{ "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": 1.7689048051834106, "learning_rate": 4.9500000000000004e-05, "loss": 1.2425, "step": 106 }, { "epoch": 1.0, "eval_LOCATION_f1": 0.0, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.0, "eval_LOCATION_recall": 0.0, "eval_ORGANIZATION_f1": 0.0, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.0, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.0, "eval_PERSON_recall": 0.0, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 26, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.7045310735702515, "eval_overall_accuracy": 0.8448836627470603, "eval_overall_f1": 0.0, "eval_overall_precision": 0.0, "eval_overall_recall": 0.0, "eval_runtime": 0.3653, "eval_samples_per_second": 511.916, "eval_steps_per_second": 8.213, "step": 106 }, { "epoch": 2.0, "grad_norm": 1.2123279571533203, "learning_rate": 4.9e-05, "loss": 0.7049, "step": 212 }, { "epoch": 2.0, "eval_LOCATION_f1": 0.0, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.0, "eval_LOCATION_recall": 0.0, "eval_ORGANIZATION_f1": 0.0, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.0, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.0, "eval_PERSON_recall": 0.0, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 26, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.5983695983886719, "eval_overall_accuracy": 0.845634225669252, "eval_overall_f1": 0.0, "eval_overall_precision": 0.0, "eval_overall_recall": 0.0, "eval_runtime": 0.3629, "eval_samples_per_second": 515.28, "eval_steps_per_second": 8.267, "step": 212 }, { "epoch": 3.0, "grad_norm": 1.2371383905410767, "learning_rate": 4.85e-05, "loss": 0.6175, "step": 318 }, { "epoch": 3.0, "eval_LOCATION_f1": 0.0, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.0, "eval_LOCATION_recall": 0.0, "eval_ORGANIZATION_f1": 0.0, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.050314465408805034, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.25, "eval_PERSON_recall": 0.027972027972027972, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 26, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.5003284215927124, "eval_overall_accuracy": 0.851138353765324, "eval_overall_f1": 0.02185792349726776, "eval_overall_precision": 0.14814814814814814, "eval_overall_recall": 0.011799410029498525, "eval_runtime": 0.3621, "eval_samples_per_second": 516.362, "eval_steps_per_second": 8.284, "step": 318 }, { "epoch": 4.0, "grad_norm": 1.6603214740753174, "learning_rate": 4.8e-05, "loss": 0.5236, "step": 424 }, { "epoch": 4.0, "eval_LOCATION_f1": 0.14814814814814814, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.6666666666666666, "eval_LOCATION_recall": 0.08333333333333333, "eval_ORGANIZATION_f1": 0.02150537634408602, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.05555555555555555, "eval_ORGANIZATION_recall": 0.013333333333333334, "eval_PERSON_f1": 0.3206751054852321, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.40425531914893614, "eval_PERSON_recall": 0.26573426573426573, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.372093023255814, "eval_TIME_number": 26, "eval_TIME_precision": 0.47058823529411764, "eval_TIME_recall": 0.3076923076923077, "eval_loss": 0.4110596179962158, "eval_overall_accuracy": 0.879909932449337, "eval_overall_f1": 0.22222222222222224, "eval_overall_precision": 0.38405797101449274, "eval_overall_recall": 0.15634218289085547, "eval_runtime": 0.3629, "eval_samples_per_second": 515.294, "eval_steps_per_second": 8.267, "step": 424 }, { "epoch": 5.0, "grad_norm": 1.352211594581604, "learning_rate": 4.75e-05, "loss": 0.4275, "step": 530 }, { "epoch": 5.0, "eval_LOCATION_f1": 0.44067796610169496, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.5652173913043478, "eval_LOCATION_recall": 0.3611111111111111, "eval_ORGANIZATION_f1": 0.2857142857142857, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.38636363636363635, "eval_ORGANIZATION_recall": 0.22666666666666666, "eval_PERSON_f1": 0.6577181208053692, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.632258064516129, "eval_PERSON_recall": 0.6853146853146853, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.6666666666666667, "eval_TIME_number": 26, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.6153846153846154, "eval_loss": 0.3292999565601349, "eval_overall_accuracy": 0.9134350763072304, "eval_overall_f1": 0.5072697899838449, "eval_overall_precision": 0.5607142857142857, "eval_overall_recall": 0.4631268436578171, "eval_runtime": 0.3636, "eval_samples_per_second": 514.257, "eval_steps_per_second": 8.25, "step": 530 }, { "epoch": 6.0, "grad_norm": 1.139642357826233, "learning_rate": 4.7e-05, "loss": 0.3439, "step": 636 }, { "epoch": 6.0, "eval_LOCATION_f1": 0.5833333333333334, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.5833333333333334, "eval_LOCATION_recall": 0.5833333333333334, "eval_ORGANIZATION_f1": 0.42758620689655175, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.44285714285714284, "eval_ORGANIZATION_recall": 0.41333333333333333, "eval_PERSON_f1": 0.7735849056603774, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7028571428571428, "eval_PERSON_recall": 0.8601398601398601, "eval_QUANTITY_f1": 0.20408163265306123, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.19230769230769232, "eval_QUANTITY_recall": 0.21739130434782608, "eval_TIME_f1": 0.6909090909090909, "eval_TIME_number": 26, "eval_TIME_precision": 0.6551724137931034, "eval_TIME_recall": 0.7307692307692307, "eval_loss": 0.27195486426353455, "eval_overall_accuracy": 0.9281961471103327, "eval_overall_f1": 0.6188466947960619, "eval_overall_precision": 0.5913978494623656, "eval_overall_recall": 0.6489675516224189, "eval_runtime": 0.3647, "eval_samples_per_second": 512.778, "eval_steps_per_second": 8.226, "step": 636 }, { "epoch": 7.0, "grad_norm": 0.8564109802246094, "learning_rate": 4.6500000000000005e-05, "loss": 0.2863, "step": 742 }, { "epoch": 7.0, "eval_LOCATION_f1": 0.6838709677419356, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.6385542168674698, "eval_LOCATION_recall": 0.7361111111111112, "eval_ORGANIZATION_f1": 0.513157894736842, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5064935064935064, "eval_ORGANIZATION_recall": 0.52, "eval_PERSON_f1": 0.810126582278481, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7398843930635838, "eval_PERSON_recall": 0.8951048951048951, "eval_QUANTITY_f1": 0.30188679245283023, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.26666666666666666, "eval_QUANTITY_recall": 0.34782608695652173, "eval_TIME_f1": 0.7272727272727274, "eval_TIME_number": 26, "eval_TIME_precision": 0.6896551724137931, "eval_TIME_recall": 0.7692307692307693, "eval_loss": 0.23611050844192505, "eval_overall_accuracy": 0.9331998999249437, "eval_overall_f1": 0.6785225718194254, "eval_overall_precision": 0.6326530612244898, "eval_overall_recall": 0.7315634218289085, "eval_runtime": 0.3672, "eval_samples_per_second": 509.262, "eval_steps_per_second": 8.17, "step": 742 }, { "epoch": 8.0, "grad_norm": 3.0055572986602783, "learning_rate": 4.600000000000001e-05, "loss": 0.2491, "step": 848 }, { "epoch": 8.0, "eval_LOCATION_f1": 0.7402597402597403, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.6951219512195121, "eval_LOCATION_recall": 0.7916666666666666, "eval_ORGANIZATION_f1": 0.5833333333333333, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5268817204301075, "eval_ORGANIZATION_recall": 0.6533333333333333, "eval_PERSON_f1": 0.8242811501597443, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7588235294117647, "eval_PERSON_recall": 0.9020979020979021, "eval_QUANTITY_f1": 0.30188679245283023, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.26666666666666666, "eval_QUANTITY_recall": 0.34782608695652173, "eval_TIME_f1": 0.7272727272727274, "eval_TIME_number": 26, "eval_TIME_precision": 0.6896551724137931, "eval_TIME_recall": 0.7692307692307693, "eval_loss": 0.2096979320049286, "eval_overall_accuracy": 0.9377032774580936, "eval_overall_f1": 0.7079407806191118, "eval_overall_precision": 0.650990099009901, "eval_overall_recall": 0.775811209439528, "eval_runtime": 0.3656, "eval_samples_per_second": 511.444, "eval_steps_per_second": 8.205, "step": 848 }, { "epoch": 9.0, "grad_norm": 1.5356519222259521, "learning_rate": 4.55e-05, "loss": 0.2268, "step": 954 }, { "epoch": 9.0, "eval_LOCATION_f1": 0.7770700636942675, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7176470588235294, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.5697674418604651, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5051546391752577, "eval_ORGANIZATION_recall": 0.6533333333333333, "eval_PERSON_f1": 0.8280254777070064, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7602339181286549, "eval_PERSON_recall": 0.9090909090909091, "eval_QUANTITY_f1": 0.39999999999999997, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.37037037037037035, "eval_QUANTITY_recall": 0.43478260869565216, "eval_TIME_f1": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.19844365119934082, "eval_overall_accuracy": 0.9389542156617463, "eval_overall_f1": 0.7236315086782376, "eval_overall_precision": 0.6609756097560976, "eval_overall_recall": 0.799410029498525, "eval_runtime": 0.3696, "eval_samples_per_second": 505.96, "eval_steps_per_second": 8.117, "step": 954 }, { "epoch": 10.0, "grad_norm": 2.2877798080444336, "learning_rate": 4.5e-05, "loss": 0.2079, "step": 1060 }, { "epoch": 10.0, "eval_LOCATION_f1": 0.779874213836478, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7126436781609196, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.5730994152046783, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5104166666666666, "eval_ORGANIZATION_recall": 0.6533333333333333, "eval_PERSON_f1": 0.8317460317460318, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7616279069767442, "eval_PERSON_recall": 0.916083916083916, "eval_QUANTITY_f1": 0.4642857142857143, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.3939393939393939, "eval_QUANTITY_recall": 0.5652173913043478, "eval_TIME_f1": 0.7368421052631579, "eval_TIME_number": 26, "eval_TIME_precision": 0.6774193548387096, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.18590350449085236, "eval_overall_accuracy": 0.940205153865399, "eval_overall_f1": 0.7282321899736148, "eval_overall_precision": 0.6587112171837709, "eval_overall_recall": 0.8141592920353983, "eval_runtime": 0.3737, "eval_samples_per_second": 500.396, "eval_steps_per_second": 8.028, "step": 1060 }, { "epoch": 11.0, "grad_norm": 1.7066142559051514, "learning_rate": 4.4500000000000004e-05, "loss": 0.196, "step": 1166 }, { "epoch": 11.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.6101694915254237, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5294117647058824, "eval_ORGANIZATION_recall": 0.72, "eval_PERSON_f1": 0.8242811501597443, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7588235294117647, "eval_PERSON_recall": 0.9020979020979021, "eval_QUANTITY_f1": 0.4482758620689655, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.37142857142857144, "eval_QUANTITY_recall": 0.5652173913043478, "eval_TIME_f1": 0.7241379310344829, "eval_TIME_number": 26, "eval_TIME_precision": 0.65625, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.17409172654151917, "eval_overall_accuracy": 0.9424568426319739, "eval_overall_f1": 0.732283464566929, "eval_overall_precision": 0.6595744680851063, "eval_overall_recall": 0.8230088495575221, "eval_runtime": 0.3679, "eval_samples_per_second": 508.26, "eval_steps_per_second": 8.154, "step": 1166 }, { "epoch": 12.0, "grad_norm": 2.2652781009674072, "learning_rate": 4.4000000000000006e-05, "loss": 0.1883, "step": 1272 }, { "epoch": 12.