{ "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": 3.0579540729522705, "learning_rate": 4.9500000000000004e-05, "loss": 0.3605, "step": 106 }, { "epoch": 1.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.696969696969697, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.8670886075949367, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8353658536585366, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.71875, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6764705882352942, "eval_QUANTITY_recall": 0.7666666666666667, "eval_TIME_f1": 0.8852459016393444, "eval_TIME_number": 29, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.9310344827586207, "eval_loss": 0.14203932881355286, "eval_overall_accuracy": 0.9562099871959027, "eval_overall_f1": 0.8172942817294282, "eval_overall_precision": 0.7730870712401056, "eval_overall_recall": 0.8668639053254438, "eval_runtime": 0.3189, "eval_samples_per_second": 586.358, "eval_steps_per_second": 9.407, "step": 106 }, { "epoch": 2.0, "grad_norm": 2.4212687015533447, "learning_rate": 4.9e-05, "loss": 0.1203, "step": 212 }, { "epoch": 2.0, "eval_LOCATION_f1": 0.8266666666666668, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7654320987654321, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6917293233082706, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6133333333333333, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.8867924528301887, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8493975903614458, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.6865671641791045, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6216216216216216, "eval_QUANTITY_recall": 0.7666666666666667, "eval_TIME_f1": 0.75, "eval_TIME_number": 29, "eval_TIME_precision": 0.6857142857142857, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.14541447162628174, "eval_overall_accuracy": 0.9556978233034571, "eval_overall_f1": 0.8087431693989071, "eval_overall_precision": 0.751269035532995, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.3201, "eval_samples_per_second": 584.228, "eval_steps_per_second": 9.373, "step": 212 }, { "epoch": 3.0, "grad_norm": 5.2256245613098145, "learning_rate": 4.85e-05, "loss": 0.0755, "step": 318 }, { "epoch": 3.0, "eval_LOCATION_f1": 0.8609271523178808, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7926829268292683, "eval_LOCATION_recall": 0.9420289855072463, "eval_ORGANIZATION_f1": 0.71875, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6571428571428571, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.8571428571428571, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8117647058823529, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8852459016393444, "eval_TIME_number": 29, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.9310344827586207, "eval_loss": 0.14322705566883087, "eval_overall_accuracy": 0.9613316261203585, "eval_overall_f1": 0.8292011019283746, "eval_overall_precision": 0.7757731958762887, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.3175, "eval_samples_per_second": 588.914, "eval_steps_per_second": 9.448, "step": 318 }, { "epoch": 4.0, "grad_norm": 1.6368614435195923, "learning_rate": 4.8e-05, "loss": 0.0504, "step": 424 }, { "epoch": 4.0, "eval_LOCATION_f1": 0.8456375838926175, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7875, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6495726495726496, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6440677966101694, "eval_ORGANIZATION_recall": 0.6551724137931034, "eval_PERSON_f1": 0.8734177215189874, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 29, "eval_TIME_precision": 0.6842105263157895, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.14780984818935394, "eval_overall_accuracy": 0.9597951344430218, "eval_overall_f1": 0.8185654008438817, "eval_overall_precision": 0.7801608579088471, "eval_overall_recall": 0.8609467455621301, "eval_runtime": 0.3217, "eval_samples_per_second": 581.313, "eval_steps_per_second": 9.326, "step": 424 }, { "epoch": 5.0, "grad_norm": 2.231923818588257, "learning_rate": 4.75e-05, "loss": 0.0318, "step": 530 }, { "epoch": 5.0, "eval_LOCATION_f1": 0.8472222222222223, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8133333333333334, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7555555555555555, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.8793103448275862, "eval_PERSON_f1": 0.9079365079365079, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8773006134969326, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 29, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.18356788158416748, "eval_overall_accuracy": 0.9597951344430218, "eval_overall_f1": 0.8515950069348128, "eval_overall_precision": 0.8015665796344648, "eval_overall_recall": 0.908284023668639, "eval_runtime": 0.3175, "eval_samples_per_second": 588.92, "eval_steps_per_second": 9.448, "step": 530 }, { "epoch": 6.0, "grad_norm": 4.4022064208984375, "learning_rate": 4.7e-05, "loss": 0.0239, "step": 636 }, { "epoch": 6.0, "eval_LOCATION_f1": 0.8450704225352113, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.821917808219178, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7014925373134329, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.618421052631579, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8478964401294499, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8343949044585988, "eval_PERSON_recall": 0.8618421052631579, "eval_QUANTITY_f1": 0.819672131147541, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8064516129032258, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8524590163934426, "eval_TIME_number": 29, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.1694508045911789, "eval_overall_accuracy": 0.9577464788732394, "eval_overall_f1": 0.8175388967468176, "eval_overall_precision": 0.7831978319783198, "eval_overall_recall": 0.8550295857988166, "eval_runtime": 0.3257, "eval_samples_per_second": 574.211, "eval_steps_per_second": 9.212, "step": 636 }, { "epoch": 7.0, "grad_norm": 0.2985347509384155, "learning_rate": 4.6500000000000005e-05, "loss": 0.0238, "step": 742 }, { "epoch": 7.0, "eval_LOCATION_f1": 0.853146853146853, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8243243243243243, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.75, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6857142857142857, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.8616352201257862, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8253012048192772, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.19530388712882996, "eval_overall_accuracy": 0.9608194622279129, "eval_overall_f1": 0.8256624825662484, "eval_overall_precision": 0.7810026385224275, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.3219, "eval_samples_per_second": 580.938, "eval_steps_per_second": 9.32, "step": 742 }, { "epoch": 8.0, "grad_norm": 0.04798915982246399, "learning_rate": 4.600000000000001e-05, "loss": 0.0134, "step": 848 }, { "epoch": 8.0, "eval_LOCATION_f1": 0.8435374149659864, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.768, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7164179104477612, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.8652037617554859, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8263473053892215, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.23003453016281128, "eval_overall_accuracy": 0.9633802816901409, "eval_overall_f1": 0.8387096774193548, "eval_overall_precision": 0.7973333333333333, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3389, "eval_samples_per_second": 551.794, "eval_steps_per_second": 8.852, "step": 848 }, { "epoch": 9.0, "grad_norm": 0.5828952789306641, "learning_rate": 4.55e-05, "loss": 0.0097, "step": 954 }, { "epoch": 9.0, "eval_LOCATION_f1": 0.8356164383561644, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7922077922077922, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7401574803149606, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6811594202898551, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8859934853420195, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8774193548387097, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.896551724137931, "eval_TIME_number": 29, "eval_TIME_precision": 0.896551724137931, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.23057876527309418, "eval_overall_accuracy": 0.9580025608194622, "eval_overall_f1": 0.8404558404558404, "eval_overall_precision": 0.8104395604395604, "eval_overall_recall": 0.8727810650887574, "eval_runtime": 0.3211, "eval_samples_per_second": 582.432, "eval_steps_per_second": 9.344, "step": 954 }, { "epoch": 10.0, "grad_norm": 0.18654245138168335, "learning_rate": 4.5e-05, "loss": 0.0078, "step": 1060 }, { "epoch": 10.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7906976744186047, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7183098591549296, "eval_ORGANIZATION_recall": 0.8793103448275862, "eval_PERSON_f1": 0.8753993610223643, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8509316770186336, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.896551724137931, "eval_TIME_number": 29, "eval_TIME_precision": 0.896551724137931, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.2440958321094513, "eval_overall_accuracy": 0.9664532650448143, "eval_overall_f1": 0.849507735583685, "eval_overall_precision": 0.8096514745308311, "eval_overall_recall": 0.893491124260355, "eval_runtime": 0.3238, "eval_samples_per_second": 577.519, "eval_steps_per_second": 9.265, "step": 1060 }, { "epoch": 11.0, "grad_norm": 0.014143639244139194, "learning_rate": 4.4500000000000004e-05, "loss": 0.0057, "step": 1166 }, { "epoch": 11.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6440677966101694, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6333333333333333, "eval_ORGANIZATION_recall": 0.6551724137931034, "eval_PERSON_f1": 0.8838709677419354, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8670886075949367, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8524590163934426, "eval_TIME_number": 29, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.2606862783432007, "eval_overall_accuracy": 0.9613316261203585, "eval_overall_f1": 0.8309455587392551, "eval_overall_precision": 0.8055555555555556, "eval_overall_recall": 0.8579881656804734, "eval_runtime": 0.32, "eval_samples_per_second": 584.447, "eval_steps_per_second": 9.376, "step": 1166 }, { "epoch": 12.0, "grad_norm": 0.8590062260627747, "learning_rate": 4.4000000000000006e-05, "loss": 0.0057, "step": 1272 }, { "epoch": 12.0, "eval_LOCATION_f1": 0.8368794326241135, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8194444444444444, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7627118644067795, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.75, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.8706624605678233, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8363636363636363, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.8064516129032259, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.78125, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8620689655172413, "eval_TIME_number": 29, "eval_TIME_precision": 0.8620689655172413, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.2562354505062103, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8390804597701149, "eval_overall_precision": 0.8156424581005587, "eval_overall_recall": 0.863905325443787, "eval_runtime": 0.3245, "eval_samples_per_second": 576.335, "eval_steps_per_second": 9.246, "step": 1272 }, { "epoch": 13.0, "grad_norm": 0.005929162725806236, "learning_rate": 4.35e-05, "loss": 0.0041, "step": 1378 }, { "epoch": 13.0, "eval_LOCATION_f1": 0.8724832214765101, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8125, "eval_LOCATION_recall": 0.9420289855072463, "eval_ORGANIZATION_f1": 0.7768595041322314, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.746031746031746, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8690095846645369, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.84472049689441, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.819672131147541, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8064516129032258, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.26208436489105225, "eval_overall_accuracy": 0.964404609475032, "eval_overall_f1": 0.8506401137980085, "eval_overall_precision": 0.8191780821917808, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3219, "eval_samples_per_second": 580.969, "eval_steps_per_second": 9.32, "step": 1378 }, { "epoch": 14.0, "grad_norm": 0.20337995886802673, "learning_rate": 4.3e-05, "loss": 0.0045, "step": 1484 }, { "epoch": 14.0, "eval_LOCATION_f1": 0.8311688311688311, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7529411764705882, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7241379310344829, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7241379310344828, "eval_ORGANIZATION_recall": 0.7241379310344828, "eval_PERSON_f1": 0.8717948717948718, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.85, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8253968253968255, "eval_TIME_number": 29, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.2810960114002228, "eval_overall_accuracy": 0.9633802816901409, "eval_overall_f1": 0.8305084745762711, "eval_overall_precision": 0.7945945945945946, "eval_overall_recall": 0.8698224852071006, "eval_runtime": 0.3298, "eval_samples_per_second": 566.967, "eval_steps_per_second": 9.096, "step": 1484 }, { "epoch": 15.0, "grad_norm": 1.0766212940216064, "learning_rate": 4.25e-05, "loss": 0.0048, "step": 1590 }, { "epoch": 15.0, "eval_LOCATION_f1": 0.8666666666666666, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8024691358024691, "eval_LOCATION_recall": 0.9420289855072463, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8881789137380192, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.8125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 29, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.26082485914230347, "eval_overall_accuracy": 0.9626120358514725, "eval_overall_f1": 0.8535211267605635, "eval_overall_precision": 0.8145161290322581, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.3242, "eval_samples_per_second": 576.835, "eval_steps_per_second": 9.254, "step": 1590 }, { "epoch": 16.0, "grad_norm": 0.31145572662353516, "learning_rate": 4.2e-05, "loss": 0.0054, "step": 1696 }, { "epoch": 16.0, "eval_LOCATION_f1": 0.8591549295774648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8356164383561644, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7441860465116279, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.676056338028169, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.8980891719745223, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8703703703703703, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8771929824561403, "eval_TIME_number": 29, "eval_TIME_precision": 0.8928571428571429, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.26623842120170593, "eval_overall_accuracy": 0.9608194622279129, "eval_overall_f1": 0.8551136363636364, "eval_overall_precision": 0.8224043715846995, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.3327, "eval_samples_per_second": 562.013, "eval_steps_per_second": 9.016, "step": 1696 }, { "epoch": 17.0, "grad_norm": 0.1136045828461647, "learning_rate": 4.15e-05, "loss": 0.0048, "step": 1802 }, { "epoch": 17.0, "eval_LOCATION_f1": 0.8666666666666666, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8024691358024691, "eval_LOCATION_recall": 0.9420289855072463, "eval_ORGANIZATION_f1": 0.7301587301587301, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6764705882352942, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.8673139158576052, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8535031847133758, "eval_PERSON_recall": 0.881578947368421, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7575757575757576, "eval_TIME_number": 29, "eval_TIME_precision": 0.6756756756756757, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.28109654784202576, "eval_overall_accuracy": 0.9613316261203585, "eval_overall_f1": 0.8263305322128851, "eval_overall_precision": 0.7845744680851063, "eval_overall_recall": 0.8727810650887574, "eval_runtime": 0.3218, "eval_samples_per_second": 581.076, "eval_steps_per_second": 9.322, "step": 1802 }, { "epoch": 18.0, "grad_norm": 0.021722104400396347, "learning_rate": 4.1e-05, "loss": 0.0039, "step": 1908 }, { "epoch": 18.0, "eval_LOCATION_f1": 0.8591549295774648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8356164383561644, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7692307692307692, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6944444444444444, "eval_ORGANIZATION_recall": 0.8620689655172413, "eval_PERSON_f1": 0.8375, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7976190476190477, "eval_PERSON_recall": 0.881578947368421, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8064516129032258, "eval_TIME_number": 29, "eval_TIME_precision": 0.7575757575757576, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.29267749190330505, "eval_overall_accuracy": 0.9574903969270167, "eval_overall_f1": 0.8217270194986072, "eval_overall_precision": 0.7763157894736842, "eval_overall_recall": 0.8727810650887574, "eval_runtime": 0.3291, "eval_samples_per_second": 568.172, "eval_steps_per_second": 9.115, "step": 1908 }, { "epoch": 19.0, "grad_norm": 0.02122313901782036, "learning_rate": 4.05e-05, "loss": 0.0038, "step": 2014 }, { "epoch": 19.0, "eval_LOCATION_f1": 0.8767123287671235, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8311688311688312, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.6666666666666667, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6176470588235294, "eval_ORGANIZATION_recall": 0.7241379310344828, "eval_PERSON_f1": 0.8974358974358975, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.875, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8064516129032259, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.78125, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8524590163934426, "eval_TIME_number": 29, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.2553775906562805, "eval_overall_accuracy": 0.9633802816901409, "eval_overall_f1": 0.8401697312588403, "eval_overall_precision": 0.8048780487804879, "eval_overall_recall": 0.878698224852071, "eval_runtime": 0.3254, "eval_samples_per_second": 574.754, "eval_steps_per_second": 9.221, "step": 2014 }, { "epoch": 20.0, "grad_norm": 0.002756689442321658, "learning_rate": 4e-05, "loss": 0.0044, "step": 2120 }, { "epoch": 20.0, "eval_LOCATION_f1": 0.8289473684210527, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7107438016528926, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6825396825396826, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.879746835443038, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.8125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8253968253968255, "eval_TIME_number": 29, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.2622649371623993, "eval_overall_accuracy": 0.9620998719590269, "eval_overall_f1": 0.8366197183098592, "eval_overall_precision": 0.7983870967741935, "eval_overall_recall": 0.878698224852071, "eval_runtime": 0.3319, "eval_samples_per_second": 563.374, "eval_steps_per_second": 9.038, "step": 2120 }, { "epoch": 21.0, "grad_norm": 0.012515822425484657, "learning_rate": 3.9500000000000005e-05, "loss": 0.0033, "step": 2226 }, { "epoch": 21.0, "eval_LOCATION_f1": 0.8513513513513514, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.735042735042735, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7288135593220338, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.8853503184713376, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8580246913580247, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.7878787878787877, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.27664482593536377, "eval_overall_accuracy": 0.9600512163892445, "eval_overall_f1": 0.8397163120567377, "eval_overall_precision": 0.8065395095367848, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.3226, "eval_samples_per_second": 579.696, "eval_steps_per_second": 9.3, "step": 2226 }, { "epoch": 22.0, "grad_norm": 0.001122328918427229, "learning_rate": 3.9000000000000006e-05, "loss": 0.0048, "step": 2332 }, { "epoch": 22.0, "eval_LOCATION_f1": 0.8904109589041096, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8441558441558441, "eval_LOCATION_recall": 0.9420289855072463, "eval_ORGANIZATION_f1": 0.7727272727272727, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6891891891891891, "eval_ORGANIZATION_recall": 0.8793103448275862, "eval_PERSON_f1": 0.8974358974358975, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.875, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.26052865386009216, "eval_overall_accuracy": 0.9651728553137003, "eval_overall_f1": 0.8651685393258427, "eval_overall_precision": 0.8235294117647058, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.33, "eval_samples_per_second": 566.654, "eval_steps_per_second": 9.091, "step": 2332 }, { "epoch": 23.0, "grad_norm": 0.01085362397134304, "learning_rate": 3.85e-05, "loss": 0.003, "step": 2438 }, { "epoch": 23.0, "eval_LOCATION_f1": 0.8378378378378378, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7848101265822784, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.7727272727272727, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6891891891891891, "eval_ORGANIZATION_recall": 0.8793103448275862, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 29, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.2736039459705353, "eval_overall_accuracy": 0.9646606914212548, "eval_overall_f1": 0.8567415730337079, "eval_overall_precision": 0.8155080213903744, "eval_overall_recall": 0.9023668639053254, "eval_runtime": 0.3239, "eval_samples_per_second": 577.377, "eval_steps_per_second": 9.263, "step": 2438 }, { "epoch": 24.0, "grad_norm": 0.02887049876153469, "learning_rate": 3.8e-05, "loss": 0.0024, "step": 2544 }, { "epoch": 24.0, "eval_LOCATION_f1": 0.8666666666666666, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8024691358024691, "eval_LOCATION_recall": 0.9420289855072463, "eval_ORGANIZATION_f1": 0.7244094488188977, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9090909090909091, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8974358974358975, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.28270941972732544, "eval_overall_accuracy": 0.9646606914212548, "eval_overall_f1": 0.8559322033898306, "eval_overall_precision": 0.8189189189189189, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.3467, "eval_samples_per_second": 539.396, "eval_steps_per_second": 8.653, "step": 2544 }, { "epoch": 25.0, "grad_norm": 0.0016468241810798645, "learning_rate": 3.7500000000000003e-05, "loss": 0.0024, "step": 2650 }, { "epoch": 25.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7681159420289855, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6625, "eval_ORGANIZATION_recall": 0.9137931034482759, "eval_PERSON_f1": 0.8980891719745223, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8703703703703703, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.896551724137931, "eval_TIME_number": 29, "eval_TIME_precision": 0.896551724137931, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.28754085302352905, "eval_overall_accuracy": 0.9646606914212548, "eval_overall_f1": 0.8587257617728532, "eval_overall_precision": 0.8072916666666666, "eval_overall_recall": 0.9171597633136095, "eval_runtime": 0.3225, "eval_samples_per_second": 579.871, "eval_steps_per_second": 9.303, "step": 2650 }, { "epoch": 26.0, "grad_norm": 0.22259019315242767, "learning_rate": 3.7e-05, "loss": 0.0025, "step": 2756 }, { "epoch": 26.0, "eval_LOCATION_f1": 0.8378378378378378, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7848101265822784, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.728813559322034, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7166666666666667, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.8924050632911392, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8597560975609756, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.2877175509929657, "eval_overall_accuracy": 0.9641485275288092, "eval_overall_f1": 0.8477951635846374, "eval_overall_precision": 0.8164383561643835, "eval_overall_recall": 0.8816568047337278, "eval_runtime": 0.3224, "eval_samples_per_second": 580.076, "eval_steps_per_second": 9.306, "step": 2756 }, { "epoch": 27.0, "grad_norm": 0.013442899100482464, "learning_rate": 3.65e-05, "loss": 0.0038, "step": 2862 }, { "epoch": 27.0, "eval_LOCATION_f1": 0.8289473684210527, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6825396825396826, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6323529411764706, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.9196141479099678, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89937106918239, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8387096774193549, "eval_TIME_number": 29, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.29557737708091736, "eval_overall_accuracy": 0.9610755441741358, "eval_overall_f1": 0.840782122905028, "eval_overall_precision": 0.7962962962962963, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.3217, "eval_samples_per_second": 581.31, "eval_steps_per_second": 9.326, "step": 2862 }, { "epoch": 28.0, "grad_norm": 0.033651720732450485, "learning_rate": 3.6e-05, "loss": 0.0046, "step": 2968 }, { "epoch": 28.0, "eval_LOCATION_f1": 0.8609271523178808, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7926829268292683, "eval_LOCATION_recall": 0.9420289855072463, "eval_ORGANIZATION_f1": 0.7559055118110236, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6956521739130435, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.9044585987261147, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8765432098765432, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.2740738093852997, "eval_overall_accuracy": 0.9649167733674776, "eval_overall_f1": 0.8599439775910365, "eval_overall_precision": 0.8164893617021277, "eval_overall_recall": 0.908284023668639, "eval_runtime": 0.3277, "eval_samples_per_second": 570.688, "eval_steps_per_second": 9.155, "step": 2968 }, { "epoch": 29.0, "grad_norm": 0.0036596679128706455, "learning_rate": 3.55e-05, "loss": 0.0022, "step": 3074 }, { "epoch": 29.0, "eval_LOCATION_f1": 0.8689655172413793, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8289473684210527, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7936507936507937, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7352941176470589, "eval_ORGANIZATION_recall": 0.8620689655172413, "eval_PERSON_f1": 0.9126213592233009, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8980891719745223, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.896551724137931, "eval_TIME_number": 29, "eval_TIME_precision": 0.896551724137931, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.280216246843338, "eval_overall_accuracy": 0.9667093469910372, "eval_overall_f1": 0.8730385164051355, "eval_overall_precision": 0.8429752066115702, "eval_overall_recall": 0.9053254437869822, "eval_runtime": 0.3236, "eval_samples_per_second": 577.801, "eval_steps_per_second": 9.27, "step": 3074 }, { "epoch": 30.0, "grad_norm": 0.09640705585479736, "learning_rate": 3.5e-05, "loss": 0.002, "step": 3180 }, { "epoch": 30.0, "eval_LOCATION_f1": 0.8590604026845639, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7903225806451614, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7424242424242424, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9038461538461539, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.88125, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.896551724137931, "eval_TIME_number": 29, "eval_TIME_precision": 0.896551724137931, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.29095637798309326, "eval_overall_accuracy": 0.9674775928297055, "eval_overall_f1": 0.8680851063829786, "eval_overall_precision": 0.8337874659400545, "eval_overall_recall": 0.9053254437869822, "eval_runtime": 0.3288, "eval_samples_per_second": 568.665, "eval_steps_per_second": 9.123, "step": 3180 }, { "epoch": 31.0, "grad_norm": 0.002530389465391636, "learning_rate": 3.45e-05, "loss": 0.0015, "step": 3286 }, { "epoch": 31.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.768, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7164179104477612, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.9049180327868853, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.9019607843137255, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.896551724137931, "eval_TIME_number": 29, "eval_TIME_precision": 0.896551724137931, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.29163551330566406, "eval_overall_accuracy": 0.9661971830985916, "eval_overall_f1": 0.8637015781922526, "eval_overall_precision": 0.8384401114206128, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.3204, "eval_samples_per_second": 583.719, "eval_steps_per_second": 9.364, "step": 3286 }, { "epoch": 32.0, "grad_norm": 0.03596256300806999, "learning_rate": 3.4000000000000007e-05, "loss": 0.004, "step": 3392 }, { "epoch": 32.0, "eval_LOCATION_f1": 0.881118881118881, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8513513513513513, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7704918032786885, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.734375, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.9003215434083601, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8805031446540881, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8135593220338982, "eval_TIME_number": 29, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.285200834274292, "eval_overall_accuracy": 0.9649167733674776, "eval_overall_f1": 0.860832137733142, "eval_overall_precision": 0.8356545961002786, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.333, "eval_samples_per_second": 561.561, "eval_steps_per_second": 9.009, "step": 3392 }, { "epoch": 33.0, "grad_norm": 0.008540854789316654, "learning_rate": 3.35e-05, "loss": 0.0038, "step": 3498 }, { "epoch": 33.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.8032786885245901, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.765625, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9015873015873016, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8196721311475409, "eval_TIME_number": 29, "eval_TIME_precision": 0.78125, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.28712666034698486, "eval_overall_accuracy": 0.9649167733674776, "eval_overall_f1": 0.8640226628895185, "eval_overall_precision": 0.8288043478260869, "eval_overall_recall": 0.9023668639053254, "eval_runtime": 0.3198, "eval_samples_per_second": 584.775, "eval_steps_per_second": 9.381, "step": 3498 }, { "epoch": 34.0, "grad_norm": 0.0038193664513528347, "learning_rate": 3.3e-05, "loss": 0.0042, "step": 3604 }, { "epoch": 34.0, "eval_LOCATION_f1": 0.8749999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.84, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7272727272727273, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6486486486486487, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.8996763754045308, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8853503184713376, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 29, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.29013821482658386, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8543140028288543, "eval_overall_precision": 0.8184281842818428, "eval_overall_recall": 0.893491124260355, "eval_runtime": 0.3361, "eval_samples_per_second": 556.385, "eval_steps_per_second": 8.926, "step": 3604 }, { "epoch": 35.0, "grad_norm": 0.014040589332580566, "learning_rate": 3.2500000000000004e-05, "loss": 0.0026, "step": 3710 }, { "epoch": 35.0, "eval_LOCATION_f1": 0.8533333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7936507936507937, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7352941176470589, "eval_ORGANIZATION_recall": 0.8620689655172413, "eval_PERSON_f1": 0.9161290322580645, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8987341772151899, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 29, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.27812227606773376, "eval_overall_accuracy": 0.9659411011523688, "eval_overall_f1": 0.8700564971751412, "eval_overall_precision": 0.8324324324324325, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.3232, "eval_samples_per_second": 578.539, "eval_steps_per_second": 9.281, "step": 3710 }, { "epoch": 36.0, "grad_norm": 0.0036135606933385134, "learning_rate": 3.2000000000000005e-05, "loss": 0.0021, "step": 3816 }, { "epoch": 36.0, "eval_LOCATION_f1": 0.8551724137931034, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8157894736842105, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.8091603053435115, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.726027397260274, "eval_ORGANIZATION_recall": 0.9137931034482759, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8771929824561403, "eval_TIME_number": 29, "eval_TIME_precision": 0.8928571428571429, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.29289114475250244, "eval_overall_accuracy": 0.9641485275288092, "eval_overall_f1": 0.8668555240793201, "eval_overall_precision": 0.8315217391304348, "eval_overall_recall": 0.9053254437869822, "eval_runtime": 0.3214, "eval_samples_per_second": 581.814, "eval_steps_per_second": 9.334, "step": 3816 }, { "epoch": 37.0, "grad_norm": 0.047017503529787064, "learning_rate": 3.15e-05, "loss": 0.002, "step": 3922 }, { "epoch": 37.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7967479674796748, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7538461538461538, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9078947368421053, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.9078947368421053, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.2750895619392395, "eval_overall_accuracy": 0.9641485275288092, "eval_overall_f1": 0.8612303290414879, "eval_overall_precision": 0.8337950138504155, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.3236, "eval_samples_per_second": 577.827, "eval_steps_per_second": 9.27, "step": 3922 }, { "epoch": 38.0, "grad_norm": 0.002975118113681674, "learning_rate": 3.1e-05, "loss": 0.0032, "step": 4028 }, { "epoch": 38.0, "eval_LOCATION_f1": 0.8344370860927153, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7682926829268293, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7933884297520662, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7619047619047619, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.9096774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8924050632911392, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.292982280254364, "eval_overall_accuracy": 0.9669654289372599, "eval_overall_f1": 0.8607954545454546, "eval_overall_precision": 0.8278688524590164, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.3205, "eval_samples_per_second": 583.486, "eval_steps_per_second": 9.361, "step": 4028 }, { "epoch": 39.0, "grad_norm": 0.048705920577049255, "learning_rate": 3.05e-05, "loss": 0.0014, "step": 4134 }, { "epoch": 39.0, "eval_LOCATION_f1": 0.888888888888889, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8533333333333334, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7833333333333333, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7580645161290323, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.9009584664536742, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8757763975155279, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.26422762870788574, "eval_overall_accuracy": 0.9677336747759283, "eval_overall_f1": 0.8681948424068767, "eval_overall_precision": 0.8416666666666667, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.3204, "eval_samples_per_second": 583.697, "eval_steps_per_second": 9.364, "step": 4134 }, { "epoch": 40.0, "grad_norm": 0.0028175306506454945, "learning_rate": 3e-05, "loss": 0.0022, "step": 4240 }, { "epoch": 40.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7479674796747967, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7076923076923077, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8620689655172413, "eval_TIME_number": 29, "eval_TIME_precision": 0.8620689655172413, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.30111193656921387, "eval_overall_accuracy": 0.9661971830985916, "eval_overall_f1": 0.8534850640113798, "eval_overall_precision": 0.821917808219178, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.3358, "eval_samples_per_second": 556.909, "eval_steps_per_second": 8.934, "step": 4240 }, { "epoch": 41.0, "grad_norm": 0.017286457121372223, "learning_rate": 2.95e-05, "loss": 0.0023, "step": 4346 }, { "epoch": 41.0, "eval_LOCATION_f1": 0.8689655172413793, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8289473684210527, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.752136752136752, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7457627118644068, "eval_ORGANIZATION_recall": 0.7586206896551724, "eval_PERSON_f1": 0.8974358974358975, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.875, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8620689655172413, "eval_TIME_number": 29, "eval_TIME_precision": 0.8620689655172413, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.29203903675079346, "eval_overall_accuracy": 0.9659411011523688, "eval_overall_f1": 0.8587896253602305, "eval_overall_precision": 0.8370786516853933, "eval_overall_recall": 0.8816568047337278, "eval_runtime": 0.3197, "eval_samples_per_second": 584.864, "eval_steps_per_second": 9.383, "step": 4346 }, { "epoch": 42.0, "grad_norm": 0.021444261074066162, "learning_rate": 2.9e-05, "loss": 0.0026, "step": 4452 }, { "epoch": 42.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7868852459016394, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.75, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.8974358974358975, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.875, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.2897973358631134, "eval_overall_accuracy": 0.9646606914212548, "eval_overall_f1": 0.8607954545454546, "eval_overall_precision": 0.8278688524590164, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.3355, "eval_samples_per_second": 557.358, "eval_steps_per_second": 8.942, "step": 4452 }, { "epoch": 43.0, "grad_norm": 0.01654691994190216, "learning_rate": 2.8499999999999998e-05, "loss": 0.0015, "step": 4558 }, { "epoch": 43.0, "eval_LOCATION_f1": 0.8533333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7819548872180451, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6933333333333334, "eval_ORGANIZATION_recall": 0.896551724137931, "eval_PERSON_f1": 0.9067524115755626, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8867924528301887, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.31039759516716003, "eval_overall_accuracy": 0.9649167733674776, "eval_overall_f1": 0.8603351955307262, "eval_overall_precision": 0.8148148148148148, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.3294, "eval_samples_per_second": 567.728, "eval_steps_per_second": 9.108, "step": 4558 }, { "epoch": 44.0, "grad_norm": 0.013932665809988976, "learning_rate": 2.8000000000000003e-05, "loss": 0.0016, "step": 4664 }, { "epoch": 44.0, "eval_LOCATION_f1": 0.8456375838926175, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7875, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7999999999999999, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.746268656716418, "eval_ORGANIZATION_recall": 0.8620689655172413, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8421052631578947, "eval_TIME_number": 29, "eval_TIME_precision": 0.8571428571428571, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.30845847725868225, "eval_overall_accuracy": 0.9641485275288092, "eval_overall_f1": 0.8620199146514936, "eval_overall_precision": 0.8301369863013699, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.3211, "eval_samples_per_second": 582.336, "eval_steps_per_second": 9.342, "step": 4664 }, { "epoch": 45.0, "grad_norm": 0.011009820736944675, "learning_rate": 2.7500000000000004e-05, "loss": 0.0018, "step": 4770 }, { "epoch": 45.0, "eval_LOCATION_f1": 0.8590604026845639, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7596899224806202, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6901408450704225, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9003215434083601, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8805031446540881, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.3025805950164795, "eval_overall_accuracy": 0.9615877080665813, "eval_overall_f1": 0.8551336146272854, "eval_overall_precision": 0.8150134048257373, "eval_overall_recall": 0.8994082840236687, "eval_runtime": 0.3247, "eval_samples_per_second": 575.917, "eval_steps_per_second": 9.239, "step": 4770 }, { "epoch": 46.0, "grad_norm": 13.414834022521973, "learning_rate": 2.7000000000000002e-05, "loss": 0.0033, "step": 4876 }, { "epoch": 46.0, "eval_LOCATION_f1": 0.8366013071895425, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7619047619047619, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7479674796747967, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7076923076923077, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.8945686900958467, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8695652173913043, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.2862217128276825, "eval_overall_accuracy": 0.963124199743918, "eval_overall_f1": 0.8455056179775281, "eval_overall_precision": 0.8048128342245989, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.335, "eval_samples_per_second": 558.225, "eval_steps_per_second": 8.955, "step": 4876 }, { "epoch": 47.0, "grad_norm": 0.003819537116214633, "learning_rate": 2.6500000000000004e-05, "loss": 0.0007, "step": 4982 }, { "epoch": 47.0, "eval_LOCATION_f1": 0.888888888888889, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8533333333333334, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7666666666666667, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7419354838709677, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9126213592233009, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8980891719745223, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8620689655172413, "eval_TIME_number": 29, "eval_TIME_precision": 0.8620689655172413, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.28280648589134216, "eval_overall_accuracy": 0.9690140845070423, "eval_overall_f1": 0.8715728715728714, "eval_overall_precision": 0.8507042253521127, "eval_overall_recall": 0.893491124260355, "eval_runtime": 0.3231, "eval_samples_per_second": 578.72, "eval_steps_per_second": 9.284, "step": 4982 }, { "epoch": 48.0, "grad_norm": 0.046515222638845444, "learning_rate": 2.6000000000000002e-05, "loss": 0.0018, "step": 5088 }, { "epoch": 48.0, "eval_LOCATION_f1": 0.8767123287671235, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8311688311688312, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.75, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6857142857142857, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.2690236270427704, "eval_overall_accuracy": 0.9664532650448143, "eval_overall_f1": 0.8595744680851063, "eval_overall_precision": 0.8256130790190735, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.3232, "eval_samples_per_second": 578.625, "eval_steps_per_second": 9.283, "step": 5088 }, { "epoch": 49.0, "grad_norm": 0.002773936837911606, "learning_rate": 2.5500000000000003e-05, "loss": 0.0005, "step": 5194 }, { "epoch": 49.0, "eval_LOCATION_f1": 0.870748299319728, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7317073170731708, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6923076923076923, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.8881789137380192, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.870967741935484, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.84375, "eval_QUANTITY_recall": 0.9, "eval_TIME_f1": 0.8620689655172413, "eval_TIME_number": 29, "eval_TIME_precision": 0.8620689655172413, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.28763094544410706, "eval_overall_accuracy": 0.9641485275288092, "eval_overall_f1": 0.8534850640113798, "eval_overall_precision": 0.821917808219178, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.3215, "eval_samples_per_second": 581.6, "eval_steps_per_second": 9.33, "step": 5194 }, { "epoch": 50.0, "grad_norm": 0.001465336070396006, "learning_rate": 2.5e-05, "loss": 0.0017, "step": 5300 }, { "epoch": 50.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.711864406779661, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7, "eval_ORGANIZATION_recall": 0.7241379310344828, "eval_PERSON_f1": 0.9061488673139159, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89171974522293, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.3069976568222046, "eval_overall_accuracy": 0.964404609475032, "eval_overall_f1": 0.8522238163558107, "eval_overall_precision": 0.8272980501392758, "eval_overall_recall": 0.878698224852071, "eval_runtime": 0.3366, "eval_samples_per_second": 555.511, "eval_steps_per_second": 8.912, "step": 5300 }, { "epoch": 51.0, "grad_norm": 0.0014170885551720858, "learning_rate": 2.45e-05, "loss": 0.0009, "step": 5406 }, { "epoch": 51.0, "eval_LOCATION_f1": 0.870748299319728, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7812500000000001, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7142857142857143, "eval_ORGANIZATION_recall": 0.8620689655172413, "eval_PERSON_f1": 0.9061488673139159, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89171974522293, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.3090084195137024, "eval_overall_accuracy": 0.9649167733674776, "eval_overall_f1": 0.8652482269503546, "eval_overall_precision": 0.8310626702997275, "eval_overall_recall": 0.9023668639053254, "eval_runtime": 0.3236, "eval_samples_per_second": 577.785, "eval_steps_per_second": 9.269, "step": 5406 }, { "epoch": 52.0, "grad_norm": 0.009222417138516903, "learning_rate": 2.4e-05, "loss": 0.0005, "step": 5512 }, { "epoch": 52.0, "eval_LOCATION_f1": 0.8590604026845639, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7377049180327868, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.703125, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.8996763754045308, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8853503184713376, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3099108636379242, "eval_overall_accuracy": 0.9656850192061459, "eval_overall_f1": 0.855920114122682, "eval_overall_precision": 0.8264462809917356, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.3275, "eval_samples_per_second": 570.979, "eval_steps_per_second": 9.16, "step": 5512 }, { "epoch": 53.0, "grad_norm": 0.0005486037116497755, "learning_rate": 2.35e-05, "loss": 0.001, "step": 5618 }, { "epoch": 53.0, "eval_LOCATION_f1": 0.8533333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7666666666666667, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7419354838709677, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.8996763754045308, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8853503184713376, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 29, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.31158438324928284, "eval_overall_accuracy": 0.9649167733674776, "eval_overall_f1": 0.8587731811697575, "eval_overall_precision": 0.8292011019283747, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.3209, "eval_samples_per_second": 582.696, "eval_steps_per_second": 9.348, "step": 5618 }, { "epoch": 54.0, "grad_norm": 0.0006028018542565405, "learning_rate": 2.3000000000000003e-05, "loss": 0.0006, "step": 5724 }, { "epoch": 54.0, "eval_LOCATION_f1": 0.8533333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7377049180327868, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.703125, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.9055374592833876, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.896774193548387, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.317971795797348, "eval_overall_accuracy": 0.964404609475032, "eval_overall_f1": 0.8542857142857142, "eval_overall_precision": 0.8259668508287292, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3274, "eval_samples_per_second": 571.109, "eval_steps_per_second": 9.162, "step": 5724 }, { "epoch": 55.0, "grad_norm": 0.0006948837544769049, "learning_rate": 2.25e-05, "loss": 0.0004, "step": 5830 }, { "epoch": 55.0, "eval_LOCATION_f1": 0.8590604026845639, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7500000000000001, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7258064516129032, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8620689655172413, "eval_TIME_number": 29, "eval_TIME_precision": 0.8620689655172413, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.32179853320121765, "eval_overall_accuracy": 0.9646606914212548, "eval_overall_f1": 0.8583690987124463, "eval_overall_precision": 0.8310249307479224, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.3207, "eval_samples_per_second": 583.185, "eval_steps_per_second": 9.356, "step": 5830 }, { "epoch": 56.0, "grad_norm": 0.0012037695851176977, "learning_rate": 2.2000000000000003e-05, "loss": 0.0006, "step": 5936 }, { "epoch": 56.0, "eval_LOCATION_f1": 0.8533333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7333333333333333, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7096774193548387, "eval_ORGANIZATION_recall": 0.7586206896551724, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.33105283975601196, "eval_overall_accuracy": 0.9633802816901409, "eval_overall_f1": 0.8518518518518519, "eval_overall_precision": 0.8214285714285714, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3391, "eval_samples_per_second": 551.529, "eval_steps_per_second": 8.848, "step": 5936 }, { "epoch": 57.0, "grad_norm": 0.0022144129034131765, "learning_rate": 2.15e-05, "loss": 0.0009, "step": 6042 }, { "epoch": 57.0, "eval_LOCATION_f1": 0.8476821192052981, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7804878048780488, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7419354838709677, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.696969696969697, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.879746835443038, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.31793665885925293, "eval_overall_accuracy": 0.964404609475032, "eval_overall_f1": 0.8486562942008485, "eval_overall_precision": 0.8130081300813008, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.3249, "eval_samples_per_second": 575.562, "eval_steps_per_second": 9.234, "step": 6042 }, { "epoch": 58.0, "grad_norm": 0.0016710077179595828, "learning_rate": 2.1e-05, "loss": 0.002, "step": 6148 }, { "epoch": 58.0, "eval_LOCATION_f1": 0.870748299319728, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.6725663716814159, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6909090909090909, "eval_ORGANIZATION_recall": 0.6551724137931034, "eval_PERSON_f1": 0.9155844155844156, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.9038461538461539, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8064516129032259, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.78125, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.896551724137931, "eval_TIME_number": 29, "eval_TIME_precision": 0.896551724137931, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.27503037452697754, "eval_overall_accuracy": 0.9638924455825865, "eval_overall_f1": 0.8546511627906976, "eval_overall_precision": 0.84, "eval_overall_recall": 0.8698224852071006, "eval_runtime": 0.3317, "eval_samples_per_second": 563.712, "eval_steps_per_second": 9.044, "step": 6148 }, { "epoch": 59.0, "grad_norm": 0.03837126865983009, "learning_rate": 2.05e-05, "loss": 0.0018, "step": 6254 }, { "epoch": 59.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7540983606557378, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.71875, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.8996763754045308, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8853503184713376, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8771929824561403, "eval_TIME_number": 29, "eval_TIME_precision": 0.8928571428571429, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.29145359992980957, "eval_overall_accuracy": 0.9656850192061459, "eval_overall_f1": 0.8583690987124463, "eval_overall_precision": 0.8310249307479224, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.3233, "eval_samples_per_second": 578.416, "eval_steps_per_second": 9.279, "step": 6254 }, { "epoch": 60.0, "grad_norm": 0.10238273441791534, "learning_rate": 2e-05, "loss": 0.0008, "step": 6360 }, { "epoch": 60.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7027027027027026, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7358490566037735, "eval_ORGANIZATION_recall": 0.6724137931034483, "eval_PERSON_f1": 0.9025974025974026, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8910256410256411, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8771929824561403, "eval_TIME_number": 29, "eval_TIME_precision": 0.8928571428571429, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.31033989787101746, "eval_overall_accuracy": 0.9649167733674776, "eval_overall_f1": 0.8542274052478134, "eval_overall_precision": 0.8419540229885057, "eval_overall_recall": 0.8668639053254438, "eval_runtime": 0.3317, "eval_samples_per_second": 563.83, "eval_steps_per_second": 9.045, "step": 6360 }, { "epoch": 61.0, "grad_norm": 0.002005122834816575, "learning_rate": 1.9500000000000003e-05, "loss": 0.0013, "step": 6466 }, { "epoch": 61.0, "eval_LOCATION_f1": 0.8749999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.84, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7868852459016394, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.75, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.9003215434083601, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8805031446540881, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.896551724137931, "eval_TIME_number": 29, "eval_TIME_precision": 0.896551724137931, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.2831355929374695, "eval_overall_accuracy": 0.9661971830985916, "eval_overall_f1": 0.8681948424068767, "eval_overall_precision": 0.8416666666666667, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.3193, "eval_samples_per_second": 585.653, "eval_steps_per_second": 9.395, "step": 6466 }, { "epoch": 62.0, "grad_norm": 0.0019113136222586036, "learning_rate": 1.9e-05, "loss": 0.0013, "step": 6572 }, { "epoch": 62.0, "eval_LOCATION_f1": 0.870748299319728, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7999999999999999, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.746268656716418, "eval_ORGANIZATION_recall": 0.8620689655172413, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.896551724137931, "eval_TIME_number": 29, "eval_TIME_precision": 0.896551724137931, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.29855355620384216, "eval_overall_accuracy": 0.967989756722151, "eval_overall_f1": 0.8717948717948717, "eval_overall_precision": 0.8406593406593407, "eval_overall_recall": 0.9053254437869822, "eval_runtime": 0.327, "eval_samples_per_second": 571.832, "eval_steps_per_second": 9.174, "step": 6572 }, { "epoch": 63.0, "grad_norm": 0.0004677773977164179, "learning_rate": 1.85e-05, "loss": 0.0009, "step": 6678 }, { "epoch": 63.0, "eval_LOCATION_f1": 0.8513513513513514, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.8064516129032258, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7575757575757576, "eval_ORGANIZATION_recall": 0.8620689655172413, "eval_PERSON_f1": 0.8881789137380192, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.8387096774193549, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.8125, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.896551724137931, "eval_TIME_number": 29, "eval_TIME_precision": 0.896551724137931, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3033183217048645, "eval_overall_accuracy": 0.9661971830985916, "eval_overall_f1": 0.8624113475177306, "eval_overall_precision": 0.8283378746594006, "eval_overall_recall": 0.8994082840236687, "eval_runtime": 0.3215, "eval_samples_per_second": 581.707, "eval_steps_per_second": 9.332, "step": 6678 }, { "epoch": 64.0, "grad_norm": 0.005429080221801996, "learning_rate": 1.8e-05, "loss": 0.0017, "step": 6784 }, { "epoch": 64.0, "eval_LOCATION_f1": 0.8476821192052981, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7804878048780488, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7906976744186047, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7183098591549296, "eval_ORGANIZATION_recall": 0.8793103448275862, "eval_PERSON_f1": 0.9038461538461539, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.88125, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.30157363414764404, "eval_overall_accuracy": 0.9667093469910372, "eval_overall_f1": 0.8627450980392156, "eval_overall_precision": 0.8191489361702128, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.3301, "eval_samples_per_second": 566.553, "eval_steps_per_second": 9.089, "step": 6784 }, { "epoch": 65.0, "grad_norm": 0.0004326178168412298, "learning_rate": 1.75e-05, "loss": 0.0007, "step": 6890 }, { "epoch": 65.0, "eval_LOCATION_f1": 0.8590604026845639, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7751937984496124, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.704225352112676, "eval_ORGANIZATION_recall": 0.8620689655172413, "eval_PERSON_f1": 0.9038461538461539, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.88125, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.896551724137931, "eval_TIME_number": 29, "eval_TIME_precision": 0.896551724137931, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3076171875, "eval_overall_accuracy": 0.9661971830985916, "eval_overall_f1": 0.8635724331926863, "eval_overall_precision": 0.8230563002680965, "eval_overall_recall": 0.908284023668639, "eval_runtime": 0.3217, "eval_samples_per_second": 581.291, "eval_steps_per_second": 9.326, "step": 6890 }, { "epoch": 66.0, "grad_norm": 0.001978162443265319, "learning_rate": 1.7000000000000003e-05, "loss": 0.0013, "step": 6996 }, { "epoch": 66.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7999999999999999, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.746268656716418, "eval_ORGANIZATION_recall": 0.8620689655172413, "eval_PERSON_f1": 0.9096774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8924050632911392, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8387096774193549, "eval_TIME_number": 29, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.2962900996208191, "eval_overall_accuracy": 0.9638924455825865, "eval_overall_f1": 0.8656294200848657, "eval_overall_precision": 0.8292682926829268, "eval_overall_recall": 0.9053254437869822, "eval_runtime": 0.3273, "eval_samples_per_second": 571.366, "eval_steps_per_second": 9.166, "step": 6996 }, { "epoch": 67.0, "grad_norm": 0.000865288486238569, "learning_rate": 1.65e-05, "loss": 0.0011, "step": 7102 }, { "epoch": 67.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7317073170731708, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6923076923076923, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.8974358974358975, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.875, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 29, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3187943994998932, "eval_overall_accuracy": 0.9633802816901409, "eval_overall_f1": 0.851063829787234, "eval_overall_precision": 0.8174386920980926, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.3211, "eval_samples_per_second": 582.391, "eval_steps_per_second": 9.343, "step": 7102 }, { "epoch": 68.0, "grad_norm": 0.00021025155729148537, "learning_rate": 1.6000000000000003e-05, "loss": 0.0009, "step": 7208 }, { "epoch": 68.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.784, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7313432835820896, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.8987341772151899, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 29, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.33562034368515015, "eval_overall_accuracy": 0.964404609475032, "eval_overall_f1": 0.8623595505617977, "eval_overall_precision": 0.820855614973262, "eval_overall_recall": 0.908284023668639, "eval_runtime": 0.3272, "eval_samples_per_second": 571.432, "eval_steps_per_second": 9.167, "step": 7208 }, { "epoch": 69.0, "grad_norm": 0.032114915549755096, "learning_rate": 1.55e-05, "loss": 0.001, "step": 7314 }, { "epoch": 69.0, "eval_LOCATION_f1": 0.8783783783783783, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8227848101265823, "eval_LOCATION_recall": 0.9420289855072463, "eval_ORGANIZATION_f1": 0.7377049180327868, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.703125, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.9260450160771704, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.9056603773584906, "eval_PERSON_recall": 0.9473684210526315, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 29, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.30885857343673706, "eval_overall_accuracy": 0.9654289372599232, "eval_overall_f1": 0.8693181818181819, "eval_overall_precision": 0.8360655737704918, "eval_overall_recall": 0.9053254437869822, "eval_runtime": 0.3216, "eval_samples_per_second": 581.431, "eval_steps_per_second": 9.328, "step": 7314 }, { "epoch": 70.0, "grad_norm": 0.0254677664488554, "learning_rate": 1.5e-05, "loss": 0.001, "step": 7420 }, { "epoch": 70.0, "eval_LOCATION_f1": 0.870748299319728, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.8091603053435115, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.726027397260274, "eval_ORGANIZATION_recall": 0.9137931034482759, "eval_PERSON_f1": 0.9102564102564101, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8875, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 29, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3140678107738495, "eval_overall_accuracy": 0.9669654289372599, "eval_overall_f1": 0.8723702664796634, "eval_overall_precision": 0.8293333333333334, "eval_overall_recall": 0.9201183431952663, "eval_runtime": 0.339, "eval_samples_per_second": 551.686, "eval_steps_per_second": 8.851, "step": 7420 }, { "epoch": 71.0, "grad_norm": 0.0020287446677684784, "learning_rate": 1.45e-05, "loss": 0.0006, "step": 7526 }, { "epoch": 71.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7777777777777778, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7205882352941176, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9320388349514562, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.9171974522292994, "eval_PERSON_recall": 0.9473684210526315, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.2926411032676697, "eval_overall_accuracy": 0.9682458386683739, "eval_overall_f1": 0.876595744680851, "eval_overall_precision": 0.8419618528610354, "eval_overall_recall": 0.9142011834319527, "eval_runtime": 0.3255, "eval_samples_per_second": 574.564, "eval_steps_per_second": 9.218, "step": 7526 }, { "epoch": 72.0, "grad_norm": 0.0008131638751365244, "learning_rate": 1.4000000000000001e-05, "loss": 0.0003, "step": 7632 }, { "epoch": 72.0, "eval_LOCATION_f1": 0.8590604026845639, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7999999999999999, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.746268656716418, "eval_ORGANIZATION_recall": 0.8620689655172413, "eval_PERSON_f1": 0.9255663430420712, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.910828025477707, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 29, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.316145658493042, "eval_overall_accuracy": 0.9669654289372599, "eval_overall_f1": 0.8753541076487252, "eval_overall_precision": 0.8396739130434783, "eval_overall_recall": 0.9142011834319527, "eval_runtime": 0.3261, "eval_samples_per_second": 573.373, "eval_steps_per_second": 9.198, "step": 7632 }, { "epoch": 73.0, "grad_norm": 0.000352115195710212, "learning_rate": 1.3500000000000001e-05, "loss": 0.0008, "step": 7738 }, { "epoch": 73.0, "eval_LOCATION_f1": 0.8533333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7936507936507937, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7352941176470589, "eval_ORGANIZATION_recall": 0.8620689655172413, "eval_PERSON_f1": 0.9102564102564101, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8875, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.31928354501724243, "eval_overall_accuracy": 0.9674775928297055, "eval_overall_f1": 0.867605633802817, "eval_overall_precision": 0.8279569892473119, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.3197, "eval_samples_per_second": 584.939, "eval_steps_per_second": 9.384, "step": 7738 }, { "epoch": 74.0, "grad_norm": 0.0021537726279348135, "learning_rate": 1.3000000000000001e-05, "loss": 0.0007, "step": 7844 }, { "epoch": 74.0, "eval_LOCATION_f1": 0.8590604026845639, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7868852459016394, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.75, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.9131832797427653, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8930817610062893, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3125959038734436, "eval_overall_accuracy": 0.9661971830985916, "eval_overall_f1": 0.8693181818181819, "eval_overall_precision": 0.8360655737704918, "eval_overall_recall": 0.9053254437869822, "eval_runtime": 0.334, "eval_samples_per_second": 559.859, "eval_steps_per_second": 8.982, "step": 7844 }, { "epoch": 75.0, "grad_norm": 0.0009629224659875035, "learning_rate": 1.25e-05, "loss": 0.0002, "step": 7950 }, { "epoch": 75.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7999999999999999, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7741935483870968, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.31075483560562134, "eval_overall_accuracy": 0.9656850192061459, "eval_overall_f1": 0.8685714285714285, "eval_overall_precision": 0.8397790055248618, "eval_overall_recall": 0.8994082840236687, "eval_runtime": 0.3244, "eval_samples_per_second": 576.373, "eval_steps_per_second": 9.247, "step": 7950 }, { "epoch": 76.0, "grad_norm": 0.0005110618658363819, "learning_rate": 1.2e-05, "loss": 0.0003, "step": 8056 }, { "epoch": 76.0, "eval_LOCATION_f1": 0.870748299319728, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.8160000000000001, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7611940298507462, "eval_ORGANIZATION_recall": 0.8793103448275862, "eval_PERSON_f1": 0.910828025477707, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8827160493827161, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3103707730770111, "eval_overall_accuracy": 0.9667093469910372, "eval_overall_f1": 0.8757062146892656, "eval_overall_precision": 0.8378378378378378, "eval_overall_recall": 0.9171597633136095, "eval_runtime": 0.3262, "eval_samples_per_second": 573.268, "eval_steps_per_second": 9.197, "step": 8056 }, { "epoch": 77.0, "grad_norm": 0.0007651924388483167, "learning_rate": 1.1500000000000002e-05, "loss": 0.0003, "step": 8162 }, { "epoch": 77.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.8188976377952756, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7536231884057971, "eval_ORGANIZATION_recall": 0.896551724137931, "eval_PERSON_f1": 0.9196141479099678, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89937106918239, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3196667730808258, "eval_overall_accuracy": 0.9682458386683739, "eval_overall_f1": 0.8785310734463276, "eval_overall_precision": 0.8405405405405405, "eval_overall_recall": 0.9201183431952663, "eval_runtime": 0.3219, "eval_samples_per_second": 580.999, "eval_steps_per_second": 9.321, "step": 8162 }, { "epoch": 78.0, "grad_norm": 0.0005060500116087496, "learning_rate": 1.1000000000000001e-05, "loss": 0.0005, "step": 8268 }, { "epoch": 78.0, "eval_LOCATION_f1": 0.8311688311688311, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7529411764705882, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7846153846153847, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7083333333333334, "eval_ORGANIZATION_recall": 0.8793103448275862, "eval_PERSON_f1": 0.9015873015873016, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 29, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3422912657260895, "eval_overall_accuracy": 0.9636363636363636, "eval_overall_f1": 0.8559556786703602, "eval_overall_precision": 0.8046875, "eval_overall_recall": 0.9142011834319527, "eval_runtime": 0.3309, "eval_samples_per_second": 565.193, "eval_steps_per_second": 9.067, "step": 8268 }, { "epoch": 79.0, "grad_norm": 0.0006566674564965069, "learning_rate": 1.05e-05, "loss": 0.0002, "step": 8374 }, { "epoch": 79.0, "eval_LOCATION_f1": 0.870748299319728, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.8253968253968255, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7647058823529411, "eval_ORGANIZATION_recall": 0.896551724137931, "eval_PERSON_f1": 0.9073482428115016, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8819875776397516, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.33246731758117676, "eval_overall_accuracy": 0.967989756722151, "eval_overall_f1": 0.8757062146892656, "eval_overall_precision": 0.8378378378378378, "eval_overall_recall": 0.9171597633136095, "eval_runtime": 0.3216, "eval_samples_per_second": 581.551, "eval_steps_per_second": 9.33, "step": 8374 }, { "epoch": 80.0, "grad_norm": 0.00022042440832592547, "learning_rate": 1e-05, "loss": 0.0002, "step": 8480 }, { "epoch": 80.0, "eval_LOCATION_f1": 0.8767123287671235, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8311688311688312, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7256637168141592, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7454545454545455, "eval_ORGANIZATION_recall": 0.7068965517241379, "eval_PERSON_f1": 0.9073482428115016, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8819875776397516, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.33535081148147583, "eval_overall_accuracy": 0.9654289372599232, "eval_overall_f1": 0.861671469740634, "eval_overall_precision": 0.8398876404494382, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3346, "eval_samples_per_second": 558.874, "eval_steps_per_second": 8.966, "step": 8480 }, { "epoch": 81.0, "grad_norm": 0.0007291326764971018, "learning_rate": 9.5e-06, "loss": 0.0004, "step": 8586 }, { "epoch": 81.0, "eval_LOCATION_f1": 0.8456375838926175, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7875, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7741935483870968, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7272727272727273, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.8974358974358975, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.875, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 29, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3405434489250183, "eval_overall_accuracy": 0.9641485275288092, "eval_overall_f1": 0.8559322033898306, "eval_overall_precision": 0.8189189189189189, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.3228, "eval_samples_per_second": 579.316, "eval_steps_per_second": 9.294, "step": 8586 }, { "epoch": 82.0, "grad_norm": 0.00018406176241114736, "learning_rate": 9e-06, "loss": 0.0002, "step": 8692 }, { "epoch": 82.0, "eval_LOCATION_f1": 0.8767123287671235, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8311688311688312, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7563025210084033, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7377049180327869, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.9102564102564101, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8875, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.33905231952667236, "eval_overall_accuracy": 0.9664532650448143, "eval_overall_f1": 0.8669527896995709, "eval_overall_precision": 0.8393351800554016, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.3217, "eval_samples_per_second": 581.317, "eval_steps_per_second": 9.326, "step": 8692 }, { "epoch": 83.0, "grad_norm": 0.0005490140756592155, "learning_rate": 8.500000000000002e-06, "loss": 0.0003, "step": 8798 }, { "epoch": 83.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7479674796747967, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7076923076923077, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9038461538461539, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.88125, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.348821759223938, "eval_overall_accuracy": 0.9636363636363636, "eval_overall_f1": 0.8595744680851063, "eval_overall_precision": 0.8256130790190735, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.3214, "eval_samples_per_second": 581.755, "eval_steps_per_second": 9.333, "step": 8798 }, { "epoch": 84.0, "grad_norm": 0.0003215703763999045, "learning_rate": 8.000000000000001e-06, "loss": 0.0002, "step": 8904 }, { "epoch": 84.0, "eval_LOCATION_f1": 0.870748299319728, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7563025210084033, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7377049180327869, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.9137380191693291, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8881987577639752, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.343229740858078, "eval_overall_accuracy": 0.9651728553137003, "eval_overall_f1": 0.8673323823109843, "eval_overall_precision": 0.837465564738292, "eval_overall_recall": 0.8994082840236687, "eval_runtime": 0.3342, "eval_samples_per_second": 559.576, "eval_steps_per_second": 8.977, "step": 8904 }, { "epoch": 85.0, "grad_norm": 0.00015092955436557531, "learning_rate": 7.5e-06, "loss": 0.0003, "step": 9010 }, { "epoch": 85.0, "eval_LOCATION_f1": 0.8590604026845639, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7804878048780489, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7384615384615385, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.9166666666666667, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89375, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.34420961141586304, "eval_overall_accuracy": 0.9654289372599232, "eval_overall_f1": 0.8696883852691217, "eval_overall_precision": 0.8342391304347826, "eval_overall_recall": 0.908284023668639, "eval_runtime": 0.3181, "eval_samples_per_second": 587.95, "eval_steps_per_second": 9.432, "step": 9010 }, { "epoch": 86.0, "grad_norm": 0.0005039689131081104, "learning_rate": 7.000000000000001e-06, "loss": 0.0005, "step": 9116 }, { "epoch": 86.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7903225806451614, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7424242424242424, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9196141479099678, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89937106918239, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3417365849018097, "eval_overall_accuracy": 0.9661971830985916, "eval_overall_f1": 0.873758865248227, "eval_overall_precision": 0.8392370572207084, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.3234, "eval_samples_per_second": 578.156, "eval_steps_per_second": 9.275, "step": 9116 }, { "epoch": 87.0, "grad_norm": 0.00023389511625282466, "learning_rate": 6.5000000000000004e-06, "loss": 0.0002, "step": 9222 }, { "epoch": 87.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7777777777777778, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7205882352941176, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9166666666666667, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89375, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 29, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3444933593273163, "eval_overall_accuracy": 0.9654289372599232, "eval_overall_f1": 0.8688293370944994, "eval_overall_precision": 0.8301886792452831, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.319, "eval_samples_per_second": 586.225, "eval_steps_per_second": 9.405, "step": 9222 }, { "epoch": 88.0, "grad_norm": 0.0009348023450002074, "learning_rate": 6e-06, "loss": 0.0002, "step": 9328 }, { "epoch": 88.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7777777777777778, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7205882352941176, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9131832797427653, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8930817610062893, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 29, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3449549674987793, "eval_overall_accuracy": 0.9651728553137003, "eval_overall_f1": 0.867231638418079, "eval_overall_precision": 0.8297297297297297, "eval_overall_recall": 0.908284023668639, "eval_runtime": 0.3216, "eval_samples_per_second": 581.43, "eval_steps_per_second": 9.328, "step": 9328 }, { "epoch": 89.0, "grad_norm": 0.10062725096940994, "learning_rate": 5.500000000000001e-06, "loss": 0.0002, "step": 9434 }, { "epoch": 89.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7777777777777778, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7205882352941176, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9196141479099678, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89937106918239, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3450436592102051, "eval_overall_accuracy": 0.9659411011523688, "eval_overall_f1": 0.8712871287128714, "eval_overall_precision": 0.8346883468834688, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.3226, "eval_samples_per_second": 579.728, "eval_steps_per_second": 9.3, "step": 9434 }, { "epoch": 90.0, "grad_norm": 0.00016394459817092866, "learning_rate": 5e-06, "loss": 0.0002, "step": 9540 }, { "epoch": 90.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7777777777777778, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7205882352941176, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9196141479099678, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89937106918239, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3440031111240387, "eval_overall_accuracy": 0.9661971830985916, "eval_overall_f1": 0.8712871287128714, "eval_overall_precision": 0.8346883468834688, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.3218, "eval_samples_per_second": 581.062, "eval_steps_per_second": 9.322, "step": 9540 }, { "epoch": 91.0, "grad_norm": 0.00035388587275519967, "learning_rate": 4.5e-06, "loss": 0.0002, "step": 9646 }, { "epoch": 91.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7777777777777778, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7205882352941176, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9196141479099678, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89937106918239, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3439503610134125, "eval_overall_accuracy": 0.9661971830985916, "eval_overall_f1": 0.8712871287128714, "eval_overall_precision": 0.8346883468834688, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.3221, "eval_samples_per_second": 580.542, "eval_steps_per_second": 9.314, "step": 9646 }, { "epoch": 92.0, "grad_norm": 0.0005183388711884618, "learning_rate": 4.000000000000001e-06, "loss": 0.0002, "step": 9752 }, { "epoch": 92.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7777777777777778, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7205882352941176, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9196141479099678, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89937106918239, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.34474003314971924, "eval_overall_accuracy": 0.9661971830985916, "eval_overall_f1": 0.8712871287128714, "eval_overall_precision": 0.8346883468834688, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.3227, "eval_samples_per_second": 579.512, "eval_steps_per_second": 9.297, "step": 9752 }, { "epoch": 93.0, "grad_norm": 0.00015504320617765188, "learning_rate": 3.5000000000000004e-06, "loss": 0.0004, "step": 9858 }, { "epoch": 93.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.765625, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9196141479099678, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89937106918239, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.34853395819664, "eval_overall_accuracy": 0.9656850192061459, "eval_overall_f1": 0.8688293370944994, "eval_overall_precision": 0.8301886792452831, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.3252, "eval_samples_per_second": 575.06, "eval_steps_per_second": 9.226, "step": 9858 }, { "epoch": 94.0, "grad_norm": 0.0016579556977376342, "learning_rate": 3e-06, "loss": 0.0002, "step": 9964 }, { "epoch": 94.0, "eval_LOCATION_f1": 0.870748299319728, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7903225806451614, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7424242424242424, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9225806451612903, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.9050632911392406, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.34736061096191406, "eval_overall_accuracy": 0.9672215108834827, "eval_overall_f1": 0.8762446657183499, "eval_overall_precision": 0.8438356164383561, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.324, "eval_samples_per_second": 577.077, "eval_steps_per_second": 9.258, "step": 9964 }, { "epoch": 95.0, "grad_norm": 0.0002204200136475265, "learning_rate": 2.5e-06, "loss": 0.0002, "step": 10070 }, { "epoch": 95.0, "eval_LOCATION_f1": 0.870748299319728, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7903225806451614, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7424242424242424, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9225806451612903, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.9050632911392406, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3477398753166199, "eval_overall_accuracy": 0.9669654289372599, "eval_overall_f1": 0.8762446657183499, "eval_overall_precision": 0.8438356164383561, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.3352, "eval_samples_per_second": 557.803, "eval_steps_per_second": 8.949, "step": 10070 }, { "epoch": 96.0, "grad_norm": 0.0003840687859337777, "learning_rate": 2.0000000000000003e-06, "loss": 0.0002, "step": 10176 }, { "epoch": 96.0, "eval_LOCATION_f1": 0.870748299319728, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7903225806451614, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7424242424242424, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9196141479099678, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89937106918239, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.34747499227523804, "eval_overall_accuracy": 0.9669654289372599, "eval_overall_f1": 0.875, "eval_overall_precision": 0.8415300546448088, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.3248, "eval_samples_per_second": 575.753, "eval_steps_per_second": 9.237, "step": 10176 }, { "epoch": 97.0, "grad_norm": 0.0001158128070528619, "learning_rate": 1.5e-06, "loss": 0.0002, "step": 10282 }, { "epoch": 97.0, "eval_LOCATION_f1": 0.870748299319728, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7903225806451614, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7424242424242424, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9196141479099678, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89937106918239, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.34782785177230835, "eval_overall_accuracy": 0.9669654289372599, "eval_overall_f1": 0.875, "eval_overall_precision": 0.8415300546448088, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.3347, "eval_samples_per_second": 558.788, "eval_steps_per_second": 8.965, "step": 10282 }, { "epoch": 98.0, "grad_norm": 0.0001685286551946774, "learning_rate": 1.0000000000000002e-06, "loss": 0.0001, "step": 10388 }, { "epoch": 98.0, "eval_LOCATION_f1": 0.870748299319728, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7903225806451614, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7424242424242424, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9196141479099678, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89937106918239, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3480530083179474, "eval_overall_accuracy": 0.9669654289372599, "eval_overall_f1": 0.875, "eval_overall_precision": 0.8415300546448088, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.3236, "eval_samples_per_second": 577.794, "eval_steps_per_second": 9.269, "step": 10388 }, { "epoch": 99.0, "grad_norm": 0.0004627603921107948, "learning_rate": 5.000000000000001e-07, "loss": 0.0003, "step": 10494 }, { "epoch": 99.0, "eval_LOCATION_f1": 0.870748299319728, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7903225806451614, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7424242424242424, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9196141479099678, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89937106918239, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.3480047881603241, "eval_overall_accuracy": 0.9669654289372599, "eval_overall_f1": 0.875, "eval_overall_precision": 0.8415300546448088, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.33, "eval_samples_per_second": 566.586, "eval_steps_per_second": 9.09, "step": 10494 }, { "epoch": 100.0, "grad_norm": 0.00016238813987001777, "learning_rate": 0.0, "loss": 0.0002, "step": 10600 }, { "epoch": 100.0, "eval_LOCATION_f1": 0.870748299319728, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8205128205128205, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7903225806451614, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7424242424242424, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9225806451612903, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.9050632911392406, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8813559322033899, "eval_TIME_number": 29, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.34784960746765137, "eval_overall_accuracy": 0.9669654289372599, "eval_overall_f1": 0.8762446657183499, "eval_overall_precision": 0.8438356164383561, "eval_overall_recall": 0.9112426035502958, "eval_runtime": 0.3263, "eval_samples_per_second": 573.017, "eval_steps_per_second": 9.193, "step": 10600 }, { "epoch": 100.0, "step": 10600, "total_flos": 4488439619319522.0, "train_loss": 0.00870069551422208, "train_runtime": 967.5082, "train_samples_per_second": 174.365, "train_steps_per_second": 10.956 } ], "logging_steps": 500, "max_steps": 10600, "num_input_tokens_seen": 0, "num_train_epochs": 100, "save_steps": 500, "total_flos": 4488439619319522.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }