{ "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": 1.3276965618133545, "learning_rate": 4.9500000000000004e-05, "loss": 0.9884, "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": 0.05555555555555556, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.18518518518518517, "eval_PERSON_recall": 0.032679738562091505, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 31, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.5702175498008728, "eval_overall_accuracy": 0.8394847659152836, "eval_overall_f1": 0.02583979328165375, "eval_overall_precision": 0.12195121951219512, "eval_overall_recall": 0.014450867052023121, "eval_runtime": 0.3816, "eval_samples_per_second": 489.996, "eval_steps_per_second": 7.861, "step": 106 }, { "epoch": 2.0, "grad_norm": 1.2860430479049683, "learning_rate": 4.9e-05, "loss": 0.4955, "step": 212 }, { "epoch": 2.0, "eval_LOCATION_f1": 0.2653061224489796, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.4482758620689655, "eval_LOCATION_recall": 0.18840579710144928, "eval_ORGANIZATION_f1": 0.02197802197802198, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.03333333333333333, "eval_ORGANIZATION_recall": 0.01639344262295082, "eval_PERSON_f1": 0.5800000000000001, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.46963562753036436, "eval_PERSON_recall": 0.7581699346405228, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.2807017543859649, "eval_TIME_number": 31, "eval_TIME_precision": 0.3076923076923077, "eval_TIME_recall": 0.25806451612903225, "eval_loss": 0.3471650779247284, "eval_overall_accuracy": 0.8934852613326728, "eval_overall_f1": 0.404099560761347, "eval_overall_precision": 0.4094955489614243, "eval_overall_recall": 0.3988439306358382, "eval_runtime": 0.3859, "eval_samples_per_second": 484.547, "eval_steps_per_second": 7.773, "step": 212 }, { "epoch": 3.0, "grad_norm": 1.3444463014602661, "learning_rate": 4.85e-05, "loss": 0.3135, "step": 318 }, { "epoch": 3.0, "eval_LOCATION_f1": 0.6625766871165644, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.574468085106383, "eval_LOCATION_recall": 0.782608695652174, "eval_ORGANIZATION_f1": 0.411764705882353, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.37333333333333335, "eval_ORGANIZATION_recall": 0.45901639344262296, "eval_PERSON_f1": 0.8263473053892217, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7624309392265194, "eval_PERSON_recall": 0.9019607843137255, "eval_QUANTITY_f1": 0.5384615384615383, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.45652173913043476, "eval_QUANTITY_recall": 0.65625, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.21259430050849915, "eval_overall_accuracy": 0.9328709437701264, "eval_overall_f1": 0.6863753213367609, "eval_overall_precision": 0.6180555555555556, "eval_overall_recall": 0.7716763005780347, "eval_runtime": 0.3847, "eval_samples_per_second": 486.154, "eval_steps_per_second": 7.799, "step": 318 }, { "epoch": 4.0, "grad_norm": 0.8087641000747681, "learning_rate": 4.8e-05, "loss": 0.2135, "step": 424 }, { "epoch": 4.0, "eval_LOCATION_f1": 0.6863905325443788, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.58, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.5342465753424658, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.4588235294117647, "eval_ORGANIZATION_recall": 0.639344262295082, "eval_PERSON_f1": 0.8650306748466258, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.815028901734104, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.5301204819277109, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.43137254901960786, "eval_QUANTITY_recall": 0.6875, "eval_TIME_f1": 0.6933333333333334, "eval_TIME_number": 31, "eval_TIME_precision": 0.5909090909090909, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1868126541376114, "eval_overall_accuracy": 0.9363388654941789, "eval_overall_f1": 0.7158948685857323, "eval_overall_precision": 0.6313465783664459, "eval_overall_recall": 0.8265895953757225, "eval_runtime": 0.3867, "eval_samples_per_second": 483.541, "eval_steps_per_second": 7.757, "step": 424 }, { "epoch": 5.0, "grad_norm": 0.7300416231155396, "learning_rate": 4.75e-05, "loss": 0.1776, "step": 530 }, { "epoch": 5.0, "eval_LOCATION_f1": 0.75, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6867469879518072, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6363636363636364, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5268817204301075, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8685015290519879, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8160919540229885, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.6666666666666665, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.8666666666666666, "eval_TIME_number": 31, "eval_TIME_precision": 0.896551724137931, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1490359902381897, "eval_overall_accuracy": 0.9509536784741145, "eval_overall_f1": 0.7790849673202613, "eval_overall_precision": 0.711217183770883, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.3848, "eval_samples_per_second": 485.967, "eval_steps_per_second": 7.796, "step": 530 }, { "epoch": 6.0, "grad_norm": 0.5000984072685242, "learning_rate": 4.7e-05, "loss": 0.1582, "step": 636 }, { "epoch": 6.0, "eval_LOCATION_f1": 0.7374999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6483516483516484, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6308724832214765, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5340909090909091, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8800000000000001, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8313953488372093, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.6666666666666665, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.8484848484848486, "eval_TIME_number": 31, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13689373433589935, "eval_overall_accuracy": 0.955907852365618, "eval_overall_f1": 0.7797927461139896, "eval_overall_precision": 0.7065727699530516, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3913, "eval_samples_per_second": 477.855, "eval_steps_per_second": 7.666, "step": 636 }, { "epoch": 7.0, "grad_norm": 0.5657930374145508, "learning_rate": 4.6500000000000005e-05, "loss": 0.1452, "step": 742 }, { "epoch": 7.0, "eval_LOCATION_f1": 0.7814569536423841, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7195121951219512, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6351351351351352, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5402298850574713, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8792569659442725, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8352941176470589, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7012987012987012, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6, "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": 0.13930517435073853, "eval_overall_accuracy": 0.9549170175873173, "eval_overall_f1": 0.7921568627450979, "eval_overall_precision": 0.7231503579952268, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3855, "eval_samples_per_second": 485.023, "eval_steps_per_second": 7.781, "step": 742 }, { "epoch": 8.0, "grad_norm": 0.5769292116165161, "learning_rate": 4.600000000000001e-05, "loss": 0.1352, "step": 848 }, { "epoch": 8.0, "eval_LOCATION_f1": 0.7777777777777779, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7466666666666667, "eval_LOCATION_recall": 0.8115942028985508, "eval_ORGANIZATION_f1": 0.6573426573426574, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.573170731707317, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8909657320872275, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8511904761904762, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7042253521126761, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6410256410256411, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7428571428571428, "eval_TIME_number": 31, "eval_TIME_precision": 0.6666666666666666, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13159207999706268, "eval_overall_accuracy": 0.9566509784493435, "eval_overall_f1": 0.7930574098798397, "eval_overall_precision": 0.7369727047146402, "eval_overall_recall": 0.8583815028901735, "eval_runtime": 0.3876, "eval_samples_per_second": 482.492, "eval_steps_per_second": 7.741, "step": 848 }, { "epoch": 9.0, "grad_norm": 0.8698073029518127, "learning_rate": 4.55e-05, "loss": 0.1268, "step": 954 }, { "epoch": 9.0, "eval_LOCATION_f1": 0.7814569536423841, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7195121951219512, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6277372262773723, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5657894736842105, "eval_ORGANIZATION_recall": 0.7049180327868853, "eval_PERSON_f1": 0.8819875776397514, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8402366863905325, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7647058823529411, "eval_TIME_number": 31, "eval_TIME_precision": 0.7027027027027027, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12754933536052704, "eval_overall_accuracy": 0.9564032697547684, "eval_overall_f1": 0.7887700534759359, "eval_overall_precision": 0.7338308457711443, "eval_overall_recall": 0.8526011560693642, "eval_runtime": 0.3894, "eval_samples_per_second": 480.263, "eval_steps_per_second": 7.705, "step": 954 }, { "epoch": 10.0, "grad_norm": 1.0785250663757324, "learning_rate": 4.5e-05, "loss": 0.1197, "step": 1060 }, { "epoch": 10.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6715328467153285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6052631578947368, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8840125391849529, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8493975903614458, "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": 0.7536231884057972, "eval_TIME_number": 31, "eval_TIME_precision": 0.6842105263157895, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12433285266160965, "eval_overall_accuracy": 0.9581372306167947, "eval_overall_f1": 0.8016085790884719, "eval_overall_precision": 0.7475, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.397, "eval_samples_per_second": 470.974, "eval_steps_per_second": 7.556, "step": 1060 }, { "epoch": 11.0, "grad_norm": 0.5205019116401672, "learning_rate": 4.4500000000000004e-05, "loss": 0.1149, "step": 1166 }, { "epoch": 11.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6713286713286712, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5853658536585366, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7012987012987012, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6, "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": 0.12975481152534485, "eval_overall_accuracy": 0.9578895219222194, "eval_overall_f1": 0.8111702127659576, "eval_overall_precision": 0.7512315270935961, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3918, "eval_samples_per_second": 477.323, "eval_steps_per_second": 7.658, "step": 1166 }, { "epoch": 12.0, "grad_norm": 0.7858980298042297, "learning_rate": 4.4000000000000006e-05, "loss": 0.1074, "step": 1272 }, { "epoch": 12.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5875, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.72, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.627906976744186, "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": 0.1298319697380066, "eval_overall_accuracy": 0.9583849393113698, "eval_overall_f1": 0.8221024258760109, "eval_overall_precision": 0.7702020202020202, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3994, "eval_samples_per_second": 468.158, "eval_steps_per_second": 7.511, "step": 1272 }, { "epoch": 13.0, "grad_norm": 0.4752401113510132, "learning_rate": 4.35e-05, "loss": 0.1021, "step": 1378 }, { "epoch": 13.0, "eval_LOCATION_f1": 0.802721088435374, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7564102564102564, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6583850931677019, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.53, "eval_ORGANIZATION_recall": 0.8688524590163934, "eval_PERSON_f1": 0.8944099378881987, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8520710059171598, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.75, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.675, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7714285714285716, "eval_TIME_number": 31, "eval_TIME_precision": 0.6923076923076923, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1448844075202942, "eval_overall_accuracy": 0.9541738915035918, "eval_overall_f1": 0.8031088082901554, "eval_overall_precision": 0.7276995305164319, "eval_overall_recall": 0.8959537572254336, "eval_runtime": 0.3905, "eval_samples_per_second": 478.918, "eval_steps_per_second": 7.683, "step": 1378 }, { "epoch": 14.0, "grad_norm": 1.1324974298477173, "learning_rate": 4.3e-05, "loss": 0.1, "step": 1484 }, { "epoch": 14.0, "eval_LOCATION_f1": 0.8275862068965517, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6758620689655173, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5833333333333334, "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": 0.7297297297297298, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6428571428571429, "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": 0.13795705139636993, "eval_overall_accuracy": 0.9564032697547684, "eval_overall_f1": 0.8127490039840638, "eval_overall_precision": 0.7518427518427518, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3893, "eval_samples_per_second": 480.306, "eval_steps_per_second": 7.705, "step": 1484 }, { "epoch": 15.0, "grad_norm": 0.16871798038482666, "learning_rate": 4.25e-05, "loss": 0.0956, "step": 1590 }, { "epoch": 15.0, "eval_LOCATION_f1": 0.7945205479452054, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7532467532467533, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.711111111111111, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6486486486486487, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9113924050632911, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8834355828220859, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.75, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.675, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1301039159297943, "eval_overall_accuracy": 0.9598711914788209, "eval_overall_f1": 0.8244897959183674, "eval_overall_precision": 0.7789203084832905, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3918, "eval_samples_per_second": 477.272, "eval_steps_per_second": 7.657, "step": 1590 }, { "epoch": 16.0, "grad_norm": 0.8204237818717957, "learning_rate": 4.2e-05, "loss": 0.0952, "step": 1696 }, { "epoch": 16.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.676056338028169, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5925925925925926, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9034267912772587, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8630952380952381, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8709677419354839, "eval_TIME_number": 31, "eval_TIME_precision": 0.8709677419354839, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1324119120836258, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.8198924731182795, "eval_overall_precision": 0.7663316582914573, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3896, "eval_samples_per_second": 479.952, "eval_steps_per_second": 7.7, "step": 1696 }, { "epoch": 17.0, "grad_norm": 0.4006306231021881, "learning_rate": 4.15e-05, "loss": 0.09, "step": 1802 }, { "epoch": 17.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6891891891891891, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5862068965517241, "eval_ORGANIZATION_recall": 0.8360655737704918, "eval_PERSON_f1": 0.9015873015873016, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8765432098765432, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7714285714285714, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7105263157894737, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13277021050453186, "eval_overall_accuracy": 0.9591280653950953, "eval_overall_f1": 0.8246318607764391, "eval_overall_precision": 0.7680798004987531, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.3907, "eval_samples_per_second": 478.596, "eval_steps_per_second": 7.678, "step": 1802 }, { "epoch": 18.0, "grad_norm": 0.4975588917732239, "learning_rate": 4.1e-05, "loss": 0.0862, "step": 1908 }, { "epoch": 18.0, "eval_LOCATION_f1": 0.7945205479452054, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7532467532467533, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6917293233082706, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.9206349206349207, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8950617283950617, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.75, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.675, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.8059701492537312, "eval_TIME_number": 31, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.12552687525749207, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8267394270122783, "eval_overall_precision": 0.7829457364341085, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.392, "eval_samples_per_second": 477.02, "eval_steps_per_second": 7.653, "step": 1908 }, { "epoch": 19.0, "grad_norm": 1.087817907333374, "learning_rate": 4.05e-05, "loss": 0.0825, "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": 0.7338129496402876, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6538461538461539, "eval_ORGANIZATION_recall": 0.8360655737704918, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "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": 0.1247437596321106, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8265582655826559, "eval_overall_precision": 0.7780612244897959, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3889, "eval_samples_per_second": 480.895, "eval_steps_per_second": 7.715, "step": 2014 }, { "epoch": 20.0, "grad_norm": 0.5643526315689087, "learning_rate": 4e-05, "loss": 0.0814, "step": 2120 }, { "epoch": 20.0, "eval_LOCATION_f1": 0.8251748251748252, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7972972972972973, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6758620689655173, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5833333333333334, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.915360501567398, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8795180722891566, "eval_PERSON_recall": 0.954248366013072, "eval_QUANTITY_f1": 0.7605633802816902, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6923076923076923, "eval_QUANTITY_recall": 0.84375, "eval_TIME_f1": 0.7647058823529411, "eval_TIME_number": 31, "eval_TIME_precision": 0.7027027027027027, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13298088312149048, "eval_overall_accuracy": 0.9588803567005202, "eval_overall_f1": 0.8230563002680965, "eval_overall_precision": 0.7675, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3914, "eval_samples_per_second": 477.753, "eval_steps_per_second": 7.664, "step": 2120 }, { "epoch": 21.0, "grad_norm": 0.49631890654563904, "learning_rate": 3.9500000000000005e-05, "loss": 0.0782, "step": 2226 }, { "epoch": 21.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6861313868613139, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.618421052631579, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.90625, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8682634730538922, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.684931506849315, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6097560975609756, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7647058823529411, "eval_TIME_number": 31, "eval_TIME_precision": 0.7027027027027027, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14317455887794495, "eval_overall_accuracy": 0.9564032697547684, "eval_overall_f1": 0.8085676037483266, "eval_overall_precision": 0.7531172069825436, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3893, "eval_samples_per_second": 480.407, "eval_steps_per_second": 7.707, "step": 2226 }, { "epoch": 22.0, "grad_norm": 0.576837420463562, "learning_rate": 3.9000000000000006e-05, "loss": 0.0799, "step": 2332 }, { "epoch": 22.0, "eval_LOCATION_f1": 0.8378378378378378, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7848101265822784, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6625, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5353535353535354, "eval_ORGANIZATION_recall": 0.8688524590163934, "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": 0.7941176470588235, "eval_TIME_number": 31, "eval_TIME_precision": 0.7297297297297297, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.145122691988945, "eval_overall_accuracy": 0.9556601436710429, "eval_overall_f1": 0.8167539267015707, "eval_overall_precision": 0.7464114832535885, "eval_overall_recall": 0.9017341040462428, "eval_runtime": 0.3888, "eval_samples_per_second": 481.001, "eval_steps_per_second": 7.717, "step": 2332 }, { "epoch": 23.0, "grad_norm": 0.6475539207458496, "learning_rate": 3.85e-05, "loss": 0.0756, "step": 2438 }, { "epoch": 23.0, "eval_LOCATION_f1": 0.8391608391608392, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8108108108108109, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6857142857142857, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6075949367088608, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8924050632911392, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8650306748466258, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.684931506849315, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6097560975609756, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14067424833774567, "eval_overall_accuracy": 0.9573941045330691, "eval_overall_f1": 0.8119079837618404, "eval_overall_precision": 0.7633587786259542, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3936, "eval_samples_per_second": 475.15, "eval_steps_per_second": 7.623, "step": 2438 }, { "epoch": 24.0, "grad_norm": 1.1648420095443726, "learning_rate": 3.8e-05, "loss": 0.0711, "step": 2544 }, { "epoch": 24.0, "eval_LOCATION_f1": 0.8055555555555556, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7733333333333333, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6993006993006993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6097560975609756, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9090909090909091, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8734939759036144, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13308101892471313, "eval_overall_accuracy": 0.9593757740896706, "eval_overall_f1": 0.8232118758434549, "eval_overall_precision": 0.7721518987341772, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3865, "eval_samples_per_second": 483.85, "eval_steps_per_second": 7.762, "step": 2544 }, { "epoch": 25.0, "grad_norm": 0.6172886490821838, "learning_rate": 3.7500000000000003e-05, "loss": 0.0715, "step": 2650 }, { "epoch": 25.0, "eval_LOCATION_f1": 0.8322147651006713, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.775, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6944444444444445, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6024096385542169, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9235668789808917, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.9006211180124224, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "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": 0.13262183964252472, "eval_overall_accuracy": 0.9623482784245727, "eval_overall_f1": 0.8348993288590604, "eval_overall_precision": 0.7794486215538847, "eval_overall_recall": 0.8988439306358381, "eval_runtime": 0.385, "eval_samples_per_second": 485.683, "eval_steps_per_second": 7.792, "step": 2650 }, { "epoch": 26.0, "grad_norm": 0.9105387926101685, "learning_rate": 3.7e-05, "loss": 0.0699, "step": 2756 }, { "epoch": 26.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7183098591549297, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6296296296296297, "eval_ORGANIZATION_recall": 0.8360655737704918, "eval_PERSON_f1": 0.9028213166144202, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8674698795180723, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.684931506849315, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6097560975609756, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13964460790157318, "eval_overall_accuracy": 0.9593757740896706, "eval_overall_f1": 0.8214765100671141, "eval_overall_precision": 0.7669172932330827, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3863, "eval_samples_per_second": 484.081, "eval_steps_per_second": 7.766, "step": 2756 }, { "epoch": 27.0, "grad_norm": 0.36196014285087585, "learning_rate": 3.65e-05, "loss": 0.064, "step": 2862 }, { "epoch": 27.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "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": 0.90625, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8682634730538922, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "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": 0.1338304877281189, "eval_overall_accuracy": 0.9628436958137231, "eval_overall_f1": 0.8342391304347826, "eval_overall_precision": 0.7871794871794872, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3874, "eval_samples_per_second": 482.744, "eval_steps_per_second": 7.745, "step": 2862 }, { "epoch": 28.0, "grad_norm": 1.0824393033981323, "learning_rate": 3.6e-05, "loss": 0.066, "step": 2968 }, { "epoch": 28.0, "eval_LOCATION_f1": 0.8378378378378378, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7848101265822784, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6101694915254237, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.631578947368421, "eval_ORGANIZATION_recall": 0.5901639344262295, "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": 0.7714285714285716, "eval_TIME_number": 31, "eval_TIME_precision": 0.6923076923076923, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.13949762284755707, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.8227146814404432, "eval_overall_precision": 0.7898936170212766, "eval_overall_recall": 0.8583815028901735, "eval_runtime": 0.3857, "eval_samples_per_second": 484.772, "eval_steps_per_second": 7.777, "step": 2968 }, { "epoch": 29.0, "grad_norm": 0.5354642271995544, "learning_rate": 3.55e-05, "loss": 0.0643, "step": 3074 }, { "epoch": 29.0, "eval_LOCATION_f1": 0.8187919463087248, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7625, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7132867132867133, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6219512195121951, "eval_ORGANIZATION_recall": 0.8360655737704918, "eval_PERSON_f1": 0.9090909090909091, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8734939759036144, "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": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14336097240447998, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8310991957104559, "eval_overall_precision": 0.775, "eval_overall_recall": 0.8959537572254336, "eval_runtime": 0.3849, "eval_samples_per_second": 485.861, "eval_steps_per_second": 7.795, "step": 3074 }, { "epoch": 30.0, "grad_norm": 0.510343611240387, "learning_rate": 3.5e-05, "loss": 0.0613, "step": 3180 }, { "epoch": 30.0, "eval_LOCATION_f1": 0.8356164383561644, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7922077922077922, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6805555555555556, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5903614457831325, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.9113924050632911, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8834355828220859, "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": 0.14164263010025024, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8331071913161464, "eval_overall_precision": 0.7851662404092071, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3859, "eval_samples_per_second": 484.52, "eval_steps_per_second": 7.773, "step": 3180 }, { "epoch": 31.0, "grad_norm": 0.2627265453338623, "learning_rate": 3.45e-05, "loss": 0.0611, "step": 3286 }, { "epoch": 31.0, "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": 0.9171974522292994, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8944099378881988, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14434608817100525, "eval_overall_accuracy": 0.9601189001733961, "eval_overall_f1": 0.8278688524590163, "eval_overall_precision": 0.7849740932642487, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3867, "eval_samples_per_second": 483.549, "eval_steps_per_second": 7.757, "step": 3286 }, { "epoch": 32.0, "grad_norm": 0.390147864818573, "learning_rate": 3.4000000000000007e-05, "loss": 0.0594, "step": 3392 }, { "epoch": 32.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7142857142857143, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6329113924050633, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9119496855345912, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8787878787878788, "eval_PERSON_recall": 0.9477124183006536, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.136785626411438, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8286099865047234, "eval_overall_precision": 0.7772151898734178, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3856, "eval_samples_per_second": 484.949, "eval_steps_per_second": 7.78, "step": 3392 }, { "epoch": 33.0, "grad_norm": 0.2763284146785736, "learning_rate": 3.35e-05, "loss": 0.0591, "step": 3498 }, { "epoch": 33.0, "eval_LOCATION_f1": 0.8322147651006713, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.775, "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": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "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": 0.14011235535144806, "eval_overall_accuracy": 0.9623482784245727, "eval_overall_f1": 0.8301369863013699, "eval_overall_precision": 0.7890625, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3868, "eval_samples_per_second": 483.465, "eval_steps_per_second": 7.756, "step": 3498 }, { "epoch": 34.0, "grad_norm": 0.430482417345047, "learning_rate": 3.3e-05, "loss": 0.0586, "step": 3604 }, { "epoch": 34.0, "eval_LOCATION_f1": 0.8299319727891156, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7092198581560285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.625, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9142857142857143, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8888888888888888, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "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": 0.13805538415908813, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8396739130434783, "eval_overall_precision": 0.7923076923076923, "eval_overall_recall": 0.8930635838150289, "eval_runtime": 0.3863, "eval_samples_per_second": 484.077, "eval_steps_per_second": 7.766, "step": 3604 }, { "epoch": 35.0, "grad_norm": 0.8361353874206543, "learning_rate": 3.2500000000000004e-05, "loss": 0.0557, "step": 3710 }, { "epoch": 35.0, "eval_LOCATION_f1": 0.8266666666666668, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7654320987654321, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6433566433566433, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5609756097560976, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "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": 0.14485345780849457, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.8194070080862532, "eval_overall_precision": 0.7676767676767676, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3876, "eval_samples_per_second": 482.457, "eval_steps_per_second": 7.74, "step": 3710 }, { "epoch": 36.0, "grad_norm": 0.42881178855895996, "learning_rate": 3.2000000000000005e-05, "loss": 0.055, "step": 3816 }, { "epoch": 36.0, "eval_LOCATION_f1": 0.8299319727891156, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6438356164383562, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5529411764705883, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9044585987261147, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8819875776397516, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "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": 0.14788949489593506, "eval_overall_accuracy": 0.9593757740896706, "eval_overall_f1": 0.8172043010752688, "eval_overall_precision": 0.7638190954773869, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3884, "eval_samples_per_second": 481.484, "eval_steps_per_second": 7.724, "step": 3816 }, { "epoch": 37.0, "grad_norm": 7.659615993499756, "learning_rate": 3.15e-05, "loss": 0.0549, "step": 3922 }, { "epoch": 37.0, "eval_LOCATION_f1": 0.8299319727891156, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6944444444444445, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6024096385542169, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1483921855688095, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.8268456375838926, "eval_overall_precision": 0.7719298245614035, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.3848, "eval_samples_per_second": 485.97, "eval_steps_per_second": 7.796, "step": 3922 }, { "epoch": 38.0, "grad_norm": 0.8882097601890564, "learning_rate": 3.1e-05, "loss": 0.0516, "step": 4028 }, { "epoch": 38.0, "eval_LOCATION_f1": 0.8299319727891156, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.782051282051282, "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": 0.9085173501577287, "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": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.15167877078056335, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8315217391304348, "eval_overall_precision": 0.7846153846153846, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3878, "eval_samples_per_second": 482.157, "eval_steps_per_second": 7.735, "step": 4028 }, { "epoch": 39.0, "grad_norm": 0.6768080592155457, "learning_rate": 3.05e-05, "loss": 0.0525, "step": 4134 }, { "epoch": 39.0, "eval_LOCATION_f1": 0.8356164383561644, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7922077922077922, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6911764705882353, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6266666666666667, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.875, "eval_TIME_number": 31, "eval_TIME_precision": 0.8484848484848485, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13869328796863556, "eval_overall_accuracy": 0.9643299479811741, "eval_overall_f1": 0.8333333333333334, "eval_overall_precision": 0.7901554404145078, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.385, "eval_samples_per_second": 485.742, "eval_steps_per_second": 7.793, "step": 4134 }, { "epoch": 40.0, "grad_norm": 0.5459471344947815, "learning_rate": 3e-05, "loss": 0.0493, "step": 4240 }, { "epoch": 40.0, "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": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7941176470588235, "eval_TIME_number": 31, "eval_TIME_precision": 0.7297297297297297, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14060817658901215, "eval_overall_accuracy": 0.9628436958137231, "eval_overall_f1": 0.8299319727891157, "eval_overall_precision": 0.7840616966580977, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3891, "eval_samples_per_second": 480.639, "eval_steps_per_second": 7.711, "step": 4240 }, { "epoch": 41.0, "grad_norm": 0.5123444199562073, "learning_rate": 2.95e-05, "loss": 0.0498, "step": 4346 }, { "epoch": 41.0, "eval_LOCATION_f1": 0.8413793103448277, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8026315789473685, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7142857142857143, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6329113924050633, "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": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8709677419354839, "eval_TIME_number": 31, "eval_TIME_precision": 0.8709677419354839, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1391770839691162, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8392370572207084, "eval_overall_precision": 0.7938144329896907, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.386, "eval_samples_per_second": 484.485, "eval_steps_per_second": 7.772, "step": 4346 }, { "epoch": 42.0, "grad_norm": 0.6083254814147949, "learning_rate": 2.9e-05, "loss": 0.048, "step": 4452 }, { "epoch": 42.0, "eval_LOCATION_f1": 0.8472222222222223, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8133333333333334, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6713286713286712, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5853658536585366, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7936507936507936, "eval_TIME_number": 31, "eval_TIME_precision": 0.78125, "eval_TIME_recall": 0.8064516129032258, "eval_loss": 0.14638996124267578, "eval_overall_accuracy": 0.9598711914788209, "eval_overall_f1": 0.8201634877384196, "eval_overall_precision": 0.7757731958762887, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3891, "eval_samples_per_second": 480.596, "eval_steps_per_second": 7.71, "step": 4452 }, { "epoch": 43.0, "grad_norm": 0.5588040947914124, "learning_rate": 2.8499999999999998e-05, "loss": 0.0514, "step": 4558 }, { "epoch": 43.0, "eval_LOCATION_f1": 0.7755102040816326, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7307692307692307, "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": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7462686567164178, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14348997175693512, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.8164383561643834, "eval_overall_precision": 0.7760416666666666, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.3866, "eval_samples_per_second": 483.701, "eval_steps_per_second": 7.76, "step": 4558 }, { "epoch": 44.0, "grad_norm": 0.9377841949462891, "learning_rate": 2.8000000000000003e-05, "loss": 0.0482, "step": 4664 }, { "epoch": 44.0, "eval_LOCATION_f1": 0.8266666666666668, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7654320987654321, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.7092198581560285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.625, "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": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14863348007202148, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8263795423956932, "eval_overall_precision": 0.7732997481108312, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3896, "eval_samples_per_second": 480.005, "eval_steps_per_second": 7.701, "step": 4664 }, { "epoch": 45.0, "grad_norm": 0.9494560956954956, "learning_rate": 2.7500000000000004e-05, "loss": 0.0453, "step": 4770 }, { "epoch": 45.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6950354609929078, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6125, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7164179104477612, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6857142857142857, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15008646249771118, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.8217687074829931, "eval_overall_precision": 0.7763496143958869, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3863, "eval_samples_per_second": 484.086, "eval_steps_per_second": 7.766, "step": 4770 }, { "epoch": 46.0, "grad_norm": 0.34856438636779785, "learning_rate": 2.7000000000000002e-05, "loss": 0.0444, "step": 4876 }, { "epoch": 46.0, "eval_LOCATION_f1": 0.8275862068965517, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6808510638297871, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8709677419354839, "eval_TIME_number": 31, "eval_TIME_precision": 0.8709677419354839, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1433335840702057, "eval_overall_accuracy": 0.9633391132028735, "eval_overall_f1": 0.8283378746594006, "eval_overall_precision": 0.7835051546391752, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3863, "eval_samples_per_second": 484.054, "eval_steps_per_second": 7.766, "step": 4876 }, { "epoch": 47.0, "grad_norm": 0.7428375482559204, "learning_rate": 2.6500000000000004e-05, "loss": 0.0428, "step": 4982 }, { "epoch": 47.0, "eval_LOCATION_f1": 0.8299319727891156, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.647887323943662, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5679012345679012, "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": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14804230630397797, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8217687074829931, "eval_overall_precision": 0.7763496143958869, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3881, "eval_samples_per_second": 481.848, "eval_steps_per_second": 7.73, "step": 4982 }, { "epoch": 48.0, "grad_norm": 0.6548387408256531, "learning_rate": 2.6000000000000002e-05, "loss": 0.0416, "step": 5088 }, { "epoch": 48.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "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": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "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": 0.8387096774193549, "eval_TIME_number": 31, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1478779911994934, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8256130790190735, "eval_overall_precision": 0.7809278350515464, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.389, "eval_samples_per_second": 480.738, "eval_steps_per_second": 7.712, "step": 5088 }, { "epoch": 49.0, "grad_norm": 0.26041945815086365, "learning_rate": 2.5500000000000003e-05, "loss": 0.0434, "step": 5194 }, { "epoch": 49.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6811594202898551, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6103896103896104, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "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": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1512691229581833, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8276797829036635, "eval_overall_precision": 0.7800511508951407, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3846, "eval_samples_per_second": 486.244, "eval_steps_per_second": 7.801, "step": 5194 }, { "epoch": 50.0, "grad_norm": 0.3981456756591797, "learning_rate": 2.5e-05, "loss": 0.0421, "step": 5300 }, { "epoch": 50.0, "eval_LOCATION_f1": 0.8299319727891156, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6956521739130435, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6233766233766234, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9056603773584905, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8727272727272727, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.14921875298023224, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8310626702997275, "eval_overall_precision": 0.7860824742268041, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.386, "eval_samples_per_second": 484.478, "eval_steps_per_second": 7.772, "step": 5300 }, { "epoch": 51.0, "grad_norm": 1.7932168245315552, "learning_rate": 2.45e-05, "loss": 0.0423, "step": 5406 }, { "epoch": 51.0, "eval_LOCATION_f1": 0.8413793103448277, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8026315789473685, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7183098591549297, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6296296296296297, "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": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1472812443971634, "eval_overall_accuracy": 0.9645776566757494, "eval_overall_f1": 0.842391304347826, "eval_overall_precision": 0.7948717948717948, "eval_overall_recall": 0.8959537572254336, "eval_runtime": 0.3876, "eval_samples_per_second": 482.414, "eval_steps_per_second": 7.739, "step": 5406 }, { "epoch": 52.0, "grad_norm": 0.5850203633308411, "learning_rate": 2.4e-05, "loss": 0.0421, "step": 5512 }, { "epoch": 52.0, "eval_LOCATION_f1": 0.8275862068965517, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6758620689655173, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5833333333333334, "eval_ORGANIZATION_recall": 0.8032786885245902, "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": 0.8387096774193549, "eval_TIME_number": 31, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15393322706222534, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.828804347826087, "eval_overall_precision": 0.782051282051282, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3875, "eval_samples_per_second": 482.581, "eval_steps_per_second": 7.742, "step": 5512 }, { "epoch": 53.0, "grad_norm": 1.0686652660369873, "learning_rate": 2.35e-05, "loss": 0.0415, "step": 5618 }, { "epoch": 53.0, "eval_LOCATION_f1": 0.8082191780821918, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7662337662337663, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6713286713286712, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5853658536585366, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "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": 0.15448956191539764, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8249660786974219, "eval_overall_precision": 0.7774936061381074, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3853, "eval_samples_per_second": 485.361, "eval_steps_per_second": 7.787, "step": 5618 }, { "epoch": 54.0, "grad_norm": 0.8126365542411804, "learning_rate": 2.3000000000000003e-05, "loss": 0.0396, "step": 5724 }, { "epoch": 54.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.689655172413793, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5952380952380952, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15855492651462555, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8238482384823848, "eval_overall_precision": 0.7755102040816326, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3842, "eval_samples_per_second": 486.682, "eval_steps_per_second": 7.808, "step": 5724 }, { "epoch": 55.0, "grad_norm": 1.2497072219848633, "learning_rate": 2.25e-05, "loss": 0.0375, "step": 5830 }, { "epoch": 55.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6808510638297871, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15633077919483185, "eval_overall_accuracy": 0.9601189001733961, "eval_overall_f1": 0.8217687074829931, "eval_overall_precision": 0.7763496143958869, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3845, "eval_samples_per_second": 486.402, "eval_steps_per_second": 7.803, "step": 5830 }, { "epoch": 56.0, "grad_norm": 0.8850880861282349, "learning_rate": 2.2000000000000003e-05, "loss": 0.0379, "step": 5936 }, { "epoch": 56.0, "eval_LOCATION_f1": 0.8194444444444444, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7866666666666666, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.647887323943662, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5679012345679012, "eval_ORGANIZATION_recall": 0.7540983606557377, "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": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15333446860313416, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8174386920980926, "eval_overall_precision": 0.7731958762886598, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3861, "eval_samples_per_second": 484.289, "eval_steps_per_second": 7.769, "step": 5936 }, { "epoch": 57.0, "grad_norm": 1.2842954397201538, "learning_rate": 2.15e-05, "loss": 0.0354, "step": 6042 }, { "epoch": 57.0, "eval_LOCATION_f1": 0.8356164383561644, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7922077922077922, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6618705035971222, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5897435897435898, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1612398326396942, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8233695652173912, "eval_overall_precision": 0.7769230769230769, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3884, "eval_samples_per_second": 481.508, "eval_steps_per_second": 7.725, "step": 6042 }, { "epoch": 58.0, "grad_norm": 0.25821393728256226, "learning_rate": 2.1e-05, "loss": 0.0363, "step": 6148 }, { "epoch": 58.0, "eval_LOCATION_f1": 0.8275862068965517, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6527777777777777, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5662650602409639, "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": 0.7941176470588235, "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": 0.15247274935245514, "eval_overall_accuracy": 0.9623482784245727, "eval_overall_f1": 0.8222523744911805, "eval_overall_precision": 0.7749360613810742, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3891, "eval_samples_per_second": 480.628, "eval_steps_per_second": 7.711, "step": 6148 }, { "epoch": 59.0, "grad_norm": 0.374012291431427, "learning_rate": 2.05e-05, "loss": 0.0333, "step": 6254 }, { "epoch": 59.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6811594202898551, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6103896103896104, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9056603773584905, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8727272727272727, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7462686567164178, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7142857142857143, "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": 0.15879231691360474, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8244897959183674, "eval_overall_precision": 0.7789203084832905, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3912, "eval_samples_per_second": 477.956, "eval_steps_per_second": 7.668, "step": 6254 }, { "epoch": 60.0, "grad_norm": 0.7695782780647278, "learning_rate": 2e-05, "loss": 0.0352, "step": 6360 }, { "epoch": 60.0, "eval_LOCATION_f1": 0.8187919463087248, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7625, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6575342465753424, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5647058823529412, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9050632911392406, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8773006134969326, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7575757575757576, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1653706580400467, "eval_overall_accuracy": 0.9611097349516968, "eval_overall_f1": 0.8205128205128205, "eval_overall_precision": 0.769620253164557, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3873, "eval_samples_per_second": 482.8, "eval_steps_per_second": 7.745, "step": 6360 }, { "epoch": 61.0, "grad_norm": 0.5492474436759949, "learning_rate": 1.9500000000000003e-05, "loss": 0.035, "step": 6466 }, { "epoch": 61.0, "eval_LOCATION_f1": 0.8111888111888113, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7837837837837838, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5875, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.15602223575115204, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8207934336525308, "eval_overall_precision": 0.7792207792207793, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3853, "eval_samples_per_second": 485.362, "eval_steps_per_second": 7.787, "step": 6466 }, { "epoch": 62.0, "grad_norm": 0.4717317819595337, "learning_rate": 1.9e-05, "loss": 0.0326, "step": 6572 }, { "epoch": 62.0, "eval_LOCATION_f1": 0.8356164383561644, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7922077922077922, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5783132530120482, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7575757575757576, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8615384615384616, "eval_TIME_number": 31, "eval_TIME_precision": 0.8235294117647058, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.16442739963531494, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8238482384823848, "eval_overall_precision": 0.7755102040816326, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3869, "eval_samples_per_second": 483.383, "eval_steps_per_second": 7.755, "step": 6572 }, { "epoch": 63.0, "grad_norm": 0.7986805438995361, "learning_rate": 1.85e-05, "loss": 0.0329, "step": 6678 }, { "epoch": 63.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6808510638297871, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7462686567164178, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.164092019200325, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8222523744911805, "eval_overall_precision": 0.7749360613810742, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3898, "eval_samples_per_second": 479.741, "eval_steps_per_second": 7.696, "step": 6678 }, { "epoch": 64.0, "grad_norm": 0.864476203918457, "learning_rate": 1.8e-05, "loss": 0.0335, "step": 6784 }, { "epoch": 64.0, "eval_LOCATION_f1": 0.8391608391608392, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8108108108108109, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6950354609929078, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6125, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "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": 0.16267791390419006, "eval_overall_accuracy": 0.9638345305920237, "eval_overall_f1": 0.8310626702997275, "eval_overall_precision": 0.7860824742268041, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.4009, "eval_samples_per_second": 466.506, "eval_steps_per_second": 7.484, "step": 6784 }, { "epoch": 65.0, "grad_norm": 0.5071347951889038, "learning_rate": 1.75e-05, "loss": 0.0322, "step": 6890 }, { "epoch": 65.0, "eval_LOCATION_f1": 0.8275862068965517, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6714285714285714, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5949367088607594, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "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": 0.16230082511901855, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8256130790190735, "eval_overall_precision": 0.7809278350515464, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3863, "eval_samples_per_second": 484.059, "eval_steps_per_second": 7.766, "step": 6890 }, { "epoch": 66.0, "grad_norm": 0.529727041721344, "learning_rate": 1.7000000000000003e-05, "loss": 0.0332, "step": 6996 }, { "epoch": 66.0, "eval_LOCATION_f1": 0.8413793103448277, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8026315789473685, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6901408450704226, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6049382716049383, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "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": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1601356863975525, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8342391304347826, "eval_overall_precision": 0.7871794871794872, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3874, "eval_samples_per_second": 482.644, "eval_steps_per_second": 7.743, "step": 6996 }, { "epoch": 67.0, "grad_norm": 0.737204372882843, "learning_rate": 1.65e-05, "loss": 0.0327, "step": 7102 }, { "epoch": 67.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6950354609929078, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6125, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.9015873015873016, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8765432098765432, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1585276573896408, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8328767123287673, "eval_overall_precision": 0.7916666666666666, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3867, "eval_samples_per_second": 483.545, "eval_steps_per_second": 7.757, "step": 7102 }, { "epoch": 68.0, "grad_norm": 1.4248096942901611, "learning_rate": 1.6000000000000003e-05, "loss": 0.0327, "step": 7208 }, { "epoch": 68.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6993006993006993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6097560975609756, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "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": 0.1642405092716217, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8346883468834689, "eval_overall_precision": 0.7857142857142857, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.3863, "eval_samples_per_second": 484.08, "eval_steps_per_second": 7.766, "step": 7208 }, { "epoch": 69.0, "grad_norm": 0.7958378195762634, "learning_rate": 1.55e-05, "loss": 0.0331, "step": 7314 }, { "epoch": 69.0, "eval_LOCATION_f1": 0.8450704225352113, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.821917808219178, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6956521739130435, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6233766233766234, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1593960076570511, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8301369863013699, "eval_overall_precision": 0.7890625, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3895, "eval_samples_per_second": 480.086, "eval_steps_per_second": 7.702, "step": 7314 }, { "epoch": 70.0, "grad_norm": 1.0356825590133667, "learning_rate": 1.5e-05, "loss": 0.0311, "step": 7420 }, { "epoch": 70.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6762589928057554, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6025641025641025, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.875, "eval_TIME_number": 31, "eval_TIME_precision": 0.8484848484848485, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.16732904314994812, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.825136612021858, "eval_overall_precision": 0.7823834196891192, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3887, "eval_samples_per_second": 481.081, "eval_steps_per_second": 7.718, "step": 7420 }, { "epoch": 71.0, "grad_norm": 0.7192361950874329, "learning_rate": 1.45e-05, "loss": 0.0302, "step": 7526 }, { "epoch": 71.0, "eval_LOCATION_f1": 0.8391608391608392, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8108108108108109, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6901408450704226, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6049382716049383, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "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": 0.16542688012123108, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8310626702997275, "eval_overall_precision": 0.7860824742268041, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3855, "eval_samples_per_second": 485.116, "eval_steps_per_second": 7.783, "step": 7526 }, { "epoch": 72.0, "grad_norm": 0.7832820415496826, "learning_rate": 1.4000000000000001e-05, "loss": 0.0276, "step": 7632 }, { "epoch": 72.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6950354609929078, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6125, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7462686567164178, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.16764099895954132, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8306010928961748, "eval_overall_precision": 0.7875647668393783, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3869, "eval_samples_per_second": 483.3, "eval_steps_per_second": 7.753, "step": 7632 }, { "epoch": 73.0, "grad_norm": 2.416990041732788, "learning_rate": 1.3500000000000001e-05, "loss": 0.0304, "step": 7738 }, { "epoch": 73.0, "eval_LOCATION_f1": 0.8391608391608392, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8108108108108109, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6762589928057554, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6025641025641025, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7462686567164178, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8888888888888888, "eval_TIME_number": 31, "eval_TIME_precision": 0.875, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.15734872221946716, "eval_overall_accuracy": 0.9650730740648997, "eval_overall_f1": 0.831275720164609, "eval_overall_precision": 0.7911227154046997, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3874, "eval_samples_per_second": 482.65, "eval_steps_per_second": 7.743, "step": 7738 }, { "epoch": 74.0, "grad_norm": 0.3634456694126129, "learning_rate": 1.3000000000000001e-05, "loss": 0.029, "step": 7844 }, { "epoch": 74.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6808510638297871, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6, "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": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "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": 0.1682179570198059, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8285322359396434, "eval_overall_precision": 0.7885117493472585, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3894, "eval_samples_per_second": 480.224, "eval_steps_per_second": 7.704, "step": 7844 }, { "epoch": 75.0, "grad_norm": 0.6786316633224487, "learning_rate": 1.25e-05, "loss": 0.0293, "step": 7950 }, { "epoch": 75.0, "eval_LOCATION_f1": 0.8275862068965517, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6808510638297871, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "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": 0.16986426711082458, "eval_overall_accuracy": 0.9623482784245727, "eval_overall_f1": 0.829467939972715, "eval_overall_precision": 0.7855297157622739, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3896, "eval_samples_per_second": 479.922, "eval_steps_per_second": 7.699, "step": 7950 }, { "epoch": 76.0, "grad_norm": 1.5058990716934204, "learning_rate": 1.2e-05, "loss": 0.0292, "step": 8056 }, { "epoch": 76.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6993006993006993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6097560975609756, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "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": 0.17141401767730713, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8331071913161464, "eval_overall_precision": 0.7851662404092071, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3846, "eval_samples_per_second": 486.17, "eval_steps_per_second": 7.8, "step": 8056 }, { "epoch": 77.0, "grad_norm": 1.132621169090271, "learning_rate": 1.1500000000000002e-05, "loss": 0.0292, "step": 8162 }, { "epoch": 77.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6714285714285714, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5949367088607594, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7575757575757576, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8709677419354839, "eval_TIME_number": 31, "eval_TIME_precision": 0.8709677419354839, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.16126488149166107, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8257887517146777, "eval_overall_precision": 0.7859007832898173, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3876, "eval_samples_per_second": 482.467, "eval_steps_per_second": 7.74, "step": 8162 }, { "epoch": 78.0, "grad_norm": 0.44842055439949036, "learning_rate": 1.1000000000000001e-05, "loss": 0.0259, "step": 8268 }, { "epoch": 78.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6906474820143885, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6153846153846154, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9050632911392406, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8773006134969326, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8923076923076922, "eval_TIME_number": 31, "eval_TIME_precision": 0.8529411764705882, "eval_TIME_recall": 0.9354838709677419, "eval_loss": 0.1647026389837265, "eval_overall_accuracy": 0.9638345305920237, "eval_overall_f1": 0.8349249658935879, "eval_overall_precision": 0.7906976744186046, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3867, "eval_samples_per_second": 483.633, "eval_steps_per_second": 7.759, "step": 8268 }, { "epoch": 79.0, "grad_norm": 0.33243757486343384, "learning_rate": 1.05e-05, "loss": 0.0274, "step": 8374 }, { "epoch": 79.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6811594202898551, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6103896103896104, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7575757575757576, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.16486360132694244, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8296703296703297, "eval_overall_precision": 0.7905759162303665, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3908, "eval_samples_per_second": 478.542, "eval_steps_per_second": 7.677, "step": 8374 }, { "epoch": 80.0, "grad_norm": 0.611662745475769, "learning_rate": 1e-05, "loss": 0.0269, "step": 8480 }, { "epoch": 80.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5875, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.9085173501577287, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8780487804878049, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "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": 0.1668892353773117, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8272108843537415, "eval_overall_precision": 0.781491002570694, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3859, "eval_samples_per_second": 484.581, "eval_steps_per_second": 7.774, "step": 8480 }, { "epoch": 81.0, "grad_norm": 1.7247461080551147, "learning_rate": 9.5e-06, "loss": 0.028, "step": 8586 }, { "epoch": 81.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6714285714285714, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5949367088607594, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.896551724137931, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8614457831325302, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7272727272727272, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7058823529411765, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.8484848484848486, "eval_TIME_number": 31, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.16706372797489166, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8195386702849389, "eval_overall_precision": 0.7723785166240409, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3872, "eval_samples_per_second": 482.916, "eval_steps_per_second": 7.747, "step": 8586 }, { "epoch": 82.0, "grad_norm": 1.11622953414917, "learning_rate": 9e-06, "loss": 0.0279, "step": 8692 }, { "epoch": 82.0, "eval_LOCATION_f1": 0.8275862068965517, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6993006993006993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6097560975609756, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7462686567164178, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8307692307692308, "eval_TIME_number": 31, "eval_TIME_precision": 0.7941176470588235, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.16788186132907867, "eval_overall_accuracy": 0.9623482784245727, "eval_overall_f1": 0.8249660786974219, "eval_overall_precision": 0.7774936061381074, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3861, "eval_samples_per_second": 484.392, "eval_steps_per_second": 7.771, "step": 8692 }, { "epoch": 83.0, "grad_norm": 0.8482971787452698, "learning_rate": 8.500000000000002e-06, "loss": 0.0258, "step": 8798 }, { "epoch": 83.0, "eval_LOCATION_f1": 0.8450704225352113, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.821917808219178, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7092198581560285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.625, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9050632911392406, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8773006134969326, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.787878787878788, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8888888888888888, "eval_TIME_number": 31, "eval_TIME_precision": 0.875, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.16492000222206116, "eval_overall_accuracy": 0.9643299479811741, "eval_overall_f1": 0.8434065934065934, "eval_overall_precision": 0.8036649214659686, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3875, "eval_samples_per_second": 482.605, "eval_steps_per_second": 7.742, "step": 8798 }, { "epoch": 84.0, "grad_norm": 0.978729248046875, "learning_rate": 8.000000000000001e-06, "loss": 0.0272, "step": 8904 }, { "epoch": 84.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7092198581560285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.625, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9050632911392406, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8773006134969326, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7462686567164178, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8615384615384616, "eval_TIME_number": 31, "eval_TIME_precision": 0.8235294117647058, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.168557271361351, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8349249658935879, "eval_overall_precision": 0.7906976744186046, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3876, "eval_samples_per_second": 482.459, "eval_steps_per_second": 7.74, "step": 8904 }, { "epoch": 85.0, "grad_norm": 0.5526589751243591, "learning_rate": 7.5e-06, "loss": 0.0261, "step": 9010 }, { "epoch": 85.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "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": 0.16906413435935974, "eval_overall_accuracy": 0.964082239286599, "eval_overall_f1": 0.8326530612244898, "eval_overall_precision": 0.7866323907455013, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3858, "eval_samples_per_second": 484.691, "eval_steps_per_second": 7.776, "step": 9010 }, { "epoch": 86.0, "grad_norm": 0.9508800506591797, "learning_rate": 7.000000000000001e-06, "loss": 0.0254, "step": 9116 }, { "epoch": 86.0, "eval_LOCATION_f1": 0.8299319727891156, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.676056338028169, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5925925925925926, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "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": 0.1746217906475067, "eval_overall_accuracy": 0.9623482784245727, "eval_overall_f1": 0.8254397834912043, "eval_overall_precision": 0.7760814249363868, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3854, "eval_samples_per_second": 485.246, "eval_steps_per_second": 7.785, "step": 9116 }, { "epoch": 87.0, "grad_norm": 0.8900957107543945, "learning_rate": 6.5000000000000004e-06, "loss": 0.028, "step": 9222 }, { "epoch": 87.0, "eval_LOCATION_f1": 0.8391608391608392, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8108108108108109, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6713286713286712, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5853658536585366, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "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": 0.16688643395900726, "eval_overall_accuracy": 0.9648253653703245, "eval_overall_f1": 0.8333333333333334, "eval_overall_precision": 0.7901554404145078, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3876, "eval_samples_per_second": 482.511, "eval_steps_per_second": 7.741, "step": 9222 }, { "epoch": 88.0, "grad_norm": 0.27362629771232605, "learning_rate": 6e-06, "loss": 0.0244, "step": 9328 }, { "epoch": 88.0, "eval_LOCATION_f1": 0.8413793103448277, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8026315789473685, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6901408450704226, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6049382716049383, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.9050632911392406, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8773006134969326, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1714063584804535, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8349249658935879, "eval_overall_precision": 0.7906976744186046, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3861, "eval_samples_per_second": 484.303, "eval_steps_per_second": 7.77, "step": 9328 }, { "epoch": 89.0, "grad_norm": 0.8111550211906433, "learning_rate": 5.500000000000001e-06, "loss": 0.0241, "step": 9434 }, { "epoch": 89.0, "eval_LOCATION_f1": 0.8391608391608392, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8108108108108109, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6619718309859155, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5802469135802469, "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": 0.7575757575757576, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.875, "eval_TIME_number": 31, "eval_TIME_precision": 0.8484848484848485, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.17061959207057953, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8262653898768809, "eval_overall_precision": 0.7844155844155845, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3865, "eval_samples_per_second": 483.843, "eval_steps_per_second": 7.762, "step": 9434 }, { "epoch": 90.0, "grad_norm": 1.0249470472335815, "learning_rate": 5e-06, "loss": 0.0243, "step": 9540 }, { "epoch": 90.0, "eval_LOCATION_f1": 0.8391608391608392, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8108108108108109, "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": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7575757575757576, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1695098727941513, "eval_overall_accuracy": 0.9628436958137231, "eval_overall_f1": 0.8225584594222832, "eval_overall_precision": 0.7847769028871391, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.3906, "eval_samples_per_second": 478.784, "eval_steps_per_second": 7.681, "step": 9540 }, { "epoch": 91.0, "grad_norm": 0.33852913975715637, "learning_rate": 4.5e-06, "loss": 0.0275, "step": 9646 }, { "epoch": 91.0, "eval_LOCATION_f1": 0.8391608391608392, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8108108108108109, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6713286713286712, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5853658536585366, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8253968253968254, "eval_TIME_number": 31, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1680055409669876, "eval_overall_accuracy": 0.9638345305920237, "eval_overall_f1": 0.8267394270122783, "eval_overall_precision": 0.7829457364341085, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3855, "eval_samples_per_second": 485.059, "eval_steps_per_second": 7.782, "step": 9646 }, { "epoch": 92.0, "grad_norm": 0.39975494146347046, "learning_rate": 4.000000000000001e-06, "loss": 0.0255, "step": 9752 }, { "epoch": 92.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "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": 0.16812948882579803, "eval_overall_accuracy": 0.9633391132028735, "eval_overall_f1": 0.8306010928961748, "eval_overall_precision": 0.7875647668393783, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3868, "eval_samples_per_second": 483.398, "eval_steps_per_second": 7.755, "step": 9752 }, { "epoch": 93.0, "grad_norm": 1.0481526851654053, "learning_rate": 3.5000000000000004e-06, "loss": 0.0263, "step": 9858 }, { "epoch": 93.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6993006993006993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6097560975609756, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "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": 0.17125730216503143, "eval_overall_accuracy": 0.9633391132028735, "eval_overall_f1": 0.8321964529331515, "eval_overall_precision": 0.7881136950904393, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3893, "eval_samples_per_second": 480.408, "eval_steps_per_second": 7.707, "step": 9858 }, { "epoch": 94.0, "grad_norm": 0.5582793951034546, "learning_rate": 3e-06, "loss": 0.0241, "step": 9964 }, { "epoch": 94.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6713286713286712, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5853658536585366, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8930817610062893, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8606060606060606, "eval_PERSON_recall": 0.9281045751633987, "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": 0.1685493141412735, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8256130790190735, "eval_overall_precision": 0.7809278350515464, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3861, "eval_samples_per_second": 484.357, "eval_steps_per_second": 7.77, "step": 9964 }, { "epoch": 95.0, "grad_norm": 0.343916118144989, "learning_rate": 2.5e-06, "loss": 0.0226, "step": 10070 }, { "epoch": 95.0, "eval_LOCATION_f1": 0.8275862068965517, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6993006993006993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6097560975609756, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "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": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.17299310863018036, "eval_overall_accuracy": 0.964082239286599, "eval_overall_f1": 0.8342391304347826, "eval_overall_precision": 0.7871794871794872, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3875, "eval_samples_per_second": 482.546, "eval_steps_per_second": 7.741, "step": 10070 }, { "epoch": 96.0, "grad_norm": 0.19797514379024506, "learning_rate": 2.0000000000000003e-06, "loss": 0.0255, "step": 10176 }, { "epoch": 96.0, "eval_LOCATION_f1": 0.8275862068965517, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6805555555555556, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5903614457831325, "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": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "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": 0.17226825654506683, "eval_overall_accuracy": 0.9633391132028735, "eval_overall_f1": 0.828146143437077, "eval_overall_precision": 0.7786259541984732, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3868, "eval_samples_per_second": 483.481, "eval_steps_per_second": 7.756, "step": 10176 }, { "epoch": 97.0, "grad_norm": 0.902725100517273, "learning_rate": 1.5e-06, "loss": 0.0235, "step": 10282 }, { "epoch": 97.0, "eval_LOCATION_f1": 0.8391608391608392, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8108108108108109, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "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": 0.8615384615384616, "eval_TIME_number": 31, "eval_TIME_precision": 0.8235294117647058, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.17186929285526276, "eval_overall_accuracy": 0.9645776566757494, "eval_overall_f1": 0.8380952380952382, "eval_overall_precision": 0.7917737789203085, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.3861, "eval_samples_per_second": 484.282, "eval_steps_per_second": 7.769, "step": 10282 }, { "epoch": 98.0, "grad_norm": 0.300263911485672, "learning_rate": 1.0000000000000002e-06, "loss": 0.0247, "step": 10388 }, { "epoch": 98.0, "eval_LOCATION_f1": 0.8333333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "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": 0.875, "eval_TIME_number": 31, "eval_TIME_precision": 0.8484848484848485, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.17275255918502808, "eval_overall_accuracy": 0.9643299479811741, "eval_overall_f1": 0.8392370572207084, "eval_overall_precision": 0.7938144329896907, "eval_overall_recall": 0.8901734104046243, "eval_runtime": 0.3883, "eval_samples_per_second": 481.567, "eval_steps_per_second": 7.726, "step": 10388 }, { "epoch": 99.0, "grad_norm": 0.9367396831512451, "learning_rate": 5.000000000000001e-07, "loss": 0.0249, "step": 10494 }, { "epoch": 99.0, "eval_LOCATION_f1": 0.8275862068965517, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "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": 0.17310978472232819, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8353741496598639, "eval_overall_precision": 0.7892030848329049, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3856, "eval_samples_per_second": 484.952, "eval_steps_per_second": 7.78, "step": 10494 }, { "epoch": 100.0, "grad_norm": 0.12492021173238754, "learning_rate": 0.0, "loss": 0.0219, "step": 10600 }, { "epoch": 100.0, "eval_LOCATION_f1": 0.8275862068965517, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7894736842105263, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.9022082018927446, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8719512195121951, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7428571428571429, "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": 0.17298303544521332, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8353741496598639, "eval_overall_precision": 0.7892030848329049, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3865, "eval_samples_per_second": 483.831, "eval_steps_per_second": 7.762, "step": 10600 }, { "epoch": 100.0, "step": 10600, "total_flos": 5088556202474382.0, "train_loss": 0.07048136641394417, "train_runtime": 625.2984, "train_samples_per_second": 269.791, "train_steps_per_second": 16.952 } ], "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 }