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.6190476190476191, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5591397849462365, "eval_ORGANIZATION_recall": 0.6933333333333334, "eval_PERSON_f1": 0.8333333333333333, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7692307692307693, "eval_PERSON_recall": 0.9090909090909091, "eval_QUANTITY_f1": 0.5384615384615384, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.4827586206896552, "eval_QUANTITY_recall": 0.6086956521739131, "eval_TIME_f1": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1675482839345932, "eval_overall_accuracy": 0.9444583437578183, "eval_overall_f1": 0.7466307277628033, "eval_overall_precision": 0.6873449131513648, "eval_overall_recall": 0.8171091445427728, "eval_runtime": 0.3683, "eval_samples_per_second": 507.675, "eval_steps_per_second": 8.145, "step": 1272 }, { "epoch": 13.0, "grad_norm": 1.0421539545059204, "learning_rate": 4.35e-05, "loss": 0.1791, "step": 1378 }, { "epoch": 13.0, "eval_LOCATION_f1": 0.8, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.6363636363636365, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5544554455445545, "eval_ORGANIZATION_recall": 0.7466666666666667, "eval_PERSON_f1": 0.8461538461538461, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7810650887573964, "eval_PERSON_recall": 0.9230769230769231, "eval_QUANTITY_f1": 0.49056603773584906, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.43333333333333335, "eval_QUANTITY_recall": 0.5652173913043478, "eval_TIME_f1": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.16065628826618195, "eval_overall_accuracy": 0.9474605954465849, "eval_overall_f1": 0.7550200803212852, "eval_overall_precision": 0.6911764705882353, "eval_overall_recall": 0.831858407079646, "eval_runtime": 0.3687, "eval_samples_per_second": 507.134, "eval_steps_per_second": 8.136, "step": 1378 }, { "epoch": 14.0, "grad_norm": 1.3106502294540405, "learning_rate": 4.3e-05, "loss": 0.1739, "step": 1484 }, { "epoch": 14.0, "eval_LOCATION_f1": 0.7891156462585034, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7733333333333333, "eval_LOCATION_recall": 0.8055555555555556, "eval_ORGANIZATION_f1": 0.6368715083798883, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5480769230769231, "eval_ORGANIZATION_recall": 0.76, "eval_PERSON_f1": 0.8618421052631579, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8136645962732919, "eval_PERSON_recall": 0.916083916083916, "eval_QUANTITY_f1": 0.47058823529411764, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.42857142857142855, "eval_QUANTITY_recall": 0.5217391304347826, "eval_TIME_f1": 0.7636363636363636, "eval_TIME_number": 26, "eval_TIME_precision": 0.7241379310344828, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1563156098127365, "eval_overall_accuracy": 0.9482111583687766, "eval_overall_f1": 0.7581521739130435, "eval_overall_precision": 0.7027707808564232, "eval_overall_recall": 0.8230088495575221, "eval_runtime": 0.3646, "eval_samples_per_second": 512.838, "eval_steps_per_second": 8.227, "step": 1484 }, { "epoch": 15.0, "grad_norm": 0.6575543880462646, "learning_rate": 4.25e-05, "loss": 0.1715, "step": 1590 }, { "epoch": 15.0, "eval_LOCATION_f1": 0.8, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.6395348837209303, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5670103092783505, "eval_ORGANIZATION_recall": 0.7333333333333333, "eval_PERSON_f1": 0.868421052631579, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8198757763975155, "eval_PERSON_recall": 0.9230769230769231, "eval_QUANTITY_f1": 0.5490196078431373, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6086956521739131, "eval_TIME_f1": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1505950689315796, "eval_overall_accuracy": 0.9509632224168126, "eval_overall_f1": 0.7694406548431105, "eval_overall_precision": 0.7157360406091371, "eval_overall_recall": 0.831858407079646, "eval_runtime": 0.3661, "eval_samples_per_second": 510.766, "eval_steps_per_second": 8.194, "step": 1590 }, { "epoch": 16.0, "grad_norm": 1.1762727499008179, "learning_rate": 4.2e-05, "loss": 0.164, "step": 1696 }, { "epoch": 16.0, "eval_LOCATION_f1": 0.7763157894736842, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5648148148148148, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.8599348534201955, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8048780487804879, "eval_PERSON_recall": 0.9230769230769231, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.15550078451633453, "eval_overall_accuracy": 0.950713034776082, "eval_overall_f1": 0.7776298268974702, "eval_overall_precision": 0.7087378640776699, "eval_overall_recall": 0.8613569321533924, "eval_runtime": 0.3675, "eval_samples_per_second": 508.791, "eval_steps_per_second": 8.162, "step": 1696 }, { "epoch": 17.0, "grad_norm": 0.8056671619415283, "learning_rate": 4.15e-05, "loss": 0.1562, "step": 1802 }, { "epoch": 17.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.6779661016949153, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5882352941176471, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8599348534201955, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8048780487804879, "eval_PERSON_recall": 0.9230769230769231, "eval_QUANTITY_f1": 0.6785714285714286, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5757575757575758, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.7368421052631579, "eval_TIME_number": 26, "eval_TIME_precision": 0.6774193548387096, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.1546037793159485, "eval_overall_accuracy": 0.9517137853390043, "eval_overall_f1": 0.7808764940239045, "eval_overall_precision": 0.7101449275362319, "eval_overall_recall": 0.8672566371681416, "eval_runtime": 0.3663, "eval_samples_per_second": 510.508, "eval_steps_per_second": 8.19, "step": 1802 }, { "epoch": 18.0, "grad_norm": 1.005129337310791, "learning_rate": 4.1e-05, "loss": 0.1566, "step": 1908 }, { "epoch": 18.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.6557377049180328, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5555555555555556, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8469055374592834, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7926829268292683, "eval_PERSON_recall": 0.9090909090909091, "eval_QUANTITY_f1": 0.7037037037037037, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6129032258064516, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.7719298245614036, "eval_TIME_number": 26, "eval_TIME_precision": 0.7096774193548387, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1545158177614212, "eval_overall_accuracy": 0.950713034776082, "eval_overall_f1": 0.7724867724867724, "eval_overall_precision": 0.7002398081534772, "eval_overall_recall": 0.8613569321533924, "eval_runtime": 0.367, "eval_samples_per_second": 509.482, "eval_steps_per_second": 8.174, "step": 1908 }, { "epoch": 19.0, "grad_norm": 1.0019595623016357, "learning_rate": 4.05e-05, "loss": 0.1515, "step": 2014 }, { "epoch": 19.0, "eval_LOCATION_f1": 0.7662337662337662, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7195121951219512, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.6785714285714285, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6129032258064516, "eval_ORGANIZATION_recall": 0.76, "eval_PERSON_f1": 0.8516129032258065, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7904191616766467, "eval_PERSON_recall": 0.9230769230769231, "eval_QUANTITY_f1": 0.6785714285714286, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5757575757575758, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8070175438596492, "eval_TIME_number": 26, "eval_TIME_precision": 0.7419354838709677, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.14740312099456787, "eval_overall_accuracy": 0.9527145359019265, "eval_overall_f1": 0.7785234899328859, "eval_overall_precision": 0.7142857142857143, "eval_overall_recall": 0.855457227138643, "eval_runtime": 0.3706, "eval_samples_per_second": 504.606, "eval_steps_per_second": 8.095, "step": 2014 }, { "epoch": 20.0, "grad_norm": 1.5229716300964355, "learning_rate": 4e-05, "loss": 0.1462, "step": 2120 }, { "epoch": 20.0, "eval_LOCATION_f1": 0.7721518987341772, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7093023255813954, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.6560846560846562, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.543859649122807, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.8451612903225807, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.7844311377245509, "eval_PERSON_recall": 0.916083916083916, "eval_QUANTITY_f1": 0.6785714285714286, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5757575757575758, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.7586206896551724, "eval_TIME_number": 26, "eval_TIME_precision": 0.6875, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.15897774696350098, "eval_overall_accuracy": 0.9477107830873155, "eval_overall_f1": 0.7652399481193256, "eval_overall_precision": 0.6828703703703703, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3667, "eval_samples_per_second": 510.01, "eval_steps_per_second": 8.182, "step": 2120 }, { "epoch": 21.0, "grad_norm": 1.1792644262313843, "learning_rate": 3.9500000000000005e-05, "loss": 0.147, "step": 2226 }, { "epoch": 21.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7093023255813953, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6288659793814433, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.8636363636363636, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.806060606060606, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6792452830188679, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8214285714285715, "eval_TIME_number": 26, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.14740444719791412, "eval_overall_accuracy": 0.9552164123092319, "eval_overall_f1": 0.793010752688172, "eval_overall_precision": 0.7283950617283951, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3696, "eval_samples_per_second": 505.935, "eval_steps_per_second": 8.117, "step": 2226 }, { "epoch": 22.0, "grad_norm": 0.8306211829185486, "learning_rate": 3.9000000000000006e-05, "loss": 0.1439, "step": 2332 }, { "epoch": 22.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.6927374301675977, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5961538461538461, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.8664495114006516, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8109756097560976, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6909090909090908, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.59375, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8214285714285715, "eval_TIME_number": 26, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.14796702563762665, "eval_overall_accuracy": 0.9537152864648486, "eval_overall_f1": 0.7946666666666666, "eval_overall_precision": 0.7250608272506083, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.3684, "eval_samples_per_second": 507.627, "eval_steps_per_second": 8.144, "step": 2332 }, { "epoch": 23.0, "grad_norm": 1.1865582466125488, "learning_rate": 3.85e-05, "loss": 0.1409, "step": 2438 }, { "epoch": 23.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.6888888888888889, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5904761904761905, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.8664495114006516, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8109756097560976, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.7037037037037037, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.6129032258064516, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8214285714285715, "eval_TIME_number": 26, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.1460741013288498, "eval_overall_accuracy": 0.9544658493870403, "eval_overall_f1": 0.7946666666666666, "eval_overall_precision": 0.7250608272506083, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.3682, "eval_samples_per_second": 507.874, "eval_steps_per_second": 8.148, "step": 2438 }, { "epoch": 24.0, "grad_norm": 1.667884111404419, "learning_rate": 3.8e-05, "loss": 0.1404, "step": 2544 }, { "epoch": 24.0, "eval_LOCATION_f1": 0.782051282051282, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7261904761904762, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.6966292134831461, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6019417475728155, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.8786885245901639, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8271604938271605, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6909090909090908, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.59375, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8214285714285715, "eval_TIME_number": 26, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.1475837379693985, "eval_overall_accuracy": 0.9544658493870403, "eval_overall_f1": 0.7973333333333333, "eval_overall_precision": 0.7274939172749392, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.3705, "eval_samples_per_second": 504.716, "eval_steps_per_second": 8.097, "step": 2544 }, { "epoch": 25.0, "grad_norm": 1.446142554283142, "learning_rate": 3.7500000000000003e-05, "loss": 0.1389, "step": 2650 }, { "epoch": 25.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.6826347305389221, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6195652173913043, "eval_ORGANIZATION_recall": 0.76, "eval_PERSON_f1": 0.8786885245901639, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8271604938271605, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6909090909090908, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.59375, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8070175438596492, "eval_TIME_number": 26, "eval_TIME_precision": 0.7419354838709677, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.1446392685174942, "eval_overall_accuracy": 0.9552164123092319, "eval_overall_f1": 0.7951153324287653, "eval_overall_precision": 0.7361809045226131, "eval_overall_recall": 0.8643067846607669, "eval_runtime": 0.3692, "eval_samples_per_second": 506.541, "eval_steps_per_second": 8.126, "step": 2650 }, { "epoch": 26.0, "grad_norm": 1.0518804788589478, "learning_rate": 3.7e-05, "loss": 0.1364, "step": 2756 }, { "epoch": 26.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7126436781609197, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6262626262626263, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.8758169934640523, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8220858895705522, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6785714285714286, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5757575757575758, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.14412684738636017, "eval_overall_accuracy": 0.9547160370277709, "eval_overall_f1": 0.7951807228915664, "eval_overall_precision": 0.7279411764705882, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3656, "eval_samples_per_second": 511.51, "eval_steps_per_second": 8.206, "step": 2756 }, { "epoch": 27.0, "grad_norm": 1.7476898431777954, "learning_rate": 3.65e-05, "loss": 0.1312, "step": 2862 }, { "epoch": 27.0, "eval_LOCATION_f1": 0.782051282051282, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7261904761904762, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7239263803680981, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6704545454545454, "eval_ORGANIZATION_recall": 0.7866666666666666, "eval_PERSON_f1": 0.8881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8385093167701864, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6785714285714286, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5757575757575758, "eval_QUANTITY_recall": 0.8260869565217391, "eval_TIME_f1": 0.8214285714285715, "eval_TIME_number": 26, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.1471412628889084, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.8081632653061224, "eval_overall_precision": 0.75, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3664, "eval_samples_per_second": 510.345, "eval_steps_per_second": 8.187, "step": 2862 }, { "epoch": 28.0, "grad_norm": 0.9621694087982178, "learning_rate": 3.6e-05, "loss": 0.1322, "step": 2968 }, { "epoch": 28.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7228915662650602, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6593406593406593, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.868421052631579, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8198757763975155, "eval_PERSON_recall": 0.9230769230769231, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5806451612903226, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8214285714285715, "eval_TIME_number": 26, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.13902726769447327, "eval_overall_accuracy": 0.9564673505128847, "eval_overall_f1": 0.8021828103683494, "eval_overall_precision": 0.7461928934010152, "eval_overall_recall": 0.8672566371681416, "eval_runtime": 0.367, "eval_samples_per_second": 509.498, "eval_steps_per_second": 8.174, "step": 2968 }, { "epoch": 29.0, "grad_norm": 1.5748867988586426, "learning_rate": 3.55e-05, "loss": 0.132, "step": 3074 }, { "epoch": 29.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.6823529411764706, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6105263157894737, "eval_ORGANIZATION_recall": 0.7733333333333333, "eval_PERSON_f1": 0.8910891089108911, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.84375, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5806451612903226, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8214285714285715, "eval_TIME_number": 26, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.13819527626037598, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.8016304347826085, "eval_overall_precision": 0.743073047858942, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3679, "eval_samples_per_second": 508.251, "eval_steps_per_second": 8.154, "step": 3074 }, { "epoch": 30.0, "grad_norm": 1.0397722721099854, "learning_rate": 3.5e-05, "loss": 0.1343, "step": 3180 }, { "epoch": 30.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7052023121387283, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6224489795918368, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.8881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8385093167701864, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5806451612903226, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8214285714285715, "eval_TIME_number": 26, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.14312416315078735, "eval_overall_accuracy": 0.9559669752314236, "eval_overall_f1": 0.8054054054054054, "eval_overall_precision": 0.743142144638404, "eval_overall_recall": 0.8790560471976401, "eval_runtime": 0.3676, "eval_samples_per_second": 508.726, "eval_steps_per_second": 8.161, "step": 3180 }, { "epoch": 31.0, "grad_norm": 0.7364059686660767, "learning_rate": 3.45e-05, "loss": 0.1269, "step": 3286 }, { "epoch": 31.0, "eval_LOCATION_f1": 0.7922077922077924, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7142857142857142, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6451612903225806, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8385093167701864, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5806451612903226, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8214285714285715, "eval_TIME_number": 26, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.13839270174503326, "eval_overall_accuracy": 0.9564673505128847, "eval_overall_f1": 0.8070652173913044, "eval_overall_precision": 0.7481108312342569, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3671, "eval_samples_per_second": 509.347, "eval_steps_per_second": 8.171, "step": 3286 }, { "epoch": 32.0, "grad_norm": 1.7341716289520264, "learning_rate": 3.4000000000000007e-05, "loss": 0.1254, "step": 3392 }, { "epoch": 32.0, "eval_LOCATION_f1": 0.7922077922077924, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.6976744186046512, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6185567010309279, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8910891089108911, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.84375, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5806451612903226, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8214285714285715, "eval_TIME_number": 26, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.13537481427192688, "eval_overall_accuracy": 0.9564673505128847, "eval_overall_f1": 0.803788903924222, "eval_overall_precision": 0.7425, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3694, "eval_samples_per_second": 506.237, "eval_steps_per_second": 8.121, "step": 3392 }, { "epoch": 33.0, "grad_norm": 2.0608887672424316, "learning_rate": 3.35e-05, "loss": 0.1235, "step": 3498 }, { "epoch": 33.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7142857142857142, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6451612903225806, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8910891089108911, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.84375, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.6545454545454547, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5625, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8214285714285715, "eval_TIME_number": 26, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.13739992678165436, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.8032564450474898, "eval_overall_precision": 0.7437185929648241, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3679, "eval_samples_per_second": 508.294, "eval_steps_per_second": 8.154, "step": 3498 }, { "epoch": 34.0, "grad_norm": 0.6567090153694153, "learning_rate": 3.3e-05, "loss": 0.1209, "step": 3604 }, { "epoch": 34.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.6976744186046512, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6185567010309279, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8874172185430464, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8427672955974843, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.8214285714285715, "eval_TIME_number": 26, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.14198723435401917, "eval_overall_accuracy": 0.9552164123092319, "eval_overall_f1": 0.7967479674796748, "eval_overall_precision": 0.7368421052631579, "eval_overall_recall": 0.8672566371681416, "eval_runtime": 0.3712, "eval_samples_per_second": 503.83, "eval_steps_per_second": 8.083, "step": 3604 }, { "epoch": 35.0, "grad_norm": 2.041060209274292, "learning_rate": 3.2500000000000004e-05, "loss": 0.1259, "step": 3710 }, { "epoch": 35.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7017543859649122, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.625, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8837209302325583, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8417721518987342, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5806451612903226, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.8214285714285715, "eval_TIME_number": 26, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.13486161828041077, "eval_overall_accuracy": 0.9564673505128847, "eval_overall_f1": 0.7999999999999999, "eval_overall_precision": 0.7424242424242424, "eval_overall_recall": 0.8672566371681416, "eval_runtime": 0.366, "eval_samples_per_second": 510.88, "eval_steps_per_second": 8.196, "step": 3710 }, { "epoch": 36.0, "grad_norm": 2.4899356365203857, "learning_rate": 3.2000000000000005e-05, "loss": 0.1202, "step": 3816 }, { "epoch": 36.0, "eval_LOCATION_f1": 0.7894736842105262, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.728395061728395, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6781609195402298, "eval_ORGANIZATION_recall": 0.7866666666666666, "eval_PERSON_f1": 0.8844884488448846, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8375, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.8214285714285715, "eval_TIME_number": 26, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.1338643580675125, "eval_overall_accuracy": 0.957968476357268, "eval_overall_f1": 0.8060522696011003, "eval_overall_precision": 0.7551546391752577, "eval_overall_recall": 0.8643067846607669, "eval_runtime": 0.3672, "eval_samples_per_second": 509.259, "eval_steps_per_second": 8.17, "step": 3816 }, { "epoch": 37.0, "grad_norm": 2.3477532863616943, "learning_rate": 3.15e-05, "loss": 0.1196, "step": 3922 }, { "epoch": 37.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.6931818181818181, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6039603960396039, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.8874172185430464, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8427672955974843, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6071428571428571, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5151515151515151, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13877151906490326, "eval_overall_accuracy": 0.9547160370277709, "eval_overall_f1": 0.7940780619111709, "eval_overall_precision": 0.7301980198019802, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3714, "eval_samples_per_second": 503.434, "eval_steps_per_second": 8.076, "step": 3922 }, { "epoch": 38.0, "grad_norm": 1.8977165222167969, "learning_rate": 3.1e-05, "loss": 0.1162, "step": 4028 }, { "epoch": 38.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.6892655367231638, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.5980392156862745, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.8844884488448846, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8375, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.14035829901695251, "eval_overall_accuracy": 0.9539654741055792, "eval_overall_f1": 0.793010752688172, "eval_overall_precision": 0.7283950617283951, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3696, "eval_samples_per_second": 506.021, "eval_steps_per_second": 8.118, "step": 4028 }, { "epoch": 39.0, "grad_norm": 0.73508620262146, "learning_rate": 3.05e-05, "loss": 0.1151, "step": 4134 }, { "epoch": 39.0, "eval_LOCATION_f1": 0.8026315789473685, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7625, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.718562874251497, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6521739130434783, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8844884488448846, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8375, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6071428571428571, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5151515151515151, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.8363636363636363, "eval_TIME_number": 26, "eval_TIME_precision": 0.7931034482758621, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.1357470005750656, "eval_overall_accuracy": 0.9569677257943457, "eval_overall_f1": 0.8049113233287858, "eval_overall_precision": 0.748730964467005, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3673, "eval_samples_per_second": 509.136, "eval_steps_per_second": 8.168, "step": 4134 }, { "epoch": 40.0, "grad_norm": 1.4492342472076416, "learning_rate": 3e-05, "loss": 0.1168, "step": 4240 }, { "epoch": 40.0, "eval_LOCATION_f1": 0.7894736842105262, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7272727272727272, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8844884488448846, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8375, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.8214285714285715, "eval_TIME_number": 26, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.8846153846153846, "eval_loss": 0.13538053631782532, "eval_overall_accuracy": 0.9569677257943457, "eval_overall_f1": 0.8043775649794802, "eval_overall_precision": 0.75, "eval_overall_recall": 0.8672566371681416, "eval_runtime": 0.3717, "eval_samples_per_second": 503.129, "eval_steps_per_second": 8.072, "step": 4240 }, { "epoch": 41.0, "grad_norm": 1.3708605766296387, "learning_rate": 2.95e-05, "loss": 0.1155, "step": 4346 }, { "epoch": 41.0, "eval_LOCATION_f1": 0.7894736842105262, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7093023255813953, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6288659793814433, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.8750000000000001, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8260869565217391, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13868868350982666, "eval_overall_accuracy": 0.9544658493870403, "eval_overall_f1": 0.7929634641407307, "eval_overall_precision": 0.7325, "eval_overall_recall": 0.8643067846607669, "eval_runtime": 0.3671, "eval_samples_per_second": 509.445, "eval_steps_per_second": 8.173, "step": 4346 }, { "epoch": 42.0, "grad_norm": 7.47493314743042, "learning_rate": 2.9e-05, "loss": 0.1154, "step": 4452 }, { "epoch": 42.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7058823529411765, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.631578947368421, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8721311475409836, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8209876543209876, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6071428571428571, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5151515151515151, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1388857662677765, "eval_overall_accuracy": 0.9542156617463098, "eval_overall_f1": 0.7891891891891892, "eval_overall_precision": 0.7281795511221946, "eval_overall_recall": 0.8613569321533924, "eval_runtime": 0.3677, "eval_samples_per_second": 508.563, "eval_steps_per_second": 8.159, "step": 4452 }, { "epoch": 43.0, "grad_norm": 1.265225887298584, "learning_rate": 2.8499999999999998e-05, "loss": 0.1122, "step": 4558 }, { "epoch": 43.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7337278106508875, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6595744680851063, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.8844884488448846, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8375, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13678917288780212, "eval_overall_accuracy": 0.9567175381536153, "eval_overall_f1": 0.8043478260869565, "eval_overall_precision": 0.7455919395465995, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3671, "eval_samples_per_second": 509.441, "eval_steps_per_second": 8.173, "step": 4558 }, { "epoch": 44.0, "grad_norm": 2.3092923164367676, "learning_rate": 2.8000000000000003e-05, "loss": 0.1136, "step": 4664 }, { "epoch": 44.0, "eval_LOCATION_f1": 0.8026315789473685, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7625, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.718562874251497, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6521739130434783, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8910891089108911, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.84375, "eval_PERSON_recall": 0.9440559440559441, "eval_QUANTITY_f1": 0.5818181818181818, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13602600991725922, "eval_overall_accuracy": 0.955716787590693, "eval_overall_f1": 0.8021828103683494, "eval_overall_precision": 0.7461928934010152, "eval_overall_recall": 0.8672566371681416, "eval_runtime": 0.368, "eval_samples_per_second": 508.124, "eval_steps_per_second": 8.152, "step": 4664 }, { "epoch": 45.0, "grad_norm": 0.8689550757408142, "learning_rate": 2.7500000000000004e-05, "loss": 0.1114, "step": 4770 }, { "epoch": 45.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7093023255813953, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6288659793814433, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8322981366459627, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6428571428571429, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5454545454545454, "eval_QUANTITY_recall": 0.782608695652174, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.14141933619976044, "eval_overall_accuracy": 0.9542156617463098, "eval_overall_f1": 0.7989203778677463, "eval_overall_precision": 0.736318407960199, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3656, "eval_samples_per_second": 511.537, "eval_steps_per_second": 8.206, "step": 4770 }, { "epoch": 46.0, "grad_norm": 1.0664989948272705, "learning_rate": 2.7000000000000002e-05, "loss": 0.1108, "step": 4876 }, { "epoch": 46.0, "eval_LOCATION_f1": 0.7922077922077924, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7305389221556886, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6630434782608695, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8322981366459627, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6071428571428571, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5151515151515151, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1365976333618164, "eval_overall_accuracy": 0.955716787590693, "eval_overall_f1": 0.8005427408412482, "eval_overall_precision": 0.7412060301507538, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3677, "eval_samples_per_second": 508.5, "eval_steps_per_second": 8.158, "step": 4876 }, { "epoch": 47.0, "grad_norm": 1.2270129919052124, "learning_rate": 2.6500000000000004e-05, "loss": 0.1106, "step": 4982 }, { "epoch": 47.0, "eval_LOCATION_f1": 0.8026315789473685, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7625, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.6931818181818181, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6039603960396039, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8322981366459627, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6071428571428571, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5151515151515151, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14072464406490326, "eval_overall_accuracy": 0.9532149111833875, "eval_overall_f1": 0.7903225806451615, "eval_overall_precision": 0.725925925925926, "eval_overall_recall": 0.8672566371681416, "eval_runtime": 0.3688, "eval_samples_per_second": 507.099, "eval_steps_per_second": 8.135, "step": 4982 }, { "epoch": 48.0, "grad_norm": 1.274558424949646, "learning_rate": 2.6000000000000002e-05, "loss": 0.1101, "step": 5088 }, { "epoch": 48.0, "eval_LOCATION_f1": 0.7894736842105262, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7023809523809524, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6344086021505376, "eval_ORGANIZATION_recall": 0.7866666666666666, "eval_PERSON_f1": 0.8844884488448846, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8375, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.5925925925925926, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5161290322580645, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13291141390800476, "eval_overall_accuracy": 0.9564673505128847, "eval_overall_f1": 0.7939972714870397, "eval_overall_precision": 0.7385786802030457, "eval_overall_recall": 0.8584070796460177, "eval_runtime": 0.3658, "eval_samples_per_second": 511.256, "eval_steps_per_second": 8.202, "step": 5088 }, { "epoch": 49.0, "grad_norm": 5.524200439453125, "learning_rate": 2.5500000000000003e-05, "loss": 0.1085, "step": 5194 }, { "epoch": 49.0, "eval_LOCATION_f1": 0.8, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8611111111111112, "eval_ORGANIZATION_f1": 0.7167630057803468, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6326530612244898, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.880794701986755, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8364779874213837, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13722103834152222, "eval_overall_accuracy": 0.9554665999499625, "eval_overall_f1": 0.7989203778677463, "eval_overall_precision": 0.736318407960199, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3659, "eval_samples_per_second": 511.108, "eval_steps_per_second": 8.2, "step": 5194 }, { "epoch": 50.0, "grad_norm": 2.365539073944092, "learning_rate": 2.5e-05, "loss": 0.1072, "step": 5300 }, { "epoch": 50.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7195121951219511, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6629213483146067, "eval_ORGANIZATION_recall": 0.7866666666666666, "eval_PERSON_f1": 0.8874172185430464, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8427672955974843, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.5818181818181818, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.13088534772396088, "eval_overall_accuracy": 0.9567175381536153, "eval_overall_f1": 0.7945205479452054, "eval_overall_precision": 0.7416879795396419, "eval_overall_recall": 0.855457227138643, "eval_runtime": 0.3699, "eval_samples_per_second": 505.579, "eval_steps_per_second": 8.111, "step": 5300 }, { "epoch": 51.0, "grad_norm": 1.6447672843933105, "learning_rate": 2.45e-05, "loss": 0.1058, "step": 5406 }, { "epoch": 51.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.710843373493976, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6483516483516484, "eval_ORGANIZATION_recall": 0.7866666666666666, "eval_PERSON_f1": 0.8903654485049833, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8481012658227848, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.5818181818181818, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13000808656215668, "eval_overall_accuracy": 0.9567175381536153, "eval_overall_f1": 0.7961696306429548, "eval_overall_precision": 0.7423469387755102, "eval_overall_recall": 0.8584070796460177, "eval_runtime": 0.3686, "eval_samples_per_second": 507.368, "eval_steps_per_second": 8.14, "step": 5406 }, { "epoch": 52.0, "grad_norm": 1.2449003458023071, "learning_rate": 2.4e-05, "loss": 0.1059, "step": 5512 }, { "epoch": 52.0, "eval_LOCATION_f1": 0.7894736842105262, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7228915662650602, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6593406593406593, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8770764119601329, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8354430379746836, "eval_PERSON_recall": 0.9230769230769231, "eval_QUANTITY_f1": 0.5818181818181818, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13208739459514618, "eval_overall_accuracy": 0.9559669752314236, "eval_overall_f1": 0.7945205479452054, "eval_overall_precision": 0.7416879795396419, "eval_overall_recall": 0.855457227138643, "eval_runtime": 0.3682, "eval_samples_per_second": 507.861, "eval_steps_per_second": 8.148, "step": 5512 }, { "epoch": 53.0, "grad_norm": 1.1816686391830444, "learning_rate": 2.35e-05, "loss": 0.1041, "step": 5618 }, { "epoch": 53.0, "eval_LOCATION_f1": 0.7922077922077924, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7218934911242603, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.648936170212766, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.8874172185430464, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8427672955974843, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.13470833003520966, "eval_overall_accuracy": 0.9559669752314236, "eval_overall_f1": 0.7989130434782608, "eval_overall_precision": 0.7405541561712846, "eval_overall_recall": 0.8672566371681416, "eval_runtime": 0.3682, "eval_samples_per_second": 507.924, "eval_steps_per_second": 8.149, "step": 5618 }, { "epoch": 54.0, "grad_norm": 1.8244051933288574, "learning_rate": 2.3000000000000003e-05, "loss": 0.105, "step": 5724 }, { "epoch": 54.0, "eval_LOCATION_f1": 0.7894736842105262, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7100591715976332, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6382978723404256, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8866666666666668, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8471337579617835, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.5818181818181818, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.13241316378116608, "eval_overall_accuracy": 0.9552164123092319, "eval_overall_f1": 0.7923497267759563, "eval_overall_precision": 0.7379134860050891, "eval_overall_recall": 0.855457227138643, "eval_runtime": 0.3673, "eval_samples_per_second": 509.15, "eval_steps_per_second": 8.168, "step": 5724 }, { "epoch": 55.0, "grad_norm": 1.478981614112854, "learning_rate": 2.25e-05, "loss": 0.1079, "step": 5830 }, { "epoch": 55.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7241379310344828, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6363636363636364, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8750000000000001, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8260869565217391, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.5964912280701754, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14122512936592102, "eval_overall_accuracy": 0.9547160370277709, "eval_overall_f1": 0.7903225806451615, "eval_overall_precision": 0.725925925925926, "eval_overall_recall": 0.8672566371681416, "eval_runtime": 0.3652, "eval_samples_per_second": 511.98, "eval_steps_per_second": 8.214, "step": 5830 }, { "epoch": 56.0, "grad_norm": 2.2784554958343506, "learning_rate": 2.2000000000000003e-05, "loss": 0.106, "step": 5936 }, { "epoch": 56.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7058823529411765, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.631578947368421, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8800000000000001, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8407643312101911, "eval_PERSON_recall": 0.9230769230769231, "eval_QUANTITY_f1": 0.6071428571428571, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5151515151515151, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.13478219509124756, "eval_overall_accuracy": 0.955716787590693, "eval_overall_f1": 0.7918367346938775, "eval_overall_precision": 0.7348484848484849, "eval_overall_recall": 0.8584070796460177, "eval_runtime": 0.3684, "eval_samples_per_second": 507.6, "eval_steps_per_second": 8.143, "step": 5936 }, { "epoch": 57.0, "grad_norm": 1.2413791418075562, "learning_rate": 2.15e-05, "loss": 0.1052, "step": 6042 }, { "epoch": 57.0, "eval_LOCATION_f1": 0.7922077922077924, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7272727272727272, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8800000000000001, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8407643312101911, "eval_PERSON_recall": 0.9230769230769231, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13233782351016998, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.7999999999999999, "eval_overall_precision": 0.7468030690537084, "eval_overall_recall": 0.8613569321533924, "eval_runtime": 0.3696, "eval_samples_per_second": 505.994, "eval_steps_per_second": 8.118, "step": 6042 }, { "epoch": 58.0, "grad_norm": 0.674037754535675, "learning_rate": 2.1e-05, "loss": 0.1027, "step": 6148 }, { "epoch": 58.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8472222222222222, "eval_ORGANIZATION_f1": 0.7294117647058824, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6526315789473685, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.8874172185430464, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8427672955974843, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1358455866575241, "eval_overall_accuracy": 0.9559669752314236, "eval_overall_f1": 0.8043478260869565, "eval_overall_precision": 0.7455919395465995, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3647, "eval_samples_per_second": 512.778, "eval_steps_per_second": 8.226, "step": 6148 }, { "epoch": 59.0, "grad_norm": 1.5519734621047974, "learning_rate": 2.05e-05, "loss": 0.1015, "step": 6254 }, { "epoch": 59.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7218934911242603, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.648936170212766, "eval_ORGANIZATION_recall": 0.8133333333333334, "eval_PERSON_f1": 0.8874172185430464, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8427672955974843, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13320086896419525, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.7999999999999999, "eval_overall_precision": 0.7424242424242424, "eval_overall_recall": 0.8672566371681416, "eval_runtime": 0.3681, "eval_samples_per_second": 508.048, "eval_steps_per_second": 8.151, "step": 6254 }, { "epoch": 60.0, "grad_norm": 0.9659972786903381, "learning_rate": 2e-05, "loss": 0.104, "step": 6360 }, { "epoch": 60.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7455621301775148, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6702127659574468, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.880794701986755, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8364779874213837, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6071428571428571, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5151515151515151, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13656935095787048, "eval_overall_accuracy": 0.955716787590693, "eval_overall_f1": 0.8005427408412482, "eval_overall_precision": 0.7412060301507538, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3668, "eval_samples_per_second": 509.875, "eval_steps_per_second": 8.18, "step": 6360 }, { "epoch": 61.0, "grad_norm": 1.9661595821380615, "learning_rate": 1.9500000000000003e-05, "loss": 0.1032, "step": 6466 }, { "epoch": 61.0, "eval_LOCATION_f1": 0.7763157894736842, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7619047619047621, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6881720430107527, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8778877887788779, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.83125, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13553115725517273, "eval_overall_accuracy": 0.9564673505128847, "eval_overall_f1": 0.8049113233287858, "eval_overall_precision": 0.748730964467005, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3714, "eval_samples_per_second": 503.532, "eval_steps_per_second": 8.078, "step": 6466 }, { "epoch": 62.0, "grad_norm": 0.8635398149490356, "learning_rate": 1.9e-05, "loss": 0.0997, "step": 6572 }, { "epoch": 62.0, "eval_LOCATION_f1": 0.7947019867549668, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7544910179640718, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6847826086956522, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8778877887788779, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.83125, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13528038561344147, "eval_overall_accuracy": 0.9572179134350763, "eval_overall_f1": 0.8071135430916553, "eval_overall_precision": 0.7525510204081632, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3676, "eval_samples_per_second": 508.688, "eval_steps_per_second": 8.161, "step": 6572 }, { "epoch": 63.0, "grad_norm": 0.8887146711349487, "learning_rate": 1.85e-05, "loss": 0.1013, "step": 6678 }, { "epoch": 63.0, "eval_LOCATION_f1": 0.7947019867549668, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7142857142857142, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6451612903225806, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.880794701986755, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8364779874213837, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1327866017818451, "eval_overall_accuracy": 0.9572179134350763, "eval_overall_f1": 0.7999999999999999, "eval_overall_precision": 0.7468030690537084, "eval_overall_recall": 0.8613569321533924, "eval_runtime": 0.3667, "eval_samples_per_second": 509.93, "eval_steps_per_second": 8.181, "step": 6678 }, { "epoch": 64.0, "grad_norm": 3.188112735748291, "learning_rate": 1.8e-05, "loss": 0.099, "step": 6784 }, { "epoch": 64.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7471264367816093, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6565656565656566, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8758169934640523, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8220858895705522, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6071428571428571, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5151515151515151, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.75, "eval_TIME_number": 26, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8076923076923077, "eval_loss": 0.14283233880996704, "eval_overall_accuracy": 0.9542156617463098, "eval_overall_f1": 0.7951807228915664, "eval_overall_precision": 0.7279411764705882, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3655, "eval_samples_per_second": 511.573, "eval_steps_per_second": 8.207, "step": 6784 }, { "epoch": 65.0, "grad_norm": 1.5820664167404175, "learning_rate": 1.75e-05, "loss": 0.0979, "step": 6890 }, { "epoch": 65.0, "eval_LOCATION_f1": 0.7947019867549668, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7515151515151515, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6888888888888889, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.8903654485049833, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8481012658227848, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13239729404449463, "eval_overall_accuracy": 0.9577182887165374, "eval_overall_f1": 0.8115543328748279, "eval_overall_precision": 0.7603092783505154, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3677, "eval_samples_per_second": 508.619, "eval_steps_per_second": 8.16, "step": 6890 }, { "epoch": 66.0, "grad_norm": 0.7768399715423584, "learning_rate": 1.7000000000000003e-05, "loss": 0.0956, "step": 6996 }, { "epoch": 66.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7664670658682634, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6956521739130435, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8758169934640523, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8220858895705522, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6071428571428571, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5151515151515151, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13874579966068268, "eval_overall_accuracy": 0.9559669752314236, "eval_overall_f1": 0.803788903924222, "eval_overall_precision": 0.7425, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3701, "eval_samples_per_second": 505.308, "eval_steps_per_second": 8.107, "step": 6996 }, { "epoch": 67.0, "grad_norm": 0.4351659119129181, "learning_rate": 1.65e-05, "loss": 0.1005, "step": 7102 }, { "epoch": 67.0, "eval_LOCATION_f1": 0.7763157894736842, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7544910179640718, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6847826086956522, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8844884488448846, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8375, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6071428571428571, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5151515151515151, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13533051311969757, "eval_overall_accuracy": 0.9567175381536153, "eval_overall_f1": 0.8038147138964578, "eval_overall_precision": 0.7468354430379747, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3684, "eval_samples_per_second": 507.649, "eval_steps_per_second": 8.144, "step": 7102 }, { "epoch": 68.0, "grad_norm": 1.473336100578308, "learning_rate": 1.6000000000000003e-05, "loss": 0.0985, "step": 7208 }, { "epoch": 68.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7294117647058824, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6526315789473685, "eval_ORGANIZATION_recall": 0.8266666666666667, "eval_PERSON_f1": 0.8844884488448846, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8375, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6071428571428571, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5151515151515151, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13884368538856506, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.7972972972972973, "eval_overall_precision": 0.7356608478802993, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.366, "eval_samples_per_second": 510.966, "eval_steps_per_second": 8.197, "step": 7208 }, { "epoch": 69.0, "grad_norm": 1.8830732107162476, "learning_rate": 1.55e-05, "loss": 0.0986, "step": 7314 }, { "epoch": 69.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7590361445783131, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6923076923076923, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8903654485049833, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8481012658227848, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6037735849056605, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5333333333333333, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13436004519462585, "eval_overall_accuracy": 0.9572179134350763, "eval_overall_f1": 0.8104395604395604, "eval_overall_precision": 0.7583547557840618, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3672, "eval_samples_per_second": 509.28, "eval_steps_per_second": 8.17, "step": 7314 }, { "epoch": 70.0, "grad_norm": 2.655252695083618, "learning_rate": 1.5e-05, "loss": 0.1004, "step": 7420 }, { "epoch": 70.0, "eval_LOCATION_f1": 0.781456953642384, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7468354430379747, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7664670658682634, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6956521739130435, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8874172185430464, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8427672955974843, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.5925925925925926, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5161290322580645, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13383792340755463, "eval_overall_accuracy": 0.9577182887165374, "eval_overall_f1": 0.8093278463648834, "eval_overall_precision": 0.7564102564102564, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3671, "eval_samples_per_second": 509.385, "eval_steps_per_second": 8.172, "step": 7420 }, { "epoch": 71.0, "grad_norm": 1.9365965127944946, "learning_rate": 1.45e-05, "loss": 0.0977, "step": 7526 }, { "epoch": 71.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7710843373493976, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7032967032967034, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8874172185430464, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8427672955974843, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6071428571428571, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5151515151515151, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1355029046535492, "eval_overall_accuracy": 0.9567175381536153, "eval_overall_f1": 0.8092643051771118, "eval_overall_precision": 0.7518987341772152, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3673, "eval_samples_per_second": 509.147, "eval_steps_per_second": 8.168, "step": 7526 }, { "epoch": 72.0, "grad_norm": 1.2887853384017944, "learning_rate": 1.4000000000000001e-05, "loss": 0.0979, "step": 7632 }, { "epoch": 72.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7664670658682634, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6956521739130435, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8322981366459627, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6071428571428571, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5151515151515151, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13754044473171234, "eval_overall_accuracy": 0.9559669752314236, "eval_overall_f1": 0.8048780487804879, "eval_overall_precision": 0.7443609022556391, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3662, "eval_samples_per_second": 510.658, "eval_steps_per_second": 8.192, "step": 7632 }, { "epoch": 73.0, "grad_norm": 1.7939187288284302, "learning_rate": 1.3500000000000001e-05, "loss": 0.0975, "step": 7738 }, { "epoch": 73.0, "eval_LOCATION_f1": 0.7763157894736842, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7619047619047621, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6881720430107527, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8903654485049833, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8481012658227848, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6037735849056605, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5333333333333333, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13354170322418213, "eval_overall_accuracy": 0.9574681010758068, "eval_overall_f1": 0.8093278463648834, "eval_overall_precision": 0.7564102564102564, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3648, "eval_samples_per_second": 512.565, "eval_steps_per_second": 8.223, "step": 7738 }, { "epoch": 74.0, "grad_norm": 1.6603038311004639, "learning_rate": 1.3000000000000001e-05, "loss": 0.0949, "step": 7844 }, { "epoch": 74.0, "eval_LOCATION_f1": 0.7692307692307692, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7142857142857143, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7529411764705883, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6736842105263158, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8322981366459627, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6071428571428571, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5151515151515151, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1418963074684143, "eval_overall_accuracy": 0.9559669752314236, "eval_overall_f1": 0.8005390835579514, "eval_overall_precision": 0.7369727047146402, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3681, "eval_samples_per_second": 507.992, "eval_steps_per_second": 8.15, "step": 7844 }, { "epoch": 75.0, "grad_norm": 1.3170303106307983, "learning_rate": 1.25e-05, "loss": 0.0963, "step": 7950 }, { "epoch": 75.0, "eval_LOCATION_f1": 0.7662337662337662, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7195121951219512, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7529411764705883, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6736842105263158, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8844884488448846, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8375, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13844850659370422, "eval_overall_accuracy": 0.9564673505128847, "eval_overall_f1": 0.8032564450474898, "eval_overall_precision": 0.7437185929648241, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3659, "eval_samples_per_second": 511.107, "eval_steps_per_second": 8.2, "step": 7950 }, { "epoch": 76.0, "grad_norm": 1.5277084112167358, "learning_rate": 1.2e-05, "loss": 0.0971, "step": 8056 }, { "epoch": 76.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7485380116959064, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8844884488448846, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8375, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13785386085510254, "eval_overall_accuracy": 0.9567175381536153, "eval_overall_f1": 0.8048780487804879, "eval_overall_precision": 0.7443609022556391, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3665, "eval_samples_per_second": 510.279, "eval_steps_per_second": 8.186, "step": 8056 }, { "epoch": 77.0, "grad_norm": 0.8428215384483337, "learning_rate": 1.1500000000000002e-05, "loss": 0.0947, "step": 8162 }, { "epoch": 77.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7710843373493976, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7032967032967034, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8874172185430464, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8427672955974843, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13634774088859558, "eval_overall_accuracy": 0.9574681010758068, "eval_overall_f1": 0.8103683492496591, "eval_overall_precision": 0.7538071065989848, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3654, "eval_samples_per_second": 511.793, "eval_steps_per_second": 8.211, "step": 8162 }, { "epoch": 78.0, "grad_norm": 1.4167349338531494, "learning_rate": 1.1000000000000001e-05, "loss": 0.094, "step": 8268 }, { "epoch": 78.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7664670658682634, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6956521739130435, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8874172185430464, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8427672955974843, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.5925925925925926, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5161290322580645, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13534387946128845, "eval_overall_accuracy": 0.9574681010758068, "eval_overall_f1": 0.8076398362892225, "eval_overall_precision": 0.751269035532995, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3682, "eval_samples_per_second": 507.828, "eval_steps_per_second": 8.147, "step": 8268 }, { "epoch": 79.0, "grad_norm": 1.7719656229019165, "learning_rate": 1.05e-05, "loss": 0.0952, "step": 8374 }, { "epoch": 79.0, "eval_LOCATION_f1": 0.7662337662337662, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7195121951219512, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7710843373493976, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7032967032967034, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8933333333333333, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8535031847133758, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13364560902118683, "eval_overall_accuracy": 0.9574681010758068, "eval_overall_f1": 0.810958904109589, "eval_overall_precision": 0.7570332480818415, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3653, "eval_samples_per_second": 511.976, "eval_steps_per_second": 8.214, "step": 8374 }, { "epoch": 80.0, "grad_norm": 0.5514072179794312, "learning_rate": 1e-05, "loss": 0.093, "step": 8480 }, { "epoch": 80.0, "eval_LOCATION_f1": 0.7692307692307692, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7142857142857143, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7630057803468209, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.673469387755102, "eval_ORGANIZATION_recall": 0.88, "eval_PERSON_f1": 0.8786885245901639, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8271604938271605, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.5964912280701754, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1440369337797165, "eval_overall_accuracy": 0.955716787590693, "eval_overall_f1": 0.8005354752342704, "eval_overall_precision": 0.7328431372549019, "eval_overall_recall": 0.8820058997050148, "eval_runtime": 0.3663, "eval_samples_per_second": 510.448, "eval_steps_per_second": 8.189, "step": 8480 }, { "epoch": 81.0, "grad_norm": 5.109943866729736, "learning_rate": 9.5e-06, "loss": 0.0945, "step": 8586 }, { "epoch": 81.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7710843373493976, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7032967032967034, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8874172185430464, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8427672955974843, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1353655308485031, "eval_overall_accuracy": 0.9574681010758068, "eval_overall_f1": 0.8103683492496591, "eval_overall_precision": 0.7538071065989848, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.3661, "eval_samples_per_second": 510.802, "eval_steps_per_second": 8.195, "step": 8586 }, { "epoch": 82.0, "grad_norm": 1.6781513690948486, "learning_rate": 9e-06, "loss": 0.0932, "step": 8692 }, { "epoch": 82.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.757396449704142, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6808510638297872, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8844884488448846, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8375, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13809841871261597, "eval_overall_accuracy": 0.9567175381536153, "eval_overall_f1": 0.8059701492537314, "eval_overall_precision": 0.7462311557788944, "eval_overall_recall": 0.8761061946902655, "eval_runtime": 0.365, "eval_samples_per_second": 512.289, "eval_steps_per_second": 8.219, "step": 8692 }, { "epoch": 83.0, "grad_norm": 2.0040693283081055, "learning_rate": 8.500000000000002e-06, "loss": 0.0934, "step": 8798 }, { "epoch": 83.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7590361445783131, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6923076923076923, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8874172185430464, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8427672955974843, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.5925925925925926, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5161290322580645, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1354428231716156, "eval_overall_accuracy": 0.9572179134350763, "eval_overall_f1": 0.8060109289617485, "eval_overall_precision": 0.7506361323155216, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3655, "eval_samples_per_second": 511.641, "eval_steps_per_second": 8.208, "step": 8798 }, { "epoch": 84.0, "grad_norm": 1.2204951047897339, "learning_rate": 8.000000000000001e-06, "loss": 0.0932, "step": 8904 }, { "epoch": 84.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7682926829268292, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7078651685393258, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8778877887788779, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.83125, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.5818181818181818, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1367093026638031, "eval_overall_accuracy": 0.9569677257943457, "eval_overall_f1": 0.8021828103683494, "eval_overall_precision": 0.7461928934010152, "eval_overall_recall": 0.8672566371681416, "eval_runtime": 0.3706, "eval_samples_per_second": 504.639, "eval_steps_per_second": 8.096, "step": 8904 }, { "epoch": 85.0, "grad_norm": 2.190737724304199, "learning_rate": 7.5e-06, "loss": 0.0945, "step": 9010 }, { "epoch": 85.0, "eval_LOCATION_f1": 0.7662337662337662, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7195121951219512, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7730061349693251, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7159090909090909, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8874172185430464, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8427672955974843, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.5818181818181818, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13541610538959503, "eval_overall_accuracy": 0.9572179134350763, "eval_overall_f1": 0.8054794520547945, "eval_overall_precision": 0.7519181585677749, "eval_overall_recall": 0.8672566371681416, "eval_runtime": 0.3685, "eval_samples_per_second": 507.473, "eval_steps_per_second": 8.141, "step": 9010 }, { "epoch": 86.0, "grad_norm": 1.4965229034423828, "learning_rate": 7.000000000000001e-06, "loss": 0.0957, "step": 9116 }, { "epoch": 86.0, "eval_LOCATION_f1": 0.7662337662337662, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7195121951219512, "eval_LOCATION_recall": 0.8194444444444444, "eval_ORGANIZATION_f1": 0.7730061349693251, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7159090909090909, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8874172185430464, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8427672955974843, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13595686852931976, "eval_overall_accuracy": 0.9574681010758068, "eval_overall_f1": 0.8082191780821917, "eval_overall_precision": 0.7544757033248082, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3704, "eval_samples_per_second": 504.884, "eval_steps_per_second": 8.1, "step": 9116 }, { "epoch": 87.0, "grad_norm": 2.8275413513183594, "learning_rate": 6.5000000000000004e-06, "loss": 0.0914, "step": 9222 }, { "epoch": 87.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.75, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6774193548387096, "eval_ORGANIZATION_recall": 0.84, "eval_PERSON_f1": 0.8874172185430464, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8427672955974843, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.5818181818181818, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13588273525238037, "eval_overall_accuracy": 0.9572179134350763, "eval_overall_f1": 0.8027210884353742, "eval_overall_precision": 0.7449494949494949, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.371, "eval_samples_per_second": 504.042, "eval_steps_per_second": 8.086, "step": 9222 }, { "epoch": 88.0, "grad_norm": 1.2798036336898804, "learning_rate": 6e-06, "loss": 0.0922, "step": 9328 }, { "epoch": 88.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.757396449704142, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6808510638297872, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8778877887788779, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.83125, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13768021762371063, "eval_overall_accuracy": 0.9564673505128847, "eval_overall_f1": 0.8021680216802167, "eval_overall_precision": 0.7418546365914787, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3706, "eval_samples_per_second": 504.639, "eval_steps_per_second": 8.096, "step": 9328 }, { "epoch": 89.0, "grad_norm": 1.222822904586792, "learning_rate": 5.500000000000001e-06, "loss": 0.0929, "step": 9434 }, { "epoch": 89.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7664670658682634, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6956521739130435, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8778877887788779, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.83125, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.5818181818181818, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13699018955230713, "eval_overall_accuracy": 0.9569677257943457, "eval_overall_f1": 0.8027210884353742, "eval_overall_precision": 0.7449494949494949, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3709, "eval_samples_per_second": 504.197, "eval_steps_per_second": 8.089, "step": 9434 }, { "epoch": 90.0, "grad_norm": 2.000778913497925, "learning_rate": 5e-06, "loss": 0.0921, "step": 9540 }, { "epoch": 90.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7664670658682634, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6956521739130435, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8778877887788779, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.83125, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6296296296296297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5483870967741935, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13693767786026, "eval_overall_accuracy": 0.9569677257943457, "eval_overall_f1": 0.8054421768707483, "eval_overall_precision": 0.7474747474747475, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3689, "eval_samples_per_second": 506.896, "eval_steps_per_second": 8.132, "step": 9540 }, { "epoch": 91.0, "grad_norm": 1.0267360210418701, "learning_rate": 4.5e-06, "loss": 0.0932, "step": 9646 }, { "epoch": 91.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7757575757575759, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7111111111111111, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8778877887788779, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.83125, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.6181818181818182, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.53125, "eval_QUANTITY_recall": 0.7391304347826086, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13678419589996338, "eval_overall_accuracy": 0.9569677257943457, "eval_overall_f1": 0.8065395095367849, "eval_overall_precision": 0.7493670886075949, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3726, "eval_samples_per_second": 501.846, "eval_steps_per_second": 8.051, "step": 9646 }, { "epoch": 92.0, "grad_norm": 2.0935046672821045, "learning_rate": 4.000000000000001e-06, "loss": 0.0949, "step": 9752 }, { "epoch": 92.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7757575757575759, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7111111111111111, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8844884488448846, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8375, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.5925925925925926, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5161290322580645, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.8, "eval_TIME_number": 26, "eval_TIME_precision": 0.7586206896551724, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13567474484443665, "eval_overall_accuracy": 0.9577182887165374, "eval_overall_f1": 0.8087431693989071, "eval_overall_precision": 0.7531806615776081, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3688, "eval_samples_per_second": 506.984, "eval_steps_per_second": 8.133, "step": 9752 }, { "epoch": 93.0, "grad_norm": 0.7623223066329956, "learning_rate": 3.5000000000000004e-06, "loss": 0.0914, "step": 9858 }, { "epoch": 93.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7664670658682634, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6956521739130435, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8778877887788779, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.83125, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.5714285714285715, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.48484848484848486, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13628067076206207, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.8005427408412482, "eval_overall_precision": 0.7412060301507538, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3698, "eval_samples_per_second": 505.734, "eval_steps_per_second": 8.113, "step": 9858 }, { "epoch": 94.0, "grad_norm": 1.1992981433868408, "learning_rate": 3e-06, "loss": 0.0897, "step": 9964 }, { "epoch": 94.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7710843373493976, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7032967032967034, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8750000000000001, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8260869565217391, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.5614035087719297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.47058823529411764, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.1369829624891281, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.7994579945799458, "eval_overall_precision": 0.7393483709273183, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.3709, "eval_samples_per_second": 504.23, "eval_steps_per_second": 8.089, "step": 9964 }, { "epoch": 95.0, "grad_norm": 0.7576304078102112, "learning_rate": 2.5e-06, "loss": 0.0915, "step": 10070 }, { "epoch": 95.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7692307692307693, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6914893617021277, "eval_ORGANIZATION_recall": 0.8666666666666667, "eval_PERSON_f1": 0.8750000000000001, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8260869565217391, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.5614035087719297, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.47058823529411764, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13803991675376892, "eval_overall_accuracy": 0.9564673505128847, "eval_overall_f1": 0.7989203778677463, "eval_overall_precision": 0.736318407960199, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3696, "eval_samples_per_second": 506.003, "eval_steps_per_second": 8.118, "step": 10070 }, { "epoch": 96.0, "grad_norm": 0.40266284346580505, "learning_rate": 2.0000000000000003e-06, "loss": 0.0925, "step": 10176 }, { "epoch": 96.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7664670658682634, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6956521739130435, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.8750000000000001, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8260869565217391, "eval_PERSON_recall": 0.9300699300699301, "eval_QUANTITY_f1": 0.5714285714285715, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.48484848484848486, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13717274367809296, "eval_overall_accuracy": 0.9562171628721541, "eval_overall_f1": 0.7994579945799458, "eval_overall_precision": 0.7393483709273183, "eval_overall_recall": 0.8702064896755162, "eval_runtime": 0.369, "eval_samples_per_second": 506.829, "eval_steps_per_second": 8.131, "step": 10176 }, { "epoch": 97.0, "grad_norm": 1.2193140983581543, "learning_rate": 1.5e-06, "loss": 0.0921, "step": 10282 }, { "epoch": 97.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7664670658682634, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6956521739130435, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8322981366459627, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.5818181818181818, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13716921210289001, "eval_overall_accuracy": 0.9567175381536153, "eval_overall_f1": 0.8032564450474898, "eval_overall_precision": 0.7437185929648241, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3682, "eval_samples_per_second": 507.822, "eval_steps_per_second": 8.147, "step": 10282 }, { "epoch": 98.0, "grad_norm": 1.019181251525879, "learning_rate": 1.0000000000000002e-06, "loss": 0.091, "step": 10388 }, { "epoch": 98.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7664670658682634, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.6956521739130435, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8322981366459627, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.5818181818181818, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13718858361244202, "eval_overall_accuracy": 0.9567175381536153, "eval_overall_f1": 0.8032564450474898, "eval_overall_precision": 0.7437185929648241, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3688, "eval_samples_per_second": 507.027, "eval_steps_per_second": 8.134, "step": 10388 }, { "epoch": 99.0, "grad_norm": 1.836106777191162, "learning_rate": 5.000000000000001e-07, "loss": 0.0927, "step": 10494 }, { "epoch": 99.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7710843373493976, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7032967032967034, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8322981366459627, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.5818181818181818, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13720610737800598, "eval_overall_accuracy": 0.9564673505128847, "eval_overall_f1": 0.8043478260869565, "eval_overall_precision": 0.7455919395465995, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.3726, "eval_samples_per_second": 501.886, "eval_steps_per_second": 8.052, "step": 10494 }, { "epoch": 100.0, "grad_norm": 1.6062757968902588, "learning_rate": 0.0, "loss": 0.0918, "step": 10600 }, { "epoch": 100.0, "eval_LOCATION_f1": 0.7741935483870969, "eval_LOCATION_number": 72, "eval_LOCATION_precision": 0.7228915662650602, "eval_LOCATION_recall": 0.8333333333333334, "eval_ORGANIZATION_f1": 0.7757575757575759, "eval_ORGANIZATION_number": 75, "eval_ORGANIZATION_precision": 0.7111111111111111, "eval_ORGANIZATION_recall": 0.8533333333333334, "eval_PERSON_f1": 0.881578947368421, "eval_PERSON_number": 143, "eval_PERSON_precision": 0.8322981366459627, "eval_PERSON_recall": 0.9370629370629371, "eval_QUANTITY_f1": 0.5818181818181818, "eval_QUANTITY_number": 23, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6956521739130435, "eval_TIME_f1": 0.7857142857142856, "eval_TIME_number": 26, "eval_TIME_precision": 0.7333333333333333, "eval_TIME_recall": 0.8461538461538461, "eval_loss": 0.13732145726680756, "eval_overall_accuracy": 0.9567175381536153, "eval_overall_f1": 0.8054421768707483, "eval_overall_precision": 0.7474747474747475, "eval_overall_recall": 0.8731563421828908, "eval_runtime": 0.369, "eval_samples_per_second": 506.754, "eval_steps_per_second": 8.13, "step": 10600 }, { "epoch": 100.0, "step": 10600, "total_flos": 4517924176755654.0, "train_loss": 0.15071111247224628, "train_runtime": 577.2988, "train_samples_per_second": 292.223, "train_steps_per_second": 18.361 } ], "logging_steps": 500, "max_steps": 10600, "num_input_tokens_seen": 0, "num_train_epochs": 100, "save_steps": 500, "total_flos": 4517924176755654.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }