{ "best_metric": 0.681284212993957, "best_model_checkpoint": "/bigwork/nhwpziet/appropriateness-style-transfer/data/models/multilabel-debertav3-conservative/fold0/fold0.0/checkpoint-1250", "epoch": 18.229166666666668, "global_step": 1750, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 2.6, "eval_Appropriateness_macroF1": 0.6499349052509764, "eval_Appropriateness_precision": 0.663745660824655, "eval_Appropriateness_recall": 0.6624663978494624, "eval_Commitment_macroF1": 0.48068768147730356, "eval_Commitment_precision": 0.6111764705882352, "eval_Commitment_recall": 0.5880626223091976, "eval_Committed Openness_macroF1": 0.5892457057505601, "eval_Committed Openness_precision": 0.6571428571428571, "eval_Committed Openness_recall": 0.6731601731601732, "eval_Committed Seriousness_macroF1": 0.6182764603817235, "eval_Committed Seriousness_precision": 0.6083439761600681, "eval_Committed Seriousness_recall": 0.77997799779978, "eval_Emotional Intensity_macroF1": 0.574343023682986, "eval_Emotional Intensity_precision": 0.5939801879603759, "eval_Emotional Intensity_recall": 0.6541666666666667, "eval_Emotional Typology_macroF1": 0.5431247790738777, "eval_Emotional Typology_precision": 0.6008333333333333, "eval_Emotional Typology_recall": 0.65625, "eval_Emotions_macroF1": 0.530779524924724, "eval_Emotions_precision": 0.5917211328976035, "eval_Emotions_recall": 0.6085163418909165, "eval_Intelligibility_macroF1": 0.6261437908496732, "eval_Intelligibility_precision": 0.625, "eval_Intelligibility_recall": 0.6328999638858794, "eval_Intelligible Organization_macroF1": 0.5602359709424212, "eval_Intelligible Organization_precision": 0.5534420289855072, "eval_Intelligible Organization_recall": 0.6025789626195306, "eval_Intelligible Position_macroF1": 0.6010933398284214, "eval_Intelligible Position_precision": 0.5964783923519656, "eval_Intelligible Position_recall": 0.6235632183908046, "eval_Intelligible Relevance_macroF1": 0.528479573942976, "eval_Intelligible Relevance_precision": 0.5802107728337236, "eval_Intelligible Relevance_recall": 0.6112658080983873, "eval_Not classified_macroF1": 0.4965675057208238, "eval_Not classified_precision": 0.49318181818181817, "eval_Not classified_recall": 0.5, "eval_Orthography_macroF1": 0.5675185241191593, "eval_Orthography_precision": 0.5641177243463408, "eval_Orthography_recall": 0.7877358490566038, "eval_Other_macroF1": 0.6333333333333333, "eval_Other_precision": 0.6477093206951027, "eval_Other_recall": 0.6220095693779903, "eval_loss": 1.0271475315093994, "eval_mean_F1": 0.5714117228056399, "eval_mean_precision": 0.5990774054501132, "eval_mean_recall": 0.6430466836503852, "eval_runtime": 2.5376, "eval_samples_per_second": 86.696, "eval_steps_per_second": 5.517, "step": 250 }, { "epoch": 5.21, "learning_rate": 2.483101851851852e-06, "loss": 0.9858, "step": 500 }, { "epoch": 5.21, "eval_Appropriateness_macroF1": 0.665130632415188, "eval_Appropriateness_precision": 0.7096551724137932, "eval_Appropriateness_recall": 0.6915322580645161, "eval_Commitment_macroF1": 0.7509093975090939, "eval_Commitment_precision": 0.7618189102564102, "eval_Commitment_recall": 0.7435933277420557, "eval_Committed Openness_macroF1": 0.7043862174872828, "eval_Committed Openness_precision": 0.7002627627627627, "eval_Committed Openness_recall": 0.7099567099567099, "eval_Committed Seriousness_macroF1": 0.7135416666666666, "eval_Committed Seriousness_precision": 0.6732215153267784, "eval_Committed Seriousness_recall": 0.8294829482948295, "eval_Emotional Intensity_macroF1": 0.679588485017508, "eval_Emotional Intensity_precision": 0.6660829284826573, "eval_Emotional Intensity_recall": 0.7041666666666666, "eval_Emotional Typology_macroF1": 0.6851543561435789, "eval_Emotional Typology_precision": 0.672855451512216, "eval_Emotional Typology_recall": 0.7073863636363636, "eval_Emotions_macroF1": 0.714746897409436, "eval_Emotions_precision": 0.7212543554006968, "eval_Emotions_recall": 0.709506134653057, "eval_Intelligibility_macroF1": 0.634313796343138, "eval_Intelligibility_precision": 0.6514896304874198, "eval_Intelligibility_recall": 0.6299205489346335, "eval_Intelligible Organization_macroF1": 0.5869602321215225, "eval_Intelligible Organization_precision": 0.5771428571428572, "eval_Intelligible Organization_recall": 0.676035931614025, "eval_Intelligible Position_macroF1": 0.6466018283244253, "eval_Intelligible Position_precision": 0.6393939393939394, "eval_Intelligible Position_recall": 0.6580459770114943, "eval_Intelligible Relevance_macroF1": 0.6084230126783319, "eval_Intelligible Relevance_precision": 0.6041666666666666, "eval_Intelligible Relevance_recall": 0.6160227404571296, "eval_Not classified_macroF1": 0.48717948717948717, "eval_Not classified_precision": 0.49292452830188677, "eval_Not classified_recall": 0.4815668202764977, "eval_Orthography_macroF1": 0.5915611814345991, "eval_Orthography_precision": 0.5756166002067642, "eval_Orthography_recall": 0.8018867924528301, "eval_Other_macroF1": 0.6100006112843084, "eval_Other_precision": 0.5868421052631579, "eval_Other_recall": 0.7153110047846889, "eval_loss": 0.9632763266563416, "eval_mean_F1": 0.6484641287153262, "eval_mean_precision": 0.6451948159727147, "eval_mean_recall": 0.6910295874675355, "eval_runtime": 2.3793, "eval_samples_per_second": 92.466, "eval_steps_per_second": 5.884, "step": 500 }, { "epoch": 7.81, "eval_Appropriateness_macroF1": 0.6687855470056876, "eval_Appropriateness_precision": 0.7210960960960962, "eval_Appropriateness_recall": 0.6979166666666667, "eval_Commitment_macroF1": 0.7442119098170052, "eval_Commitment_precision": 0.778556095356457, "eval_Commitment_recall": 0.7297549156648961, "eval_Committed Openness_macroF1": 0.6861471861471862, "eval_Committed Openness_precision": 0.6861471861471862, "eval_Committed Openness_recall": 0.6861471861471862, "eval_Committed Seriousness_macroF1": 0.7894233070112466, "eval_Committed Seriousness_precision": 0.758078231292517, "eval_Committed Seriousness_recall": 0.8338833883388339, "eval_Emotional Intensity_macroF1": 0.671913835956918, "eval_Emotional Intensity_precision": 0.665079365079365, "eval_Emotional Intensity_recall": 0.6805555555555556, "eval_Emotional Typology_macroF1": 0.6675863881224543, "eval_Emotional Typology_precision": 0.6706795077581594, "eval_Emotional Typology_recall": 0.6647727272727273, "eval_Emotions_macroF1": 0.6727568690185514, "eval_Emotions_precision": 0.6957771114442779, "eval_Emotions_recall": 0.6615630477368801, "eval_Intelligibility_macroF1": 0.6358605696781047, "eval_Intelligibility_precision": 0.6641622415546267, "eval_Intelligibility_recall": 0.6311845431563741, "eval_Intelligible Organization_macroF1": 0.6031397786553557, "eval_Intelligible Organization_precision": 0.5866545893719807, "eval_Intelligible Organization_recall": 0.6663286004056794, "eval_Intelligible Position_macroF1": 0.6535852713178294, "eval_Intelligible Position_precision": 0.6494117647058824, "eval_Intelligible Position_recall": 0.6586706646676661, "eval_Intelligible Relevance_macroF1": 0.6247058823529412, "eval_Intelligible Relevance_precision": 0.6265664160401002, "eval_Intelligible Relevance_recall": 0.6230421162547859, "eval_Not classified_macroF1": 0.46987951807228917, "eval_Not classified_precision": 0.49242424242424243, "eval_Not classified_recall": 0.44930875576036866, "eval_Orthography_macroF1": 0.6369636963696369, "eval_Orthography_precision": 0.6019345238095238, "eval_Orthography_recall": 0.8231132075471699, "eval_Other_macroF1": 0.6201803184346825, "eval_Other_precision": 0.5941220238095238, "eval_Other_recall": 0.7200956937799043, "eval_loss": 1.0039398670196533, "eval_mean_F1": 0.6532242912828492, "eval_mean_precision": 0.6564778139207099, "eval_mean_recall": 0.6804526477824782, "eval_runtime": 2.3736, "eval_samples_per_second": 92.687, "eval_steps_per_second": 5.898, "step": 750 }, { "epoch": 10.42, "learning_rate": 1.6439814814814818e-06, "loss": 0.6344, "step": 1000 }, { "epoch": 10.42, "eval_Appropriateness_macroF1": 0.7227215438335501, "eval_Appropriateness_precision": 0.7335093454027324, "eval_Appropriateness_recall": 0.7340389784946236, "eval_Commitment_macroF1": 0.7471264367816092, "eval_Commitment_precision": 0.7442557442557443, "eval_Commitment_recall": 0.75062901873078, "eval_Committed Openness_macroF1": 0.7027304072313857, "eval_Committed Openness_precision": 0.6964285714285714, "eval_Committed Openness_recall": 0.7164502164502164, "eval_Committed Seriousness_macroF1": 0.7809150020502607, "eval_Committed Seriousness_precision": 0.7471794871794872, "eval_Committed Seriousness_recall": 0.8314081408140814, "eval_Emotional Intensity_macroF1": 0.7108560413563481, "eval_Emotional Intensity_precision": 0.6917723476647077, "eval_Emotional Intensity_recall": 0.7583333333333333, "eval_Emotional Typology_macroF1": 0.6484848484848484, "eval_Emotional Typology_precision": 0.6385281385281385, "eval_Emotional Typology_recall": 0.6818181818181819, "eval_Emotions_macroF1": 0.7161290322580646, "eval_Emotions_precision": 0.7097610135329686, "eval_Emotions_recall": 0.7253325085060316, "eval_Intelligibility_macroF1": 0.6560919540229884, "eval_Intelligibility_precision": 0.6597222222222222, "eval_Intelligibility_recall": 0.653665583243048, "eval_Intelligible Organization_macroF1": 0.6163150492264416, "eval_Intelligible Organization_precision": 0.5989583333333333, "eval_Intelligible Organization_recall": 0.6541582150101419, "eval_Intelligible Position_macroF1": 0.6809374637428935, "eval_Intelligible Position_precision": 0.6711672473867596, "eval_Intelligible Position_recall": 0.6964017991004497, "eval_Intelligible Relevance_macroF1": 0.6410148436677545, "eval_Intelligible Relevance_precision": 0.6337918251877865, "eval_Intelligible Relevance_recall": 0.6591251885369533, "eval_Not classified_macroF1": 0.4835680751173709, "eval_Not classified_precision": 0.49282296650717705, "eval_Not classified_recall": 0.47465437788018433, "eval_Orthography_macroF1": 0.6474358974358975, "eval_Orthography_precision": 0.6151960784313726, "eval_Orthography_recall": 0.7216981132075472, "eval_Other_macroF1": 0.6251457268406422, "eval_Other_precision": 0.607843137254902, "eval_Other_recall": 0.65311004784689, "eval_loss": 1.042500615119934, "eval_mean_F1": 0.6699623087178611, "eval_mean_precision": 0.6600668898797073, "eval_mean_recall": 0.6936302644980331, "eval_runtime": 2.3751, "eval_samples_per_second": 92.628, "eval_steps_per_second": 5.895, "step": 1000 }, { "epoch": 13.02, "eval_Appropriateness_macroF1": 0.7133461562325495, "eval_Appropriateness_precision": 0.7343254138433828, "eval_Appropriateness_recall": 0.729502688172043, "eval_Commitment_macroF1": 0.7317334894156667, "eval_Commitment_precision": 0.7467780183524075, "eval_Commitment_recall": 0.7230453825365762, "eval_Committed Openness_macroF1": 0.6888108477221735, "eval_Committed Openness_precision": 0.6873065015479876, "eval_Committed Openness_recall": 0.6904761904761905, "eval_Committed Seriousness_macroF1": 0.8377037086714506, "eval_Committed Seriousness_precision": 0.8296674522126211, "eval_Committed Seriousness_recall": 0.8462596259625963, "eval_Emotional Intensity_macroF1": 0.7021316792090431, "eval_Emotional Intensity_precision": 0.68795683954055, "eval_Emotional Intensity_recall": 0.725, "eval_Emotional Typology_macroF1": 0.6717985439789951, "eval_Emotional Typology_precision": 0.6619812583668006, "eval_Emotional Typology_recall": 0.6875, "eval_Emotions_macroF1": 0.7263898811886428, "eval_Emotions_precision": 0.7332317073170731, "eval_Emotions_recall": 0.7208475100525827, "eval_Intelligibility_macroF1": 0.6780801872988002, "eval_Intelligibility_precision": 0.7053571428571428, "eval_Intelligibility_recall": 0.670278078728783, "eval_Intelligible Organization_macroF1": 0.6212121212121213, "eval_Intelligible Organization_precision": 0.6037228938783343, "eval_Intelligible Organization_recall": 0.6566212691973341, "eval_Intelligible Position_macroF1": 0.6759941089837997, "eval_Intelligible Position_precision": 0.6702053602506091, "eval_Intelligible Position_recall": 0.6832833583208395, "eval_Intelligible Relevance_macroF1": 0.6514073348506237, "eval_Intelligible Relevance_precision": 0.6504120879120879, "eval_Intelligible Relevance_recall": 0.6524538809606684, "eval_Not classified_macroF1": 0.48598130841121495, "eval_Not classified_precision": 0.4928909952606635, "eval_Not classified_recall": 0.4792626728110599, "eval_Orthography_macroF1": 0.6974621827728466, "eval_Orthography_precision": 0.6722488038277512, "eval_Orthography_recall": 0.7334905660377358, "eval_Other_macroF1": 0.6559274319674695, "eval_Other_precision": 0.6498397435897436, "eval_Other_recall": 0.6626794258373205, "eval_loss": 1.1269534826278687, "eval_mean_F1": 0.681284212993957, "eval_mean_precision": 0.6804231584826539, "eval_mean_recall": 0.690050046363838, "eval_runtime": 2.3748, "eval_samples_per_second": 92.64, "eval_steps_per_second": 5.895, "step": 1250 }, { "epoch": 15.62, "learning_rate": 8.048611111111111e-07, "loss": 0.4806, "step": 1500 }, { "epoch": 15.62, "eval_Appropriateness_macroF1": 0.7136304469100602, "eval_Appropriateness_precision": 0.7265263157894737, "eval_Appropriateness_recall": 0.7259744623655914, "eval_Commitment_macroF1": 0.7376972530683812, "eval_Commitment_precision": 0.7385510510510511, "eval_Commitment_recall": 0.7368837946137359, "eval_Committed Openness_macroF1": 0.6961904761904762, "eval_Committed Openness_precision": 0.6914105886708626, "eval_Committed Openness_recall": 0.7034632034632035, "eval_Committed Seriousness_macroF1": 0.8271798900235664, "eval_Committed Seriousness_precision": 0.8125, "eval_Committed Seriousness_recall": 0.8437843784378438, "eval_Emotional Intensity_macroF1": 0.715986019710948, "eval_Emotional Intensity_precision": 0.7007193409908342, "eval_Emotional Intensity_recall": 0.7402777777777778, "eval_Emotional Typology_macroF1": 0.6764705882352942, "eval_Emotional Typology_precision": 0.6652874564459931, "eval_Emotional Typology_recall": 0.6960227272727273, "eval_Emotions_macroF1": 0.7250000000000001, "eval_Emotions_precision": 0.7274449942099168, "eval_Emotions_recall": 0.7227549231879575, "eval_Intelligibility_macroF1": 0.655406195207481, "eval_Intelligibility_precision": 0.6635937957272462, "eval_Intelligibility_recall": 0.6514084507042254, "eval_Intelligible Organization_macroF1": 0.6212121212121213, "eval_Intelligible Organization_precision": 0.6037228938783343, "eval_Intelligible Organization_recall": 0.6566212691973341, "eval_Intelligible Position_macroF1": 0.6520167212744323, "eval_Intelligible Position_precision": 0.6427083333333333, "eval_Intelligible Position_recall": 0.6711644177911045, "eval_Intelligible Relevance_macroF1": 0.6329781508987191, "eval_Intelligible Relevance_precision": 0.626731371954302, "eval_Intelligible Relevance_recall": 0.6454345051630119, "eval_Not classified_macroF1": 0.48598130841121495, "eval_Not classified_precision": 0.4928909952606635, "eval_Not classified_recall": 0.4792626728110599, "eval_Orthography_macroF1": 0.6524486571879936, "eval_Orthography_precision": 0.638095238095238, "eval_Orthography_recall": 0.6709905660377358, "eval_Other_macroF1": 0.6249573815206273, "eval_Other_precision": 0.6309523809523809, "eval_Other_recall": 0.6196172248803828, "eval_loss": 1.1886050701141357, "eval_mean_F1": 0.6726539435608083, "eval_mean_precision": 0.6686524825971165, "eval_mean_recall": 0.6831185981216922, "eval_runtime": 2.3741, "eval_samples_per_second": 92.666, "eval_steps_per_second": 5.897, "step": 1500 }, { "epoch": 18.23, "eval_Appropriateness_macroF1": 0.7089947089947091, "eval_Appropriateness_precision": 0.7166666666666667, "eval_Appropriateness_recall": 0.7184139784946236, "eval_Commitment_macroF1": 0.7352832284339134, "eval_Commitment_precision": 0.7337931034482759, "eval_Commitment_recall": 0.7369303885937937, "eval_Committed Openness_macroF1": 0.684019684019684, "eval_Committed Openness_precision": 0.6788211788211789, "eval_Committed Openness_recall": 0.6937229437229437, "eval_Committed Seriousness_macroF1": 0.8075, "eval_Committed Seriousness_precision": 0.7828282828282829, "eval_Committed Seriousness_recall": 0.8388338833883389, "eval_Emotional Intensity_macroF1": 0.715986019710948, "eval_Emotional Intensity_precision": 0.7007193409908342, "eval_Emotional Intensity_recall": 0.7402777777777778, "eval_Emotional Typology_macroF1": 0.6764705882352942, "eval_Emotional Typology_precision": 0.6652874564459931, "eval_Emotional Typology_recall": 0.6960227272727273, "eval_Emotions_macroF1": 0.7293122856619283, "eval_Emotions_precision": 0.7331843337590465, "eval_Emotions_recall": 0.7258995772760078, "eval_Intelligibility_macroF1": 0.666206896551724, "eval_Intelligibility_precision": 0.670045045045045, "eval_Intelligibility_recall": 0.6635969664138678, "eval_Intelligible Organization_macroF1": 0.6464646464646464, "eval_Intelligible Organization_precision": 0.6248320859719823, "eval_Intelligible Organization_recall": 0.6884960880904085, "eval_Intelligible Position_macroF1": 0.6686656261124346, "eval_Intelligible Position_precision": 0.6573200992555832, "eval_Intelligible Position_recall": 0.6980259870064968, "eval_Intelligible Relevance_macroF1": 0.6294346773344563, "eval_Intelligible Relevance_precision": 0.6230611647644132, "eval_Intelligible Relevance_recall": 0.646362687086669, "eval_Not classified_macroF1": 0.48598130841121495, "eval_Not classified_precision": 0.4928909952606635, "eval_Not classified_recall": 0.4792626728110599, "eval_Orthography_macroF1": 0.6974621827728466, "eval_Orthography_precision": 0.6722488038277512, "eval_Orthography_recall": 0.7334905660377358, "eval_Other_macroF1": 0.6559274319674695, "eval_Other_precision": 0.6498397435897436, "eval_Other_recall": 0.6626794258373205, "eval_loss": 1.1870639324188232, "eval_mean_F1": 0.6791220917622336, "eval_mean_precision": 0.6715384500482472, "eval_mean_recall": 0.6944296907006979, "eval_runtime": 2.3724, "eval_samples_per_second": 92.734, "eval_steps_per_second": 5.901, "step": 1750 } ], "max_steps": 1920, "num_train_epochs": 20, "total_flos": 9734558105656692.0, "trial_name": null, "trial_params": null }