_overall_precision": 0.8046272493573264, "eval_overall_recall": 0.8917378917378918, "eval_runtime": 0.3859, "eval_samples_per_second": 484.618, "eval_steps_per_second": 7.775, "step": 6996 }, { "epoch": 67.0, "grad_norm": 0.15823009610176086, "learning_rate": 1.65e-05, "loss": 0.0314, "step": 7102 }, { "epoch": 67.0, "eval_LOCATION_f1": 0.8741721854304636, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8461538461538461, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7014925373134329, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6811594202898551, "eval_ORGANIZATION_recall": 0.7230769230769231, "eval_PERSON_f1": 0.896103896103896, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8734177215189873, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7936507936507937, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.7945205479452054, "eval_TIME_number": 34, "eval_TIME_precision": 0.7435897435897436, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.16559243202209473, "eval_overall_accuracy": 0.9643120846665025, "eval_overall_f1": 0.8367626886145405, "eval_overall_precision": 0.8068783068783069, "eval_overall_recall": 0.8689458689458689, "eval_runtime": 0.3883, "eval_samples_per_second": 481.631, "eval_steps_per_second": 7.727, "step": 7102 }, { "epoch": 68.0, "grad_norm": 0.8872466087341309, "learning_rate": 1.6000000000000003e-05, "loss": 0.0313, "step": 7208 }, { "epoch": 68.0, "eval_LOCATION_f1": 0.8724832214765101, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8552631578947368, "eval_LOCATION_recall": 0.8904109589041096, "eval_ORGANIZATION_f1": 0.7464788732394366, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6883116883116883, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8831168831168831, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8607594936708861, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.7936507936507937, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8055555555555555, "eval_TIME_number": 34, "eval_TIME_precision": 0.7631578947368421, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.17109757661819458, "eval_overall_accuracy": 0.9643120846665025, "eval_overall_f1": 0.8392370572207084, "eval_overall_precision": 0.804177545691906, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3857, "eval_samples_per_second": 484.796, "eval_steps_per_second": 7.777, "step": 7208 }, { "epoch": 69.0, "grad_norm": 0.13313980400562286, "learning_rate": 1.55e-05, "loss": 0.0319, "step": 7314 }, { "epoch": 69.0, "eval_LOCATION_f1": 0.8666666666666666, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8441558441558441, "eval_LOCATION_recall": 0.8904109589041096, "eval_ORGANIZATION_f1": 0.7671232876712328, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.691358024691358, "eval_ORGANIZATION_recall": 0.8615384615384616, "eval_PERSON_f1": 0.8802588996763754, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8553459119496856, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.8196721311475409, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.78125, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.17586369812488556, "eval_overall_accuracy": 0.9628353433423579, "eval_overall_f1": 0.8455284552845528, "eval_overall_precision": 0.8062015503875969, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.3855, "eval_samples_per_second": 485.143, "eval_steps_per_second": 7.783, "step": 7314 }, { "epoch": 70.0, "grad_norm": 0.6439195871353149, "learning_rate": 1.5e-05, "loss": 0.0303, "step": 7420 }, { "epoch": 70.0, "eval_LOCATION_f1": 0.8724832214765101, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8552631578947368, "eval_LOCATION_recall": 0.8904109589041096, "eval_ORGANIZATION_f1": 0.7428571428571429, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6933333333333334, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.86875, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.7936507936507937, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8219178082191781, "eval_TIME_number": 34, "eval_TIME_precision": 0.7692307692307693, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1740642637014389, "eval_overall_accuracy": 0.9635737140044303, "eval_overall_f1": 0.8462585034013606, "eval_overall_precision": 0.8098958333333334, "eval_overall_recall": 0.886039886039886, "eval_runtime": 0.3882, "eval_samples_per_second": 481.683, "eval_steps_per_second": 7.728, "step": 7420 }, { "epoch": 71.0, "grad_norm": 1.417320728302002, "learning_rate": 1.45e-05, "loss": 0.0299, "step": 7526 }, { "epoch": 71.0, "eval_LOCATION_f1": 0.8741721854304636, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8461538461538461, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7552447552447553, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6923076923076923, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8996763754045306, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8742138364779874, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.8196721311475409, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.78125, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8732394366197184, "eval_TIME_number": 34, "eval_TIME_precision": 0.8378378378378378, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.17045490443706512, "eval_overall_accuracy": 0.9650504553285749, "eval_overall_f1": 0.8571428571428573, "eval_overall_precision": 0.8203125, "eval_overall_recall": 0.8974358974358975, "eval_runtime": 0.389, "eval_samples_per_second": 480.776, "eval_steps_per_second": 7.713, "step": 7526 }, { "epoch": 72.0, "grad_norm": 0.37806442379951477, "learning_rate": 1.4000000000000001e-05, "loss": 0.0289, "step": 7632 }, { "epoch": 72.0, "eval_LOCATION_f1": 0.855263157894737, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8227848101265823, "eval_LOCATION_recall": 0.8904109589041096, "eval_ORGANIZATION_f1": 0.7246376811594203, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.684931506849315, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8810289389067525, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8509316770186336, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.8196721311475409, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.78125, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1736210733652115, "eval_overall_accuracy": 0.9635737140044303, "eval_overall_f1": 0.8365122615803815, "eval_overall_precision": 0.8015665796344648, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.3865, "eval_samples_per_second": 483.842, "eval_steps_per_second": 7.762, "step": 7632 }, { "epoch": 73.0, "grad_norm": 0.2804931700229645, "learning_rate": 1.3500000000000001e-05, "loss": 0.029, "step": 7738 }, { "epoch": 73.0, "eval_LOCATION_f1": 0.8590604026845637, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8421052631578947, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.76056338028169, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.7012987012987013, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8996763754045306, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8742138364779874, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.8064516129032258, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1748729646205902, "eval_overall_accuracy": 0.9648043317745508, "eval_overall_f1": 0.8501362397820162, "eval_overall_precision": 0.814621409921671, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.3874, "eval_samples_per_second": 482.759, "eval_steps_per_second": 7.745, "step": 7738 }, { "epoch": 74.0, "grad_norm": 0.4218845069408417, "learning_rate": 1.3000000000000001e-05, "loss": 0.0271, "step": 7844 }, { "epoch": 74.0, "eval_LOCATION_f1": 0.8724832214765101, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8552631578947368, "eval_LOCATION_recall": 0.8904109589041096, "eval_ORGANIZATION_f1": 0.7536231884057971, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.7123287671232876, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8996763754045306, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8742138364779874, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.8196721311475409, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.78125, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.17355231940746307, "eval_overall_accuracy": 0.9667733202067438, "eval_overall_f1": 0.8532235939643347, "eval_overall_precision": 0.8227513227513228, "eval_overall_recall": 0.886039886039886, "eval_runtime": 0.3863, "eval_samples_per_second": 484.063, "eval_steps_per_second": 7.766, "step": 7844 }, { "epoch": 75.0, "grad_norm": 0.338538259267807, "learning_rate": 1.25e-05, "loss": 0.0283, "step": 7950 }, { "epoch": 75.0, "eval_LOCATION_f1": 0.8684210526315789, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8354430379746836, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7464788732394366, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6883116883116883, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.9061488673139159, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8805031446540881, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.8064516129032258, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8450704225352113, "eval_TIME_number": 34, "eval_TIME_precision": 0.8108108108108109, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.17770251631736755, "eval_overall_accuracy": 0.9643120846665025, "eval_overall_f1": 0.8532608695652173, "eval_overall_precision": 0.8155844155844156, "eval_overall_recall": 0.8945868945868946, "eval_runtime": 0.3884, "eval_samples_per_second": 481.456, "eval_steps_per_second": 7.724, "step": 7950 }, { "epoch": 76.0, "grad_norm": 0.8112855553627014, "learning_rate": 1.2e-05, "loss": 0.0292, "step": 8056 }, { "epoch": 76.0, "eval_LOCATION_f1": 0.8741721854304636, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8461538461538461, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7534246575342466, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6790123456790124, "eval_ORGANIZATION_recall": 0.8461538461538461, "eval_PERSON_f1": 0.9096774193548387, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.88125, "eval_PERSON_recall": 0.94, "eval_QUANTITY_f1": 0.7936507936507937, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1849164366722107, "eval_overall_accuracy": 0.9638198375584544, "eval_overall_f1": 0.8544474393530996, "eval_overall_precision": 0.8107416879795396, "eval_overall_recall": 0.9031339031339032, "eval_runtime": 0.3868, "eval_samples_per_second": 483.423, "eval_steps_per_second": 7.755, "step": 8056 }, { "epoch": 77.0, "grad_norm": 0.6936742067337036, "learning_rate": 1.1500000000000002e-05, "loss": 0.0287, "step": 8162 }, { "epoch": 77.0, "eval_LOCATION_f1": 0.8724832214765101, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8552631578947368, "eval_LOCATION_recall": 0.8904109589041096, "eval_ORGANIZATION_f1": 0.7552447552447553, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6923076923076923, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.9025974025974027, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.879746835443038, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.7936507936507937, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.17852583527565002, "eval_overall_accuracy": 0.9640659611124784, "eval_overall_f1": 0.8517006802721088, "eval_overall_precision": 0.8151041666666666, "eval_overall_recall": 0.8917378917378918, "eval_runtime": 0.385, "eval_samples_per_second": 485.697, "eval_steps_per_second": 7.792, "step": 8162 }, { "epoch": 78.0, "grad_norm": 0.9536997675895691, "learning_rate": 1.1000000000000001e-05, "loss": 0.0258, "step": 8268 }, { "epoch": 78.0, "eval_LOCATION_f1": 0.870748299319728, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8648648648648649, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.7647058823529411, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.7323943661971831, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8925081433224756, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8726114649681529, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.8196721311475409, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.78125, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 34, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.17140330374240875, "eval_overall_accuracy": 0.9662810730986956, "eval_overall_f1": 0.854368932038835, "eval_overall_precision": 0.8324324324324325, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3856, "eval_samples_per_second": 484.945, "eval_steps_per_second": 7.78, "step": 8268 }, { "epoch": 79.0, "grad_norm": 0.6820342540740967, "learning_rate": 1.05e-05, "loss": 0.0275, "step": 8374 }, { "epoch": 79.0, "eval_LOCATION_f1": 0.8741721854304636, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8461538461538461, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8932038834951457, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8679245283018868, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7812500000000001, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.17593428492546082, "eval_overall_accuracy": 0.9628353433423579, "eval_overall_f1": 0.8401084010840107, "eval_overall_precision": 0.8010335917312662, "eval_overall_recall": 0.8831908831908832, "eval_runtime": 0.3861, "eval_samples_per_second": 484.292, "eval_steps_per_second": 7.769, "step": 8374 }, { "epoch": 80.0, "grad_norm": 0.6609770655632019, "learning_rate": 1e-05, "loss": 0.0288, "step": 8480 }, { "epoch": 80.0, "eval_LOCATION_f1": 0.8859060402684564, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.868421052631579, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7285714285714285, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.68, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.9025974025974027, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.879746835443038, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.8524590163934426, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.17412517964839935, "eval_overall_accuracy": 0.9640659611124784, "eval_overall_f1": 0.854794520547945, "eval_overall_precision": 0.8232189973614775, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.3848, "eval_samples_per_second": 485.904, "eval_steps_per_second": 7.795, "step": 8480 }, { "epoch": 81.0, "grad_norm": 0.8274201154708862, "learning_rate": 9.5e-06, "loss": 0.0283, "step": 8586 }, { "epoch": 81.0, "eval_LOCATION_f1": 0.8741721854304636, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8461538461538461, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7536231884057971, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.7123287671232876, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.887459807073955, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8571428571428571, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7812500000000001, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.17435409128665924, "eval_overall_accuracy": 0.9635737140044303, "eval_overall_f1": 0.8451086956521738, "eval_overall_precision": 0.8077922077922078, "eval_overall_recall": 0.886039886039886, "eval_runtime": 0.3852, "eval_samples_per_second": 485.468, "eval_steps_per_second": 7.788, "step": 8586 }, { "epoch": 82.0, "grad_norm": 1.3721864223480225, "learning_rate": 9e-06, "loss": 0.027, "step": 8692 }, { "epoch": 82.0, "eval_LOCATION_f1": 0.855263157894737, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8227848101265823, "eval_LOCATION_recall": 0.8904109589041096, "eval_ORGANIZATION_f1": 0.7285714285714285, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.68, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8990228013029316, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8789808917197452, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.861111111111111, "eval_TIME_number": 34, "eval_TIME_precision": 0.8157894736842105, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.17581164836883545, "eval_overall_accuracy": 0.9643120846665025, "eval_overall_f1": 0.8485675306957708, "eval_overall_precision": 0.8141361256544503, "eval_overall_recall": 0.886039886039886, "eval_runtime": 0.3868, "eval_samples_per_second": 483.477, "eval_steps_per_second": 7.756, "step": 8692 }, { "epoch": 83.0, "grad_norm": 1.29371178150177, "learning_rate": 8.500000000000002e-06, "loss": 0.0254, "step": 8798 }, { "epoch": 83.0, "eval_LOCATION_f1": 0.8533333333333334, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8311688311688312, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.7222222222222222, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6582278481012658, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.896103896103896, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8734177215189873, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7812500000000001, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.18245863914489746, "eval_overall_accuracy": 0.9628353433423579, "eval_overall_f1": 0.8373983739837397, "eval_overall_precision": 0.7984496124031008, "eval_overall_recall": 0.8803418803418803, "eval_runtime": 0.384, "eval_samples_per_second": 487.005, "eval_steps_per_second": 7.813, "step": 8798 }, { "epoch": 84.0, "grad_norm": 0.759432852268219, "learning_rate": 8.000000000000001e-06, "loss": 0.0267, "step": 8904 }, { "epoch": 84.0, "eval_LOCATION_f1": 0.8684210526315789, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8354430379746836, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7412587412587412, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6794871794871795, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.887459807073955, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8571428571428571, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7812500000000001, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8219178082191781, "eval_TIME_number": 34, "eval_TIME_precision": 0.7692307692307693, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.18526050448417664, "eval_overall_accuracy": 0.9635737140044303, "eval_overall_f1": 0.8398384925975775, "eval_overall_precision": 0.7959183673469388, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.3862, "eval_samples_per_second": 484.175, "eval_steps_per_second": 7.768, "step": 8904 }, { "epoch": 85.0, "grad_norm": 0.7862147092819214, "learning_rate": 7.5e-06, "loss": 0.0244, "step": 9010 }, { "epoch": 85.0, "eval_LOCATION_f1": 0.8627450980392157, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.825, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7142857142857142, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8932038834951457, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8679245283018868, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.8253968253968255, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.18103930354118347, "eval_overall_accuracy": 0.9643120846665025, "eval_overall_f1": 0.8412483039348712, "eval_overall_precision": 0.8031088082901554, "eval_overall_recall": 0.8831908831908832, "eval_runtime": 0.3835, "eval_samples_per_second": 487.614, "eval_steps_per_second": 7.823, "step": 9010 }, { "epoch": 86.0, "grad_norm": 0.45432260632514954, "learning_rate": 7.000000000000001e-06, "loss": 0.0241, "step": 9116 }, { "epoch": 86.0, "eval_LOCATION_f1": 0.881578947368421, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8481012658227848, "eval_LOCATION_recall": 0.9178082191780822, "eval_ORGANIZATION_f1": 0.7313432835820897, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.7101449275362319, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8932038834951457, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8679245283018868, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.8253968253968255, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.17840129137039185, "eval_overall_accuracy": 0.965296578882599, "eval_overall_f1": 0.8493150684931507, "eval_overall_precision": 0.8179419525065963, "eval_overall_recall": 0.8831908831908832, "eval_runtime": 0.3896, "eval_samples_per_second": 479.954, "eval_steps_per_second": 7.7, "step": 9116 }, { "epoch": 87.0, "grad_norm": 1.0281379222869873, "learning_rate": 6.5000000000000004e-06, "loss": 0.0257, "step": 9222 }, { "epoch": 87.0, "eval_LOCATION_f1": 0.8758169934640524, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8375, "eval_LOCATION_recall": 0.9178082191780822, "eval_ORGANIZATION_f1": 0.7272727272727272, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.86875, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.7936507936507937, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1823926866054535, "eval_overall_accuracy": 0.9635737140044303, "eval_overall_f1": 0.844804318488529, "eval_overall_precision": 0.8025641025641026, "eval_overall_recall": 0.8917378917378918, "eval_runtime": 0.3857, "eval_samples_per_second": 484.808, "eval_steps_per_second": 7.778, "step": 9222 }, { "epoch": 88.0, "grad_norm": 0.4464998245239258, "learning_rate": 6e-06, "loss": 0.0253, "step": 9328 }, { "epoch": 88.0, "eval_LOCATION_f1": 0.8874172185430463, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8589743589743589, "eval_LOCATION_recall": 0.9178082191780822, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.86875, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.7812500000000001, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.18025493621826172, "eval_overall_accuracy": 0.9640659611124784, "eval_overall_f1": 0.8443843031123139, "eval_overall_precision": 0.8041237113402062, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.3854, "eval_samples_per_second": 485.254, "eval_steps_per_second": 7.785, "step": 9328 }, { "epoch": 89.0, "grad_norm": 1.2788630723953247, "learning_rate": 5.500000000000001e-06, "loss": 0.026, "step": 9434 }, { "epoch": 89.0, "eval_LOCATION_f1": 0.8758169934640524, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8375, "eval_LOCATION_recall": 0.9178082191780822, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.86875, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.75, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6857142857142857, "eval_QUANTITY_recall": 0.8275862068965517, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.18378011882305145, "eval_overall_accuracy": 0.9623430962343096, "eval_overall_f1": 0.8394062078272606, "eval_overall_precision": 0.7974358974358975, "eval_overall_recall": 0.886039886039886, "eval_runtime": 0.3838, "eval_samples_per_second": 487.27, "eval_steps_per_second": 7.817, "step": 9434 }, { "epoch": 90.0, "grad_norm": 0.9298455715179443, "learning_rate": 5e-06, "loss": 0.0246, "step": 9540 }, { "epoch": 90.0, "eval_LOCATION_f1": 0.8933333333333333, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8701298701298701, "eval_LOCATION_recall": 0.9178082191780822, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8903225806451613, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8625, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.896551724137931, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.18070749938488007, "eval_overall_accuracy": 0.9638198375584544, "eval_overall_f1": 0.8478260869565218, "eval_overall_precision": 0.8103896103896104, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.3861, "eval_samples_per_second": 484.354, "eval_steps_per_second": 7.77, "step": 9540 }, { "epoch": 91.0, "grad_norm": 0.9396980404853821, "learning_rate": 4.5e-06, "loss": 0.023, "step": 9646 }, { "epoch": 91.0, "eval_LOCATION_f1": 0.8874172185430463, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8589743589743589, "eval_LOCATION_recall": 0.9178082191780822, "eval_ORGANIZATION_f1": 0.7042253521126761, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6493506493506493, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.9061488673139159, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8805031446540881, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.7936507936507937, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.18405993282794952, "eval_overall_accuracy": 0.9640659611124784, "eval_overall_f1": 0.8466757123473541, "eval_overall_precision": 0.8082901554404145, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.3855, "eval_samples_per_second": 485.096, "eval_steps_per_second": 7.782, "step": 9646 }, { "epoch": 92.0, "grad_norm": 0.77614825963974, "learning_rate": 4.000000000000001e-06, "loss": 0.0235, "step": 9752 }, { "epoch": 92.0, "eval_LOCATION_f1": 0.881578947368421, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8481012658227848, "eval_LOCATION_recall": 0.9178082191780822, "eval_ORGANIZATION_f1": 0.7285714285714285, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.68, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.9061488673139159, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8805031446540881, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.7936507936507937, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.18313735723495483, "eval_overall_accuracy": 0.9648043317745508, "eval_overall_f1": 0.8505434782608695, "eval_overall_precision": 0.812987012987013, "eval_overall_recall": 0.8917378917378918, "eval_runtime": 0.3848, "eval_samples_per_second": 485.911, "eval_steps_per_second": 7.795, "step": 9752 }, { "epoch": 93.0, "grad_norm": 0.6140993237495422, "learning_rate": 3.5000000000000004e-06, "loss": 0.0228, "step": 9858 }, { "epoch": 93.0, "eval_LOCATION_f1": 0.8627450980392157, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.825, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7361111111111112, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6708860759493671, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.9061488673139159, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8805031446540881, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.8196721311475409, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.78125, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.18428488075733185, "eval_overall_accuracy": 0.9640659611124784, "eval_overall_f1": 0.8497970230040596, "eval_overall_precision": 0.8092783505154639, "eval_overall_recall": 0.8945868945868946, "eval_runtime": 0.3855, "eval_samples_per_second": 485.12, "eval_steps_per_second": 7.783, "step": 9858 }, { "epoch": 94.0, "grad_norm": 0.7894928455352783, "learning_rate": 3e-06, "loss": 0.024, "step": 9964 }, { "epoch": 94.0, "eval_LOCATION_f1": 0.8758169934640524, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8375, "eval_LOCATION_recall": 0.9178082191780822, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.9061488673139159, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8805031446540881, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.7936507936507937, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.18454931676387787, "eval_overall_accuracy": 0.9635737140044303, "eval_overall_f1": 0.8470906630581868, "eval_overall_precision": 0.8067010309278351, "eval_overall_recall": 0.8917378917378918, "eval_runtime": 0.3874, "eval_samples_per_second": 482.705, "eval_steps_per_second": 7.744, "step": 9964 }, { "epoch": 95.0, "grad_norm": 0.5310998558998108, "learning_rate": 2.5e-06, "loss": 0.024, "step": 10070 }, { "epoch": 95.0, "eval_LOCATION_f1": 0.8874172185430463, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8589743589743589, "eval_LOCATION_recall": 0.9178082191780822, "eval_ORGANIZATION_f1": 0.7132867132867133, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6538461538461539, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.9061488673139159, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8805031446540881, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.8064516129032258, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.18248838186264038, "eval_overall_accuracy": 0.9640659611124784, "eval_overall_f1": 0.8493894165535957, "eval_overall_precision": 0.810880829015544, "eval_overall_recall": 0.8917378917378918, "eval_runtime": 0.3942, "eval_samples_per_second": 474.406, "eval_steps_per_second": 7.611, "step": 10070 }, { "epoch": 96.0, "grad_norm": 0.7802311778068542, "learning_rate": 2.0000000000000003e-06, "loss": 0.0247, "step": 10176 }, { "epoch": 96.0, "eval_LOCATION_f1": 0.8741721854304636, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8461538461538461, "eval_LOCATION_recall": 0.9041095890410958, "eval_ORGANIZATION_f1": 0.7083333333333334, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6455696202531646, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.86875, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.8064516129032258, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.18491245806217194, "eval_overall_accuracy": 0.9635737140044303, "eval_overall_f1": 0.8416779431664412, "eval_overall_precision": 0.8015463917525774, "eval_overall_recall": 0.886039886039886, "eval_runtime": 0.3909, "eval_samples_per_second": 478.441, "eval_steps_per_second": 7.676, "step": 10176 }, { "epoch": 97.0, "grad_norm": 0.7217825055122375, "learning_rate": 1.5e-06, "loss": 0.0236, "step": 10282 }, { "epoch": 97.0, "eval_LOCATION_f1": 0.881578947368421, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8481012658227848, "eval_LOCATION_recall": 0.9178082191780822, "eval_ORGANIZATION_f1": 0.7234042553191491, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6710526315789473, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.86875, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.8064516129032258, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.18391452729701996, "eval_overall_accuracy": 0.9638198375584544, "eval_overall_f1": 0.8466757123473541, "eval_overall_precision": 0.8082901554404145, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.3914, "eval_samples_per_second": 477.725, "eval_steps_per_second": 7.664, "step": 10282 }, { "epoch": 98.0, "grad_norm": 0.31892678141593933, "learning_rate": 1.0000000000000002e-06, "loss": 0.0228, "step": 10388 }, { "epoch": 98.0, "eval_LOCATION_f1": 0.8758169934640524, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8375, "eval_LOCATION_recall": 0.9178082191780822, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.86875, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.8064516129032258, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.18566611409187317, "eval_overall_accuracy": 0.9635737140044303, "eval_overall_f1": 0.8443843031123139, "eval_overall_precision": 0.8041237113402062, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.385, "eval_samples_per_second": 485.655, "eval_steps_per_second": 7.791, "step": 10388 }, { "epoch": 99.0, "grad_norm": 1.421492099761963, "learning_rate": 5.000000000000001e-07, "loss": 0.025, "step": 10494 }, { "epoch": 99.0, "eval_LOCATION_f1": 0.881578947368421, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8481012658227848, "eval_LOCATION_recall": 0.9178082191780822, "eval_ORGANIZATION_f1": 0.7132867132867133, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6538461538461539, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.86875, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.8064516129032258, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.18506501615047455, "eval_overall_accuracy": 0.9638198375584544, "eval_overall_f1": 0.8443843031123139, "eval_overall_precision": 0.8041237113402062, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.3874, "eval_samples_per_second": 482.766, "eval_steps_per_second": 7.745, "step": 10494 }, { "epoch": 100.0, "grad_norm": 0.21340006589889526, "learning_rate": 0.0, "loss": 0.023, "step": 10600 }, { "epoch": 100.0, "eval_LOCATION_f1": 0.8758169934640524, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.8375, "eval_LOCATION_recall": 0.9178082191780822, "eval_ORGANIZATION_f1": 0.7132867132867133, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6538461538461539, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.86875, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.8064516129032258, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8620689655172413, "eval_TIME_f1": 0.8333333333333333, "eval_TIME_number": 34, "eval_TIME_precision": 0.7894736842105263, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1850329041481018, "eval_overall_accuracy": 0.9635737140044303, "eval_overall_f1": 0.8432432432432433, "eval_overall_precision": 0.8020565552699229, "eval_overall_recall": 0.8888888888888888, "eval_runtime": 0.3863, "eval_samples_per_second": 484.103, "eval_steps_per_second": 7.766, "step": 10600 }, { "epoch": 100.0, "step": 10600, "total_flos": 5043631411410816.0, "train_loss": 0.07131878634668747, "train_runtime": 621.5745, "train_samples_per_second": 271.568, "train_steps_per_second": 17.053 } ], "logging_steps": 500, "max_steps": 10600, "num_input_tokens_seen": 0, "num_train_epochs": 100, "save_steps": 500, "total_flos": 5043631411410816.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }