{ "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": 2.430300712585449, "learning_rate": 4.9500000000000004e-05, "loss": 1.1444, "step": 106 }, { "epoch": 1.0, "eval_LOCATION_f1": 0.0, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.0, "eval_LOCATION_recall": 0.0, "eval_ORGANIZATION_f1": 0.0, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.0, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.0, "eval_PERSON_recall": 0.0, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 31, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.6989501118659973, "eval_overall_accuracy": 0.8352737181075056, "eval_overall_f1": 0.0, "eval_overall_precision": 0.0, "eval_overall_recall": 0.0, "eval_runtime": 0.3328, "eval_samples_per_second": 561.979, "eval_steps_per_second": 9.016, "step": 106 }, { "epoch": 2.0, "grad_norm": 1.2830387353897095, "learning_rate": 4.9e-05, "loss": 0.663, "step": 212 }, { "epoch": 2.0, "eval_LOCATION_f1": 0.0, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.0, "eval_LOCATION_recall": 0.0, "eval_ORGANIZATION_f1": 0.0, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.059523809523809534, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.3333333333333333, "eval_PERSON_recall": 0.032679738562091505, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 31, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.5583326816558838, "eval_overall_accuracy": 0.8384939311369829, "eval_overall_f1": 0.02724795640326975, "eval_overall_precision": 0.23809523809523808, "eval_overall_recall": 0.014450867052023121, "eval_runtime": 0.3298, "eval_samples_per_second": 566.973, "eval_steps_per_second": 9.096, "step": 212 }, { "epoch": 3.0, "grad_norm": 1.8097186088562012, "learning_rate": 4.85e-05, "loss": 0.5434, "step": 318 }, { "epoch": 3.0, "eval_LOCATION_f1": 0.07792207792207792, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.375, "eval_LOCATION_recall": 0.043478260869565216, "eval_ORGANIZATION_f1": 0.024096385542168676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.045454545454545456, "eval_ORGANIZATION_recall": 0.01639344262295082, "eval_PERSON_f1": 0.3687943262411348, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.40310077519379844, "eval_PERSON_recall": 0.33986928104575165, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.45283018867924524, "eval_TIME_number": 31, "eval_TIME_precision": 0.5454545454545454, "eval_TIME_recall": 0.3870967741935484, "eval_loss": 0.4402874708175659, "eval_overall_accuracy": 0.8746594005449592, "eval_overall_f1": 0.25660377358490566, "eval_overall_precision": 0.3695652173913043, "eval_overall_recall": 0.19653179190751446, "eval_runtime": 0.3309, "eval_samples_per_second": 565.189, "eval_steps_per_second": 9.067, "step": 318 }, { "epoch": 4.0, "grad_norm": 2.2711915969848633, "learning_rate": 4.8e-05, "loss": 0.4445, "step": 424 }, { "epoch": 4.0, "eval_LOCATION_f1": 0.4107142857142857, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.5348837209302325, "eval_LOCATION_recall": 0.3333333333333333, "eval_ORGANIZATION_f1": 0.19801980198019803, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.25, "eval_ORGANIZATION_recall": 0.16393442622950818, "eval_PERSON_f1": 0.5217391304347826, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.46875, "eval_PERSON_recall": 0.5882352941176471, "eval_QUANTITY_f1": 0.041666666666666664, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.0625, "eval_QUANTITY_recall": 0.03125, "eval_TIME_f1": 0.59375, "eval_TIME_number": 31, "eval_TIME_precision": 0.5757575757575758, "eval_TIME_recall": 0.6129032258064516, "eval_loss": 0.36389732360839844, "eval_overall_accuracy": 0.9004211047807779, "eval_overall_f1": 0.426865671641791, "eval_overall_precision": 0.44135802469135804, "eval_overall_recall": 0.41329479768786126, "eval_runtime": 0.3314, "eval_samples_per_second": 564.27, "eval_steps_per_second": 9.052, "step": 424 }, { "epoch": 5.0, "grad_norm": 1.2458393573760986, "learning_rate": 4.75e-05, "loss": 0.3757, "step": 530 }, { "epoch": 5.0, "eval_LOCATION_f1": 0.5531914893617021, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.5416666666666666, "eval_LOCATION_recall": 0.5652173913043478, "eval_ORGANIZATION_f1": 0.25210084033613445, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.25862068965517243, "eval_ORGANIZATION_recall": 0.2459016393442623, "eval_PERSON_f1": 0.6132596685082872, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.5311004784688995, "eval_PERSON_recall": 0.7254901960784313, "eval_QUANTITY_f1": 0.4444444444444444, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.45161290322580644, "eval_QUANTITY_recall": 0.4375, "eval_TIME_f1": 0.626865671641791, "eval_TIME_number": 31, "eval_TIME_precision": 0.5833333333333334, "eval_TIME_recall": 0.6774193548387096, "eval_loss": 0.31899556517601013, "eval_overall_accuracy": 0.9160267525390141, "eval_overall_f1": 0.5319148936170213, "eval_overall_precision": 0.49261083743842365, "eval_overall_recall": 0.5780346820809249, "eval_runtime": 0.332, "eval_samples_per_second": 563.27, "eval_steps_per_second": 9.036, "step": 530 }, { "epoch": 6.0, "grad_norm": 1.3306622505187988, "learning_rate": 4.7e-05, "loss": 0.3296, "step": 636 }, { "epoch": 6.0, "eval_LOCATION_f1": 0.5771812080536913, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.5375, "eval_LOCATION_recall": 0.6231884057971014, "eval_ORGANIZATION_f1": 0.4736842105263158, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5094339622641509, "eval_ORGANIZATION_recall": 0.4426229508196721, "eval_PERSON_f1": 0.6572237960339942, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.58, "eval_PERSON_recall": 0.7581699346405228, "eval_QUANTITY_f1": 0.48484848484848486, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.47058823529411764, "eval_QUANTITY_recall": 0.5, "eval_TIME_f1": 0.7619047619047619, "eval_TIME_number": 31, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.7741935483870968, "eval_loss": 0.27275437116622925, "eval_overall_accuracy": 0.9284121872677731, "eval_overall_f1": 0.6067114093959732, "eval_overall_precision": 0.5664160401002506, "eval_overall_recall": 0.653179190751445, "eval_runtime": 0.3315, "eval_samples_per_second": 564.1, "eval_steps_per_second": 9.05, "step": 636 }, { "epoch": 7.0, "grad_norm": 1.0643121004104614, "learning_rate": 4.6500000000000005e-05, "loss": 0.2902, "step": 742 }, { "epoch": 7.0, "eval_LOCATION_f1": 0.6410256410256409, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.5747126436781609, "eval_LOCATION_recall": 0.7246376811594203, "eval_ORGANIZATION_f1": 0.47328244274809156, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.44285714285714284, "eval_ORGANIZATION_recall": 0.5081967213114754, "eval_PERSON_f1": 0.7435158501440923, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.6649484536082474, "eval_PERSON_recall": 0.8431372549019608, "eval_QUANTITY_f1": 0.5753424657534246, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5121951219512195, "eval_QUANTITY_recall": 0.65625, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.24877597391605377, "eval_overall_accuracy": 0.9341094872430022, "eval_overall_f1": 0.6666666666666666, "eval_overall_precision": 0.6047058823529412, "eval_overall_recall": 0.7427745664739884, "eval_runtime": 0.3315, "eval_samples_per_second": 564.034, "eval_steps_per_second": 9.049, "step": 742 }, { "epoch": 8.0, "grad_norm": 1.2694265842437744, "learning_rate": 4.600000000000001e-05, "loss": 0.2557, "step": 848 }, { "epoch": 8.0, "eval_LOCATION_f1": 0.6538461538461539, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.5862068965517241, "eval_LOCATION_recall": 0.7391304347826086, "eval_ORGANIZATION_f1": 0.5179856115107915, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.46153846153846156, "eval_ORGANIZATION_recall": 0.5901639344262295, "eval_PERSON_f1": 0.7551622418879057, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.6881720430107527, "eval_PERSON_recall": 0.8366013071895425, "eval_QUANTITY_f1": 0.5633802816901409, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5128205128205128, "eval_QUANTITY_recall": 0.625, "eval_TIME_f1": 0.8524590163934426, "eval_TIME_number": 31, "eval_TIME_precision": 0.8666666666666667, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.2189495861530304, "eval_overall_accuracy": 0.939311369829081, "eval_overall_f1": 0.6814621409921671, "eval_overall_precision": 0.6214285714285714, "eval_overall_recall": 0.7543352601156069, "eval_runtime": 0.3318, "eval_samples_per_second": 563.618, "eval_steps_per_second": 9.042, "step": 848 }, { "epoch": 9.0, "grad_norm": 1.3103985786437988, "learning_rate": 4.55e-05, "loss": 0.2295, "step": 954 }, { "epoch": 9.0, "eval_LOCATION_f1": 0.6883116883116883, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6235294117647059, "eval_LOCATION_recall": 0.7681159420289855, "eval_ORGANIZATION_f1": 0.5606060606060606, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5211267605633803, "eval_ORGANIZATION_recall": 0.6065573770491803, "eval_PERSON_f1": 0.7963525835866261, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7443181818181818, "eval_PERSON_recall": 0.8562091503267973, "eval_QUANTITY_f1": 0.5833333333333334, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.525, "eval_QUANTITY_recall": 0.65625, "eval_TIME_f1": 0.8387096774193549, "eval_TIME_number": 31, "eval_TIME_precision": 0.8387096774193549, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.19587717950344086, "eval_overall_accuracy": 0.9437701263314342, "eval_overall_f1": 0.7156208277703603, "eval_overall_precision": 0.6650124069478908, "eval_overall_recall": 0.7745664739884393, "eval_runtime": 0.3323, "eval_samples_per_second": 562.79, "eval_steps_per_second": 9.029, "step": 954 }, { "epoch": 10.0, "grad_norm": 0.8112050890922546, "learning_rate": 4.5e-05, "loss": 0.2073, "step": 1060 }, { "epoch": 10.0, "eval_LOCATION_f1": 0.6838709677419355, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6162790697674418, "eval_LOCATION_recall": 0.7681159420289855, "eval_ORGANIZATION_f1": 0.5625, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5373134328358209, "eval_ORGANIZATION_recall": 0.5901639344262295, "eval_PERSON_f1": 0.8148148148148149, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7719298245614035, "eval_PERSON_recall": 0.8627450980392157, "eval_QUANTITY_f1": 0.5753424657534246, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5121951219512195, "eval_QUANTITY_recall": 0.65625, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.17975814640522003, "eval_overall_accuracy": 0.9452563784988853, "eval_overall_f1": 0.7231182795698925, "eval_overall_precision": 0.6758793969849246, "eval_overall_recall": 0.7774566473988439, "eval_runtime": 0.3333, "eval_samples_per_second": 560.987, "eval_steps_per_second": 9.0, "step": 1060 }, { "epoch": 11.0, "grad_norm": 1.2482295036315918, "learning_rate": 4.4500000000000004e-05, "loss": 0.1909, "step": 1166 }, { "epoch": 11.0, "eval_LOCATION_f1": 0.7012987012987013, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6352941176470588, "eval_LOCATION_recall": 0.782608695652174, "eval_ORGANIZATION_f1": 0.5714285714285714, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5277777777777778, "eval_ORGANIZATION_recall": 0.6229508196721312, "eval_PERSON_f1": 0.8123076923076923, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7674418604651163, "eval_PERSON_recall": 0.8627450980392157, "eval_QUANTITY_f1": 0.5599999999999999, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.4883720930232558, "eval_QUANTITY_recall": 0.65625, "eval_TIME_f1": 0.84375, "eval_TIME_number": 31, "eval_TIME_precision": 0.8181818181818182, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.17226055264472961, "eval_overall_accuracy": 0.9469903393609116, "eval_overall_f1": 0.7243675099866844, "eval_overall_precision": 0.671604938271605, "eval_overall_recall": 0.7861271676300579, "eval_runtime": 0.3326, "eval_samples_per_second": 562.261, "eval_steps_per_second": 9.02, "step": 1166 }, { "epoch": 12.0, "grad_norm": 2.779182195663452, "learning_rate": 4.4000000000000006e-05, "loss": 0.1803, "step": 1272 }, { "epoch": 12.0, "eval_LOCATION_f1": 0.728476821192053, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6707317073170732, "eval_LOCATION_recall": 0.7971014492753623, "eval_ORGANIZATION_f1": 0.5671641791044776, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5205479452054794, "eval_ORGANIZATION_recall": 0.6229508196721312, "eval_PERSON_f1": 0.8086419753086419, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7660818713450293, "eval_PERSON_recall": 0.8562091503267973, "eval_QUANTITY_f1": 0.6027397260273972, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5365853658536586, "eval_QUANTITY_recall": 0.6875, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.16054868698120117, "eval_overall_accuracy": 0.9507059697795393, "eval_overall_f1": 0.7328859060402685, "eval_overall_precision": 0.6842105263157895, "eval_overall_recall": 0.7890173410404624, "eval_runtime": 0.331, "eval_samples_per_second": 564.922, "eval_steps_per_second": 9.063, "step": 1272 }, { "epoch": 13.0, "grad_norm": 0.844031810760498, "learning_rate": 4.35e-05, "loss": 0.172, "step": 1378 }, { "epoch": 13.0, "eval_LOCATION_f1": 0.7450980392156864, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6785714285714286, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.5611510791366907, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5, "eval_ORGANIZATION_recall": 0.639344262295082, "eval_PERSON_f1": 0.8224299065420562, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7857142857142857, "eval_PERSON_recall": 0.8627450980392157, "eval_QUANTITY_f1": 0.5833333333333334, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.525, "eval_QUANTITY_recall": 0.65625, "eval_TIME_f1": 0.8571428571428571, "eval_TIME_number": 31, "eval_TIME_precision": 0.84375, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.15468432009220123, "eval_overall_accuracy": 0.9521922219469904, "eval_overall_f1": 0.7379679144385027, "eval_overall_precision": 0.6865671641791045, "eval_overall_recall": 0.7976878612716763, "eval_runtime": 0.3324, "eval_samples_per_second": 562.634, "eval_steps_per_second": 9.026, "step": 1378 }, { "epoch": 14.0, "grad_norm": 1.6911097764968872, "learning_rate": 4.3e-05, "loss": 0.1628, "step": 1484 }, { "epoch": 14.0, "eval_LOCATION_f1": 0.75, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6867469879518072, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.5774647887323944, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5061728395061729, "eval_ORGANIZATION_recall": 0.6721311475409836, "eval_PERSON_f1": 0.8224299065420562, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7857142857142857, "eval_PERSON_recall": 0.8627450980392157, "eval_QUANTITY_f1": 0.5753424657534246, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5121951219512195, "eval_QUANTITY_recall": 0.65625, "eval_TIME_f1": 0.8484848484848486, "eval_TIME_number": 31, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1574317067861557, "eval_overall_accuracy": 0.9497151350012385, "eval_overall_f1": 0.7400530503978779, "eval_overall_precision": 0.6838235294117647, "eval_overall_recall": 0.8063583815028902, "eval_runtime": 0.3315, "eval_samples_per_second": 564.042, "eval_steps_per_second": 9.049, "step": 1484 }, { "epoch": 15.0, "grad_norm": 0.5429168939590454, "learning_rate": 4.25e-05, "loss": 0.1563, "step": 1590 }, { "epoch": 15.0, "eval_LOCATION_f1": 0.75, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6867469879518072, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.5942028985507246, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5324675324675324, "eval_ORGANIZATION_recall": 0.6721311475409836, "eval_PERSON_f1": 0.8213166144200625, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7891566265060241, "eval_PERSON_recall": 0.8562091503267973, "eval_QUANTITY_f1": 0.5833333333333334, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.525, "eval_QUANTITY_recall": 0.65625, "eval_TIME_f1": 0.875, "eval_TIME_number": 31, "eval_TIME_precision": 0.8484848484848485, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.14687992632389069, "eval_overall_accuracy": 0.9534307654198663, "eval_overall_f1": 0.7463087248322148, "eval_overall_precision": 0.6967418546365914, "eval_overall_recall": 0.8034682080924855, "eval_runtime": 0.3339, "eval_samples_per_second": 560.125, "eval_steps_per_second": 8.986, "step": 1590 }, { "epoch": 16.0, "grad_norm": 1.0070582628250122, "learning_rate": 4.2e-05, "loss": 0.1517, "step": 1696 }, { "epoch": 16.0, "eval_LOCATION_f1": 0.7549668874172186, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6951219512195121, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6131386861313869, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5526315789473685, "eval_ORGANIZATION_recall": 0.6885245901639344, "eval_PERSON_f1": 0.8338557993730408, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8012048192771084, "eval_PERSON_recall": 0.869281045751634, "eval_QUANTITY_f1": 0.6478873239436619, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5897435897435898, "eval_QUANTITY_recall": 0.71875, "eval_TIME_f1": 0.8615384615384616, "eval_TIME_number": 31, "eval_TIME_precision": 0.8235294117647058, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.14399613440036774, "eval_overall_accuracy": 0.9546693088927422, "eval_overall_f1": 0.7617765814266488, "eval_overall_precision": 0.7128463476070529, "eval_overall_recall": 0.8179190751445087, "eval_runtime": 0.3333, "eval_samples_per_second": 561.126, "eval_steps_per_second": 9.002, "step": 1696 }, { "epoch": 17.0, "grad_norm": 0.726586639881134, "learning_rate": 4.15e-05, "loss": 0.1453, "step": 1802 }, { "epoch": 17.0, "eval_LOCATION_f1": 0.7388535031847134, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6590909090909091, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6197183098591549, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5432098765432098, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.83125, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7964071856287425, "eval_PERSON_recall": 0.869281045751634, "eval_QUANTITY_f1": 0.6575342465753423, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5853658536585366, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.8059701492537312, "eval_TIME_number": 31, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1529819667339325, "eval_overall_accuracy": 0.9507059697795393, "eval_overall_f1": 0.7536231884057972, "eval_overall_precision": 0.6924939467312349, "eval_overall_recall": 0.8265895953757225, "eval_runtime": 0.3335, "eval_samples_per_second": 560.802, "eval_steps_per_second": 8.997, "step": 1802 }, { "epoch": 18.0, "grad_norm": 1.822987675666809, "learning_rate": 4.1e-05, "loss": 0.1429, "step": 1908 }, { "epoch": 18.0, "eval_LOCATION_f1": 0.7581699346405228, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6904761904761905, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.5985401459854015, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5394736842105263, "eval_ORGANIZATION_recall": 0.6721311475409836, "eval_PERSON_f1": 0.8391167192429022, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8109756097560976, "eval_PERSON_recall": 0.869281045751634, "eval_QUANTITY_f1": 0.6756756756756757, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5952380952380952, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14502748847007751, "eval_overall_accuracy": 0.953183056725291, "eval_overall_f1": 0.7603748326639893, "eval_overall_precision": 0.7082294264339152, "eval_overall_recall": 0.8208092485549133, "eval_runtime": 0.3323, "eval_samples_per_second": 562.661, "eval_steps_per_second": 9.027, "step": 1908 }, { "epoch": 19.0, "grad_norm": 1.2786140441894531, "learning_rate": 4.05e-05, "loss": 0.1403, "step": 2014 }, { "epoch": 19.0, "eval_LOCATION_f1": 0.763157894736842, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6987951807228916, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6176470588235294, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.56, "eval_ORGANIZATION_recall": 0.6885245901639344, "eval_PERSON_f1": 0.8338557993730408, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8012048192771084, "eval_PERSON_recall": 0.869281045751634, "eval_QUANTITY_f1": 0.676056338028169, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6153846153846154, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.8615384615384616, "eval_TIME_number": 31, "eval_TIME_precision": 0.8235294117647058, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13972367346286774, "eval_overall_accuracy": 0.955907852365618, "eval_overall_f1": 0.7671601615074025, "eval_overall_precision": 0.7178841309823678, "eval_overall_recall": 0.8236994219653179, "eval_runtime": 0.3327, "eval_samples_per_second": 562.063, "eval_steps_per_second": 9.017, "step": 2014 }, { "epoch": 20.0, "grad_norm": 0.7519010305404663, "learning_rate": 4e-05, "loss": 0.1339, "step": 2120 }, { "epoch": 20.0, "eval_LOCATION_f1": 0.7354838709677418, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6627906976744186, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6187050359712231, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5512820512820513, "eval_ORGANIZATION_recall": 0.7049180327868853, "eval_PERSON_f1": 0.8286604361370716, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7916666666666666, "eval_PERSON_recall": 0.869281045751634, "eval_QUANTITY_f1": 0.6575342465753423, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5853658536585366, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.7941176470588235, "eval_TIME_number": 31, "eval_TIME_precision": 0.7297297297297297, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1472398042678833, "eval_overall_accuracy": 0.9519445132524151, "eval_overall_f1": 0.7513227513227513, "eval_overall_precision": 0.6926829268292682, "eval_overall_recall": 0.8208092485549133, "eval_runtime": 0.3321, "eval_samples_per_second": 563.13, "eval_steps_per_second": 9.034, "step": 2120 }, { "epoch": 21.0, "grad_norm": 0.5811749696731567, "learning_rate": 3.9500000000000005e-05, "loss": 0.134, "step": 2226 }, { "epoch": 21.0, "eval_LOCATION_f1": 0.7354838709677418, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6627906976744186, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6258503401360543, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5348837209302325, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8369230769230769, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7906976744186046, "eval_PERSON_recall": 0.8888888888888888, "eval_QUANTITY_f1": 0.6944444444444444, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.625, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14695529639720917, "eval_overall_accuracy": 0.9502105523903889, "eval_overall_f1": 0.7607843137254902, "eval_overall_precision": 0.6945107398568019, "eval_overall_recall": 0.8410404624277457, "eval_runtime": 0.3319, "eval_samples_per_second": 563.369, "eval_steps_per_second": 9.038, "step": 2226 }, { "epoch": 22.0, "grad_norm": 1.064430832862854, "learning_rate": 3.9000000000000006e-05, "loss": 0.131, "step": 2332 }, { "epoch": 22.0, "eval_LOCATION_f1": 0.763157894736842, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6987951807228916, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.624113475177305, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.55, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.8359133126934986, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7941176470588235, "eval_PERSON_recall": 0.8823529411764706, "eval_QUANTITY_f1": 0.6944444444444444, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.625, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7714285714285716, "eval_TIME_number": 31, "eval_TIME_precision": 0.6923076923076923, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14194293320178986, "eval_overall_accuracy": 0.953183056725291, "eval_overall_f1": 0.7625329815303432, "eval_overall_precision": 0.7014563106796117, "eval_overall_recall": 0.8352601156069365, "eval_runtime": 0.3256, "eval_samples_per_second": 574.383, "eval_steps_per_second": 9.215, "step": 2332 }, { "epoch": 23.0, "grad_norm": 0.5735294222831726, "learning_rate": 3.85e-05, "loss": 0.1292, "step": 2438 }, { "epoch": 23.0, "eval_LOCATION_f1": 0.778523489932886, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.725, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6277372262773723, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5657894736842105, "eval_ORGANIZATION_recall": 0.7049180327868853, "eval_PERSON_f1": 0.8447204968944099, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8047337278106509, "eval_PERSON_recall": 0.8888888888888888, "eval_QUANTITY_f1": 0.7042253521126761, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6410256410256411, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8181818181818182, "eval_TIME_number": 31, "eval_TIME_precision": 0.7714285714285715, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1338079273700714, "eval_overall_accuracy": 0.9583849393113698, "eval_overall_f1": 0.7758389261744967, "eval_overall_precision": 0.7243107769423559, "eval_overall_recall": 0.8352601156069365, "eval_runtime": 0.3263, "eval_samples_per_second": 573.164, "eval_steps_per_second": 9.195, "step": 2438 }, { "epoch": 24.0, "grad_norm": 1.6434870958328247, "learning_rate": 3.8e-05, "loss": 0.1245, "step": 2544 }, { "epoch": 24.0, "eval_LOCATION_f1": 0.7388535031847134, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6590909090909091, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6293706293706294, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5487804878048781, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.8571428571428571, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8165680473372781, "eval_PERSON_recall": 0.9019607843137255, "eval_QUANTITY_f1": 0.6756756756756757, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5952380952380952, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7428571428571428, "eval_TIME_number": 31, "eval_TIME_precision": 0.6666666666666666, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.147781103849411, "eval_overall_accuracy": 0.9519445132524151, "eval_overall_f1": 0.762402088772846, "eval_overall_precision": 0.6952380952380952, "eval_overall_recall": 0.8439306358381503, "eval_runtime": 0.3334, "eval_samples_per_second": 560.916, "eval_steps_per_second": 8.999, "step": 2544 }, { "epoch": 25.0, "grad_norm": 0.742203950881958, "learning_rate": 3.7500000000000003e-05, "loss": 0.1239, "step": 2650 }, { "epoch": 25.0, "eval_LOCATION_f1": 0.7814569536423841, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7195121951219512, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6338028169014086, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5555555555555556, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.8535825545171339, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8154761904761905, "eval_PERSON_recall": 0.8954248366013072, "eval_QUANTITY_f1": 0.684931506849315, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6097560975609756, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7647058823529411, "eval_TIME_number": 31, "eval_TIME_precision": 0.7027027027027027, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13900037109851837, "eval_overall_accuracy": 0.9554124349764677, "eval_overall_f1": 0.7735099337748343, "eval_overall_precision": 0.7139364303178484, "eval_overall_recall": 0.8439306358381503, "eval_runtime": 0.3323, "eval_samples_per_second": 562.747, "eval_steps_per_second": 9.028, "step": 2650 }, { "epoch": 26.0, "grad_norm": 0.991144061088562, "learning_rate": 3.7e-05, "loss": 0.1241, "step": 2756 }, { "epoch": 26.0, "eval_LOCATION_f1": 0.763157894736842, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6987951807228916, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6433566433566433, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5609756097560976, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8633540372670808, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8224852071005917, "eval_PERSON_recall": 0.9084967320261438, "eval_QUANTITY_f1": 0.6666666666666666, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5813953488372093, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7536231884057972, "eval_TIME_number": 31, "eval_TIME_precision": 0.6842105263157895, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13951300084590912, "eval_overall_accuracy": 0.9541738915035918, "eval_overall_f1": 0.7726675427069645, "eval_overall_precision": 0.708433734939759, "eval_overall_recall": 0.8497109826589595, "eval_runtime": 0.333, "eval_samples_per_second": 561.644, "eval_steps_per_second": 9.01, "step": 2756 }, { "epoch": 27.0, "grad_norm": 1.1069492101669312, "learning_rate": 3.65e-05, "loss": 0.1236, "step": 2862 }, { "epoch": 27.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.626865671641791, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5753424657534246, "eval_ORGANIZATION_recall": 0.6885245901639344, "eval_PERSON_f1": 0.8624999999999999, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8263473053892215, "eval_PERSON_recall": 0.9019607843137255, "eval_QUANTITY_f1": 0.6756756756756757, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5952380952380952, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7428571428571428, "eval_TIME_number": 31, "eval_TIME_precision": 0.6666666666666666, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13548590242862701, "eval_overall_accuracy": 0.9564032697547684, "eval_overall_f1": 0.7780748663101604, "eval_overall_precision": 0.7238805970149254, "eval_overall_recall": 0.8410404624277457, "eval_runtime": 0.3264, "eval_samples_per_second": 572.992, "eval_steps_per_second": 9.192, "step": 2862 }, { "epoch": 28.0, "grad_norm": 0.893926203250885, "learning_rate": 3.6e-05, "loss": 0.1189, "step": 2968 }, { "epoch": 28.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6074074074074074, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5540540540540541, "eval_ORGANIZATION_recall": 0.6721311475409836, "eval_PERSON_f1": 0.8633540372670808, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8224852071005917, "eval_PERSON_recall": 0.9084967320261438, "eval_QUANTITY_f1": 0.6944444444444444, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.625, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7536231884057972, "eval_TIME_number": 31, "eval_TIME_precision": 0.6842105263157895, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13185539841651917, "eval_overall_accuracy": 0.9578895219222194, "eval_overall_f1": 0.7754010695187166, "eval_overall_precision": 0.7213930348258707, "eval_overall_recall": 0.838150289017341, "eval_runtime": 0.3327, "eval_samples_per_second": 562.15, "eval_steps_per_second": 9.018, "step": 2968 }, { "epoch": 29.0, "grad_norm": 1.665179967880249, "learning_rate": 3.55e-05, "loss": 0.1163, "step": 3074 }, { "epoch": 29.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6060606060606061, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5633802816901409, "eval_ORGANIZATION_recall": 0.6557377049180327, "eval_PERSON_f1": 0.8598130841121495, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8214285714285714, "eval_PERSON_recall": 0.9019607843137255, "eval_QUANTITY_f1": 0.6956521739130435, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.875, "eval_TIME_number": 31, "eval_TIME_precision": 0.8484848484848485, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13032348453998566, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.7891156462585035, "eval_overall_precision": 0.7455012853470437, "eval_overall_recall": 0.838150289017341, "eval_runtime": 0.3327, "eval_samples_per_second": 562.047, "eval_steps_per_second": 9.017, "step": 3074 }, { "epoch": 30.0, "grad_norm": 0.9628661274909973, "learning_rate": 3.5e-05, "loss": 0.1151, "step": 3180 }, { "epoch": 30.0, "eval_LOCATION_f1": 0.76, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7037037037037037, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5974025974025974, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8624999999999999, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8263473053892215, "eval_PERSON_recall": 0.9019607843137255, "eval_QUANTITY_f1": 0.6956521739130435, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1332600861787796, "eval_overall_accuracy": 0.958632648005945, "eval_overall_f1": 0.782258064516129, "eval_overall_precision": 0.7311557788944724, "eval_overall_recall": 0.8410404624277457, "eval_runtime": 0.3327, "eval_samples_per_second": 562.028, "eval_steps_per_second": 9.016, "step": 3180 }, { "epoch": 31.0, "grad_norm": 0.40495026111602783, "learning_rate": 3.45e-05, "loss": 0.1159, "step": 3286 }, { "epoch": 31.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6165413533834587, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5694444444444444, "eval_ORGANIZATION_recall": 0.6721311475409836, "eval_PERSON_f1": 0.8722741433021807, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8333333333333334, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7042253521126761, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6410256410256411, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13211479783058167, "eval_overall_accuracy": 0.958632648005945, "eval_overall_f1": 0.7854251012145749, "eval_overall_precision": 0.7367088607594937, "eval_overall_recall": 0.8410404624277457, "eval_runtime": 0.3267, "eval_samples_per_second": 572.363, "eval_steps_per_second": 9.182, "step": 3286 }, { "epoch": 32.0, "grad_norm": 1.324985146522522, "learning_rate": 3.4000000000000007e-05, "loss": 0.1104, "step": 3392 }, { "epoch": 32.0, "eval_LOCATION_f1": 0.778523489932886, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.725, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.676470588235294, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6133333333333333, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8687500000000001, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8323353293413174, "eval_PERSON_recall": 0.9084967320261438, "eval_QUANTITY_f1": 0.6956521739130435, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13009528815746307, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.7918918918918919, "eval_overall_precision": 0.7436548223350253, "eval_overall_recall": 0.846820809248555, "eval_runtime": 0.3258, "eval_samples_per_second": 574.048, "eval_steps_per_second": 9.209, "step": 3392 }, { "epoch": 33.0, "grad_norm": 2.763446569442749, "learning_rate": 3.35e-05, "loss": 0.1111, "step": 3498 }, { "epoch": 33.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6470588235294118, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5866666666666667, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.8722741433021807, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8333333333333334, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7042253521126761, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6410256410256411, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7647058823529411, "eval_TIME_number": 31, "eval_TIME_precision": 0.7027027027027027, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13236965239048004, "eval_overall_accuracy": 0.9593757740896706, "eval_overall_f1": 0.7882037533512065, "eval_overall_precision": 0.735, "eval_overall_recall": 0.8497109826589595, "eval_runtime": 0.3328, "eval_samples_per_second": 561.901, "eval_steps_per_second": 9.014, "step": 3498 }, { "epoch": 34.0, "grad_norm": 0.4679914116859436, "learning_rate": 3.3e-05, "loss": 0.1103, "step": 3604 }, { "epoch": 34.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6714285714285714, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5949367088607594, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.875, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8383233532934131, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.6944444444444444, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.625, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7536231884057972, "eval_TIME_number": 31, "eval_TIME_precision": 0.6842105263157895, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1343124508857727, "eval_overall_accuracy": 0.9576418132276443, "eval_overall_f1": 0.7909454061251664, "eval_overall_precision": 0.7333333333333333, "eval_overall_recall": 0.8583815028901735, "eval_runtime": 0.3328, "eval_samples_per_second": 561.977, "eval_steps_per_second": 9.016, "step": 3604 }, { "epoch": 35.0, "grad_norm": 2.02740216255188, "learning_rate": 3.2500000000000004e-05, "loss": 0.11, "step": 3710 }, { "epoch": 35.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6666666666666667, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6081081081081081, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.8769716088328076, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8475609756097561, "eval_PERSON_recall": 0.9084967320261438, "eval_QUANTITY_f1": 0.6944444444444444, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.625, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13133490085601807, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.7945945945945947, "eval_overall_precision": 0.7461928934010152, "eval_overall_recall": 0.8497109826589595, "eval_runtime": 0.328, "eval_samples_per_second": 570.125, "eval_steps_per_second": 9.146, "step": 3710 }, { "epoch": 36.0, "grad_norm": 0.7887612581253052, "learning_rate": 3.2000000000000005e-05, "loss": 0.1097, "step": 3816 }, { "epoch": 36.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6363636363636364, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5915492957746479, "eval_ORGANIZATION_recall": 0.6885245901639344, "eval_PERSON_f1": 0.875, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8383233532934131, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.6944444444444444, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.625, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7647058823529411, "eval_TIME_number": 31, "eval_TIME_precision": 0.7027027027027027, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12940670549869537, "eval_overall_accuracy": 0.9591280653950953, "eval_overall_f1": 0.7897574123989218, "eval_overall_precision": 0.73989898989899, "eval_overall_recall": 0.846820809248555, "eval_runtime": 0.3308, "eval_samples_per_second": 565.237, "eval_steps_per_second": 9.068, "step": 3816 }, { "epoch": 37.0, "grad_norm": 1.632466435432434, "learning_rate": 3.15e-05, "loss": 0.1053, "step": 3922 }, { "epoch": 37.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7007299270072993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.631578947368421, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8722741433021807, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8333333333333334, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.6944444444444444, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.625, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13323675096035004, "eval_overall_accuracy": 0.9593757740896706, "eval_overall_f1": 0.7989276139410187, "eval_overall_precision": 0.745, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.3266, "eval_samples_per_second": 572.555, "eval_steps_per_second": 9.185, "step": 3922 }, { "epoch": 38.0, "grad_norm": 0.9233851432800293, "learning_rate": 3.1e-05, "loss": 0.1052, "step": 4028 }, { "epoch": 38.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7164179104477612, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6575342465753424, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8722741433021807, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8333333333333334, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12981662154197693, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8102981029810298, "eval_overall_precision": 0.7627551020408163, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.3318, "eval_samples_per_second": 563.527, "eval_steps_per_second": 9.041, "step": 4028 }, { "epoch": 39.0, "grad_norm": 1.1834499835968018, "learning_rate": 3.05e-05, "loss": 0.1005, "step": 4134 }, { "epoch": 39.0, "eval_LOCATION_f1": 0.821917808219178, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7792207792207793, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6870229007633588, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6428571428571429, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.8777429467084639, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8433734939759037, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12637227773666382, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8087431693989071, "eval_overall_precision": 0.7668393782383419, "eval_overall_recall": 0.8554913294797688, "eval_runtime": 0.3324, "eval_samples_per_second": 562.615, "eval_steps_per_second": 9.026, "step": 4134 }, { "epoch": 40.0, "grad_norm": 0.9927902221679688, "learning_rate": 3e-05, "loss": 0.103, "step": 4240 }, { "epoch": 40.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7067669172932329, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6527777777777778, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.875, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8383233532934131, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.6944444444444444, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.625, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12951116263866425, "eval_overall_accuracy": 0.9611097349516968, "eval_overall_f1": 0.8054054054054054, "eval_overall_precision": 0.7563451776649747, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.3265, "eval_samples_per_second": 572.657, "eval_steps_per_second": 9.187, "step": 4240 }, { "epoch": 41.0, "grad_norm": 0.8560711741447449, "learning_rate": 2.95e-05, "loss": 0.1024, "step": 4346 }, { "epoch": 41.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6962962962962963, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6351351351351351, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.875, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8383233532934131, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12939083576202393, "eval_overall_accuracy": 0.9611097349516968, "eval_overall_f1": 0.8064952638700946, "eval_overall_precision": 0.7582697201017812, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.327, "eval_samples_per_second": 571.893, "eval_steps_per_second": 9.175, "step": 4346 }, { "epoch": 42.0, "grad_norm": 1.0656765699386597, "learning_rate": 2.9e-05, "loss": 0.1009, "step": 4452 }, { "epoch": 42.0, "eval_LOCATION_f1": 0.7972972972972974, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7468354430379747, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6962962962962963, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6351351351351351, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8785046728971961, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8392857142857143, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13172192871570587, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8043184885290148, "eval_overall_precision": 0.7544303797468355, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.3271, "eval_samples_per_second": 571.673, "eval_steps_per_second": 9.171, "step": 4452 }, { "epoch": 43.0, "grad_norm": 0.8540602922439575, "learning_rate": 2.8499999999999998e-05, "loss": 0.1019, "step": 4558 }, { "epoch": 43.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7007299270072993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.631578947368421, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8785046728971961, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8392857142857143, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.6944444444444444, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.625, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7536231884057972, "eval_TIME_number": 31, "eval_TIME_precision": 0.6842105263157895, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13470353186130524, "eval_overall_accuracy": 0.9598711914788209, "eval_overall_f1": 0.8032128514056226, "eval_overall_precision": 0.7481296758104738, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3263, "eval_samples_per_second": 573.074, "eval_steps_per_second": 9.194, "step": 4558 }, { "epoch": 44.0, "grad_norm": 1.568738579750061, "learning_rate": 2.8000000000000003e-05, "loss": 0.0998, "step": 4664 }, { "epoch": 44.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7014925373134328, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6438356164383562, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8840125391849529, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8493975903614458, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12552283704280853, "eval_overall_accuracy": 0.9628436958137231, "eval_overall_f1": 0.8147138964577657, "eval_overall_precision": 0.770618556701031, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.3277, "eval_samples_per_second": 570.614, "eval_steps_per_second": 9.154, "step": 4664 }, { "epoch": 45.0, "grad_norm": 0.8983941078186035, "learning_rate": 2.7500000000000004e-05, "loss": 0.099, "step": 4770 }, { "epoch": 45.0, "eval_LOCATION_f1": 0.7972972972972974, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7468354430379747, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7058823529411764, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.64, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.875, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8383233532934131, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13098634779453278, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8043184885290148, "eval_overall_precision": 0.7544303797468355, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.3254, "eval_samples_per_second": 574.692, "eval_steps_per_second": 9.22, "step": 4770 }, { "epoch": 46.0, "grad_norm": 0.6761122941970825, "learning_rate": 2.7000000000000002e-05, "loss": 0.0943, "step": 4876 }, { "epoch": 46.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7101449275362318, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6363636363636364, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.875, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8383233532934131, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12825974822044373, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.8097165991902835, "eval_overall_precision": 0.759493670886076, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3336, "eval_samples_per_second": 560.515, "eval_steps_per_second": 8.992, "step": 4876 }, { "epoch": 47.0, "grad_norm": 0.5556443333625793, "learning_rate": 2.6500000000000004e-05, "loss": 0.0964, "step": 4982 }, { "epoch": 47.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7007299270072993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.631578947368421, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8777429467084639, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8433734939759037, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7042253521126761, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6410256410256411, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12963125109672546, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.8059299191374663, "eval_overall_precision": 0.7550505050505051, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.333, "eval_samples_per_second": 561.599, "eval_steps_per_second": 9.01, "step": 4982 }, { "epoch": 48.0, "grad_norm": 1.6252089738845825, "learning_rate": 2.6000000000000002e-05, "loss": 0.093, "step": 5088 }, { "epoch": 48.0, "eval_LOCATION_f1": 0.7972972972972974, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7468354430379747, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6956521739130435, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6233766233766234, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.88125, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.844311377245509, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7042253521126761, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6410256410256411, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13150960206985474, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.803763440860215, "eval_overall_precision": 0.7512562814070352, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.3321, "eval_samples_per_second": 563.117, "eval_steps_per_second": 9.034, "step": 5088 }, { "epoch": 49.0, "grad_norm": 2.281259298324585, "learning_rate": 2.5500000000000003e-05, "loss": 0.095, "step": 5194 }, { "epoch": 49.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6956521739130435, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6233766233766234, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8777429467084639, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8433734939759037, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6666666666666666, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12873758375644684, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.8075880758807589, "eval_overall_precision": 0.7602040816326531, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.3255, "eval_samples_per_second": 574.424, "eval_steps_per_second": 9.215, "step": 5194 }, { "epoch": 50.0, "grad_norm": 1.0862303972244263, "learning_rate": 2.5e-05, "loss": 0.0931, "step": 5300 }, { "epoch": 50.0, "eval_LOCATION_f1": 0.802721088435374, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7564102564102564, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7022900763358779, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6571428571428571, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8777429467084639, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8433734939759037, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12418641149997711, "eval_overall_accuracy": 0.9628436958137231, "eval_overall_f1": 0.812071330589849, "eval_overall_precision": 0.7728459530026109, "eval_overall_recall": 0.8554913294797688, "eval_runtime": 0.3324, "eval_samples_per_second": 562.606, "eval_steps_per_second": 9.026, "step": 5300 }, { "epoch": 51.0, "grad_norm": 0.8711085319519043, "learning_rate": 2.45e-05, "loss": 0.0913, "step": 5406 }, { "epoch": 51.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7101449275362318, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6363636363636364, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.875, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8383233532934131, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12821562588214874, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8108108108108107, "eval_overall_precision": 0.7614213197969543, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3328, "eval_samples_per_second": 561.834, "eval_steps_per_second": 9.013, "step": 5406 }, { "epoch": 52.0, "grad_norm": 1.1370666027069092, "learning_rate": 2.4e-05, "loss": 0.0903, "step": 5512 }, { "epoch": 52.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7132867132867133, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6219512195121951, "eval_ORGANIZATION_recall": 0.8360655737704918, "eval_PERSON_f1": 0.8819875776397514, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8402366863905325, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13088764250278473, "eval_overall_accuracy": 0.9611097349516968, "eval_overall_f1": 0.8128342245989304, "eval_overall_precision": 0.7562189054726368, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3326, "eval_samples_per_second": 562.204, "eval_steps_per_second": 9.019, "step": 5512 }, { "epoch": 53.0, "grad_norm": 1.300648808479309, "learning_rate": 2.35e-05, "loss": 0.0916, "step": 5618 }, { "epoch": 53.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7007299270072993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.631578947368421, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8785046728971961, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8392857142857143, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6666666666666666, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12691177427768707, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8092016238159675, "eval_overall_precision": 0.7608142493638677, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.3332, "eval_samples_per_second": 561.276, "eval_steps_per_second": 9.004, "step": 5618 }, { "epoch": 54.0, "grad_norm": 0.8109161853790283, "learning_rate": 2.3000000000000003e-05, "loss": 0.0908, "step": 5724 }, { "epoch": 54.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6870229007633588, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6428571428571429, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.875, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8383233532934131, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12619327008724213, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8076398362892223, "eval_overall_precision": 0.7648578811369509, "eval_overall_recall": 0.8554913294797688, "eval_runtime": 0.3316, "eval_samples_per_second": 564.011, "eval_steps_per_second": 9.048, "step": 5724 }, { "epoch": 55.0, "grad_norm": 1.711658000946045, "learning_rate": 2.25e-05, "loss": 0.0909, "step": 5830 }, { "epoch": 55.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7142857142857143, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6329113924050633, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8730650154798762, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8294117647058824, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1325843632221222, "eval_overall_accuracy": 0.9601189001733961, "eval_overall_f1": 0.8085676037483266, "eval_overall_precision": 0.7531172069825436, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3261, "eval_samples_per_second": 573.38, "eval_steps_per_second": 9.199, "step": 5830 }, { "epoch": 56.0, "grad_norm": 2.1303319931030273, "learning_rate": 2.2000000000000003e-05, "loss": 0.0901, "step": 5936 }, { "epoch": 56.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6969696969696969, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.647887323943662, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8840125391849529, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8493975903614458, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12528882920742035, "eval_overall_accuracy": 0.9628436958137231, "eval_overall_f1": 0.8142076502732241, "eval_overall_precision": 0.772020725388601, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.3264, "eval_samples_per_second": 573.004, "eval_steps_per_second": 9.193, "step": 5936 }, { "epoch": 57.0, "grad_norm": 0.6441662907600403, "learning_rate": 2.15e-05, "loss": 0.0887, "step": 6042 }, { "epoch": 57.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7058823529411764, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.64, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8875000000000001, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8502994011976048, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1284150779247284, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8146143437077131, "eval_overall_precision": 0.7659033078880407, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3324, "eval_samples_per_second": 562.535, "eval_steps_per_second": 9.025, "step": 6042 }, { "epoch": 58.0, "grad_norm": 7.387343406677246, "learning_rate": 2.1e-05, "loss": 0.0871, "step": 6148 }, { "epoch": 58.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7246376811594203, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6493506493506493, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8875000000000001, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8502994011976048, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13085266947746277, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.8167115902964959, "eval_overall_precision": 0.7651515151515151, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.331, "eval_samples_per_second": 564.928, "eval_steps_per_second": 9.063, "step": 6148 }, { "epoch": 59.0, "grad_norm": 0.9604142308235168, "learning_rate": 2.05e-05, "loss": 0.0873, "step": 6254 }, { "epoch": 59.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7058823529411764, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.64, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.880503144654088, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8484848484848485, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12588416039943695, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8125000000000001, "eval_overall_precision": 0.7666666666666667, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.3337, "eval_samples_per_second": 560.463, "eval_steps_per_second": 8.991, "step": 6254 }, { "epoch": 60.0, "grad_norm": 0.5629883408546448, "learning_rate": 2e-05, "loss": 0.0881, "step": 6360 }, { "epoch": 60.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7246376811594203, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6493506493506493, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8875000000000001, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8502994011976048, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7761194029850746, "eval_TIME_number": 31, "eval_TIME_precision": 0.7222222222222222, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13291847705841064, "eval_overall_accuracy": 0.9611097349516968, "eval_overall_f1": 0.8145161290322581, "eval_overall_precision": 0.7613065326633166, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3251, "eval_samples_per_second": 575.157, "eval_steps_per_second": 9.227, "step": 6360 }, { "epoch": 61.0, "grad_norm": 1.5210415124893188, "learning_rate": 1.9500000000000003e-05, "loss": 0.0862, "step": 6466 }, { "epoch": 61.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6911764705882353, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6266666666666667, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8777429467084639, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8433734939759037, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1278122216463089, "eval_overall_accuracy": 0.9623482784245727, "eval_overall_f1": 0.809782608695652, "eval_overall_precision": 0.764102564102564, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.3328, "eval_samples_per_second": 561.823, "eval_steps_per_second": 9.013, "step": 6466 }, { "epoch": 62.0, "grad_norm": 0.7378549575805664, "learning_rate": 1.9e-05, "loss": 0.0846, "step": 6572 }, { "epoch": 62.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6911764705882353, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6266666666666667, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8847352024922119, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8452380952380952, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12677760422229767, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8130081300813009, "eval_overall_precision": 0.7653061224489796, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3315, "eval_samples_per_second": 564.037, "eval_steps_per_second": 9.049, "step": 6572 }, { "epoch": 63.0, "grad_norm": 2.9116363525390625, "learning_rate": 1.85e-05, "loss": 0.0848, "step": 6678 }, { "epoch": 63.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6911764705882353, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6266666666666667, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.875, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8383233532934131, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1273198425769806, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8086838534599727, "eval_overall_precision": 0.7621483375959079, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.3319, "eval_samples_per_second": 563.372, "eval_steps_per_second": 9.038, "step": 6678 }, { "epoch": 64.0, "grad_norm": 1.1460438966751099, "learning_rate": 1.8e-05, "loss": 0.0839, "step": 6784 }, { "epoch": 64.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7183098591549297, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6296296296296297, "eval_ORGANIZATION_recall": 0.8360655737704918, "eval_PERSON_f1": 0.8847352024922119, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8452380952380952, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13079452514648438, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8161073825503355, "eval_overall_precision": 0.7619047619047619, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3319, "eval_samples_per_second": 563.454, "eval_steps_per_second": 9.039, "step": 6784 }, { "epoch": 65.0, "grad_norm": 0.6211540102958679, "learning_rate": 1.75e-05, "loss": 0.0844, "step": 6890 }, { "epoch": 65.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6956521739130435, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6233766233766234, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8785046728971961, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8392857142857143, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13039271533489227, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8097165991902835, "eval_overall_precision": 0.759493670886076, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3319, "eval_samples_per_second": 563.448, "eval_steps_per_second": 9.039, "step": 6890 }, { "epoch": 66.0, "grad_norm": 1.3352203369140625, "learning_rate": 1.7000000000000003e-05, "loss": 0.0843, "step": 6996 }, { "epoch": 66.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6956521739130435, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6233766233766234, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8757763975155279, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.834319526627219, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1285402625799179, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8097165991902835, "eval_overall_precision": 0.759493670886076, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3319, "eval_samples_per_second": 563.364, "eval_steps_per_second": 9.038, "step": 6996 }, { "epoch": 67.0, "grad_norm": 1.0625277757644653, "learning_rate": 1.65e-05, "loss": 0.0835, "step": 7102 }, { "epoch": 67.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7101449275362318, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6363636363636364, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8875000000000001, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8502994011976048, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1304752379655838, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.815114709851552, "eval_overall_precision": 0.7645569620253164, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3327, "eval_samples_per_second": 562.034, "eval_steps_per_second": 9.017, "step": 7102 }, { "epoch": 68.0, "grad_norm": 0.6711142063140869, "learning_rate": 1.6000000000000003e-05, "loss": 0.0829, "step": 7208 }, { "epoch": 68.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7050359712230215, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6282051282051282, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.88125, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.844311377245509, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13301803171634674, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8102288021534321, "eval_overall_precision": 0.7581863979848866, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3252, "eval_samples_per_second": 575.06, "eval_steps_per_second": 9.226, "step": 7208 }, { "epoch": 69.0, "grad_norm": 1.7081199884414673, "learning_rate": 1.55e-05, "loss": 0.0825, "step": 7314 }, { "epoch": 69.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7101449275362318, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6363636363636364, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.875, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8383233532934131, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1297992765903473, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8097165991902835, "eval_overall_precision": 0.759493670886076, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3271, "eval_samples_per_second": 571.614, "eval_steps_per_second": 9.17, "step": 7314 }, { "epoch": 70.0, "grad_norm": 1.5077204704284668, "learning_rate": 1.5e-05, "loss": 0.0838, "step": 7420 }, { "epoch": 70.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6962962962962963, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6351351351351351, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8867924528301887, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8545454545454545, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7058823529411765, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6666666666666666, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.8125, "eval_TIME_number": 31, "eval_TIME_precision": 0.7878787878787878, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12454633414745331, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8142076502732241, "eval_overall_precision": 0.772020725388601, "eval_overall_recall": 0.861271676300578, "eval_runtime": 0.3252, "eval_samples_per_second": 575.086, "eval_steps_per_second": 9.226, "step": 7420 }, { "epoch": 71.0, "grad_norm": 0.8420604467391968, "learning_rate": 1.45e-05, "loss": 0.082, "step": 7526 }, { "epoch": 71.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7007299270072993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.631578947368421, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8832807570977917, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8536585365853658, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12775453925132751, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8136054421768707, "eval_overall_precision": 0.7686375321336761, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.3317, "eval_samples_per_second": 563.824, "eval_steps_per_second": 9.045, "step": 7526 }, { "epoch": 72.0, "grad_norm": 1.3872723579406738, "learning_rate": 1.4000000000000001e-05, "loss": 0.0828, "step": 7632 }, { "epoch": 72.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6811594202898551, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6103896103896104, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8867924528301887, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8545454545454545, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.787878787878788, "eval_TIME_number": 31, "eval_TIME_precision": 0.7428571428571429, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12862151861190796, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8102981029810298, "eval_overall_precision": 0.7627551020408163, "eval_overall_recall": 0.8641618497109826, "eval_runtime": 0.3259, "eval_samples_per_second": 573.733, "eval_steps_per_second": 9.204, "step": 7632 }, { "epoch": 73.0, "grad_norm": 3.8698806762695312, "learning_rate": 1.3500000000000001e-05, "loss": 0.0817, "step": 7738 }, { "epoch": 73.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6618705035971222, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5897435897435898, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8875000000000001, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8502994011976048, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12658685445785522, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8108108108108107, "eval_overall_precision": 0.7614213197969543, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3322, "eval_samples_per_second": 562.901, "eval_steps_per_second": 9.03, "step": 7738 }, { "epoch": 74.0, "grad_norm": 1.848007082939148, "learning_rate": 1.3000000000000001e-05, "loss": 0.0812, "step": 7844 }, { "epoch": 74.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7050359712230215, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6282051282051282, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8875000000000001, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8502994011976048, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12929360568523407, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8173207036535859, "eval_overall_precision": 0.7684478371501272, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3317, "eval_samples_per_second": 563.837, "eval_steps_per_second": 9.046, "step": 7844 }, { "epoch": 75.0, "grad_norm": 1.7477933168411255, "learning_rate": 1.25e-05, "loss": 0.0807, "step": 7950 }, { "epoch": 75.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7007299270072993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.631578947368421, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8895899053627759, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8597560975609756, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12874720990657806, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8163265306122449, "eval_overall_precision": 0.7712082262210797, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.331, "eval_samples_per_second": 564.9, "eval_steps_per_second": 9.063, "step": 7950 }, { "epoch": 76.0, "grad_norm": 2.013258218765259, "learning_rate": 1.2e-05, "loss": 0.0812, "step": 8056 }, { "epoch": 76.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7101449275362318, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6363636363636364, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.896551724137931, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8614457831325302, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12997564673423767, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8200270635994588, "eval_overall_precision": 0.7709923664122137, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3317, "eval_samples_per_second": 563.729, "eval_steps_per_second": 9.044, "step": 8056 }, { "epoch": 77.0, "grad_norm": 1.1624475717544556, "learning_rate": 1.1500000000000002e-05, "loss": 0.0802, "step": 8162 }, { "epoch": 77.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7153284671532848, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6447368421052632, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8895899053627759, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8597560975609756, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1278444081544876, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.819047619047619, "eval_overall_precision": 0.7737789203084833, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3327, "eval_samples_per_second": 562.078, "eval_steps_per_second": 9.017, "step": 8162 }, { "epoch": 78.0, "grad_norm": 0.8729904294013977, "learning_rate": 1.1000000000000001e-05, "loss": 0.0784, "step": 8268 }, { "epoch": 78.0, "eval_LOCATION_f1": 0.8299319727891156, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.782051282051282, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7153284671532848, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6447368421052632, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8895899053627759, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8597560975609756, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1290396898984909, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8228882833787465, "eval_overall_precision": 0.7783505154639175, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3321, "eval_samples_per_second": 563.115, "eval_steps_per_second": 9.034, "step": 8268 }, { "epoch": 79.0, "grad_norm": 1.2866274118423462, "learning_rate": 1.05e-05, "loss": 0.0786, "step": 8374 }, { "epoch": 79.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7007299270072993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.631578947368421, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8895899053627759, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8597560975609756, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12725712358951569, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8163265306122449, "eval_overall_precision": 0.7712082262210797, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3322, "eval_samples_per_second": 562.981, "eval_steps_per_second": 9.032, "step": 8374 }, { "epoch": 80.0, "grad_norm": 0.41915127635002136, "learning_rate": 1e-05, "loss": 0.079, "step": 8480 }, { "epoch": 80.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7428571428571428, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6582278481012658, "eval_ORGANIZATION_recall": 0.8524590163934426, "eval_PERSON_f1": 0.8875000000000001, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8502994011976048, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1323997676372528, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8209959623149394, "eval_overall_precision": 0.7682619647355163, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3318, "eval_samples_per_second": 563.636, "eval_steps_per_second": 9.042, "step": 8480 }, { "epoch": 81.0, "grad_norm": 0.6260617971420288, "learning_rate": 9.5e-06, "loss": 0.0787, "step": 8586 }, { "epoch": 81.0, "eval_LOCATION_f1": 0.8243243243243245, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7721518987341772, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.7153284671532848, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6447368421052632, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8895899053627759, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8597560975609756, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1297990381717682, "eval_overall_accuracy": 0.9628436958137231, "eval_overall_f1": 0.8217687074829931, "eval_overall_precision": 0.7763496143958869, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3312, "eval_samples_per_second": 564.699, "eval_steps_per_second": 9.059, "step": 8586 }, { "epoch": 82.0, "grad_norm": 1.0404263734817505, "learning_rate": 9e-06, "loss": 0.0773, "step": 8692 }, { "epoch": 82.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7299270072992702, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6578947368421053, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8860759493670887, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8588957055214724, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.130036398768425, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8201634877384196, "eval_overall_precision": 0.7757731958762887, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3252, "eval_samples_per_second": 575.051, "eval_steps_per_second": 9.225, "step": 8692 }, { "epoch": 83.0, "grad_norm": 0.824061930179596, "learning_rate": 8.500000000000002e-06, "loss": 0.0774, "step": 8798 }, { "epoch": 83.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7299270072992702, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6578947368421053, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.879746835443038, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.852760736196319, "eval_PERSON_recall": 0.9084967320261438, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12832613289356232, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8174386920980926, "eval_overall_precision": 0.7731958762886598, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3309, "eval_samples_per_second": 565.051, "eval_steps_per_second": 9.065, "step": 8798 }, { "epoch": 84.0, "grad_norm": 1.388303279876709, "learning_rate": 8.000000000000001e-06, "loss": 0.08, "step": 8904 }, { "epoch": 84.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7299270072992702, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6578947368421053, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.879746835443038, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.852760736196319, "eval_PERSON_recall": 0.9084967320261438, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1284891813993454, "eval_overall_accuracy": 0.9623482784245727, "eval_overall_f1": 0.8174386920980926, "eval_overall_precision": 0.7731958762886598, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3318, "eval_samples_per_second": 563.538, "eval_steps_per_second": 9.041, "step": 8904 }, { "epoch": 85.0, "grad_norm": 1.7590463161468506, "learning_rate": 7.5e-06, "loss": 0.0793, "step": 9010 }, { "epoch": 85.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7299270072992702, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6578947368421053, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8860759493670887, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8588957055214724, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12990440428256989, "eval_overall_accuracy": 0.9623482784245727, "eval_overall_f1": 0.819047619047619, "eval_overall_precision": 0.7737789203084833, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3318, "eval_samples_per_second": 563.605, "eval_steps_per_second": 9.042, "step": 9010 }, { "epoch": 86.0, "grad_norm": 2.529705286026001, "learning_rate": 7.000000000000001e-06, "loss": 0.0785, "step": 9116 }, { "epoch": 86.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7205882352941175, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6533333333333333, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8924050632911392, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8650306748466258, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1294085532426834, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8212824010914053, "eval_overall_precision": 0.7777777777777778, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3332, "eval_samples_per_second": 561.23, "eval_steps_per_second": 9.004, "step": 9116 }, { "epoch": 87.0, "grad_norm": 2.0231552124023438, "learning_rate": 6.5000000000000004e-06, "loss": 0.0775, "step": 9222 }, { "epoch": 87.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7153284671532848, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6447368421052632, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8930817610062893, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8606060606060606, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1288805603981018, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8206521739130435, "eval_overall_precision": 0.7743589743589744, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3319, "eval_samples_per_second": 563.448, "eval_steps_per_second": 9.039, "step": 9222 }, { "epoch": 88.0, "grad_norm": 0.9647945761680603, "learning_rate": 6e-06, "loss": 0.0762, "step": 9328 }, { "epoch": 88.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7205882352941175, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6533333333333333, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12900309264659882, "eval_overall_accuracy": 0.9635868218974486, "eval_overall_f1": 0.8228882833787465, "eval_overall_precision": 0.7783505154639175, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3318, "eval_samples_per_second": 563.538, "eval_steps_per_second": 9.041, "step": 9328 }, { "epoch": 89.0, "grad_norm": 1.4031829833984375, "learning_rate": 5.500000000000001e-06, "loss": 0.0793, "step": 9434 }, { "epoch": 89.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7246376811594203, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6493506493506493, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8895899053627759, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8597560975609756, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13082054257392883, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8206521739130435, "eval_overall_precision": 0.7743589743589744, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3255, "eval_samples_per_second": 574.458, "eval_steps_per_second": 9.216, "step": 9434 }, { "epoch": 90.0, "grad_norm": 1.4430360794067383, "learning_rate": 5e-06, "loss": 0.0775, "step": 9540 }, { "epoch": 90.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7153284671532848, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6447368421052632, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.89937106918239, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8666666666666667, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12996500730514526, "eval_overall_accuracy": 0.9633391132028735, "eval_overall_f1": 0.8233695652173912, "eval_overall_precision": 0.7769230769230769, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3251, "eval_samples_per_second": 575.226, "eval_steps_per_second": 9.228, "step": 9540 }, { "epoch": 91.0, "grad_norm": 0.7988660931587219, "learning_rate": 4.5e-06, "loss": 0.0773, "step": 9646 }, { "epoch": 91.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7153284671532848, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6447368421052632, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8924050632911392, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8650306748466258, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12873530387878418, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8201634877384196, "eval_overall_precision": 0.7757731958762887, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3267, "eval_samples_per_second": 572.313, "eval_steps_per_second": 9.181, "step": 9646 }, { "epoch": 92.0, "grad_norm": 2.095036506652832, "learning_rate": 4.000000000000001e-06, "loss": 0.0779, "step": 9752 }, { "epoch": 92.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7101449275362318, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6363636363636364, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8924050632911392, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8650306748466258, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12995846569538116, "eval_overall_accuracy": 0.9628436958137231, "eval_overall_f1": 0.8201634877384196, "eval_overall_precision": 0.7757731958762887, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.333, "eval_samples_per_second": 561.506, "eval_steps_per_second": 9.008, "step": 9752 }, { "epoch": 93.0, "grad_norm": 0.5353900790214539, "learning_rate": 3.5000000000000004e-06, "loss": 0.0779, "step": 9858 }, { "epoch": 93.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7205882352941175, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6533333333333333, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8987341772151898, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8711656441717791, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12925057113170624, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8240109140518418, "eval_overall_precision": 0.7803617571059431, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3308, "eval_samples_per_second": 565.305, "eval_steps_per_second": 9.069, "step": 9858 }, { "epoch": 94.0, "grad_norm": 1.4626368284225464, "learning_rate": 3e-06, "loss": 0.0758, "step": 9964 }, { "epoch": 94.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7246376811594203, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6493506493506493, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8930817610062893, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8606060606060606, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12975382804870605, "eval_overall_accuracy": 0.9633391132028735, "eval_overall_f1": 0.8222523744911805, "eval_overall_precision": 0.7749360613810742, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3259, "eval_samples_per_second": 573.749, "eval_steps_per_second": 9.205, "step": 9964 }, { "epoch": 95.0, "grad_norm": 0.8940861225128174, "learning_rate": 2.5e-06, "loss": 0.075, "step": 10070 }, { "epoch": 95.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7246376811594203, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6493506493506493, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8930817610062893, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8606060606060606, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.13019391894340515, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8222523744911805, "eval_overall_precision": 0.7749360613810742, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3256, "eval_samples_per_second": 574.264, "eval_steps_per_second": 9.213, "step": 10070 }, { "epoch": 96.0, "grad_norm": 0.9044079780578613, "learning_rate": 2.0000000000000003e-06, "loss": 0.0767, "step": 10176 }, { "epoch": 96.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7246376811594203, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6493506493506493, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8895899053627759, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8597560975609756, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1305137574672699, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8206521739130435, "eval_overall_precision": 0.7743589743589744, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3319, "eval_samples_per_second": 563.418, "eval_steps_per_second": 9.039, "step": 10176 }, { "epoch": 97.0, "grad_norm": 1.699776291847229, "learning_rate": 1.5e-06, "loss": 0.0774, "step": 10282 }, { "epoch": 97.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7205882352941175, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6533333333333333, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12990649044513702, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8228882833787465, "eval_overall_precision": 0.7783505154639175, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3315, "eval_samples_per_second": 564.156, "eval_steps_per_second": 9.051, "step": 10282 }, { "epoch": 98.0, "grad_norm": 0.571972131729126, "learning_rate": 1.0000000000000002e-06, "loss": 0.0734, "step": 10388 }, { "epoch": 98.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7205882352941175, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6533333333333333, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12969285249710083, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8228882833787465, "eval_overall_precision": 0.7783505154639175, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3311, "eval_samples_per_second": 564.732, "eval_steps_per_second": 9.06, "step": 10388 }, { "epoch": 99.0, "grad_norm": 1.4133217334747314, "learning_rate": 5.000000000000001e-07, "loss": 0.0764, "step": 10494 }, { "epoch": 99.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7205882352941175, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6533333333333333, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8958990536277602, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8658536585365854, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12929300963878632, "eval_overall_accuracy": 0.9630914045082982, "eval_overall_f1": 0.8228882833787465, "eval_overall_precision": 0.7783505154639175, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3318, "eval_samples_per_second": 563.529, "eval_steps_per_second": 9.041, "step": 10494 }, { "epoch": 100.0, "grad_norm": 1.631034255027771, "learning_rate": 0.0, "loss": 0.0766, "step": 10600 }, { "epoch": 100.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.7205882352941175, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6533333333333333, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8924050632911392, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8650306748466258, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.12939806282520294, "eval_overall_accuracy": 0.9628436958137231, "eval_overall_f1": 0.8212824010914053, "eval_overall_precision": 0.7777777777777778, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3317, "eval_samples_per_second": 563.771, "eval_steps_per_second": 9.044, "step": 10600 }, { "epoch": 100.0, "step": 10600, "total_flos": 4572869307067182.0, "train_loss": 0.1344640188846948, "train_runtime": 602.8103, "train_samples_per_second": 279.856, "train_steps_per_second": 17.584 } ], "logging_steps": 500, "max_steps": 10600, "num_input_tokens_seen": 0, "num_train_epochs": 100, "save_steps": 500, "total_flos": 4572869307067182.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }