{ "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": 0.9385712146759033, "learning_rate": 4.9500000000000004e-05, "loss": 0.9461, "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": 58, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.012820512820512818, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.25, "eval_PERSON_recall": 0.006578947368421052, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 29, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.5987688302993774, "eval_overall_accuracy": 0.8402048655569783, "eval_overall_f1": 0.0058309037900874635, "eval_overall_precision": 0.2, "eval_overall_recall": 0.0029585798816568047, "eval_runtime": 0.3601, "eval_samples_per_second": 519.294, "eval_steps_per_second": 8.331, "step": 106 }, { "epoch": 2.0, "grad_norm": 1.142086148262024, "learning_rate": 4.9e-05, "loss": 0.5011, "step": 212 }, { "epoch": 2.0, "eval_LOCATION_f1": 0.2909090909090909, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.3902439024390244, "eval_LOCATION_recall": 0.2318840579710145, "eval_ORGANIZATION_f1": 0.1411764705882353, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.2222222222222222, "eval_ORGANIZATION_recall": 0.10344827586206896, "eval_PERSON_f1": 0.6740331491712708, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.580952380952381, "eval_PERSON_recall": 0.8026315789473685, "eval_QUANTITY_f1": 0.0784313725490196, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.09523809523809523, "eval_QUANTITY_recall": 0.06666666666666667, "eval_TIME_f1": 0.5396825396825397, "eval_TIME_number": 29, "eval_TIME_precision": 0.5, "eval_TIME_recall": 0.5862068965517241, "eval_loss": 0.329304039478302, "eval_overall_accuracy": 0.9052496798975672, "eval_overall_f1": 0.4858420268256334, "eval_overall_precision": 0.4894894894894895, "eval_overall_recall": 0.4822485207100592, "eval_runtime": 0.3647, "eval_samples_per_second": 512.76, "eval_steps_per_second": 8.226, "step": 212 }, { "epoch": 3.0, "grad_norm": 1.477553129196167, "learning_rate": 4.85e-05, "loss": 0.2868, "step": 318 }, { "epoch": 3.0, "eval_LOCATION_f1": 0.6707317073170732, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.5789473684210527, "eval_LOCATION_recall": 0.7971014492753623, "eval_ORGANIZATION_f1": 0.5270270270270271, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.43333333333333335, "eval_ORGANIZATION_recall": 0.6724137931034483, "eval_PERSON_f1": 0.806060606060606, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7471910112359551, "eval_PERSON_recall": 0.875, "eval_QUANTITY_f1": 0.6027397260273971, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.5116279069767442, "eval_QUANTITY_recall": 0.7333333333333333, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.1913897693157196, "eval_overall_accuracy": 0.9357234314980793, "eval_overall_f1": 0.704516129032258, "eval_overall_precision": 0.6247139588100686, "eval_overall_recall": 0.8076923076923077, "eval_runtime": 0.3649, "eval_samples_per_second": 512.526, "eval_steps_per_second": 8.222, "step": 318 }, { "epoch": 4.0, "grad_norm": 1.5592992305755615, "learning_rate": 4.8e-05, "loss": 0.1873, "step": 424 }, { "epoch": 4.0, "eval_LOCATION_f1": 0.8205128205128205, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.735632183908046, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.5920000000000001, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.5522388059701493, "eval_ORGANIZATION_recall": 0.6379310344827587, "eval_PERSON_f1": 0.8288288288288289, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.7624309392265194, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.6753246753246753, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.5531914893617021, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.6567164179104478, "eval_TIME_number": 29, "eval_TIME_precision": 0.5789473684210527, "eval_TIME_recall": 0.7586206896551724, "eval_loss": 0.17130739986896515, "eval_overall_accuracy": 0.942381562099872, "eval_overall_f1": 0.7572559366754616, "eval_overall_precision": 0.6833333333333333, "eval_overall_recall": 0.849112426035503, "eval_runtime": 0.3641, "eval_samples_per_second": 513.586, "eval_steps_per_second": 8.239, "step": 424 }, { "epoch": 5.0, "grad_norm": 1.5537115335464478, "learning_rate": 4.75e-05, "loss": 0.158, "step": 530 }, { "epoch": 5.0, "eval_LOCATION_f1": 0.7534246575342466, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7142857142857143, "eval_LOCATION_recall": 0.7971014492753623, "eval_ORGANIZATION_f1": 0.6330935251798561, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.5432098765432098, "eval_ORGANIZATION_recall": 0.7586206896551724, "eval_PERSON_f1": 0.8643533123028391, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8303030303030303, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7878787878787877, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.1296878606081009, "eval_overall_accuracy": 0.9549295774647887, "eval_overall_f1": 0.7895460797799173, "eval_overall_precision": 0.7377892030848329, "eval_overall_recall": 0.849112426035503, "eval_runtime": 0.3648, "eval_samples_per_second": 512.547, "eval_steps_per_second": 8.223, "step": 530 }, { "epoch": 6.0, "grad_norm": 1.2474393844604492, "learning_rate": 4.7e-05, "loss": 0.1399, "step": 636 }, { "epoch": 6.0, "eval_LOCATION_f1": 0.7870967741935485, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7093023255813954, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6615384615384615, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.5972222222222222, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.8509316770186336, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8058823529411765, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7761194029850748, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.6666666666666667, "eval_TIME_number": 29, "eval_TIME_precision": 0.5945945945945946, "eval_TIME_recall": 0.7586206896551724, "eval_loss": 0.13218359649181366, "eval_overall_accuracy": 0.9559539052496799, "eval_overall_f1": 0.7810810810810812, "eval_overall_precision": 0.7189054726368159, "eval_overall_recall": 0.8550295857988166, "eval_runtime": 0.3626, "eval_samples_per_second": 515.654, "eval_steps_per_second": 8.273, "step": 636 }, { "epoch": 7.0, "grad_norm": 0.42945849895477295, "learning_rate": 4.6500000000000005e-05, "loss": 0.129, "step": 742 }, { "epoch": 7.0, "eval_LOCATION_f1": 0.8266666666666668, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7654320987654321, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.671875, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6142857142857143, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.8598130841121495, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8165680473372781, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.7042253521126761, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6097560975609756, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.1299288421869278, "eval_overall_accuracy": 0.9556978233034571, "eval_overall_f1": 0.8, "eval_overall_precision": 0.7448979591836735, "eval_overall_recall": 0.863905325443787, "eval_runtime": 0.3658, "eval_samples_per_second": 511.192, "eval_steps_per_second": 8.201, "step": 742 }, { "epoch": 8.0, "grad_norm": 0.6201493740081787, "learning_rate": 4.600000000000001e-05, "loss": 0.1206, "step": 848 }, { "epoch": 8.0, "eval_LOCATION_f1": 0.8378378378378378, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7848101265822784, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6666666666666667, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6176470588235294, "eval_ORGANIZATION_recall": 0.7241379310344828, "eval_PERSON_f1": 0.8679245283018868, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8313253012048193, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.7301587301587302, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.696969696969697, "eval_QUANTITY_recall": 0.7666666666666667, "eval_TIME_f1": 0.7301587301587301, "eval_TIME_number": 29, "eval_TIME_precision": 0.6764705882352942, "eval_TIME_recall": 0.7931034482758621, "eval_loss": 0.12837941944599152, "eval_overall_accuracy": 0.9580025608194622, "eval_overall_f1": 0.8022284122562675, "eval_overall_precision": 0.7578947368421053, "eval_overall_recall": 0.8520710059171598, "eval_runtime": 0.3615, "eval_samples_per_second": 517.233, "eval_steps_per_second": 8.298, "step": 848 }, { "epoch": 9.0, "grad_norm": 1.2987040281295776, "learning_rate": 4.55e-05, "loss": 0.113, "step": 954 }, { "epoch": 9.0, "eval_LOCATION_f1": 0.8493150684931507, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8051948051948052, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6612903225806452, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6212121212121212, "eval_ORGANIZATION_recall": 0.7068965517241379, "eval_PERSON_f1": 0.8606811145510835, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8128654970760234, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.696969696969697, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6388888888888888, "eval_QUANTITY_recall": 0.7666666666666667, "eval_TIME_f1": 0.75, "eval_TIME_number": 29, "eval_TIME_precision": 0.6857142857142857, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.1300167590379715, "eval_overall_accuracy": 0.9569782330345711, "eval_overall_f1": 0.7994467496542187, "eval_overall_precision": 0.7506493506493507, "eval_overall_recall": 0.8550295857988166, "eval_runtime": 0.3681, "eval_samples_per_second": 507.956, "eval_steps_per_second": 8.149, "step": 954 }, { "epoch": 10.0, "grad_norm": 2.6489315032958984, "learning_rate": 4.5e-05, "loss": 0.1052, "step": 1060 }, { "epoch": 10.0, "eval_LOCATION_f1": 0.8266666666666668, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7654320987654321, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.736, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6865671641791045, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.8742138364779874, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8373493975903614, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.7272727272727272, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6666666666666666, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7419354838709677, "eval_TIME_number": 29, "eval_TIME_precision": 0.696969696969697, "eval_TIME_recall": 0.7931034482758621, "eval_loss": 0.13011391460895538, "eval_overall_accuracy": 0.9600512163892445, "eval_overall_f1": 0.8155339805825242, "eval_overall_precision": 0.7676240208877284, "eval_overall_recall": 0.8698224852071006, "eval_runtime": 0.3639, "eval_samples_per_second": 513.937, "eval_steps_per_second": 8.245, "step": 1060 }, { "epoch": 11.0, "grad_norm": 1.2084473371505737, "learning_rate": 4.4500000000000004e-05, "loss": 0.1015, "step": 1166 }, { "epoch": 11.0, "eval_LOCATION_f1": 0.8322147651006713, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.775, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6929133858267716, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6376811594202898, "eval_ORGANIZATION_recall": 0.7586206896551724, "eval_PERSON_f1": 0.8825396825396825, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.852760736196319, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.605263157894737, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.7666666666666667, "eval_TIME_f1": 0.7384615384615385, "eval_TIME_number": 29, "eval_TIME_precision": 0.6666666666666666, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13992547988891602, "eval_overall_accuracy": 0.9572343149807938, "eval_overall_f1": 0.7978142076502731, "eval_overall_precision": 0.7411167512690355, "eval_overall_recall": 0.863905325443787, "eval_runtime": 0.3632, "eval_samples_per_second": 514.923, "eval_steps_per_second": 8.261, "step": 1166 }, { "epoch": 12.0, "grad_norm": 1.8773159980773926, "learning_rate": 4.4000000000000006e-05, "loss": 0.0947, "step": 1272 }, { "epoch": 12.0, "eval_LOCATION_f1": 0.8551724137931034, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8157894736842105, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6721311475409836, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.640625, "eval_ORGANIZATION_recall": 0.7068965517241379, "eval_PERSON_f1": 0.8789808917197451, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8518518518518519, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.7575757575757577, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13281035423278809, "eval_overall_accuracy": 0.9603072983354674, "eval_overall_f1": 0.8203677510608204, "eval_overall_precision": 0.7859078590785907, "eval_overall_recall": 0.8579881656804734, "eval_runtime": 0.3602, "eval_samples_per_second": 519.165, "eval_steps_per_second": 8.329, "step": 1272 }, { "epoch": 13.0, "grad_norm": 0.6153600811958313, "learning_rate": 4.35e-05, "loss": 0.0873, "step": 1378 }, { "epoch": 13.0, "eval_LOCATION_f1": 0.8456375838926175, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7875, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6779661016949153, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.6896551724137931, "eval_PERSON_f1": 0.89171974522293, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8641975308641975, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.7301587301587302, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.696969696969697, "eval_QUANTITY_recall": 0.7666666666666667, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12352564930915833, "eval_overall_accuracy": 0.9618437900128041, "eval_overall_f1": 0.8215297450424929, "eval_overall_precision": 0.7880434782608695, "eval_overall_recall": 0.8579881656804734, "eval_runtime": 0.3606, "eval_samples_per_second": 518.529, "eval_steps_per_second": 8.319, "step": 1378 }, { "epoch": 14.0, "grad_norm": 1.5589418411254883, "learning_rate": 4.3e-05, "loss": 0.0866, "step": 1484 }, { "epoch": 14.0, "eval_LOCATION_f1": 0.8551724137931034, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8157894736842105, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.7226890756302522, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7049180327868853, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.877742946708464, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8383233532934131, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.7575757575757577, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.12825486063957214, "eval_overall_accuracy": 0.9618437900128041, "eval_overall_f1": 0.8270042194092827, "eval_overall_precision": 0.7882037533512064, "eval_overall_recall": 0.8698224852071006, "eval_runtime": 0.3611, "eval_samples_per_second": 517.813, "eval_steps_per_second": 8.307, "step": 1484 }, { "epoch": 15.0, "grad_norm": 0.9031327366828918, "learning_rate": 4.25e-05, "loss": 0.0798, "step": 1590 }, { "epoch": 15.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.6782608695652174, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6842105263157895, "eval_ORGANIZATION_recall": 0.6724137931034483, "eval_PERSON_f1": 0.9096774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8924050632911392, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.676056338028169, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.5853658536585366, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.14200492203235626, "eval_overall_accuracy": 0.9615877080665813, "eval_overall_f1": 0.8271954674220963, "eval_overall_precision": 0.7934782608695652, "eval_overall_recall": 0.863905325443787, "eval_runtime": 0.3619, "eval_samples_per_second": 516.714, "eval_steps_per_second": 8.29, "step": 1590 }, { "epoch": 16.0, "grad_norm": 0.6099029779434204, "learning_rate": 4.2e-05, "loss": 0.0752, "step": 1696 }, { "epoch": 16.0, "eval_LOCATION_f1": 0.8344370860927153, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7682926829268293, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7014925373134329, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.618421052631579, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.8987341772151899, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.6666666666666666, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.5714285714285714, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7741935483870968, "eval_TIME_number": 29, "eval_TIME_precision": 0.7272727272727273, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.1463884562253952, "eval_overall_accuracy": 0.9574903969270167, "eval_overall_f1": 0.8163265306122449, "eval_overall_precision": 0.7556675062972292, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.3632, "eval_samples_per_second": 514.892, "eval_steps_per_second": 8.26, "step": 1696 }, { "epoch": 17.0, "grad_norm": 0.517600417137146, "learning_rate": 4.15e-05, "loss": 0.0735, "step": 1802 }, { "epoch": 17.0, "eval_LOCATION_f1": 0.8456375838926175, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7875, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.732824427480916, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6575342465753424, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.8805031446540881, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8433734939759037, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.631578947368421, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7868852459016394, "eval_TIME_number": 29, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13951300084590912, "eval_overall_accuracy": 0.9592829705505762, "eval_overall_f1": 0.8225584594222833, "eval_overall_precision": 0.7686375321336761, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3629, "eval_samples_per_second": 515.265, "eval_steps_per_second": 8.266, "step": 1802 }, { "epoch": 18.0, "grad_norm": 0.641730785369873, "learning_rate": 4.1e-05, "loss": 0.0706, "step": 1908 }, { "epoch": 18.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.6833333333333333, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6612903225806451, "eval_ORGANIZATION_recall": 0.7068965517241379, "eval_PERSON_f1": 0.90282131661442, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8622754491017964, "eval_PERSON_recall": 0.9473684210526315, "eval_QUANTITY_f1": 0.6956521739130435, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6153846153846154, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.75, "eval_TIME_number": 29, "eval_TIME_precision": 0.6857142857142857, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.13999910652637482, "eval_overall_accuracy": 0.9597951344430218, "eval_overall_f1": 0.8250000000000001, "eval_overall_precision": 0.7774869109947644, "eval_overall_recall": 0.878698224852071, "eval_runtime": 0.3619, "eval_samples_per_second": 516.724, "eval_steps_per_second": 8.29, "step": 1908 }, { "epoch": 19.0, "grad_norm": 1.3220598697662354, "learning_rate": 4.05e-05, "loss": 0.0659, "step": 2014 }, { "epoch": 19.0, "eval_LOCATION_f1": 0.8767123287671235, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8311688311688312, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7040000000000001, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6567164179104478, "eval_ORGANIZATION_recall": 0.7586206896551724, "eval_PERSON_f1": 0.8831168831168831, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8717948717948718, "eval_PERSON_recall": 0.8947368421052632, "eval_QUANTITY_f1": 0.7164179104477612, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.1347155123949051, "eval_overall_accuracy": 0.9610755441741358, "eval_overall_f1": 0.8271954674220963, "eval_overall_precision": 0.7934782608695652, "eval_overall_recall": 0.863905325443787, "eval_runtime": 0.3626, "eval_samples_per_second": 515.766, "eval_steps_per_second": 8.274, "step": 2014 }, { "epoch": 20.0, "grad_norm": 0.6515225768089294, "learning_rate": 4e-05, "loss": 0.0675, "step": 2120 }, { "epoch": 20.0, "eval_LOCATION_f1": 0.863013698630137, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8181818181818182, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7107438016528926, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6825396825396826, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.8987341772151899, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7796610169491527, "eval_TIME_number": 29, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.7931034482758621, "eval_loss": 0.1337330937385559, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8385269121813032, "eval_overall_precision": 0.8043478260869565, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.3613, "eval_samples_per_second": 517.591, "eval_steps_per_second": 8.304, "step": 2120 }, { "epoch": 21.0, "grad_norm": 0.5770078301429749, "learning_rate": 3.9500000000000005e-05, "loss": 0.061, "step": 2226 }, { "epoch": 21.0, "eval_LOCATION_f1": 0.8648648648648648, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.810126582278481, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.6614173228346457, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6086956521739131, "eval_ORGANIZATION_recall": 0.7241379310344828, "eval_PERSON_f1": 0.9009584664536742, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8757763975155279, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7384615384615385, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6857142857142857, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.14680048823356628, "eval_overall_accuracy": 0.9600512163892445, "eval_overall_f1": 0.8274894810659188, "eval_overall_precision": 0.7866666666666666, "eval_overall_recall": 0.8727810650887574, "eval_runtime": 0.3613, "eval_samples_per_second": 517.577, "eval_steps_per_second": 8.303, "step": 2226 }, { "epoch": 22.0, "grad_norm": 0.7486574649810791, "learning_rate": 3.9000000000000006e-05, "loss": 0.06, "step": 2332 }, { "epoch": 22.0, "eval_LOCATION_f1": 0.8211920529801324, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7560975609756098, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.696969696969697, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.8987341772151899, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.7301587301587302, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.696969696969697, "eval_QUANTITY_recall": 0.7666666666666667, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.14529772102832794, "eval_overall_accuracy": 0.9592829705505762, "eval_overall_f1": 0.8254847645429362, "eval_overall_precision": 0.7760416666666666, "eval_overall_recall": 0.8816568047337278, "eval_runtime": 0.3623, "eval_samples_per_second": 516.214, "eval_steps_per_second": 8.282, "step": 2332 }, { "epoch": 23.0, "grad_norm": 0.2607748210430145, "learning_rate": 3.85e-05, "loss": 0.0564, "step": 2438 }, { "epoch": 23.0, "eval_LOCATION_f1": 0.8472222222222223, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8133333333333334, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6774193548387097, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6363636363636364, "eval_ORGANIZATION_recall": 0.7241379310344828, "eval_PERSON_f1": 0.8924050632911392, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8597560975609756, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7384615384615385, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6857142857142857, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7666666666666667, "eval_TIME_number": 29, "eval_TIME_precision": 0.7419354838709677, "eval_TIME_recall": 0.7931034482758621, "eval_loss": 0.14830049872398376, "eval_overall_accuracy": 0.9585147247119078, "eval_overall_f1": 0.8208744710860366, "eval_overall_precision": 0.784366576819407, "eval_overall_recall": 0.8609467455621301, "eval_runtime": 0.3616, "eval_samples_per_second": 517.181, "eval_steps_per_second": 8.297, "step": 2438 }, { "epoch": 24.0, "grad_norm": 2.595079183578491, "learning_rate": 3.8e-05, "loss": 0.0554, "step": 2544 }, { "epoch": 24.0, "eval_LOCATION_f1": 0.8551724137931034, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8157894736842105, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6885245901639345, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.65625, "eval_ORGANIZATION_recall": 0.7241379310344828, "eval_PERSON_f1": 0.8924050632911392, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8597560975609756, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7301587301587302, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.696969696969697, "eval_QUANTITY_recall": 0.7666666666666667, "eval_TIME_f1": 0.8135593220338982, "eval_TIME_number": 29, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.14491747319698334, "eval_overall_accuracy": 0.9613316261203585, "eval_overall_f1": 0.8283687943262411, "eval_overall_precision": 0.7956403269754768, "eval_overall_recall": 0.863905325443787, "eval_runtime": 0.3728, "eval_samples_per_second": 501.619, "eval_steps_per_second": 8.047, "step": 2544 }, { "epoch": 25.0, "grad_norm": 0.5846478939056396, "learning_rate": 3.7500000000000003e-05, "loss": 0.0519, "step": 2650 }, { "epoch": 25.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6774193548387096, "eval_ORGANIZATION_recall": 0.7241379310344828, "eval_PERSON_f1": 0.891025641025641, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.86875, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.13898588716983795, "eval_overall_accuracy": 0.963124199743918, "eval_overall_f1": 0.8376068376068375, "eval_overall_precision": 0.8076923076923077, "eval_overall_recall": 0.8698224852071006, "eval_runtime": 0.3627, "eval_samples_per_second": 515.609, "eval_steps_per_second": 8.272, "step": 2650 }, { "epoch": 26.0, "grad_norm": 0.6813308596611023, "learning_rate": 3.7e-05, "loss": 0.0513, "step": 2756 }, { "epoch": 26.0, "eval_LOCATION_f1": 0.8571428571428572, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8076923076923077, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6935483870967741, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6515151515151515, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.8993710691823898, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8614457831325302, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.7500000000000001, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7058823529411765, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7796610169491527, "eval_TIME_number": 29, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.7931034482758621, "eval_loss": 0.14682267606258392, "eval_overall_accuracy": 0.9600512163892445, "eval_overall_f1": 0.8314606741573034, "eval_overall_precision": 0.7914438502673797, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.3655, "eval_samples_per_second": 511.58, "eval_steps_per_second": 8.207, "step": 2756 }, { "epoch": 27.0, "grad_norm": 0.7736313939094543, "learning_rate": 3.65e-05, "loss": 0.0481, "step": 2862 }, { "epoch": 27.0, "eval_LOCATION_f1": 0.8493150684931507, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8051948051948052, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.7154471544715447, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.676923076923077, "eval_ORGANIZATION_recall": 0.7586206896551724, "eval_PERSON_f1": 0.8846153846153847, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8625, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.71875, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6764705882352942, "eval_QUANTITY_recall": 0.7666666666666667, "eval_TIME_f1": 0.7931034482758621, "eval_TIME_number": 29, "eval_TIME_precision": 0.7931034482758621, "eval_TIME_recall": 0.7931034482758621, "eval_loss": 0.1426493525505066, "eval_overall_accuracy": 0.9618437900128041, "eval_overall_f1": 0.8250355618776672, "eval_overall_precision": 0.7945205479452054, "eval_overall_recall": 0.8579881656804734, "eval_runtime": 0.3648, "eval_samples_per_second": 512.572, "eval_steps_per_second": 8.223, "step": 2862 }, { "epoch": 28.0, "grad_norm": 3.694187879562378, "learning_rate": 3.6e-05, "loss": 0.049, "step": 2968 }, { "epoch": 28.0, "eval_LOCATION_f1": 0.8590604026845639, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.703125, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6428571428571429, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.889589905362776, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8545454545454545, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.761904761904762, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7272727272727273, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.14467592537403107, "eval_overall_accuracy": 0.9613316261203585, "eval_overall_f1": 0.8340306834030683, "eval_overall_precision": 0.7889182058047494, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3626, "eval_samples_per_second": 515.74, "eval_steps_per_second": 8.274, "step": 2968 }, { "epoch": 29.0, "grad_norm": 0.9289089441299438, "learning_rate": 3.55e-05, "loss": 0.0454, "step": 3074 }, { "epoch": 29.0, "eval_LOCATION_f1": 0.8289473684210527, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7022900763358779, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.8987341772151899, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.761904761904762, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7272727272727273, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.7796610169491527, "eval_TIME_number": 29, "eval_TIME_precision": 0.7666666666666667, "eval_TIME_recall": 0.7931034482758621, "eval_loss": 0.1462765336036682, "eval_overall_accuracy": 0.9613316261203585, "eval_overall_f1": 0.826629680998613, "eval_overall_precision": 0.7780678851174935, "eval_overall_recall": 0.8816568047337278, "eval_runtime": 0.3617, "eval_samples_per_second": 517.021, "eval_steps_per_second": 8.294, "step": 3074 }, { "epoch": 30.0, "grad_norm": 0.6081207394599915, "learning_rate": 3.5e-05, "loss": 0.044, "step": 3180 }, { "epoch": 30.0, "eval_LOCATION_f1": 0.8513513513513514, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6833333333333333, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6612903225806451, "eval_ORGANIZATION_recall": 0.7068965517241379, "eval_PERSON_f1": 0.8980891719745223, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8703703703703703, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.15890125930309296, "eval_overall_accuracy": 0.9615877080665813, "eval_overall_f1": 0.8328611898016997, "eval_overall_precision": 0.7989130434782609, "eval_overall_recall": 0.8698224852071006, "eval_runtime": 0.3628, "eval_samples_per_second": 515.391, "eval_steps_per_second": 8.268, "step": 3180 }, { "epoch": 31.0, "grad_norm": 0.16668835282325745, "learning_rate": 3.45e-05, "loss": 0.0416, "step": 3286 }, { "epoch": 31.0, "eval_LOCATION_f1": 0.8590604026845639, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.6557377049180328, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.625, "eval_ORGANIZATION_recall": 0.6896551724137931, "eval_PERSON_f1": 0.8726114649681528, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.845679012345679, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8524590163934426, "eval_TIME_number": 29, "eval_TIME_precision": 0.8125, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.17196589708328247, "eval_overall_accuracy": 0.9585147247119078, "eval_overall_f1": 0.8236953455571228, "eval_overall_precision": 0.7870619946091644, "eval_overall_recall": 0.863905325443787, "eval_runtime": 0.3616, "eval_samples_per_second": 517.119, "eval_steps_per_second": 8.296, "step": 3286 }, { "epoch": 32.0, "grad_norm": 0.4284921884536743, "learning_rate": 3.4000000000000007e-05, "loss": 0.0401, "step": 3392 }, { "epoch": 32.0, "eval_LOCATION_f1": 0.8344370860927153, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7682926829268293, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6774193548387097, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6363636363636364, "eval_ORGANIZATION_recall": 0.7241379310344828, "eval_PERSON_f1": 0.8952380952380953, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8650306748466258, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.1567964404821396, "eval_overall_accuracy": 0.9613316261203585, "eval_overall_f1": 0.8314606741573034, "eval_overall_precision": 0.7914438502673797, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.362, "eval_samples_per_second": 516.616, "eval_steps_per_second": 8.288, "step": 3392 }, { "epoch": 33.0, "grad_norm": 0.5324723124504089, "learning_rate": 3.35e-05, "loss": 0.0403, "step": 3498 }, { "epoch": 33.0, "eval_LOCATION_f1": 0.8590604026845639, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.6504065040650407, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6153846153846154, "eval_ORGANIZATION_recall": 0.6896551724137931, "eval_PERSON_f1": 0.9003215434083601, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8805031446540881, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8064516129032258, "eval_TIME_number": 29, "eval_TIME_precision": 0.7575757575757576, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.16175581514835358, "eval_overall_accuracy": 0.9603072983354674, "eval_overall_f1": 0.8305084745762711, "eval_overall_precision": 0.7945945945945946, "eval_overall_recall": 0.8698224852071006, "eval_runtime": 0.3675, "eval_samples_per_second": 508.792, "eval_steps_per_second": 8.162, "step": 3498 }, { "epoch": 34.0, "grad_norm": 2.500312089920044, "learning_rate": 3.3e-05, "loss": 0.0386, "step": 3604 }, { "epoch": 34.0, "eval_LOCATION_f1": 0.8533333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7131782945736435, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.647887323943662, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.889589905362776, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8545454545454545, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7384615384615385, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6857142857142857, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.75, "eval_TIME_number": 29, "eval_TIME_precision": 0.6857142857142857, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.18283192813396454, "eval_overall_accuracy": 0.9572343149807938, "eval_overall_f1": 0.8248275862068964, "eval_overall_precision": 0.772609819121447, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3633, "eval_samples_per_second": 514.668, "eval_steps_per_second": 8.257, "step": 3604 }, { "epoch": 35.0, "grad_norm": 1.1595585346221924, "learning_rate": 3.2500000000000004e-05, "loss": 0.039, "step": 3710 }, { "epoch": 35.0, "eval_LOCATION_f1": 0.8456375838926175, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7875, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6559999999999999, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6119402985074627, "eval_ORGANIZATION_recall": 0.7068965517241379, "eval_PERSON_f1": 0.8938906752411576, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8742138364779874, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.15863440930843353, "eval_overall_accuracy": 0.9610755441741358, "eval_overall_f1": 0.8253521126760562, "eval_overall_precision": 0.7876344086021505, "eval_overall_recall": 0.8668639053254438, "eval_runtime": 0.3621, "eval_samples_per_second": 516.479, "eval_steps_per_second": 8.286, "step": 3710 }, { "epoch": 36.0, "grad_norm": 0.5105273723602295, "learning_rate": 3.2000000000000005e-05, "loss": 0.0378, "step": 3816 }, { "epoch": 36.0, "eval_LOCATION_f1": 0.8513513513513514, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6666666666666667, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.5662650602409639, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.9137380191693291, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8881987577639752, "eval_PERSON_recall": 0.9407894736842105, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 29, "eval_TIME_precision": 0.7741935483870968, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.17168986797332764, "eval_overall_accuracy": 0.9590268886043534, "eval_overall_f1": 0.8331034482758619, "eval_overall_precision": 0.7803617571059431, "eval_overall_recall": 0.893491124260355, "eval_runtime": 0.3612, "eval_samples_per_second": 517.716, "eval_steps_per_second": 8.306, "step": 3816 }, { "epoch": 37.0, "grad_norm": 0.3558787703514099, "learning_rate": 3.15e-05, "loss": 0.0376, "step": 3922 }, { "epoch": 37.0, "eval_LOCATION_f1": 0.8533333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.6612903225806452, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6212121212121212, "eval_ORGANIZATION_recall": 0.7068965517241379, "eval_PERSON_f1": 0.9102564102564101, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8875, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.16201062500476837, "eval_overall_accuracy": 0.9620998719590269, "eval_overall_f1": 0.8389830508474576, "eval_overall_precision": 0.8027027027027027, "eval_overall_recall": 0.878698224852071, "eval_runtime": 0.3603, "eval_samples_per_second": 518.978, "eval_steps_per_second": 8.326, "step": 3922 }, { "epoch": 38.0, "grad_norm": 0.9564065933227539, "learning_rate": 3.1e-05, "loss": 0.0337, "step": 4028 }, { "epoch": 38.0, "eval_LOCATION_f1": 0.8590604026845639, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7343749999999999, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6714285714285714, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.9067524115755626, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8867924528301887, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.16582073271274567, "eval_overall_accuracy": 0.9626120358514725, "eval_overall_f1": 0.8523206751054854, "eval_overall_precision": 0.8123324396782842, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.361, "eval_samples_per_second": 518.073, "eval_steps_per_second": 8.311, "step": 4028 }, { "epoch": 39.0, "grad_norm": 1.0465730428695679, "learning_rate": 3.05e-05, "loss": 0.0316, "step": 4134 }, { "epoch": 39.0, "eval_LOCATION_f1": 0.8533333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.706766917293233, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6266666666666667, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.9003215434083601, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8805031446540881, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8064516129032258, "eval_TIME_number": 29, "eval_TIME_precision": 0.7575757575757576, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.175294890999794, "eval_overall_accuracy": 0.9608194622279129, "eval_overall_f1": 0.8388888888888888, "eval_overall_precision": 0.7905759162303665, "eval_overall_recall": 0.893491124260355, "eval_runtime": 0.3612, "eval_samples_per_second": 517.778, "eval_steps_per_second": 8.307, "step": 4134 }, { "epoch": 40.0, "grad_norm": 0.7615323066711426, "learning_rate": 3e-05, "loss": 0.0309, "step": 4240 }, { "epoch": 40.0, "eval_LOCATION_f1": 0.8476821192052981, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7804878048780488, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.6721311475409836, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.640625, "eval_ORGANIZATION_recall": 0.7068965517241379, "eval_PERSON_f1": 0.9067524115755626, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8867924528301887, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7868852459016394, "eval_TIME_number": 29, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8275862068965517, "eval_loss": 0.1751646101474762, "eval_overall_accuracy": 0.9613316261203585, "eval_overall_f1": 0.8321579689703809, "eval_overall_precision": 0.7951482479784366, "eval_overall_recall": 0.8727810650887574, "eval_runtime": 0.3632, "eval_samples_per_second": 514.858, "eval_steps_per_second": 8.26, "step": 4240 }, { "epoch": 41.0, "grad_norm": 0.9296179413795471, "learning_rate": 2.95e-05, "loss": 0.0299, "step": 4346 }, { "epoch": 41.0, "eval_LOCATION_f1": 0.8533333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7313432835820897, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6447368421052632, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9009584664536742, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8757763975155279, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8196721311475409, "eval_TIME_number": 29, "eval_TIME_precision": 0.78125, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.18535542488098145, "eval_overall_accuracy": 0.9613316261203585, "eval_overall_f1": 0.8421052631578947, "eval_overall_precision": 0.7916666666666666, "eval_overall_recall": 0.8994082840236687, "eval_runtime": 0.3623, "eval_samples_per_second": 516.189, "eval_steps_per_second": 8.281, "step": 4346 }, { "epoch": 42.0, "grad_norm": 0.844611406326294, "learning_rate": 2.9e-05, "loss": 0.0279, "step": 4452 }, { "epoch": 42.0, "eval_LOCATION_f1": 0.8435374149659864, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6929133858267716, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6376811594202898, "eval_ORGANIZATION_recall": 0.7586206896551724, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.17631709575653076, "eval_overall_accuracy": 0.9633802816901409, "eval_overall_f1": 0.8385269121813032, "eval_overall_precision": 0.8043478260869565, "eval_overall_recall": 0.8757396449704142, "eval_runtime": 0.3627, "eval_samples_per_second": 515.536, "eval_steps_per_second": 8.271, "step": 4452 }, { "epoch": 43.0, "grad_norm": 4.701879024505615, "learning_rate": 2.8499999999999998e-05, "loss": 0.0314, "step": 4558 }, { "epoch": 43.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6666666666666667, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6056338028169014, "eval_ORGANIZATION_recall": 0.7413793103448276, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.879746835443038, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.7419354838709677, "eval_TIME_number": 29, "eval_TIME_precision": 0.696969696969697, "eval_TIME_recall": 0.7931034482758621, "eval_loss": 0.180297389626503, "eval_overall_accuracy": 0.9582586427656851, "eval_overall_f1": 0.8184357541899442, "eval_overall_precision": 0.7751322751322751, "eval_overall_recall": 0.8668639053254438, "eval_runtime": 0.3609, "eval_samples_per_second": 518.121, "eval_steps_per_second": 8.312, "step": 4558 }, { "epoch": 44.0, "grad_norm": 1.59341561794281, "learning_rate": 2.8000000000000003e-05, "loss": 0.0285, "step": 4664 }, { "epoch": 44.0, "eval_LOCATION_f1": 0.8456375838926175, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7875, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.703125, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6428571428571429, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.9073482428115016, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8819875776397516, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.18566596508026123, "eval_overall_accuracy": 0.9615877080665813, "eval_overall_f1": 0.8391608391608392, "eval_overall_precision": 0.7957559681697612, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.3627, "eval_samples_per_second": 515.537, "eval_steps_per_second": 8.271, "step": 4664 }, { "epoch": 45.0, "grad_norm": 0.9706313014030457, "learning_rate": 2.7500000000000004e-05, "loss": 0.0273, "step": 4770 }, { "epoch": 45.0, "eval_LOCATION_f1": 0.8181818181818181, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7411764705882353, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6875, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6285714285714286, "eval_ORGANIZATION_recall": 0.7586206896551724, "eval_PERSON_f1": 0.9067524115755626, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8867924528301887, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7272727272727272, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6666666666666666, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.8196721311475409, "eval_TIME_number": 29, "eval_TIME_precision": 0.78125, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.18910890817642212, "eval_overall_accuracy": 0.9592829705505762, "eval_overall_f1": 0.8250000000000001, "eval_overall_precision": 0.7774869109947644, "eval_overall_recall": 0.878698224852071, "eval_runtime": 0.3612, "eval_samples_per_second": 517.712, "eval_steps_per_second": 8.306, "step": 4770 }, { "epoch": 46.0, "grad_norm": 0.4735470116138458, "learning_rate": 2.7000000000000002e-05, "loss": 0.0283, "step": 4876 }, { "epoch": 46.0, "eval_LOCATION_f1": 0.8133333333333332, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6307692307692307, "eval_ORGANIZATION_recall": 0.7068965517241379, "eval_PERSON_f1": 0.8938906752411576, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8742138364779874, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.183757022023201, "eval_overall_accuracy": 0.9580025608194622, "eval_overall_f1": 0.8208744710860366, "eval_overall_precision": 0.784366576819407, "eval_overall_recall": 0.8609467455621301, "eval_runtime": 0.3621, "eval_samples_per_second": 516.387, "eval_steps_per_second": 8.284, "step": 4876 }, { "epoch": 47.0, "grad_norm": 1.1514105796813965, "learning_rate": 2.6500000000000004e-05, "loss": 0.0251, "step": 4982 }, { "epoch": 47.0, "eval_LOCATION_f1": 0.8289473684210527, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.716417910447761, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.631578947368421, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.879746835443038, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.7384615384615385, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6857142857142857, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.8064516129032258, "eval_TIME_number": 29, "eval_TIME_precision": 0.7575757575757576, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.1938750296831131, "eval_overall_accuracy": 0.9600512163892445, "eval_overall_f1": 0.8271092669432917, "eval_overall_precision": 0.7766233766233767, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.37, "eval_samples_per_second": 505.427, "eval_steps_per_second": 8.108, "step": 4982 }, { "epoch": 48.0, "grad_norm": 13.560022354125977, "learning_rate": 2.6000000000000002e-05, "loss": 0.0247, "step": 5088 }, { "epoch": 48.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.676923076923077, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6111111111111112, "eval_ORGANIZATION_recall": 0.7586206896551724, "eval_PERSON_f1": 0.9067524115755626, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8867924528301887, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7575757575757577, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8253968253968255, "eval_TIME_number": 29, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.1982179582118988, "eval_overall_accuracy": 0.9603072983354674, "eval_overall_f1": 0.8305555555555556, "eval_overall_precision": 0.7827225130890052, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3647, "eval_samples_per_second": 512.793, "eval_steps_per_second": 8.227, "step": 5088 }, { "epoch": 49.0, "grad_norm": 0.716018795967102, "learning_rate": 2.5500000000000003e-05, "loss": 0.0245, "step": 5194 }, { "epoch": 49.0, "eval_LOCATION_f1": 0.8344370860927153, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7682926829268293, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.71875, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6571428571428571, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9102564102564101, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8875, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8387096774193549, "eval_TIME_number": 29, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.18862377107143402, "eval_overall_accuracy": 0.9626120358514725, "eval_overall_f1": 0.8435754189944134, "eval_overall_precision": 0.798941798941799, "eval_overall_recall": 0.893491124260355, "eval_runtime": 0.3613, "eval_samples_per_second": 517.63, "eval_steps_per_second": 8.304, "step": 5194 }, { "epoch": 50.0, "grad_norm": 0.7329644560813904, "learning_rate": 2.5e-05, "loss": 0.0222, "step": 5300 }, { "epoch": 50.0, "eval_LOCATION_f1": 0.8611111111111112, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8266666666666667, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.6722689075630253, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6557377049180327, "eval_ORGANIZATION_recall": 0.6896551724137931, "eval_PERSON_f1": 0.8810289389067525, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8616352201257862, "eval_PERSON_recall": 0.9013157894736842, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.18427543342113495, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8333333333333334, "eval_overall_precision": 0.8100558659217877, "eval_overall_recall": 0.8579881656804734, "eval_runtime": 0.3625, "eval_samples_per_second": 515.889, "eval_steps_per_second": 8.276, "step": 5300 }, { "epoch": 51.0, "grad_norm": 0.31457802653312683, "learning_rate": 2.45e-05, "loss": 0.0223, "step": 5406 }, { "epoch": 51.0, "eval_LOCATION_f1": 0.8322147651006713, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.775, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.7286821705426356, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6619718309859155, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.9131832797427653, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8930817610062893, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.7384615384615385, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.6857142857142857, "eval_QUANTITY_recall": 0.8, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.20186367630958557, "eval_overall_accuracy": 0.9618437900128041, "eval_overall_f1": 0.841514726507714, "eval_overall_precision": 0.8, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.3617, "eval_samples_per_second": 516.949, "eval_steps_per_second": 8.293, "step": 5406 }, { "epoch": 52.0, "grad_norm": 0.7801603078842163, "learning_rate": 2.4e-05, "loss": 0.022, "step": 5512 }, { "epoch": 52.0, "eval_LOCATION_f1": 0.8435374149659864, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7948717948717948, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.703125, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6428571428571429, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.9102564102564101, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8875, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.20020708441734314, "eval_overall_accuracy": 0.9628681177976952, "eval_overall_f1": 0.8422535211267606, "eval_overall_precision": 0.803763440860215, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.364, "eval_samples_per_second": 513.785, "eval_steps_per_second": 8.243, "step": 5512 }, { "epoch": 53.0, "grad_norm": 0.5628809332847595, "learning_rate": 2.35e-05, "loss": 0.0226, "step": 5618 }, { "epoch": 53.0, "eval_LOCATION_f1": 0.8378378378378378, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7848101265822784, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.7086614173228347, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6521739130434783, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.9038461538461539, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.88125, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.2003839612007141, "eval_overall_accuracy": 0.9626120358514725, "eval_overall_f1": 0.840620592383639, "eval_overall_precision": 0.8032345013477089, "eval_overall_recall": 0.8816568047337278, "eval_runtime": 0.3645, "eval_samples_per_second": 513.059, "eval_steps_per_second": 8.231, "step": 5618 }, { "epoch": 54.0, "grad_norm": 0.676563024520874, "learning_rate": 2.3000000000000003e-05, "loss": 0.0203, "step": 5724 }, { "epoch": 54.0, "eval_LOCATION_f1": 0.8289473684210527, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7175572519083969, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6438356164383562, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.9126213592233009, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8980891719745223, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7647058823529411, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.20775069296360016, "eval_overall_accuracy": 0.9620998719590269, "eval_overall_f1": 0.8435754189944134, "eval_overall_precision": 0.798941798941799, "eval_overall_recall": 0.893491124260355, "eval_runtime": 0.3606, "eval_samples_per_second": 518.509, "eval_steps_per_second": 8.318, "step": 5724 }, { "epoch": 55.0, "grad_norm": 0.2858726680278778, "learning_rate": 2.25e-05, "loss": 0.0205, "step": 5830 }, { "epoch": 55.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.696969696969697, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9067524115755626, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8867924528301887, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8387096774193549, "eval_TIME_number": 29, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.896551724137931, "eval_loss": 0.2010103166103363, "eval_overall_accuracy": 0.9613316261203585, "eval_overall_f1": 0.8384401114206129, "eval_overall_precision": 0.7921052631578948, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.3614, "eval_samples_per_second": 517.374, "eval_steps_per_second": 8.3, "step": 5830 }, { "epoch": 56.0, "grad_norm": 0.4858570396900177, "learning_rate": 2.2000000000000003e-05, "loss": 0.02, "step": 5936 }, { "epoch": 56.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6976744186046512, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6338028169014085, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.9067524115755626, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8867924528301887, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.20158907771110535, "eval_overall_accuracy": 0.9618437900128041, "eval_overall_f1": 0.8398876404494382, "eval_overall_precision": 0.7994652406417112, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3612, "eval_samples_per_second": 517.774, "eval_steps_per_second": 8.307, "step": 5936 }, { "epoch": 57.0, "grad_norm": 0.18208715319633484, "learning_rate": 2.15e-05, "loss": 0.0183, "step": 6042 }, { "epoch": 57.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7131782945736435, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.647887323943662, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.89171974522293, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8641975308641975, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.20223386585712433, "eval_overall_accuracy": 0.9626120358514725, "eval_overall_f1": 0.8363636363636363, "eval_overall_precision": 0.7931034482758621, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3614, "eval_samples_per_second": 517.444, "eval_steps_per_second": 8.301, "step": 6042 }, { "epoch": 58.0, "grad_norm": 0.23495890200138092, "learning_rate": 2.1e-05, "loss": 0.0208, "step": 6148 }, { "epoch": 58.0, "eval_LOCATION_f1": 0.8322147651006713, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.775, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.71875, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6571428571428571, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9003215434083601, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8805031446540881, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.19618162512779236, "eval_overall_accuracy": 0.9620998719590269, "eval_overall_f1": 0.8410689170182841, "eval_overall_precision": 0.8016085790884718, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3631, "eval_samples_per_second": 515.042, "eval_steps_per_second": 8.263, "step": 6148 }, { "epoch": 59.0, "grad_norm": 0.32886990904808044, "learning_rate": 2.05e-05, "loss": 0.02, "step": 6254 }, { "epoch": 59.0, "eval_LOCATION_f1": 0.8421052631578948, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7710843373493976, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7175572519083969, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6438356164383562, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.21053260564804077, "eval_overall_accuracy": 0.9597951344430218, "eval_overall_f1": 0.8396094839609484, "eval_overall_precision": 0.7941952506596306, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.3626, "eval_samples_per_second": 515.719, "eval_steps_per_second": 8.274, "step": 6254 }, { "epoch": 60.0, "grad_norm": 0.23520979285240173, "learning_rate": 2e-05, "loss": 0.02, "step": 6360 }, { "epoch": 60.0, "eval_LOCATION_f1": 0.8513513513513514, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7559055118110236, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6956521739130435, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.879746835443038, "eval_PERSON_recall": 0.9144736842105263, "eval_QUANTITY_f1": 0.78125, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7352941176470589, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.2094646841287613, "eval_overall_accuracy": 0.9618437900128041, "eval_overall_f1": 0.846262341325811, "eval_overall_precision": 0.8086253369272237, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.3631, "eval_samples_per_second": 515.006, "eval_steps_per_second": 8.262, "step": 6360 }, { "epoch": 61.0, "grad_norm": 0.40711694955825806, "learning_rate": 1.9500000000000003e-05, "loss": 0.0189, "step": 6466 }, { "epoch": 61.0, "eval_LOCATION_f1": 0.8378378378378378, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7848101265822784, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.7642276422764227, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.7230769230769231, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.9061488673139159, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89171974522293, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.20915116369724274, "eval_overall_accuracy": 0.9628681177976952, "eval_overall_f1": 0.8506401137980085, "eval_overall_precision": 0.8191780821917808, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3634, "eval_samples_per_second": 514.544, "eval_steps_per_second": 8.255, "step": 6466 }, { "epoch": 62.0, "grad_norm": 1.4994909763336182, "learning_rate": 1.9e-05, "loss": 0.0189, "step": 6572 }, { "epoch": 62.0, "eval_LOCATION_f1": 0.8513513513513514, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7540983606557378, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.71875, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9096774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8924050632911392, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8620689655172413, "eval_TIME_number": 29, "eval_TIME_precision": 0.8620689655172413, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.19749662280082703, "eval_overall_accuracy": 0.9667093469910372, "eval_overall_f1": 0.8587731811697575, "eval_overall_precision": 0.8292011019283747, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.3617, "eval_samples_per_second": 516.966, "eval_steps_per_second": 8.294, "step": 6572 }, { "epoch": 63.0, "grad_norm": 0.330400288105011, "learning_rate": 1.85e-05, "loss": 0.0181, "step": 6678 }, { "epoch": 63.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.696969696969697, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9061488673139159, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89171974522293, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.21126015484333038, "eval_overall_accuracy": 0.963124199743918, "eval_overall_f1": 0.8375350140056023, "eval_overall_precision": 0.7952127659574468, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3627, "eval_samples_per_second": 515.593, "eval_steps_per_second": 8.272, "step": 6678 }, { "epoch": 64.0, "grad_norm": 0.14344383776187897, "learning_rate": 1.8e-05, "loss": 0.0169, "step": 6784 }, { "epoch": 64.0, "eval_LOCATION_f1": 0.8513513513513514, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7518796992481203, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8620689655172413, "eval_PERSON_f1": 0.9067524115755626, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8867924528301887, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.21455416083335876, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8503496503496504, "eval_overall_precision": 0.8063660477453581, "eval_overall_recall": 0.8994082840236687, "eval_runtime": 0.3618, "eval_samples_per_second": 516.8, "eval_steps_per_second": 8.291, "step": 6784 }, { "epoch": 65.0, "grad_norm": 0.3642537593841553, "learning_rate": 1.75e-05, "loss": 0.0156, "step": 6890 }, { "epoch": 65.0, "eval_LOCATION_f1": 0.8456375838926175, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7875, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7499999999999999, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6538461538461539, "eval_ORGANIZATION_recall": 0.8793103448275862, "eval_PERSON_f1": 0.9096774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8924050632911392, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.21249239146709442, "eval_overall_accuracy": 0.963124199743918, "eval_overall_f1": 0.8535564853556485, "eval_overall_precision": 0.8073878627968337, "eval_overall_recall": 0.9053254437869822, "eval_runtime": 0.362, "eval_samples_per_second": 516.589, "eval_steps_per_second": 8.288, "step": 6890 }, { "epoch": 66.0, "grad_norm": 0.11543180048465729, "learning_rate": 1.7000000000000003e-05, "loss": 0.0184, "step": 6996 }, { "epoch": 66.0, "eval_LOCATION_f1": 0.8421052631578948, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7710843373493976, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7419354838709677, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.696969696969697, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9015873015873016, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9342105263157895, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.22058767080307007, "eval_overall_accuracy": 0.9620998719590269, "eval_overall_f1": 0.8487394957983192, "eval_overall_precision": 0.8058510638297872, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.3598, "eval_samples_per_second": 519.803, "eval_steps_per_second": 8.339, "step": 6996 }, { "epoch": 67.0, "grad_norm": 1.020384430885315, "learning_rate": 1.65e-05, "loss": 0.0157, "step": 7102 }, { "epoch": 67.0, "eval_LOCATION_f1": 0.8289473684210527, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7596899224806202, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6901408450704225, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9067524115755626, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8867924528301887, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.2218605875968933, "eval_overall_accuracy": 0.9610755441741358, "eval_overall_f1": 0.8451882845188284, "eval_overall_precision": 0.7994722955145118, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.3612, "eval_samples_per_second": 517.753, "eval_steps_per_second": 8.306, "step": 7102 }, { "epoch": 68.0, "grad_norm": 0.15215358138084412, "learning_rate": 1.6000000000000003e-05, "loss": 0.017, "step": 7208 }, { "epoch": 68.0, "eval_LOCATION_f1": 0.8513513513513514, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7974683544303798, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7538461538461538, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6805555555555556, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9096774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8924050632911392, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.21046985685825348, "eval_overall_accuracy": 0.9641485275288092, "eval_overall_f1": 0.8551336146272854, "eval_overall_precision": 0.8150134048257373, "eval_overall_recall": 0.8994082840236687, "eval_runtime": 0.361, "eval_samples_per_second": 517.949, "eval_steps_per_second": 8.309, "step": 7208 }, { "epoch": 69.0, "grad_norm": 0.5697264671325684, "learning_rate": 1.55e-05, "loss": 0.0153, "step": 7314 }, { "epoch": 69.0, "eval_LOCATION_f1": 0.8533333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.71875, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6571428571428571, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9003215434083601, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8805031446540881, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.21243220567703247, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8455056179775281, "eval_overall_precision": 0.8048128342245989, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.3623, "eval_samples_per_second": 516.119, "eval_steps_per_second": 8.28, "step": 7314 }, { "epoch": 70.0, "grad_norm": 0.7913137078285217, "learning_rate": 1.5e-05, "loss": 0.0144, "step": 7420 }, { "epoch": 70.0, "eval_LOCATION_f1": 0.8366013071895425, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7619047619047619, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.6923076923076923, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.625, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.9096774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8924050632911392, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.21706803143024445, "eval_overall_accuracy": 0.9618437900128041, "eval_overall_f1": 0.8379888268156425, "eval_overall_precision": 0.7936507936507936, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.3628, "eval_samples_per_second": 515.393, "eval_steps_per_second": 8.268, "step": 7420 }, { "epoch": 71.0, "grad_norm": 0.3131992816925049, "learning_rate": 1.45e-05, "loss": 0.0143, "step": 7526 }, { "epoch": 71.0, "eval_LOCATION_f1": 0.8157894736842105, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8985507246376812, "eval_ORGANIZATION_f1": 0.7076923076923076, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9096774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8924050632911392, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7692307692307692, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.21970078349113464, "eval_overall_accuracy": 0.9618437900128041, "eval_overall_f1": 0.835195530726257, "eval_overall_precision": 0.791005291005291, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3658, "eval_samples_per_second": 511.219, "eval_steps_per_second": 8.201, "step": 7526 }, { "epoch": 72.0, "grad_norm": 0.9401266574859619, "learning_rate": 1.4000000000000001e-05, "loss": 0.0132, "step": 7632 }, { "epoch": 72.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6666666666666667, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6176470588235294, "eval_ORGANIZATION_recall": 0.7241379310344828, "eval_PERSON_f1": 0.8932038834951456, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8789808917197452, "eval_PERSON_recall": 0.9078947368421053, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.20829293131828308, "eval_overall_accuracy": 0.9628681177976952, "eval_overall_f1": 0.8288543140028289, "eval_overall_precision": 0.7940379403794038, "eval_overall_recall": 0.8668639053254438, "eval_runtime": 0.3608, "eval_samples_per_second": 518.242, "eval_steps_per_second": 8.314, "step": 7632 }, { "epoch": 73.0, "grad_norm": 0.03819990158081055, "learning_rate": 1.3500000000000001e-05, "loss": 0.0135, "step": 7738 }, { "epoch": 73.0, "eval_LOCATION_f1": 0.8421052631578948, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7710843373493976, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.696969696969697, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9126213592233009, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8980891719745223, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.21569667756557465, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8435754189944134, "eval_overall_precision": 0.798941798941799, "eval_overall_recall": 0.893491124260355, "eval_runtime": 0.365, "eval_samples_per_second": 512.399, "eval_steps_per_second": 8.22, "step": 7738 }, { "epoch": 74.0, "grad_norm": 0.8613461256027222, "learning_rate": 1.3000000000000001e-05, "loss": 0.0129, "step": 7844 }, { "epoch": 74.0, "eval_LOCATION_f1": 0.8476821192052981, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7804878048780488, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7175572519083969, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6438356164383562, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.9096774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8924050632911392, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.22063693404197693, "eval_overall_accuracy": 0.9628681177976952, "eval_overall_f1": 0.84593837535014, "eval_overall_precision": 0.8031914893617021, "eval_overall_recall": 0.893491124260355, "eval_runtime": 0.3617, "eval_samples_per_second": 516.955, "eval_steps_per_second": 8.293, "step": 7844 }, { "epoch": 75.0, "grad_norm": 0.024284284561872482, "learning_rate": 1.25e-05, "loss": 0.0121, "step": 7950 }, { "epoch": 75.0, "eval_LOCATION_f1": 0.8590604026845639, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.8, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7272727272727273, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6486486486486487, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.9067524115755626, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8867924528301887, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.22647179663181305, "eval_overall_accuracy": 0.9626120358514725, "eval_overall_f1": 0.8475524475524475, "eval_overall_precision": 0.8037135278514589, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.3659, "eval_samples_per_second": 511.019, "eval_steps_per_second": 8.198, "step": 7950 }, { "epoch": 76.0, "grad_norm": 4.4533610343933105, "learning_rate": 1.2e-05, "loss": 0.0128, "step": 8056 }, { "epoch": 76.0, "eval_LOCATION_f1": 0.8533333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7384615384615385, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.9067524115755626, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8867924528301887, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.21908092498779297, "eval_overall_accuracy": 0.9636363636363636, "eval_overall_f1": 0.8515406162464986, "eval_overall_precision": 0.8085106382978723, "eval_overall_recall": 0.8994082840236687, "eval_runtime": 0.3625, "eval_samples_per_second": 515.854, "eval_steps_per_second": 8.276, "step": 8056 }, { "epoch": 77.0, "grad_norm": 0.5939314365386963, "learning_rate": 1.1500000000000002e-05, "loss": 0.0129, "step": 8162 }, { "epoch": 77.0, "eval_LOCATION_f1": 0.8533333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7076923076923076, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9096774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8924050632911392, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.2162235528230667, "eval_overall_accuracy": 0.9633802816901409, "eval_overall_f1": 0.847124824684432, "eval_overall_precision": 0.8053333333333333, "eval_overall_recall": 0.893491124260355, "eval_runtime": 0.3619, "eval_samples_per_second": 516.774, "eval_steps_per_second": 8.29, "step": 8162 }, { "epoch": 78.0, "grad_norm": 0.5070800185203552, "learning_rate": 1.1000000000000001e-05, "loss": 0.0136, "step": 8268 }, { "epoch": 78.0, "eval_LOCATION_f1": 0.8456375838926175, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7875, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.711111111111111, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6233766233766234, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.9038461538461539, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.88125, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.22107018530368805, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8428372739916552, "eval_overall_precision": 0.7952755905511811, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.3608, "eval_samples_per_second": 518.35, "eval_steps_per_second": 8.316, "step": 8268 }, { "epoch": 79.0, "grad_norm": 0.4564056992530823, "learning_rate": 1.05e-05, "loss": 0.0121, "step": 8374 }, { "epoch": 79.0, "eval_LOCATION_f1": 0.8476821192052981, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7804878048780488, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7175572519083969, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6438356164383562, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.9096774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8924050632911392, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.22130298614501953, "eval_overall_accuracy": 0.9641485275288092, "eval_overall_f1": 0.8487394957983192, "eval_overall_precision": 0.8058510638297872, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.363, "eval_samples_per_second": 515.218, "eval_steps_per_second": 8.266, "step": 8374 }, { "epoch": 80.0, "grad_norm": 0.6584732532501221, "learning_rate": 1e-05, "loss": 0.0111, "step": 8480 }, { "epoch": 80.0, "eval_LOCATION_f1": 0.8476821192052981, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7804878048780488, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7441860465116279, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.676056338028169, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.9096774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8924050632911392, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.22489629685878754, "eval_overall_accuracy": 0.9636363636363636, "eval_overall_f1": 0.8499298737727911, "eval_overall_precision": 0.808, "eval_overall_recall": 0.8964497041420119, "eval_runtime": 0.3624, "eval_samples_per_second": 515.991, "eval_steps_per_second": 8.278, "step": 8480 }, { "epoch": 81.0, "grad_norm": 0.49040845036506653, "learning_rate": 9.5e-06, "loss": 0.0118, "step": 8586 }, { "epoch": 81.0, "eval_LOCATION_f1": 0.8344370860927153, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7682926829268293, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.696969696969697, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.8333333333333334, "eval_TIME_number": 29, "eval_TIME_precision": 0.8064516129032258, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.22860205173492432, "eval_overall_accuracy": 0.9618437900128041, "eval_overall_f1": 0.835195530726257, "eval_overall_precision": 0.791005291005291, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3615, "eval_samples_per_second": 517.279, "eval_steps_per_second": 8.299, "step": 8586 }, { "epoch": 82.0, "grad_norm": 0.18154391646385193, "learning_rate": 9e-06, "loss": 0.0115, "step": 8692 }, { "epoch": 82.0, "eval_LOCATION_f1": 0.8533333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7538461538461538, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6805555555555556, "eval_ORGANIZATION_recall": 0.8448275862068966, "eval_PERSON_f1": 0.9096774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8924050632911392, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.223580464720726, "eval_overall_accuracy": 0.9641485275288092, "eval_overall_f1": 0.8539325842696629, "eval_overall_precision": 0.8128342245989305, "eval_overall_recall": 0.8994082840236687, "eval_runtime": 0.3605, "eval_samples_per_second": 518.745, "eval_steps_per_second": 8.322, "step": 8692 }, { "epoch": 83.0, "grad_norm": 0.3081746995449066, "learning_rate": 8.500000000000002e-06, "loss": 0.0108, "step": 8798 }, { "epoch": 83.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.696969696969697, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9067524115755626, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8867924528301887, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.22753649950027466, "eval_overall_accuracy": 0.9626120358514725, "eval_overall_f1": 0.8391608391608392, "eval_overall_precision": 0.7957559681697612, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.3609, "eval_samples_per_second": 518.178, "eval_steps_per_second": 8.313, "step": 8798 }, { "epoch": 84.0, "grad_norm": 0.6401548385620117, "learning_rate": 8.000000000000001e-06, "loss": 0.0129, "step": 8904 }, { "epoch": 84.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.712121212121212, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6351351351351351, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.9067524115755626, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8867924528301887, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.22843700647354126, "eval_overall_accuracy": 0.9626120358514725, "eval_overall_f1": 0.8419580419580419, "eval_overall_precision": 0.7984084880636605, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.3628, "eval_samples_per_second": 515.389, "eval_steps_per_second": 8.268, "step": 8904 }, { "epoch": 85.0, "grad_norm": 2.212589979171753, "learning_rate": 7.5e-06, "loss": 0.011, "step": 9010 }, { "epoch": 85.0, "eval_LOCATION_f1": 0.8533333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7022900763358779, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9096774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8924050632911392, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.2237282544374466, "eval_overall_accuracy": 0.964404609475032, "eval_overall_f1": 0.8443197755960729, "eval_overall_precision": 0.8026666666666666, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.3618, "eval_samples_per_second": 516.865, "eval_steps_per_second": 8.292, "step": 9010 }, { "epoch": 86.0, "grad_norm": 0.2310379445552826, "learning_rate": 7.000000000000001e-06, "loss": 0.0115, "step": 9116 }, { "epoch": 86.0, "eval_LOCATION_f1": 0.8476821192052981, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7804878048780488, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7230769230769231, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6527777777777778, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.9061488673139159, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89171974522293, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.22614195942878723, "eval_overall_accuracy": 0.9633802816901409, "eval_overall_f1": 0.8455056179775281, "eval_overall_precision": 0.8048128342245989, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.3621, "eval_samples_per_second": 516.474, "eval_steps_per_second": 8.286, "step": 9116 }, { "epoch": 87.0, "grad_norm": 1.327154517173767, "learning_rate": 6.5000000000000004e-06, "loss": 0.0108, "step": 9222 }, { "epoch": 87.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6870229007633589, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6164383561643836, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.9061488673139159, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89171974522293, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.22663061320781708, "eval_overall_accuracy": 0.9623559539052496, "eval_overall_f1": 0.8370786516853933, "eval_overall_precision": 0.7967914438502673, "eval_overall_recall": 0.8816568047337278, "eval_runtime": 0.362, "eval_samples_per_second": 516.509, "eval_steps_per_second": 8.286, "step": 9222 }, { "epoch": 88.0, "grad_norm": 0.06700880080461502, "learning_rate": 6e-06, "loss": 0.011, "step": 9328 }, { "epoch": 88.0, "eval_LOCATION_f1": 0.8456375838926175, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7875, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7384615384615385, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8275862068965517, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.22872696816921234, "eval_overall_accuracy": 0.9633802816901409, "eval_overall_f1": 0.8466947960618846, "eval_overall_precision": 0.806970509383378, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.3626, "eval_samples_per_second": 515.732, "eval_steps_per_second": 8.274, "step": 9328 }, { "epoch": 89.0, "grad_norm": 1.4116276502609253, "learning_rate": 5.500000000000001e-06, "loss": 0.0107, "step": 9434 }, { "epoch": 89.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.712121212121212, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6351351351351351, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.9061488673139159, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89171974522293, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.23026646673679352, "eval_overall_accuracy": 0.963124199743918, "eval_overall_f1": 0.841514726507714, "eval_overall_precision": 0.8, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.3617, "eval_samples_per_second": 517.015, "eval_steps_per_second": 8.294, "step": 9434 }, { "epoch": 90.0, "grad_norm": 1.429292917251587, "learning_rate": 5e-06, "loss": 0.0107, "step": 9540 }, { "epoch": 90.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.696969696969697, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6216216216216216, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.2354857474565506, "eval_overall_accuracy": 0.9626120358514725, "eval_overall_f1": 0.8403361344537815, "eval_overall_precision": 0.7978723404255319, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.3614, "eval_samples_per_second": 517.49, "eval_steps_per_second": 8.302, "step": 9540 }, { "epoch": 91.0, "grad_norm": 4.1735615730285645, "learning_rate": 4.5e-06, "loss": 0.0101, "step": 9646 }, { "epoch": 91.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.6923076923076923, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.625, "eval_ORGANIZATION_recall": 0.7758620689655172, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.2317478507757187, "eval_overall_accuracy": 0.9618437900128041, "eval_overall_f1": 0.8370786516853933, "eval_overall_precision": 0.7967914438502673, "eval_overall_recall": 0.8816568047337278, "eval_runtime": 0.3582, "eval_samples_per_second": 522.104, "eval_steps_per_second": 8.376, "step": 9646 }, { "epoch": 92.0, "grad_norm": 1.6095588207244873, "learning_rate": 4.000000000000001e-06, "loss": 0.0103, "step": 9752 }, { "epoch": 92.0, "eval_LOCATION_f1": 0.8533333333333333, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7901234567901234, "eval_LOCATION_recall": 0.927536231884058, "eval_ORGANIZATION_f1": 0.7022900763358779, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6301369863013698, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.23306894302368164, "eval_overall_accuracy": 0.9633802816901409, "eval_overall_f1": 0.8443197755960729, "eval_overall_precision": 0.8026666666666666, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.363, "eval_samples_per_second": 515.199, "eval_steps_per_second": 8.265, "step": 9752 }, { "epoch": 93.0, "grad_norm": 0.20821604132652283, "learning_rate": 3.5000000000000004e-06, "loss": 0.0106, "step": 9858 }, { "epoch": 93.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7076923076923076, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9061488673139159, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89171974522293, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.23287318646907806, "eval_overall_accuracy": 0.9628681177976952, "eval_overall_f1": 0.8410689170182841, "eval_overall_precision": 0.8016085790884718, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3747, "eval_samples_per_second": 499.127, "eval_steps_per_second": 8.007, "step": 9858 }, { "epoch": 94.0, "grad_norm": 3.346036434173584, "learning_rate": 3e-06, "loss": 0.0098, "step": 9964 }, { "epoch": 94.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7230769230769231, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6527777777777778, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.9096774193548387, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8924050632911392, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.8253968253968254, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7878787878787878, "eval_QUANTITY_recall": 0.8666666666666667, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.23173053562641144, "eval_overall_accuracy": 0.9638924455825865, "eval_overall_f1": 0.848314606741573, "eval_overall_precision": 0.8074866310160428, "eval_overall_recall": 0.893491124260355, "eval_runtime": 0.3592, "eval_samples_per_second": 520.646, "eval_steps_per_second": 8.353, "step": 9964 }, { "epoch": 95.0, "grad_norm": 0.20321281254291534, "learning_rate": 2.5e-06, "loss": 0.0099, "step": 10070 }, { "epoch": 95.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7076923076923076, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9061488673139159, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.89171974522293, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.23714813590049744, "eval_overall_accuracy": 0.9628681177976952, "eval_overall_f1": 0.8410689170182841, "eval_overall_precision": 0.8016085790884718, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3575, "eval_samples_per_second": 523.045, "eval_steps_per_second": 8.391, "step": 10070 }, { "epoch": 96.0, "grad_norm": 1.4667727947235107, "learning_rate": 2.0000000000000003e-06, "loss": 0.0111, "step": 10176 }, { "epoch": 96.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7076923076923076, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9032258064516129, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8860759493670886, "eval_PERSON_recall": 0.9210526315789473, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.23259073495864868, "eval_overall_accuracy": 0.9628681177976952, "eval_overall_f1": 0.8398876404494382, "eval_overall_precision": 0.7994652406417112, "eval_overall_recall": 0.8846153846153846, "eval_runtime": 0.3593, "eval_samples_per_second": 520.441, "eval_steps_per_second": 8.349, "step": 10176 }, { "epoch": 97.0, "grad_norm": 2.3907060623168945, "learning_rate": 1.5e-06, "loss": 0.0107, "step": 10282 }, { "epoch": 97.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7230769230769231, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6527777777777778, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.9067524115755626, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8867924528301887, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.2305343896150589, "eval_overall_accuracy": 0.963124199743918, "eval_overall_f1": 0.8443197755960729, "eval_overall_precision": 0.8026666666666666, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.3613, "eval_samples_per_second": 517.595, "eval_steps_per_second": 8.304, "step": 10282 }, { "epoch": 98.0, "grad_norm": 0.084909588098526, "learning_rate": 1.0000000000000002e-06, "loss": 0.0089, "step": 10388 }, { "epoch": 98.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7131782945736435, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.647887323943662, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9067524115755626, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8867924528301887, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.23437084257602692, "eval_overall_accuracy": 0.963124199743918, "eval_overall_f1": 0.8426966292134831, "eval_overall_precision": 0.8021390374331551, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.3571, "eval_samples_per_second": 523.612, "eval_steps_per_second": 8.4, "step": 10388 }, { "epoch": 99.0, "grad_norm": 0.1909925937652588, "learning_rate": 5.000000000000001e-07, "loss": 0.0096, "step": 10494 }, { "epoch": 99.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7230769230769231, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6527777777777778, "eval_ORGANIZATION_recall": 0.8103448275862069, "eval_PERSON_f1": 0.9067524115755626, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8867924528301887, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.23227395117282867, "eval_overall_accuracy": 0.9633802816901409, "eval_overall_f1": 0.8443197755960729, "eval_overall_precision": 0.8026666666666666, "eval_overall_recall": 0.8905325443786982, "eval_runtime": 0.3635, "eval_samples_per_second": 514.415, "eval_steps_per_second": 8.253, "step": 10494 }, { "epoch": 100.0, "grad_norm": 0.3087587058544159, "learning_rate": 0.0, "loss": 0.0091, "step": 10600 }, { "epoch": 100.0, "eval_LOCATION_f1": 0.84, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7777777777777778, "eval_LOCATION_recall": 0.9130434782608695, "eval_ORGANIZATION_f1": 0.7076923076923076, "eval_ORGANIZATION_number": 58, "eval_ORGANIZATION_precision": 0.6388888888888888, "eval_ORGANIZATION_recall": 0.7931034482758621, "eval_PERSON_f1": 0.9067524115755626, "eval_PERSON_number": 152, "eval_PERSON_precision": 0.8867924528301887, "eval_PERSON_recall": 0.9276315789473685, "eval_QUANTITY_f1": 0.7936507936507938, "eval_QUANTITY_number": 30, "eval_QUANTITY_precision": 0.7575757575757576, "eval_QUANTITY_recall": 0.8333333333333334, "eval_TIME_f1": 0.847457627118644, "eval_TIME_number": 29, "eval_TIME_precision": 0.8333333333333334, "eval_TIME_recall": 0.8620689655172413, "eval_loss": 0.23294764757156372, "eval_overall_accuracy": 0.963124199743918, "eval_overall_f1": 0.841514726507714, "eval_overall_precision": 0.8, "eval_overall_recall": 0.8875739644970414, "eval_runtime": 0.3601, "eval_samples_per_second": 519.248, "eval_steps_per_second": 8.33, "step": 10600 }, { "epoch": 100.0, "step": 10600, "total_flos": 5072850468719490.0, "train_loss": 0.05370020137642914, "train_runtime": 1095.441, "train_samples_per_second": 154.002, "train_steps_per_second": 9.676 } ], "logging_steps": 500, "max_steps": 10600, "num_input_tokens_seen": 0, "num_train_epochs": 100, "save_steps": 500, "total_flos": 5072850468719490.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }