{ "best_metric": null, "best_model_checkpoint": null, "epoch": 100.0, "eval_steps": 500, "global_step": 10600, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 1.0272084474563599, "learning_rate": 4.9500000000000004e-05, "loss": 0.9918, "step": 106 }, { "epoch": 1.0, "eval_LOCATION_f1": 0.0, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.0, "eval_LOCATION_recall": 0.0, "eval_ORGANIZATION_f1": 0.0, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.047058823529411764, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.23529411764705882, "eval_PERSON_recall": 0.026143790849673203, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0588235294117647, "eval_TIME_number": 31, "eval_TIME_precision": 0.3333333333333333, "eval_TIME_recall": 0.03225806451612903, "eval_loss": 0.5814589858055115, "eval_overall_accuracy": 0.8387416398315581, "eval_overall_f1": 0.026315789473684213, "eval_overall_precision": 0.14705882352941177, "eval_overall_recall": 0.014450867052023121, "eval_runtime": 0.3818, "eval_samples_per_second": 489.811, "eval_steps_per_second": 7.858, "step": 106 }, { "epoch": 2.0, "grad_norm": 1.5510079860687256, "learning_rate": 4.9e-05, "loss": 0.5136, "step": 212 }, { "epoch": 2.0, "eval_LOCATION_f1": 0.07228915662650602, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.21428571428571427, "eval_LOCATION_recall": 0.043478260869565216, "eval_ORGANIZATION_f1": 0.02150537634408602, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.03125, "eval_ORGANIZATION_recall": 0.01639344262295082, "eval_PERSON_f1": 0.5854922279792746, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.48497854077253216, "eval_PERSON_recall": 0.738562091503268, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.4776119402985074, "eval_TIME_number": 31, "eval_TIME_precision": 0.4444444444444444, "eval_TIME_recall": 0.5161290322580645, "eval_loss": 0.3840640187263489, "eval_overall_accuracy": 0.8872925439682933, "eval_overall_f1": 0.39642324888226527, "eval_overall_precision": 0.40923076923076923, "eval_overall_recall": 0.38439306358381503, "eval_runtime": 0.3813, "eval_samples_per_second": 490.398, "eval_steps_per_second": 7.867, "step": 212 }, { "epoch": 3.0, "grad_norm": 1.2181504964828491, "learning_rate": 4.85e-05, "loss": 0.3245, "step": 318 }, { "epoch": 3.0, "eval_LOCATION_f1": 0.6335403726708074, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.5543478260869565, "eval_LOCATION_recall": 0.7391304347826086, "eval_ORGANIZATION_f1": 0.4903225806451613, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.40425531914893614, "eval_ORGANIZATION_recall": 0.6229508196721312, "eval_PERSON_f1": 0.8121212121212121, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7570621468926554, "eval_PERSON_recall": 0.8758169934640523, "eval_QUANTITY_f1": 0.5128205128205128, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.43478260869565216, "eval_QUANTITY_recall": 0.625, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.22633680701255798, "eval_overall_accuracy": 0.9291553133514986, "eval_overall_f1": 0.6852791878172589, "eval_overall_precision": 0.6108597285067874, "eval_overall_recall": 0.7803468208092486, "eval_runtime": 0.3827, "eval_samples_per_second": 488.604, "eval_steps_per_second": 7.839, "step": 318 }, { "epoch": 4.0, "grad_norm": 1.4188401699066162, "learning_rate": 4.8e-05, "loss": 0.2176, "step": 424 }, { "epoch": 4.0, "eval_LOCATION_f1": 0.6744186046511628, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.5631067961165048, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.5333333333333332, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.4864864864864865, "eval_ORGANIZATION_recall": 0.5901639344262295, "eval_PERSON_f1": 0.8338368580060423, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7752808988764045, "eval_PERSON_recall": 0.9019607843137255, "eval_QUANTITY_f1": 0.46153846153846156, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.3559322033898305, "eval_QUANTITY_recall": 0.65625, "eval_TIME_f1": 0.6578947368421053, "eval_TIME_number": 31, "eval_TIME_precision": 0.5555555555555556, "eval_TIME_recall": 0.8064516129032258, "eval_loss": 0.19828897714614868, "eval_overall_accuracy": 0.9298984394352242, "eval_overall_f1": 0.6906832298136646, "eval_overall_precision": 0.6056644880174292, "eval_overall_recall": 0.8034682080924855, "eval_runtime": 0.3817, "eval_samples_per_second": 489.958, "eval_steps_per_second": 7.86, "step": 424 }, { "epoch": 5.0, "grad_norm": 0.8591908812522888, "learning_rate": 4.75e-05, "loss": 0.1812, "step": 530 }, { "epoch": 5.0, "eval_LOCATION_f1": 0.7123287671232876, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6753246753246753, "eval_LOCATION_recall": 0.7536231884057971, "eval_ORGANIZATION_f1": 0.625, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5421686746987951, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.8650306748466258, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.815028901734104, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7222222222222223, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.65, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8387096774193549, "eval_TIME_number": 31, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14980928599834442, "eval_overall_accuracy": 0.9497151350012385, "eval_overall_f1": 0.7733333333333333, "eval_overall_precision": 0.7178217821782178, "eval_overall_recall": 0.838150289017341, "eval_runtime": 0.3817, "eval_samples_per_second": 489.861, "eval_steps_per_second": 7.859, "step": 530 }, { "epoch": 6.0, "grad_norm": 0.4265460968017578, "learning_rate": 4.7e-05, "loss": 0.1571, "step": 636 }, { "epoch": 6.0, "eval_LOCATION_f1": 0.7125, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6263736263736264, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.620253164556962, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5051546391752577, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8847352024922119, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8452380952380952, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.6756756756756757, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5952380952380952, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7536231884057972, "eval_TIME_number": 31, "eval_TIME_precision": 0.6842105263157895, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15143448114395142, "eval_overall_accuracy": 0.9464949219717612, "eval_overall_f1": 0.7647058823529412, "eval_overall_precision": 0.6857798165137615, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.381, "eval_samples_per_second": 490.81, "eval_steps_per_second": 7.874, "step": 636 }, { "epoch": 7.0, "grad_norm": 0.6821984648704529, "learning_rate": 4.6500000000000005e-05, "loss": 0.1435, "step": 742 }, { "epoch": 7.0, "eval_LOCATION_f1": 0.7388535031847134, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6590909090909091, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6712328767123288, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5764705882352941, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8711656441717791, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8208092485549133, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.641025641025641, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5434782608695652, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15106207132339478, "eval_overall_accuracy": 0.9497151350012385, "eval_overall_f1": 0.7782101167315175, "eval_overall_precision": 0.7058823529411765, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3811, "eval_samples_per_second": 490.727, "eval_steps_per_second": 7.873, "step": 742 }, { "epoch": 8.0, "grad_norm": 0.5688347220420837, "learning_rate": 4.600000000000001e-05, "loss": 0.1354, "step": 848 }, { "epoch": 8.0, "eval_LOCATION_f1": 0.778523489932886, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.725, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6363636363636364, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5268817204301075, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8757763975155279, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.834319526627219, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7123287671232876, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6341463414634146, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7027027027027026, "eval_TIME_number": 31, "eval_TIME_precision": 0.6046511627906976, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14667640626430511, "eval_overall_accuracy": 0.9504582610849641, "eval_overall_f1": 0.7772020725388601, "eval_overall_precision": 0.704225352112676, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3804, "eval_samples_per_second": 491.557, "eval_steps_per_second": 7.886, "step": 848 }, { "epoch": 9.0, "grad_norm": 1.076498031616211, "learning_rate": 4.55e-05, "loss": 0.1286, "step": 954 }, { "epoch": 9.0, "eval_LOCATION_f1": 0.7295597484276729, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6444444444444445, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6716417910447762, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6164383561643836, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.89375, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8562874251497006, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7222222222222223, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.65, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7123287671232876, "eval_TIME_number": 31, "eval_TIME_precision": 0.6190476190476191, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13916395604610443, "eval_overall_accuracy": 0.9546693088927422, "eval_overall_f1": 0.7862796833773087, "eval_overall_precision": 0.7233009708737864, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.383, "eval_samples_per_second": 488.209, "eval_steps_per_second": 7.832, "step": 954 }, { "epoch": 10.0, "grad_norm": 0.7342737317085266, "learning_rate": 4.5e-05, "loss": 0.1192, "step": 1060 }, { "epoch": 10.0, "eval_LOCATION_f1": 0.7567567567567568, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7088607594936709, "eval_LOCATION_recall": 0.8115942028985508, "eval_ORGANIZATION_f1": 0.6811594202898551, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6103896103896104, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8785046728971961, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8392857142857143, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7936507936507936, "eval_TIME_number": 31, "eval_TIME_precision": 0.78125, "eval_TIME_recall": 0.8064516129032258, "eval_loss": 0.12648716568946838, "eval_overall_accuracy": 0.9576418132276443, "eval_overall_f1": 0.7972972972972973, "eval_overall_precision": 0.748730964467005, "eval_overall_recall": 0.8526011560693642, "eval_runtime": 0.3808, "eval_samples_per_second": 491.1, "eval_steps_per_second": 7.879, "step": 1060 }, { "epoch": 11.0, "grad_norm": 0.3874886929988861, "learning_rate": 4.4500000000000004e-05, "loss": 0.111, "step": 1166 }, { "epoch": 11.0, "eval_LOCATION_f1": 0.75, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6867469879518072, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6666666666666667, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6081081081081081, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.8952380952380952, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8703703703703703, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7222222222222223, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.65, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8059701492537312, "eval_TIME_number": 31, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.12904293835163116, "eval_overall_accuracy": 0.9583849393113698, "eval_overall_f1": 0.7989203778677463, "eval_overall_precision": 0.7493670886075949, "eval_overall_recall": 0.8554913294797688, "eval_runtime": 0.3855, "eval_samples_per_second": 485.047, "eval_steps_per_second": 7.782, "step": 1166 }, { "epoch": 12.0, "grad_norm": 2.021855354309082, "learning_rate": 4.4000000000000006e-05, "loss": 0.1107, "step": 1272 }, { "epoch": 12.0, "eval_LOCATION_f1": 0.7945205479452054, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7532467532467533, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6715328467153285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6052631578947368, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8706624605678233, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.9019607843137255, "eval_QUANTITY_f1": 0.7123287671232876, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6341463414634146, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8064516129032258, "eval_TIME_number": 31, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8064516129032258, "eval_loss": 0.13058660924434662, "eval_overall_accuracy": 0.9564032697547684, "eval_overall_f1": 0.7972789115646259, "eval_overall_precision": 0.7532133676092545, "eval_overall_recall": 0.846820809248555, "eval_runtime": 0.3807, "eval_samples_per_second": 491.184, "eval_steps_per_second": 7.88, "step": 1272 }, { "epoch": 13.0, "grad_norm": 0.5758412480354309, "learning_rate": 4.35e-05, "loss": 0.102, "step": 1378 }, { "epoch": 13.0, "eval_LOCATION_f1": 0.7619047619047619, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.717948717948718, "eval_LOCATION_recall": 0.8115942028985508, "eval_ORGANIZATION_f1": 0.7210884353741497, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6162790697674418, "eval_ORGANIZATION_recall": 0.8688524590163934, "eval_PERSON_f1": 0.88125, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.844311377245509, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1381181925535202, "eval_overall_accuracy": 0.9576418132276443, "eval_overall_f1": 0.8048128342245989, "eval_overall_precision": 0.7487562189054726, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3792, "eval_samples_per_second": 493.132, "eval_steps_per_second": 7.911, "step": 1378 }, { "epoch": 14.0, "grad_norm": 1.8765839338302612, "learning_rate": 4.3e-05, "loss": 0.0995, "step": 1484 }, { "epoch": 14.0, "eval_LOCATION_f1": 0.8055555555555556, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7733333333333333, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.7591240875912408, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6842105263157895, "eval_ORGANIZATION_recall": 0.8524590163934426, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7605633802816902, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6923076923076923, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7605633802816901, "eval_TIME_number": 31, "eval_TIME_precision": 0.675, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1333017796278, "eval_overall_accuracy": 0.9598711914788209, "eval_overall_f1": 0.8286099865047234, "eval_overall_precision": 0.7772151898734178, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3856, "eval_samples_per_second": 484.98, "eval_steps_per_second": 7.78, "step": 1484 }, { "epoch": 15.0, "grad_norm": 0.3261714577674866, "learning_rate": 4.25e-05, "loss": 0.099, "step": 1590 }, { "epoch": 15.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6911764705882353, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6266666666666667, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8980891719745223, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8757763975155279, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7605633802816902, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6923076923076923, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8484848484848486, "eval_TIME_number": 31, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13288669288158417, "eval_overall_accuracy": 0.9598711914788209, "eval_overall_f1": 0.8195386702849389, "eval_overall_precision": 0.7723785166240409, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3826, "eval_samples_per_second": 488.811, "eval_steps_per_second": 7.842, "step": 1590 }, { "epoch": 16.0, "grad_norm": 0.4830576777458191, "learning_rate": 4.2e-05, "loss": 0.0931, "step": 1696 }, { "epoch": 16.0, "eval_LOCATION_f1": 0.8082191780821918, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7662337662337663, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6944444444444445, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6024096385542169, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9056603773584905, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8727272727272727, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7605633802816902, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6923076923076923, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13907834887504578, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.8247978436657681, "eval_overall_precision": 0.7727272727272727, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3853, "eval_samples_per_second": 485.328, "eval_steps_per_second": 7.786, "step": 1696 }, { "epoch": 17.0, "grad_norm": 0.4928819239139557, "learning_rate": 4.15e-05, "loss": 0.0906, "step": 1802 }, { "epoch": 17.0, "eval_LOCATION_f1": 0.7972972972972974, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7468354430379747, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.620253164556962, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7222222222222223, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.65, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.12818662822246552, "eval_overall_accuracy": 0.9598711914788209, "eval_overall_f1": 0.8167115902964959, "eval_overall_precision": 0.7651515151515151, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3827, "eval_samples_per_second": 488.583, "eval_steps_per_second": 7.838, "step": 1802 }, { "epoch": 18.0, "grad_norm": 0.7172600030899048, "learning_rate": 4.1e-05, "loss": 0.0856, "step": 1908 }, { "epoch": 18.0, "eval_LOCATION_f1": 0.8055555555555556, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7733333333333333, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6716417910447762, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6164383561643836, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7222222222222223, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.65, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8059701492537312, "eval_TIME_number": 31, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.13049036264419556, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.8130968622100955, "eval_overall_precision": 0.7700258397932817, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.3827, "eval_samples_per_second": 488.581, "eval_steps_per_second": 7.838, "step": 1908 }, { "epoch": 19.0, "grad_norm": 0.9027535915374756, "learning_rate": 4.05e-05, "loss": 0.0862, "step": 2014 }, { "epoch": 19.0, "eval_LOCATION_f1": 0.7916666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.76, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6814814814814815, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9113924050632911, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8834355828220859, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8615384615384616, "eval_TIME_number": 31, "eval_TIME_precision": 0.8235294117647058, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12171386927366257, "eval_overall_accuracy": 0.964082239286599, "eval_overall_f1": 0.8246575342465753, "eval_overall_precision": 0.7838541666666666, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3824, "eval_samples_per_second": 489.029, "eval_steps_per_second": 7.845, "step": 2014 }, { "epoch": 20.0, "grad_norm": 0.6771568059921265, "learning_rate": 4e-05, "loss": 0.0814, "step": 2120 }, { "epoch": 20.0, "eval_LOCATION_f1": 0.8137931034482757, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7763157894736842, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.697986577181208, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5909090909090909, "eval_ORGANIZATION_recall": 0.8524590163934426, "eval_PERSON_f1": 0.9056603773584905, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8727272727272727, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1427459567785263, "eval_overall_accuracy": 0.958632648005945, "eval_overall_f1": 0.8246318607764391, "eval_overall_precision": 0.7680798004987531, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.3808, "eval_samples_per_second": 491.039, "eval_steps_per_second": 7.878, "step": 2120 }, { "epoch": 21.0, "grad_norm": 0.6687225699424744, "learning_rate": 3.9500000000000005e-05, "loss": 0.0771, "step": 2226 }, { "epoch": 21.0, "eval_LOCATION_f1": 0.802721088435374, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7564102564102564, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6944444444444445, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6024096385542169, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8902821316614421, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8554216867469879, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7123287671232876, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6341463414634146, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.782608695652174, "eval_TIME_number": 31, "eval_TIME_precision": 0.7105263157894737, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14838886260986328, "eval_overall_accuracy": 0.9564032697547684, "eval_overall_f1": 0.8085106382978724, "eval_overall_precision": 0.7487684729064039, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3884, "eval_samples_per_second": 481.488, "eval_steps_per_second": 7.724, "step": 2226 }, { "epoch": 22.0, "grad_norm": 0.5799835324287415, "learning_rate": 3.9000000000000006e-05, "loss": 0.0803, "step": 2332 }, { "epoch": 22.0, "eval_LOCATION_f1": 0.8137931034482757, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7763157894736842, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6923076923076923, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5684210526315789, "eval_ORGANIZATION_recall": 0.8852459016393442, "eval_PERSON_f1": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7323943661971831, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6666666666666666, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1494436264038086, "eval_overall_accuracy": 0.9583849393113698, "eval_overall_f1": 0.8233731739707836, "eval_overall_precision": 0.7616707616707616, "eval_overall_recall": 0.8959537572254336, "eval_runtime": 0.3837, "eval_samples_per_second": 487.419, "eval_steps_per_second": 7.82, "step": 2332 }, { "epoch": 23.0, "grad_norm": 0.6878646612167358, "learning_rate": 3.85e-05, "loss": 0.0775, "step": 2438 }, { "epoch": 23.0, "eval_LOCATION_f1": 0.786206896551724, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.7007299270072993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.631578947368421, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9015873015873016, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8765432098765432, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7323943661971831, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6666666666666666, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1338999718427658, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8169398907103824, "eval_overall_precision": 0.7746113989637305, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.386, "eval_samples_per_second": 484.497, "eval_steps_per_second": 7.773, "step": 2438 }, { "epoch": 24.0, "grad_norm": 2.1059324741363525, "learning_rate": 3.8e-05, "loss": 0.0723, "step": 2544 }, { "epoch": 24.0, "eval_LOCATION_f1": 0.8194444444444444, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7866666666666666, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6766917293233082, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.625, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.896551724137931, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8614457831325302, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7123287671232876, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6341463414634146, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8405797101449276, "eval_TIME_number": 31, "eval_TIME_precision": 0.7631578947368421, "eval_TIME_recall": 0.9354838709677419, "eval_loss": 0.13374261558055878, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8184281842818428, "eval_overall_precision": 0.7704081632653061, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3878, "eval_samples_per_second": 482.16, "eval_steps_per_second": 7.735, "step": 2544 }, { "epoch": 25.0, "grad_norm": 0.4981442391872406, "learning_rate": 3.7500000000000003e-05, "loss": 0.0729, "step": 2650 }, { "epoch": 25.0, "eval_LOCATION_f1": 0.8, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7631578947368421, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.7034482758620689, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6071428571428571, "eval_ORGANIZATION_recall": 0.8360655737704918, "eval_PERSON_f1": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7123287671232876, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6341463414634146, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13796736299991608, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8165997322623829, "eval_overall_precision": 0.7605985037406484, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3871, "eval_samples_per_second": 483.14, "eval_steps_per_second": 7.751, "step": 2650 }, { "epoch": 26.0, "grad_norm": 0.8632038235664368, "learning_rate": 3.7e-05, "loss": 0.0694, "step": 2756 }, { "epoch": 26.0, "eval_LOCATION_f1": 0.8194444444444444, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7866666666666666, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6917293233082706, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9056603773584905, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8727272727272727, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7222222222222223, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.65, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8615384615384616, "eval_TIME_number": 31, "eval_TIME_precision": 0.8235294117647058, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1314733773469925, "eval_overall_accuracy": 0.9633391132028735, "eval_overall_f1": 0.8278688524590163, "eval_overall_precision": 0.7849740932642487, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3825, "eval_samples_per_second": 488.948, "eval_steps_per_second": 7.844, "step": 2756 }, { "epoch": 27.0, "grad_norm": 0.6470693945884705, "learning_rate": 3.65e-05, "loss": 0.063, "step": 2862 }, { "epoch": 27.0, "eval_LOCATION_f1": 0.8194444444444444, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7866666666666666, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.620253164556962, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.896551724137931, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8614457831325302, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7222222222222223, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.65, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8, "eval_TIME_number": 31, "eval_TIME_precision": 0.717948717948718, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13855965435504913, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8187919463087249, "eval_overall_precision": 0.7644110275689223, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3834, "eval_samples_per_second": 487.795, "eval_steps_per_second": 7.826, "step": 2862 }, { "epoch": 28.0, "grad_norm": 1.1696481704711914, "learning_rate": 3.6e-05, "loss": 0.0662, "step": 2968 }, { "epoch": 28.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6461538461538463, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6086956521739131, "eval_ORGANIZATION_recall": 0.6885245901639344, "eval_PERSON_f1": 0.9113924050632911, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8834355828220859, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8, "eval_TIME_number": 31, "eval_TIME_precision": 0.717948717948718, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1337006390094757, "eval_overall_accuracy": 0.9591280653950953, "eval_overall_f1": 0.8136054421768707, "eval_overall_precision": 0.7686375321336761, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.3817, "eval_samples_per_second": 489.934, "eval_steps_per_second": 7.86, "step": 2968 }, { "epoch": 29.0, "grad_norm": 0.6332246661186218, "learning_rate": 3.55e-05, "loss": 0.063, "step": 3074 }, { "epoch": 29.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6861313868613139, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.618421052631579, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9206349206349207, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8950617283950617, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7222222222222223, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.65, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8115942028985507, "eval_TIME_number": 31, "eval_TIME_precision": 0.7368421052631579, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13317342102527618, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8270270270270269, "eval_overall_precision": 0.7766497461928934, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3823, "eval_samples_per_second": 489.147, "eval_steps_per_second": 7.847, "step": 3074 }, { "epoch": 30.0, "grad_norm": 0.4695894122123718, "learning_rate": 3.5e-05, "loss": 0.0611, "step": 3180 }, { "epoch": 30.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6618705035971222, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5897435897435898, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9148264984227129, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8841463414634146, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7222222222222223, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.65, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1411614716053009, "eval_overall_accuracy": 0.9611097349516968, "eval_overall_f1": 0.8232118758434549, "eval_overall_precision": 0.7721518987341772, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3814, "eval_samples_per_second": 490.271, "eval_steps_per_second": 7.865, "step": 3180 }, { "epoch": 31.0, "grad_norm": 0.49676990509033203, "learning_rate": 3.45e-05, "loss": 0.0599, "step": 3286 }, { "epoch": 31.0, "eval_LOCATION_f1": 0.8194444444444444, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7866666666666666, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6870229007633588, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6428571428571429, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9148264984227129, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8841463414634146, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7323943661971831, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6666666666666666, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1362539380788803, "eval_overall_accuracy": 0.9628436958137231, "eval_overall_f1": 0.8301369863013699, "eval_overall_precision": 0.7890625, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3837, "eval_samples_per_second": 487.372, "eval_steps_per_second": 7.819, "step": 3286 }, { "epoch": 32.0, "grad_norm": 0.4171547591686249, "learning_rate": 3.4000000000000007e-05, "loss": 0.0587, "step": 3392 }, { "epoch": 32.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6323529411764707, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5733333333333334, "eval_ORGANIZATION_recall": 0.7049180327868853, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7222222222222223, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.65, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8059701492537312, "eval_TIME_number": 31, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.13879260420799255, "eval_overall_accuracy": 0.9593757740896706, "eval_overall_f1": 0.8054054054054054, "eval_overall_precision": 0.7563451776649747, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.383, "eval_samples_per_second": 488.286, "eval_steps_per_second": 7.833, "step": 3392 }, { "epoch": 33.0, "grad_norm": 0.9487641453742981, "learning_rate": 3.35e-05, "loss": 0.0586, "step": 3498 }, { "epoch": 33.0, "eval_LOCATION_f1": 0.8082191780821918, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7662337662337663, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6617647058823529, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9015873015873016, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8765432098765432, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.75, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.675, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.13592539727687836, "eval_overall_accuracy": 0.9623482784245727, "eval_overall_f1": 0.8185538881309687, "eval_overall_precision": 0.7751937984496124, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3847, "eval_samples_per_second": 486.08, "eval_steps_per_second": 7.798, "step": 3498 }, { "epoch": 34.0, "grad_norm": 0.36479949951171875, "learning_rate": 3.3e-05, "loss": 0.0568, "step": 3604 }, { "epoch": 34.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7164179104477612, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6575342465753424, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9303797468354431, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.901840490797546, "eval_PERSON_recall": 0.9607843137254902, "eval_QUANTITY_f1": 0.7605633802816902, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6923076923076923, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.782608695652174, "eval_TIME_number": 31, "eval_TIME_precision": 0.7105263157894737, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14891496300697327, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8335588633288228, "eval_overall_precision": 0.7837150127226463, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.3828, "eval_samples_per_second": 488.486, "eval_steps_per_second": 7.837, "step": 3604 }, { "epoch": 35.0, "grad_norm": 1.6607528924942017, "learning_rate": 3.2500000000000004e-05, "loss": 0.0563, "step": 3710 }, { "epoch": 35.0, "eval_LOCATION_f1": 0.7945205479452054, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7532467532467533, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.7428571428571428, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6582278481012658, "eval_ORGANIZATION_recall": 0.8524590163934426, "eval_PERSON_f1": 0.926517571884984, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.90625, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7605633802816902, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6923076923076923, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.875, "eval_TIME_number": 31, "eval_TIME_precision": 0.8484848484848485, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13815556466579437, "eval_overall_accuracy": 0.9633391132028735, "eval_overall_f1": 0.8446866485013624, "eval_overall_precision": 0.7989690721649485, "eval_overall_recall": 0.8959537572254336, "eval_runtime": 0.3811, "eval_samples_per_second": 490.694, "eval_steps_per_second": 7.872, "step": 3710 }, { "epoch": 36.0, "grad_norm": 0.37544718384742737, "learning_rate": 3.2000000000000005e-05, "loss": 0.0549, "step": 3816 }, { "epoch": 36.0, "eval_LOCATION_f1": 0.7891156462585034, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7435897435897436, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.7101449275362318, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6363636363636364, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.13398179411888123, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8233695652173912, "eval_overall_precision": 0.7769230769230769, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3859, "eval_samples_per_second": 484.607, "eval_steps_per_second": 7.774, "step": 3816 }, { "epoch": 37.0, "grad_norm": 1.0679214000701904, "learning_rate": 3.15e-05, "loss": 0.0534, "step": 3922 }, { "epoch": 37.0, "eval_LOCATION_f1": 0.8251748251748252, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7972972972972973, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6766917293233082, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.625, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9171974522292994, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8944099378881988, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.875, "eval_TIME_number": 31, "eval_TIME_precision": 0.8484848484848485, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13130351901054382, "eval_overall_accuracy": 0.9658162001486252, "eval_overall_f1": 0.8404993065187241, "eval_overall_precision": 0.808, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3837, "eval_samples_per_second": 487.405, "eval_steps_per_second": 7.819, "step": 3922 }, { "epoch": 38.0, "grad_norm": 0.24864430725574493, "learning_rate": 3.1e-05, "loss": 0.0549, "step": 4028 }, { "epoch": 38.0, "eval_LOCATION_f1": 0.7972972972972974, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7468354430379747, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6412213740458015, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6, "eval_ORGANIZATION_recall": 0.6885245901639344, "eval_PERSON_f1": 0.9177215189873417, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8895705521472392, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7222222222222223, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.65, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.875, "eval_TIME_number": 31, "eval_TIME_precision": 0.8484848484848485, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13381846249103546, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8207934336525308, "eval_overall_precision": 0.7792207792207793, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3832, "eval_samples_per_second": 487.955, "eval_steps_per_second": 7.828, "step": 4028 }, { "epoch": 39.0, "grad_norm": 0.7260211110115051, "learning_rate": 3.05e-05, "loss": 0.0503, "step": 4134 }, { "epoch": 39.0, "eval_LOCATION_f1": 0.8137931034482757, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7763157894736842, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6818181818181818, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6338028169014085, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9206349206349207, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8950617283950617, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7714285714285714, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7105263157894737, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.13943922519683838, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8347107438016529, "eval_overall_precision": 0.7973684210526316, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3818, "eval_samples_per_second": 489.726, "eval_steps_per_second": 7.857, "step": 4134 }, { "epoch": 40.0, "grad_norm": 0.6635225415229797, "learning_rate": 3e-05, "loss": 0.0492, "step": 4240 }, { "epoch": 40.0, "eval_LOCATION_f1": 0.8079470198675496, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6515151515151515, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6056338028169014, "eval_ORGANIZATION_recall": 0.7049180327868853, "eval_PERSON_f1": 0.909657320872274, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8690476190476191, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.7714285714285714, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7105263157894737, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8405797101449276, "eval_TIME_number": 31, "eval_TIME_precision": 0.7631578947368421, "eval_TIME_recall": 0.9354838709677419, "eval_loss": 0.15114636719226837, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8236877523553163, "eval_overall_precision": 0.7707808564231738, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3819, "eval_samples_per_second": 489.6, "eval_steps_per_second": 7.855, "step": 4240 }, { "epoch": 41.0, "grad_norm": 0.1464150995016098, "learning_rate": 2.95e-05, "loss": 0.0489, "step": 4346 }, { "epoch": 41.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7058823529411764, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.64, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9119496855345912, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8787878787878788, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7605633802816902, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6923076923076923, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8923076923076922, "eval_TIME_number": 31, "eval_TIME_precision": 0.8529411764705882, "eval_TIME_recall": 0.9354838709677419, "eval_loss": 0.14375168085098267, "eval_overall_accuracy": 0.9648253653703245, "eval_overall_f1": 0.8373983739837398, "eval_overall_precision": 0.7882653061224489, "eval_overall_recall": 0.8930635838150289, "eval_runtime": 0.3823, "eval_samples_per_second": 489.175, "eval_steps_per_second": 7.848, "step": 4346 }, { "epoch": 42.0, "grad_norm": 0.8611084818840027, "learning_rate": 2.9e-05, "loss": 0.0484, "step": 4452 }, { "epoch": 42.0, "eval_LOCATION_f1": 0.7891156462585034, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7435897435897436, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.7092198581560285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.625, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9177215189873417, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8895705521472392, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7714285714285714, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7105263157894737, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.15438592433929443, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.8308525033829499, "eval_overall_precision": 0.7811704834605598, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3851, "eval_samples_per_second": 485.57, "eval_steps_per_second": 7.79, "step": 4452 }, { "epoch": 43.0, "grad_norm": 0.7216106653213501, "learning_rate": 2.8499999999999998e-05, "loss": 0.0446, "step": 4558 }, { "epoch": 43.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6456692913385826, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6212121212121212, "eval_ORGANIZATION_recall": 0.6721311475409836, "eval_PERSON_f1": 0.9171974522292994, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8944099378881988, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.823529411764706, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7777777777777778, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.90625, "eval_TIME_number": 31, "eval_TIME_precision": 0.8787878787878788, "eval_TIME_recall": 0.9354838709677419, "eval_loss": 0.13229750096797943, "eval_overall_accuracy": 0.9643299479811741, "eval_overall_f1": 0.8388888888888889, "eval_overall_precision": 0.8074866310160428, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3838, "eval_samples_per_second": 487.289, "eval_steps_per_second": 7.817, "step": 4558 }, { "epoch": 44.0, "grad_norm": 0.5811746716499329, "learning_rate": 2.8000000000000003e-05, "loss": 0.0463, "step": 4664 }, { "epoch": 44.0, "eval_LOCATION_f1": 0.8157894736842105, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.7014925373134328, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6438356164383562, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7323943661971831, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6666666666666666, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14487981796264648, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8238482384823848, "eval_overall_precision": 0.7755102040816326, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3833, "eval_samples_per_second": 487.825, "eval_steps_per_second": 7.826, "step": 4664 }, { "epoch": 45.0, "grad_norm": 0.9379541277885437, "learning_rate": 2.7500000000000004e-05, "loss": 0.0457, "step": 4770 }, { "epoch": 45.0, "eval_LOCATION_f1": 0.8378378378378378, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7848101265822784, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6976744186046512, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6617647058823529, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9050632911392406, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8773006134969326, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7999999999999999, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7368421052631579, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.8484848484848486, "eval_TIME_number": 31, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13066914677619934, "eval_overall_accuracy": 0.9648253653703245, "eval_overall_f1": 0.839506172839506, "eval_overall_precision": 0.7989556135770235, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3832, "eval_samples_per_second": 488.01, "eval_steps_per_second": 7.829, "step": 4770 }, { "epoch": 46.0, "grad_norm": 0.38373321294784546, "learning_rate": 2.7000000000000002e-05, "loss": 0.0436, "step": 4876 }, { "epoch": 46.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6969696969696969, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.647887323943662, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7999999999999999, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7368421052631579, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14025072753429413, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8333333333333334, "eval_overall_precision": 0.7901554404145078, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3836, "eval_samples_per_second": 487.546, "eval_steps_per_second": 7.822, "step": 4876 }, { "epoch": 47.0, "grad_norm": 0.8705413937568665, "learning_rate": 2.6500000000000004e-05, "loss": 0.0439, "step": 4982 }, { "epoch": 47.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.682170542635659, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6470588235294118, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.9177215189873417, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8895705521472392, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7999999999999999, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7368421052631579, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1442147195339203, "eval_overall_accuracy": 0.964082239286599, "eval_overall_f1": 0.8397790055248618, "eval_overall_precision": 0.8042328042328042, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3847, "eval_samples_per_second": 486.092, "eval_steps_per_second": 7.798, "step": 4982 }, { "epoch": 48.0, "grad_norm": 0.906028151512146, "learning_rate": 2.6000000000000002e-05, "loss": 0.0425, "step": 5088 }, { "epoch": 48.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7246376811594203, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6493506493506493, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.910828025477707, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8881987577639752, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.767123287671233, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6829268292682927, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1539994776248932, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8317631224764468, "eval_overall_precision": 0.7783375314861462, "eval_overall_recall": 0.8930635838150289, "eval_runtime": 0.3824, "eval_samples_per_second": 489.027, "eval_steps_per_second": 7.845, "step": 5088 }, { "epoch": 49.0, "grad_norm": 0.25983723998069763, "learning_rate": 2.5500000000000003e-05, "loss": 0.0446, "step": 5194 }, { "epoch": 49.0, "eval_LOCATION_f1": 0.786206896551724, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6865671641791045, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9056603773584905, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8727272727272727, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7826086956521738, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7297297297297297, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8387096774193549, "eval_TIME_number": 31, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14243273437023163, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8241758241758242, "eval_overall_precision": 0.7853403141361257, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3807, "eval_samples_per_second": 491.159, "eval_steps_per_second": 7.88, "step": 5194 }, { "epoch": 50.0, "grad_norm": 0.8506327867507935, "learning_rate": 2.5e-05, "loss": 0.0409, "step": 5300 }, { "epoch": 50.0, "eval_LOCATION_f1": 0.8275862068965517, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6976744186046512, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6617647058823529, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7826086956521738, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7297297297297297, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14614629745483398, "eval_overall_accuracy": 0.9648253653703245, "eval_overall_f1": 0.833103448275862, "eval_overall_precision": 0.7968337730870713, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.383, "eval_samples_per_second": 488.264, "eval_steps_per_second": 7.833, "step": 5300 }, { "epoch": 51.0, "grad_norm": 0.6887333989143372, "learning_rate": 2.45e-05, "loss": 0.0419, "step": 5406 }, { "epoch": 51.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6799999999999999, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5730337078651685, "eval_ORGANIZATION_recall": 0.8360655737704918, "eval_PERSON_f1": 0.9119496855345912, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8787878787878788, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7714285714285714, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7105263157894737, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8615384615384616, "eval_TIME_number": 31, "eval_TIME_precision": 0.8235294117647058, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1532040238380432, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8282290279627165, "eval_overall_precision": 0.7679012345679013, "eval_overall_recall": 0.8988439306358381, "eval_runtime": 0.3837, "eval_samples_per_second": 487.302, "eval_steps_per_second": 7.818, "step": 5406 }, { "epoch": 52.0, "grad_norm": 0.8161492347717285, "learning_rate": 2.4e-05, "loss": 0.0406, "step": 5512 }, { "epoch": 52.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7164179104477612, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6575342465753424, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9079365079365078, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8827160493827161, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.823529411764706, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7777777777777778, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.8484848484848486, "eval_TIME_number": 31, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.14783500134944916, "eval_overall_accuracy": 0.9645776566757494, "eval_overall_f1": 0.8387978142076503, "eval_overall_precision": 0.7953367875647669, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3829, "eval_samples_per_second": 488.43, "eval_steps_per_second": 7.836, "step": 5512 }, { "epoch": 53.0, "grad_norm": 0.7052940130233765, "learning_rate": 2.35e-05, "loss": 0.0417, "step": 5618 }, { "epoch": 53.0, "eval_LOCATION_f1": 0.802721088435374, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7564102564102564, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6906474820143885, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6153846153846154, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9240506329113924, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8957055214723927, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8358208955223881, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.8, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.8387096774193549, "eval_TIME_number": 31, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1469346284866333, "eval_overall_accuracy": 0.9645776566757494, "eval_overall_f1": 0.8399452804377565, "eval_overall_precision": 0.7974025974025974, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3832, "eval_samples_per_second": 487.973, "eval_steps_per_second": 7.828, "step": 5618 }, { "epoch": 54.0, "grad_norm": 7.3201823234558105, "learning_rate": 2.3000000000000003e-05, "loss": 0.0387, "step": 5724 }, { "epoch": 54.0, "eval_LOCATION_f1": 0.7972972972972974, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7468354430379747, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7218045112781954, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9177215189873417, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8895705521472392, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1538899838924408, "eval_overall_accuracy": 0.9650730740648997, "eval_overall_f1": 0.8383561643835618, "eval_overall_precision": 0.796875, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3864, "eval_samples_per_second": 483.91, "eval_steps_per_second": 7.763, "step": 5724 }, { "epoch": 55.0, "grad_norm": 0.6526756882667542, "learning_rate": 2.25e-05, "loss": 0.0387, "step": 5830 }, { "epoch": 55.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6956521739130435, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6233766233766234, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9177215189873417, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8895705521472392, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7605633802816902, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6923076923076923, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14972607791423798, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8276797829036635, "eval_overall_precision": 0.7800511508951407, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3818, "eval_samples_per_second": 489.724, "eval_steps_per_second": 7.857, "step": 5830 }, { "epoch": 56.0, "grad_norm": 0.48691311478614807, "learning_rate": 2.2000000000000003e-05, "loss": 0.0385, "step": 5936 }, { "epoch": 56.0, "eval_LOCATION_f1": 0.802721088435374, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7564102564102564, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6865671641791045, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9177215189873417, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8895705521472392, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7714285714285714, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7105263157894737, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14442645013332367, "eval_overall_accuracy": 0.9645776566757494, "eval_overall_f1": 0.8306010928961748, "eval_overall_precision": 0.7875647668393783, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3823, "eval_samples_per_second": 489.133, "eval_steps_per_second": 7.847, "step": 5936 }, { "epoch": 57.0, "grad_norm": 0.5005918145179749, "learning_rate": 2.15e-05, "loss": 0.0359, "step": 6042 }, { "epoch": 57.0, "eval_LOCATION_f1": 0.8322147651006713, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.775, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6511627906976745, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6176470588235294, "eval_ORGANIZATION_recall": 0.6885245901639344, "eval_PERSON_f1": 0.9177215189873417, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8895705521472392, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14682108163833618, "eval_overall_accuracy": 0.96556849145405, "eval_overall_f1": 0.8347107438016529, "eval_overall_precision": 0.7973684210526316, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3819, "eval_samples_per_second": 489.637, "eval_steps_per_second": 7.855, "step": 6042 }, { "epoch": 58.0, "grad_norm": 0.40474098920822144, "learning_rate": 2.1e-05, "loss": 0.0366, "step": 6148 }, { "epoch": 58.0, "eval_LOCATION_f1": 0.8322147651006713, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.775, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.7014925373134328, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6438356164383562, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9177215189873417, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8895705521472392, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14990100264549255, "eval_overall_accuracy": 0.9653207827594749, "eval_overall_f1": 0.8410958904109589, "eval_overall_precision": 0.7994791666666666, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3831, "eval_samples_per_second": 488.137, "eval_steps_per_second": 7.831, "step": 6148 }, { "epoch": 59.0, "grad_norm": 0.5422191619873047, "learning_rate": 2.05e-05, "loss": 0.0349, "step": 6254 }, { "epoch": 59.0, "eval_LOCATION_f1": 0.8299319727891156, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7058823529411764, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.64, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9177215189873417, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8895705521472392, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7605633802816902, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6923076923076923, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8484848484848486, "eval_TIME_number": 31, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.15260933339595795, "eval_overall_accuracy": 0.9653207827594749, "eval_overall_f1": 0.8396739130434783, "eval_overall_precision": 0.7923076923076923, "eval_overall_recall": 0.8930635838150289, "eval_runtime": 0.3829, "eval_samples_per_second": 488.41, "eval_steps_per_second": 7.835, "step": 6254 }, { "epoch": 60.0, "grad_norm": 1.01388680934906, "learning_rate": 2e-05, "loss": 0.0358, "step": 6360 }, { "epoch": 60.0, "eval_LOCATION_f1": 0.7947019867549668, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7205882352941175, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6533333333333333, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.9148264984227129, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8841463414634146, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7714285714285714, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7105263157894737, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.875, "eval_TIME_number": 31, "eval_TIME_precision": 0.8484848484848485, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.15072497725486755, "eval_overall_accuracy": 0.9653207827594749, "eval_overall_f1": 0.8373983739837398, "eval_overall_precision": 0.7882653061224489, "eval_overall_recall": 0.8930635838150289, "eval_runtime": 0.3811, "eval_samples_per_second": 490.737, "eval_steps_per_second": 7.873, "step": 6360 }, { "epoch": 61.0, "grad_norm": 0.32948485016822815, "learning_rate": 1.9500000000000003e-05, "loss": 0.0347, "step": 6466 }, { "epoch": 61.0, "eval_LOCATION_f1": 0.8187919463087248, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7625, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6917293233082706, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9113924050632911, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8834355828220859, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1476087123155594, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8367626886145405, "eval_overall_precision": 0.7963446475195822, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3841, "eval_samples_per_second": 486.827, "eval_steps_per_second": 7.81, "step": 6466 }, { "epoch": 62.0, "grad_norm": 0.46073493361473083, "learning_rate": 1.9e-05, "loss": 0.0339, "step": 6572 }, { "epoch": 62.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6923076923076924, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6521739130434783, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.9015873015873016, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8765432098765432, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.8115942028985507, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7567567567567568, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.8709677419354839, "eval_TIME_number": 31, "eval_TIME_precision": 0.8709677419354839, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14788304269313812, "eval_overall_accuracy": 0.9653207827594749, "eval_overall_f1": 0.8370165745856354, "eval_overall_precision": 0.8015873015873016, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3849, "eval_samples_per_second": 485.837, "eval_steps_per_second": 7.794, "step": 6572 }, { "epoch": 63.0, "grad_norm": 0.10588483512401581, "learning_rate": 1.85e-05, "loss": 0.035, "step": 6678 }, { "epoch": 63.0, "eval_LOCATION_f1": 0.8187919463087248, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7625, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7313432835820896, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6712328767123288, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.910828025477707, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8881987577639752, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8709677419354839, "eval_TIME_number": 31, "eval_TIME_precision": 0.8709677419354839, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.15484392642974854, "eval_overall_accuracy": 0.9653207827594749, "eval_overall_f1": 0.844566712517194, "eval_overall_precision": 0.8057742782152231, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3828, "eval_samples_per_second": 488.461, "eval_steps_per_second": 7.836, "step": 6678 }, { "epoch": 64.0, "grad_norm": 0.8103458881378174, "learning_rate": 1.8e-05, "loss": 0.0316, "step": 6784 }, { "epoch": 64.0, "eval_LOCATION_f1": 0.8187919463087248, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7625, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7007299270072993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.631578947368421, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9182389937106918, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8848484848484849, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.7826086956521738, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7297297297297297, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8387096774193549, "eval_TIME_number": 31, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15606780350208282, "eval_overall_accuracy": 0.9633391132028735, "eval_overall_f1": 0.8380952380952382, "eval_overall_precision": 0.7917737789203085, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.3816, "eval_samples_per_second": 490.038, "eval_steps_per_second": 7.862, "step": 6784 }, { "epoch": 65.0, "grad_norm": 0.6652474403381348, "learning_rate": 1.75e-05, "loss": 0.0339, "step": 6890 }, { "epoch": 65.0, "eval_LOCATION_f1": 0.8299319727891156, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6762589928057554, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6025641025641025, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9009584664536741, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.88125, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8709677419354839, "eval_TIME_number": 31, "eval_TIME_precision": 0.8709677419354839, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.15425816178321838, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8324175824175825, "eval_overall_precision": 0.7931937172774869, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.382, "eval_samples_per_second": 489.487, "eval_steps_per_second": 7.853, "step": 6890 }, { "epoch": 66.0, "grad_norm": 0.5202561616897583, "learning_rate": 1.7000000000000003e-05, "loss": 0.0333, "step": 6996 }, { "epoch": 66.0, "eval_LOCATION_f1": 0.7837837837837838, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7341772151898734, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.7218045112781954, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9119496855345912, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8787878787878788, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1552451103925705, "eval_overall_accuracy": 0.9645776566757494, "eval_overall_f1": 0.8306010928961748, "eval_overall_precision": 0.7875647668393783, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3837, "eval_samples_per_second": 487.312, "eval_steps_per_second": 7.818, "step": 6996 }, { "epoch": 67.0, "grad_norm": 0.638265073299408, "learning_rate": 1.65e-05, "loss": 0.0328, "step": 7102 }, { "epoch": 67.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7313432835820896, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6712328767123288, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.9206349206349207, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8950617283950617, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7826086956521738, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7297297297297297, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8387096774193549, "eval_TIME_number": 31, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1508781760931015, "eval_overall_accuracy": 0.9660639088432004, "eval_overall_f1": 0.8422496570644717, "eval_overall_precision": 0.8015665796344648, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3832, "eval_samples_per_second": 488.055, "eval_steps_per_second": 7.83, "step": 7102 }, { "epoch": 68.0, "grad_norm": 0.06523913145065308, "learning_rate": 1.6000000000000003e-05, "loss": 0.0305, "step": 7208 }, { "epoch": 68.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7313432835820896, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6712328767123288, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.9044585987261147, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8819875776397516, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.75, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.675, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1613590270280838, "eval_overall_accuracy": 0.9628436958137231, "eval_overall_f1": 0.8310626702997275, "eval_overall_precision": 0.7860824742268041, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3829, "eval_samples_per_second": 488.339, "eval_steps_per_second": 7.834, "step": 7208 }, { "epoch": 69.0, "grad_norm": 0.5326893329620361, "learning_rate": 1.55e-05, "loss": 0.0331, "step": 7314 }, { "epoch": 69.0, "eval_LOCATION_f1": 0.8493150684931507, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8051948051948052, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.7076923076923076, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9079365079365078, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8827160493827161, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8888888888888888, "eval_TIME_number": 31, "eval_TIME_precision": 0.875, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.15333113074302673, "eval_overall_accuracy": 0.9648253653703245, "eval_overall_f1": 0.8488210818307905, "eval_overall_precision": 0.816, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3863, "eval_samples_per_second": 484.124, "eval_steps_per_second": 7.767, "step": 7314 }, { "epoch": 70.0, "grad_norm": 0.4003902077674866, "learning_rate": 1.5e-05, "loss": 0.0325, "step": 7420 }, { "epoch": 70.0, "eval_LOCATION_f1": 0.8356164383561644, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7922077922077922, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6861313868613139, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.618421052631579, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9113924050632911, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8834355828220859, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.15659072995185852, "eval_overall_accuracy": 0.964082239286599, "eval_overall_f1": 0.8383561643835618, "eval_overall_precision": 0.796875, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3887, "eval_samples_per_second": 481.037, "eval_steps_per_second": 7.717, "step": 7420 }, { "epoch": 71.0, "grad_norm": 0.27532684803009033, "learning_rate": 1.45e-05, "loss": 0.0284, "step": 7526 }, { "epoch": 71.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7153284671532848, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6447368421052632, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.823529411764706, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7777777777777778, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.8387096774193549, "eval_TIME_number": 31, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15998543798923492, "eval_overall_accuracy": 0.9648253653703245, "eval_overall_f1": 0.8399452804377565, "eval_overall_precision": 0.7974025974025974, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3818, "eval_samples_per_second": 489.784, "eval_steps_per_second": 7.858, "step": 7526 }, { "epoch": 72.0, "grad_norm": 0.470971941947937, "learning_rate": 1.4000000000000001e-05, "loss": 0.0323, "step": 7632 }, { "epoch": 72.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7067669172932329, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6527777777777778, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7826086956521738, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7297297297297297, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8064516129032258, "eval_TIME_number": 31, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8064516129032258, "eval_loss": 0.15766850113868713, "eval_overall_accuracy": 0.9638345305920237, "eval_overall_f1": 0.8296703296703297, "eval_overall_precision": 0.7905759162303665, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.382, "eval_samples_per_second": 489.473, "eval_steps_per_second": 7.853, "step": 7632 }, { "epoch": 73.0, "grad_norm": 0.8524491190910339, "learning_rate": 1.3500000000000001e-05, "loss": 0.0289, "step": 7738 }, { "epoch": 73.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.676470588235294, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6133333333333333, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9148264984227129, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8841463414634146, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8387096774193549, "eval_TIME_number": 31, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1593465507030487, "eval_overall_accuracy": 0.9643299479811741, "eval_overall_f1": 0.8328767123287673, "eval_overall_precision": 0.7916666666666666, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3839, "eval_samples_per_second": 487.123, "eval_steps_per_second": 7.815, "step": 7738 }, { "epoch": 74.0, "grad_norm": 0.5028882026672363, "learning_rate": 1.3000000000000001e-05, "loss": 0.0295, "step": 7844 }, { "epoch": 74.0, "eval_LOCATION_f1": 0.8378378378378378, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7848101265822784, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6567164179104478, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6027397260273972, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.9050632911392406, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8773006134969326, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7826086956521738, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7297297297297297, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.16330695152282715, "eval_overall_accuracy": 0.9633391132028735, "eval_overall_f1": 0.8262653898768809, "eval_overall_precision": 0.7844155844155845, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3841, "eval_samples_per_second": 486.881, "eval_steps_per_second": 7.811, "step": 7844 }, { "epoch": 75.0, "grad_norm": 0.5104759931564331, "learning_rate": 1.25e-05, "loss": 0.0274, "step": 7950 }, { "epoch": 75.0, "eval_LOCATION_f1": 0.8435374149659864, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6356589147286822, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6029411764705882, "eval_ORGANIZATION_recall": 0.6721311475409836, "eval_PERSON_f1": 0.910828025477707, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8881987577639752, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.16056643426418304, "eval_overall_accuracy": 0.9643299479811741, "eval_overall_f1": 0.8282548476454293, "eval_overall_precision": 0.7952127659574468, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.38, "eval_samples_per_second": 492.112, "eval_steps_per_second": 7.895, "step": 7950 }, { "epoch": 76.0, "grad_norm": 1.8361543416976929, "learning_rate": 1.2e-05, "loss": 0.0292, "step": 8056 }, { "epoch": 76.0, "eval_LOCATION_f1": 0.8322147651006713, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.775, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.676470588235294, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6133333333333333, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9177215189873417, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8895705521472392, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8064516129032258, "eval_TIME_number": 31, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8064516129032258, "eval_loss": 0.16704599559307098, "eval_overall_accuracy": 0.9643299479811741, "eval_overall_f1": 0.8356164383561644, "eval_overall_precision": 0.7942708333333334, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3798, "eval_samples_per_second": 492.394, "eval_steps_per_second": 7.899, "step": 8056 }, { "epoch": 77.0, "grad_norm": 0.2984037697315216, "learning_rate": 1.1500000000000002e-05, "loss": 0.0271, "step": 8162 }, { "epoch": 77.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.676470588235294, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6133333333333333, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9050632911392406, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8773006134969326, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.16829800605773926, "eval_overall_accuracy": 0.9645776566757494, "eval_overall_f1": 0.8283378746594006, "eval_overall_precision": 0.7835051546391752, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.382, "eval_samples_per_second": 489.498, "eval_steps_per_second": 7.853, "step": 8162 }, { "epoch": 78.0, "grad_norm": 0.5857195258140564, "learning_rate": 1.1000000000000001e-05, "loss": 0.0281, "step": 8268 }, { "epoch": 78.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6616541353383459, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6111111111111112, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.9050632911392406, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8773006134969326, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7826086956521738, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7297297297297297, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.16350550949573517, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8303448275862069, "eval_overall_precision": 0.7941952506596306, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3811, "eval_samples_per_second": 490.73, "eval_steps_per_second": 7.873, "step": 8268 }, { "epoch": 79.0, "grad_norm": 0.4454423785209656, "learning_rate": 1.05e-05, "loss": 0.026, "step": 8374 }, { "epoch": 79.0, "eval_LOCATION_f1": 0.8391608391608392, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8108108108108109, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6865671641791045, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.910828025477707, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8881987577639752, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8064516129032258, "eval_TIME_number": 31, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8064516129032258, "eval_loss": 0.15963782370090485, "eval_overall_accuracy": 0.9653207827594749, "eval_overall_f1": 0.8349514563106797, "eval_overall_precision": 0.8026666666666666, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3813, "eval_samples_per_second": 490.451, "eval_steps_per_second": 7.868, "step": 8374 }, { "epoch": 80.0, "grad_norm": 0.3006572425365448, "learning_rate": 1e-05, "loss": 0.0265, "step": 8480 }, { "epoch": 80.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7058823529411764, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.64, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9177215189873417, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8895705521472392, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7714285714285714, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7105263157894737, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1699979156255722, "eval_overall_accuracy": 0.9633391132028735, "eval_overall_f1": 0.8326530612244898, "eval_overall_precision": 0.7866323907455013, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.387, "eval_samples_per_second": 483.167, "eval_steps_per_second": 7.751, "step": 8480 }, { "epoch": 81.0, "grad_norm": 0.3541398346424103, "learning_rate": 9.5e-06, "loss": 0.0262, "step": 8586 }, { "epoch": 81.0, "eval_LOCATION_f1": 0.8299319727891156, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7014925373134328, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6438356164383562, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7826086956521738, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7297297297297297, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.16345323622226715, "eval_overall_accuracy": 0.9643299479811741, "eval_overall_f1": 0.8367626886145405, "eval_overall_precision": 0.7963446475195822, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3803, "eval_samples_per_second": 491.719, "eval_steps_per_second": 7.889, "step": 8586 }, { "epoch": 82.0, "grad_norm": 0.7298364043235779, "learning_rate": 9e-06, "loss": 0.0275, "step": 8692 }, { "epoch": 82.0, "eval_LOCATION_f1": 0.8187919463087248, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7625, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.711111111111111, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6486486486486487, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9090909090909091, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8734939759036144, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7714285714285714, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7105263157894737, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1723509579896927, "eval_overall_accuracy": 0.9628436958137231, "eval_overall_f1": 0.8319783197831978, "eval_overall_precision": 0.7831632653061225, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3814, "eval_samples_per_second": 490.283, "eval_steps_per_second": 7.866, "step": 8692 }, { "epoch": 83.0, "grad_norm": 0.17061911523342133, "learning_rate": 8.500000000000002e-06, "loss": 0.0268, "step": 8798 }, { "epoch": 83.0, "eval_LOCATION_f1": 0.8299319727891156, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7014925373134328, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6438356164383562, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.910828025477707, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8881987577639752, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7714285714285714, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7105263157894737, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1663985699415207, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8340192043895747, "eval_overall_precision": 0.793733681462141, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3818, "eval_samples_per_second": 489.836, "eval_steps_per_second": 7.858, "step": 8798 }, { "epoch": 84.0, "grad_norm": 1.4881929159164429, "learning_rate": 8.000000000000001e-06, "loss": 0.0256, "step": 8904 }, { "epoch": 84.0, "eval_LOCATION_f1": 0.8275862068965517, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7164179104477612, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6575342465753424, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.910828025477707, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8881987577639752, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.16189546883106232, "eval_overall_accuracy": 0.9653207827594749, "eval_overall_f1": 0.8397790055248618, "eval_overall_precision": 0.8042328042328042, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3841, "eval_samples_per_second": 486.853, "eval_steps_per_second": 7.81, "step": 8904 }, { "epoch": 85.0, "grad_norm": 0.3548848628997803, "learning_rate": 7.5e-06, "loss": 0.0265, "step": 9010 }, { "epoch": 85.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7175572519083969, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6714285714285714, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1618238389492035, "eval_overall_accuracy": 0.96556849145405, "eval_overall_f1": 0.8390646492434664, "eval_overall_precision": 0.800524934383202, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3818, "eval_samples_per_second": 489.793, "eval_steps_per_second": 7.858, "step": 9010 }, { "epoch": 86.0, "grad_norm": 1.7985620498657227, "learning_rate": 7.000000000000001e-06, "loss": 0.0256, "step": 9116 }, { "epoch": 86.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7014925373134328, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6438356164383562, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9148264984227129, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8841463414634146, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7714285714285714, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7105263157894737, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.16945821046829224, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8326530612244898, "eval_overall_precision": 0.7866323907455013, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.381, "eval_samples_per_second": 490.822, "eval_steps_per_second": 7.874, "step": 9116 }, { "epoch": 87.0, "grad_norm": 2.4566051959991455, "learning_rate": 6.5000000000000004e-06, "loss": 0.027, "step": 9222 }, { "epoch": 87.0, "eval_LOCATION_f1": 0.8435374149659864, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6969696969696969, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.647887323943662, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.16637147963047028, "eval_overall_accuracy": 0.9650730740648997, "eval_overall_f1": 0.8413793103448276, "eval_overall_precision": 0.8047493403693932, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.382, "eval_samples_per_second": 489.521, "eval_steps_per_second": 7.853, "step": 9222 }, { "epoch": 88.0, "grad_norm": 0.17908763885498047, "learning_rate": 6e-06, "loss": 0.0249, "step": 9328 }, { "epoch": 88.0, "eval_LOCATION_f1": 0.8435374149659864, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6969696969696969, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.647887323943662, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9182389937106918, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8848484848484849, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1701187640428543, "eval_overall_accuracy": 0.96556849145405, "eval_overall_f1": 0.8461538461538461, "eval_overall_precision": 0.806282722513089, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.3825, "eval_samples_per_second": 488.883, "eval_steps_per_second": 7.843, "step": 9328 }, { "epoch": 89.0, "grad_norm": 0.9025946855545044, "learning_rate": 5.500000000000001e-06, "loss": 0.0247, "step": 9434 }, { "epoch": 89.0, "eval_LOCATION_f1": 0.8378378378378378, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7848101265822784, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.712121212121212, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6619718309859155, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1655082106590271, "eval_overall_accuracy": 0.9653207827594749, "eval_overall_f1": 0.8429752066115701, "eval_overall_precision": 0.8052631578947368, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3811, "eval_samples_per_second": 490.73, "eval_steps_per_second": 7.873, "step": 9434 }, { "epoch": 90.0, "grad_norm": 1.3243649005889893, "learning_rate": 5e-06, "loss": 0.0235, "step": 9540 }, { "epoch": 90.0, "eval_LOCATION_f1": 0.8378378378378378, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7848101265822784, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.7164179104477612, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6575342465753424, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7941176470588235, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.75, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.17127062380313873, "eval_overall_accuracy": 0.9645776566757494, "eval_overall_f1": 0.8410958904109589, "eval_overall_precision": 0.7994791666666666, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3794, "eval_samples_per_second": 492.85, "eval_steps_per_second": 7.907, "step": 9540 }, { "epoch": 91.0, "grad_norm": 0.2453767955303192, "learning_rate": 4.5e-06, "loss": 0.0246, "step": 9646 }, { "epoch": 91.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7164179104477612, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6575342465753424, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8358208955223881, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.8, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1665855497121811, "eval_overall_accuracy": 0.9660639088432004, "eval_overall_f1": 0.8449931412894376, "eval_overall_precision": 0.804177545691906, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.3828, "eval_samples_per_second": 488.477, "eval_steps_per_second": 7.837, "step": 9646 }, { "epoch": 92.0, "grad_norm": 1.269940733909607, "learning_rate": 4.000000000000001e-06, "loss": 0.0236, "step": 9752 }, { "epoch": 92.0, "eval_LOCATION_f1": 0.8299319727891156, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7164179104477612, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6575342465753424, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.16694949567317963, "eval_overall_accuracy": 0.9660639088432004, "eval_overall_f1": 0.8434065934065934, "eval_overall_precision": 0.8036649214659686, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3845, "eval_samples_per_second": 486.384, "eval_steps_per_second": 7.803, "step": 9752 }, { "epoch": 93.0, "grad_norm": 5.042428016662598, "learning_rate": 3.5000000000000004e-06, "loss": 0.0258, "step": 9858 }, { "epoch": 93.0, "eval_LOCATION_f1": 0.8435374149659864, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.7058823529411764, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.64, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8358208955223881, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.8, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.16739746928215027, "eval_overall_accuracy": 0.9653207827594749, "eval_overall_f1": 0.8438356164383563, "eval_overall_precision": 0.8020833333333334, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.3873, "eval_samples_per_second": 482.841, "eval_steps_per_second": 7.746, "step": 9858 }, { "epoch": 94.0, "grad_norm": 0.5611863732337952, "learning_rate": 3e-06, "loss": 0.0234, "step": 9964 }, { "epoch": 94.0, "eval_LOCATION_f1": 0.8378378378378378, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7848101265822784, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.7058823529411764, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.64, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8358208955223881, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.8, "eval_QUANTITY_recall": 0.875, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.16788025200366974, "eval_overall_accuracy": 0.9658162001486252, "eval_overall_f1": 0.8426812585499317, "eval_overall_precision": 0.8, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.3818, "eval_samples_per_second": 489.745, "eval_steps_per_second": 7.857, "step": 9964 }, { "epoch": 95.0, "grad_norm": 0.447412371635437, "learning_rate": 2.5e-06, "loss": 0.0241, "step": 10070 }, { "epoch": 95.0, "eval_LOCATION_f1": 0.8378378378378378, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7848101265822784, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.7058823529411764, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.64, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7826086956521738, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7297297297297297, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.16969862580299377, "eval_overall_accuracy": 0.9643299479811741, "eval_overall_f1": 0.8376534788540245, "eval_overall_precision": 0.7932816537467701, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3808, "eval_samples_per_second": 491.035, "eval_steps_per_second": 7.878, "step": 10070 }, { "epoch": 96.0, "grad_norm": 0.7546741962432861, "learning_rate": 2.0000000000000003e-06, "loss": 0.0235, "step": 10176 }, { "epoch": 96.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.711111111111111, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6486486486486487, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1665157824754715, "eval_overall_accuracy": 0.9650730740648997, "eval_overall_f1": 0.8383561643835618, "eval_overall_precision": 0.796875, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3816, "eval_samples_per_second": 489.992, "eval_steps_per_second": 7.861, "step": 10176 }, { "epoch": 97.0, "grad_norm": 0.45943042635917664, "learning_rate": 1.5e-06, "loss": 0.0238, "step": 10282 }, { "epoch": 97.0, "eval_LOCATION_f1": 0.8187919463087248, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7625, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7067669172932329, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6527777777777778, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7826086956521738, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7297297297297297, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.16720008850097656, "eval_overall_accuracy": 0.9653207827594749, "eval_overall_f1": 0.8344733242134064, "eval_overall_precision": 0.7922077922077922, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3835, "eval_samples_per_second": 487.614, "eval_steps_per_second": 7.823, "step": 10282 }, { "epoch": 98.0, "grad_norm": 0.08422825485467911, "learning_rate": 1.0000000000000002e-06, "loss": 0.0222, "step": 10388 }, { "epoch": 98.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.711111111111111, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6486486486486487, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1667957454919815, "eval_overall_accuracy": 0.9648253653703245, "eval_overall_f1": 0.8383561643835618, "eval_overall_precision": 0.796875, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3821, "eval_samples_per_second": 489.465, "eval_steps_per_second": 7.852, "step": 10388 }, { "epoch": 99.0, "grad_norm": 0.2250053733587265, "learning_rate": 5.000000000000001e-07, "loss": 0.0239, "step": 10494 }, { "epoch": 99.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7164179104477612, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6575342465753424, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1667199730873108, "eval_overall_accuracy": 0.9648253653703245, "eval_overall_f1": 0.839506172839506, "eval_overall_precision": 0.7989556135770235, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3828, "eval_samples_per_second": 488.496, "eval_steps_per_second": 7.837, "step": 10494 }, { "epoch": 100.0, "grad_norm": 0.21176059544086456, "learning_rate": 0.0, "loss": 0.0232, "step": 10600 }, { "epoch": 100.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7164179104477612, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6575342465753424, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.8059701492537314, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7714285714285715, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.16671666502952576, "eval_overall_accuracy": 0.9650730740648997, "eval_overall_f1": 0.839506172839506, "eval_overall_precision": 0.7989556135770235, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3813, "eval_samples_per_second": 490.38, "eval_steps_per_second": 7.867, "step": 10600 }, { "epoch": 100.0, "step": 10600, "total_flos": 5088556202474382.0, "train_loss": 0.07070975787234757, "train_runtime": 630.6573, "train_samples_per_second": 267.499, "train_steps_per_second": 16.808 } ], "logging_steps": 500, "max_steps": 10600, "num_input_tokens_seen": 0, "num_train_epochs": 100, "save_steps": 500, "total_flos": 5088556202474382.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }