{ "best_metric": 0.9118745580382054, "best_model_checkpoint": "output/lkt/modernbert_encoder_lt_sv_seq_8192_sv-kt-25-v1_fold1/checkpoint-95", "epoch": 99.52892561983471, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.5289256198347108, "eval_accuracy": 0.7331542046265587, "eval_auc": 0.5143351499224811, "eval_loss": 2.040724992752075, "eval_runtime": 87.1763, "eval_samples_per_second": 17.929, "eval_steps_per_second": 0.562, "step": 1 }, { "epoch": 1.5289256198347108, "eval_accuracy": 0.7408476632776871, "eval_auc": 0.51197317676667, "eval_loss": 1.091392159461975, "eval_runtime": 87.925, "eval_samples_per_second": 17.777, "eval_steps_per_second": 0.557, "step": 2 }, { "epoch": 2.5289256198347108, "eval_accuracy": 0.73017929535671, "eval_auc": 0.5016966206823285, "eval_loss": 0.6090491414070129, "eval_runtime": 86.9757, "eval_samples_per_second": 17.971, "eval_steps_per_second": 0.563, "step": 3 }, { "epoch": 3.5289256198347108, "eval_accuracy": 0.4361599462929551, "eval_auc": 0.5311078494767836, "eval_loss": 0.7663666605949402, "eval_runtime": 87.4181, "eval_samples_per_second": 17.88, "eval_steps_per_second": 0.561, "step": 4 }, { "epoch": 4.528925619834711, "eval_accuracy": 0.46085721447071604, "eval_auc": 0.5224822287662265, "eval_loss": 0.7409077286720276, "eval_runtime": 86.8753, "eval_samples_per_second": 17.991, "eval_steps_per_second": 0.564, "step": 5 }, { "epoch": 5.528925619834711, "eval_accuracy": 0.628442663995994, "eval_auc": 0.5120648700750261, "eval_loss": 0.6520037651062012, "eval_runtime": 86.897, "eval_samples_per_second": 17.987, "eval_steps_per_second": 0.564, "step": 6 }, { "epoch": 6.528925619834711, "eval_accuracy": 0.7313003212214759, "eval_auc": 0.5084010161513127, "eval_loss": 0.6003755927085876, "eval_runtime": 87.1425, "eval_samples_per_second": 17.936, "eval_steps_per_second": 0.562, "step": 7 }, { "epoch": 7.528925619834711, "eval_accuracy": 0.7341205041242725, "eval_auc": 0.5183164612818807, "eval_loss": 0.5912967324256897, "eval_runtime": 86.9548, "eval_samples_per_second": 17.975, "eval_steps_per_second": 0.564, "step": 8 }, { "epoch": 8.52892561983471, "eval_accuracy": 0.7300701062088073, "eval_auc": 0.52227280547719, "eval_loss": 0.5922901630401611, "eval_runtime": 87.1144, "eval_samples_per_second": 17.942, "eval_steps_per_second": 0.562, "step": 9 }, { "epoch": 9.52892561983471, "eval_accuracy": 0.7153363526820958, "eval_auc": 0.519620938227537, "eval_loss": 0.6102342009544373, "eval_runtime": 87.0597, "eval_samples_per_second": 17.953, "eval_steps_per_second": 0.563, "step": 10 }, { "epoch": 10.52892561983471, "eval_accuracy": 0.7153826787512588, "eval_auc": 0.5197902476971228, "eval_loss": 0.6204488277435303, "eval_runtime": 87.5573, "eval_samples_per_second": 17.851, "eval_steps_per_second": 0.56, "step": 11 }, { "epoch": 11.52892561983471, "eval_accuracy": 0.7372763628709745, "eval_auc": 0.5502068743063773, "eval_loss": 0.5996901392936707, "eval_runtime": 86.9158, "eval_samples_per_second": 17.983, "eval_steps_per_second": 0.564, "step": 12 }, { "epoch": 12.52892561983471, "eval_accuracy": 0.734802716553477, "eval_auc": 0.5574448164030912, "eval_loss": 0.5834851861000061, "eval_runtime": 87.0333, "eval_samples_per_second": 17.959, "eval_steps_per_second": 0.563, "step": 13 }, { "epoch": 13.52892561983471, "eval_accuracy": 0.7389339804200485, "eval_auc": 0.5629247811105401, "eval_loss": 0.5793451070785522, "eval_runtime": 87.2737, "eval_samples_per_second": 17.909, "eval_steps_per_second": 0.561, "step": 14 }, { "epoch": 14.52892561983471, "eval_accuracy": 0.7359946043923619, "eval_auc": 0.5624202321874743, "eval_loss": 0.5870313048362732, "eval_runtime": 87.0434, "eval_samples_per_second": 17.957, "eval_steps_per_second": 0.563, "step": 15 }, { "epoch": 15.52892561983471, "eval_accuracy": 0.7327740912315847, "eval_auc": 0.5694981599851945, "eval_loss": 0.591485857963562, "eval_runtime": 87.1532, "eval_samples_per_second": 17.934, "eval_steps_per_second": 0.562, "step": 16 }, { "epoch": 16.52892561983471, "eval_accuracy": 0.735887601100642, "eval_auc": 0.5814546071072487, "eval_loss": 0.5902533531188965, "eval_runtime": 87.078, "eval_samples_per_second": 17.949, "eval_steps_per_second": 0.563, "step": 17 }, { "epoch": 17.52892561983471, "eval_accuracy": 0.7314548111041537, "eval_auc": 0.5843823384546716, "eval_loss": 0.5845540165901184, "eval_runtime": 87.3811, "eval_samples_per_second": 17.887, "eval_steps_per_second": 0.561, "step": 18 }, { "epoch": 18.52892561983471, "eval_accuracy": 0.7293128808573229, "eval_auc": 0.5920336706070137, "eval_loss": 0.5858773589134216, "eval_runtime": 87.4438, "eval_samples_per_second": 17.874, "eval_steps_per_second": 0.56, "step": 19 }, { "epoch": 19.52892561983471, "eval_accuracy": 0.7326169930302024, "eval_auc": 0.6028381748490906, "eval_loss": 0.5842309594154358, "eval_runtime": 87.0159, "eval_samples_per_second": 17.962, "eval_steps_per_second": 0.563, "step": 20 }, { "epoch": 20.52892561983471, "eval_accuracy": 0.7325605724567937, "eval_auc": 0.6027433860514931, "eval_loss": 0.5875126719474792, "eval_runtime": 87.2907, "eval_samples_per_second": 17.906, "eval_steps_per_second": 0.561, "step": 21 }, { "epoch": 21.52892561983471, "eval_accuracy": 0.7361993977919037, "eval_auc": 0.6182446520940644, "eval_loss": 0.5847510695457458, "eval_runtime": 87.6614, "eval_samples_per_second": 17.83, "eval_steps_per_second": 0.559, "step": 22 }, { "epoch": 22.52892561983471, "eval_accuracy": 0.7462780457118893, "eval_auc": 0.628322667206198, "eval_loss": 0.576776385307312, "eval_runtime": 87.1263, "eval_samples_per_second": 17.939, "eval_steps_per_second": 0.562, "step": 23 }, { "epoch": 23.52892561983471, "eval_accuracy": 0.7492718648581177, "eval_auc": 0.6393962023092061, "eval_loss": 0.5682416558265686, "eval_runtime": 86.9792, "eval_samples_per_second": 17.97, "eval_steps_per_second": 0.563, "step": 24 }, { "epoch": 24.52892561983471, "eval_accuracy": 0.7504689649422652, "eval_auc": 0.6549488864965162, "eval_loss": 0.5700637102127075, "eval_runtime": 87.1123, "eval_samples_per_second": 17.942, "eval_steps_per_second": 0.562, "step": 25 }, { "epoch": 25.52892561983471, "eval_accuracy": 0.7586950213489201, "eval_auc": 0.6535722943146133, "eval_loss": 0.5706145763397217, "eval_runtime": 87.1536, "eval_samples_per_second": 17.934, "eval_steps_per_second": 0.562, "step": 26 }, { "epoch": 26.52892561983471, "eval_accuracy": 0.758530292942743, "eval_auc": 0.6705127145569517, "eval_loss": 0.5659807324409485, "eval_runtime": 87.1643, "eval_samples_per_second": 17.932, "eval_steps_per_second": 0.562, "step": 27 }, { "epoch": 27.52892561983471, "eval_accuracy": 0.7626077812828601, "eval_auc": 0.6836288433471565, "eval_loss": 0.5608318448066711, "eval_runtime": 87.2631, "eval_samples_per_second": 17.911, "eval_steps_per_second": 0.562, "step": 28 }, { "epoch": 28.52892561983471, "eval_accuracy": 0.7654740908709162, "eval_auc": 0.6950791752220067, "eval_loss": 0.5519375801086426, "eval_runtime": 87.2123, "eval_samples_per_second": 17.922, "eval_steps_per_second": 0.562, "step": 29 }, { "epoch": 29.52892561983471, "eval_accuracy": 0.7769064807899759, "eval_auc": 0.7193222407927639, "eval_loss": 0.5410986542701721, "eval_runtime": 87.2445, "eval_samples_per_second": 17.915, "eval_steps_per_second": 0.562, "step": 30 }, { "epoch": 30.52892561983471, "eval_accuracy": 0.7784772688862599, "eval_auc": 0.7328795729349562, "eval_loss": 0.5388126373291016, "eval_runtime": 87.52, "eval_samples_per_second": 17.859, "eval_steps_per_second": 0.56, "step": 31 }, { "epoch": 31.52892561983471, "eval_accuracy": 0.7844610476830087, "eval_auc": 0.745194904815567, "eval_loss": 0.5323736071586609, "eval_runtime": 87.5061, "eval_samples_per_second": 17.862, "eval_steps_per_second": 0.56, "step": 32 }, { "epoch": 32.52892561983471, "eval_accuracy": 0.7868728464576855, "eval_auc": 0.7633782144987803, "eval_loss": 0.5242195129394531, "eval_runtime": 87.523, "eval_samples_per_second": 17.858, "eval_steps_per_second": 0.56, "step": 33 }, { "epoch": 33.52892561983471, "eval_accuracy": 0.801027654774835, "eval_auc": 0.7848154366679554, "eval_loss": 0.5102821588516235, "eval_runtime": 87.416, "eval_samples_per_second": 17.88, "eval_steps_per_second": 0.561, "step": 34 }, { "epoch": 34.52892561983471, "eval_accuracy": 0.8095675021895984, "eval_auc": 0.8044254944777215, "eval_loss": 0.49118560552597046, "eval_runtime": 87.4291, "eval_samples_per_second": 17.877, "eval_steps_per_second": 0.56, "step": 35 }, { "epoch": 35.52892561983471, "eval_accuracy": 0.808054481251051, "eval_auc": 0.8127819702239659, "eval_loss": 0.49621692299842834, "eval_runtime": 87.3816, "eval_samples_per_second": 17.887, "eval_steps_per_second": 0.561, "step": 36 }, { "epoch": 36.52892561983471, "eval_accuracy": 0.8106980431426545, "eval_auc": 0.8177832625735753, "eval_loss": 0.47984379529953003, "eval_runtime": 87.2654, "eval_samples_per_second": 17.911, "eval_steps_per_second": 0.562, "step": 37 }, { "epoch": 37.52892561983471, "eval_accuracy": 0.8177696435256437, "eval_auc": 0.827274967926651, "eval_loss": 0.4731045067310333, "eval_runtime": 87.7254, "eval_samples_per_second": 17.817, "eval_steps_per_second": 0.559, "step": 38 }, { "epoch": 38.52892561983471, "eval_accuracy": 0.8207282913165266, "eval_auc": 0.8375385714074627, "eval_loss": 0.47474202513694763, "eval_runtime": 87.4041, "eval_samples_per_second": 17.882, "eval_steps_per_second": 0.561, "step": 39 }, { "epoch": 39.52892561983471, "eval_accuracy": 0.8275631934595812, "eval_auc": 0.8410336724323663, "eval_loss": 0.46342405676841736, "eval_runtime": 87.8301, "eval_samples_per_second": 17.796, "eval_steps_per_second": 0.558, "step": 40 }, { "epoch": 40.52892561983471, "eval_accuracy": 0.8293715675177127, "eval_auc": 0.8441929782134601, "eval_loss": 0.45804405212402344, "eval_runtime": 87.7721, "eval_samples_per_second": 17.807, "eval_steps_per_second": 0.558, "step": 41 }, { "epoch": 41.52892561983471, "eval_accuracy": 0.8324868835257083, "eval_auc": 0.8559241505799194, "eval_loss": 0.45006582140922546, "eval_runtime": 87.8021, "eval_samples_per_second": 17.801, "eval_steps_per_second": 0.558, "step": 42 }, { "epoch": 42.52892561983471, "eval_accuracy": 0.8311230485143528, "eval_auc": 0.8587163210853371, "eval_loss": 0.4452967643737793, "eval_runtime": 87.5143, "eval_samples_per_second": 17.86, "eval_steps_per_second": 0.56, "step": 43 }, { "epoch": 43.52892561983471, "eval_accuracy": 0.8340865344380283, "eval_auc": 0.857364275353225, "eval_loss": 0.4441353678703308, "eval_runtime": 87.8752, "eval_samples_per_second": 17.787, "eval_steps_per_second": 0.558, "step": 44 }, { "epoch": 44.52892561983471, "eval_accuracy": 0.831814588274456, "eval_auc": 0.8595554642045306, "eval_loss": 0.4439769387245178, "eval_runtime": 87.3569, "eval_samples_per_second": 17.892, "eval_steps_per_second": 0.561, "step": 45 }, { "epoch": 45.52892561983471, "eval_accuracy": 0.8309363076019959, "eval_auc": 0.8652269601426812, "eval_loss": 0.44992780685424805, "eval_runtime": 87.7423, "eval_samples_per_second": 17.814, "eval_steps_per_second": 0.558, "step": 46 }, { "epoch": 46.52892561983471, "eval_accuracy": 0.8358215231927331, "eval_auc": 0.8724579775216834, "eval_loss": 0.4382532238960266, "eval_runtime": 86.7981, "eval_samples_per_second": 18.007, "eval_steps_per_second": 0.565, "step": 47 }, { "epoch": 47.52892561983471, "eval_accuracy": 0.8303788960766193, "eval_auc": 0.8759259059740221, "eval_loss": 0.44722461700439453, "eval_runtime": 87.2144, "eval_samples_per_second": 17.921, "eval_steps_per_second": 0.562, "step": 48 }, { "epoch": 48.52892561983471, "eval_accuracy": 0.8288733882900021, "eval_auc": 0.8755758560284902, "eval_loss": 0.4499235153198242, "eval_runtime": 87.4863, "eval_samples_per_second": 17.866, "eval_steps_per_second": 0.56, "step": 49 }, { "epoch": 49.52892561983471, "eval_accuracy": 0.8366122740047821, "eval_auc": 0.8722859993505708, "eval_loss": 0.43037721514701843, "eval_runtime": 87.3899, "eval_samples_per_second": 17.885, "eval_steps_per_second": 0.561, "step": 50 }, { "epoch": 50.52892561983471, "eval_accuracy": 0.8408468244084683, "eval_auc": 0.8780468282392765, "eval_loss": 0.42251306772232056, "eval_runtime": 88.0914, "eval_samples_per_second": 17.743, "eval_steps_per_second": 0.556, "step": 51 }, { "epoch": 51.52892561983471, "eval_accuracy": 0.8348957897380096, "eval_auc": 0.8806832163850822, "eval_loss": 0.4276401400566101, "eval_runtime": 87.1252, "eval_samples_per_second": 17.94, "eval_steps_per_second": 0.562, "step": 52 }, { "epoch": 52.52892561983471, "eval_accuracy": 0.8378014959240272, "eval_auc": 0.8808032157957699, "eval_loss": 0.4195541739463806, "eval_runtime": 87.7674, "eval_samples_per_second": 17.808, "eval_steps_per_second": 0.558, "step": 53 }, { "epoch": 53.52892561983471, "eval_accuracy": 0.8377568673783704, "eval_auc": 0.8786280513672797, "eval_loss": 0.4280298352241516, "eval_runtime": 87.7048, "eval_samples_per_second": 17.821, "eval_steps_per_second": 0.559, "step": 54 }, { "epoch": 54.52892561983471, "eval_accuracy": 0.8383378575903111, "eval_auc": 0.8820957840849988, "eval_loss": 0.42469218373298645, "eval_runtime": 87.1863, "eval_samples_per_second": 17.927, "eval_steps_per_second": 0.562, "step": 55 }, { "epoch": 55.52892561983471, "eval_accuracy": 0.842429061689127, "eval_auc": 0.8827017786870297, "eval_loss": 0.4173997938632965, "eval_runtime": 87.6623, "eval_samples_per_second": 17.83, "eval_steps_per_second": 0.559, "step": 56 }, { "epoch": 56.52892561983471, "eval_accuracy": 0.8355014687368862, "eval_auc": 0.8882257143168839, "eval_loss": 0.4334041178226471, "eval_runtime": 87.6362, "eval_samples_per_second": 17.835, "eval_steps_per_second": 0.559, "step": 57 }, { "epoch": 57.52892561983471, "eval_accuracy": 0.8325969153814089, "eval_auc": 0.8857916625601976, "eval_loss": 0.4321269392967224, "eval_runtime": 87.35, "eval_samples_per_second": 17.894, "eval_steps_per_second": 0.561, "step": 58 }, { "epoch": 58.52892561983471, "eval_accuracy": 0.8416129440020225, "eval_auc": 0.8910538928083584, "eval_loss": 0.40702491998672485, "eval_runtime": 87.8845, "eval_samples_per_second": 17.785, "eval_steps_per_second": 0.558, "step": 59 }, { "epoch": 59.52892561983471, "eval_accuracy": 0.8413397048960429, "eval_auc": 0.8893585400665207, "eval_loss": 0.4055131673812866, "eval_runtime": 88.2916, "eval_samples_per_second": 17.703, "eval_steps_per_second": 0.555, "step": 60 }, { "epoch": 60.52892561983471, "eval_accuracy": 0.8392555705604321, "eval_auc": 0.8901523827034017, "eval_loss": 0.42441731691360474, "eval_runtime": 87.7981, "eval_samples_per_second": 17.802, "eval_steps_per_second": 0.558, "step": 61 }, { "epoch": 61.52892561983471, "eval_accuracy": 0.8413905486148832, "eval_auc": 0.891842125915449, "eval_loss": 0.40616291761398315, "eval_runtime": 87.9641, "eval_samples_per_second": 17.769, "eval_steps_per_second": 0.557, "step": 62 }, { "epoch": 62.52892561983471, "eval_accuracy": 0.8435168887771352, "eval_auc": 0.8880043881473931, "eval_loss": 0.4057115912437439, "eval_runtime": 87.4566, "eval_samples_per_second": 17.872, "eval_steps_per_second": 0.56, "step": 63 }, { "epoch": 63.52892561983471, "eval_accuracy": 0.846263703952619, "eval_auc": 0.8953799373668658, "eval_loss": 0.3976118266582489, "eval_runtime": 87.9297, "eval_samples_per_second": 17.776, "eval_steps_per_second": 0.557, "step": 64 }, { "epoch": 64.52892561983471, "eval_accuracy": 0.8499107105776817, "eval_auc": 0.8947752373117648, "eval_loss": 0.39355602860450745, "eval_runtime": 87.5668, "eval_samples_per_second": 17.849, "eval_steps_per_second": 0.56, "step": 65 }, { "epoch": 65.52892561983471, "eval_accuracy": 0.8481150668847235, "eval_auc": 0.896237061343548, "eval_loss": 0.393976628780365, "eval_runtime": 87.8459, "eval_samples_per_second": 17.793, "eval_steps_per_second": 0.558, "step": 66 }, { "epoch": 66.52892561983471, "eval_accuracy": 0.8459397715472482, "eval_auc": 0.8930191170596469, "eval_loss": 0.3947405219078064, "eval_runtime": 86.8892, "eval_samples_per_second": 17.988, "eval_steps_per_second": 0.564, "step": 67 }, { "epoch": 67.52892561983471, "eval_accuracy": 0.8459760453876864, "eval_auc": 0.8953554221000491, "eval_loss": 0.3895111680030823, "eval_runtime": 87.5311, "eval_samples_per_second": 17.857, "eval_steps_per_second": 0.56, "step": 68 }, { "epoch": 68.52892561983471, "eval_accuracy": 0.8494102780117945, "eval_auc": 0.8994428285472086, "eval_loss": 0.39013946056365967, "eval_runtime": 87.6498, "eval_samples_per_second": 17.832, "eval_steps_per_second": 0.559, "step": 69 }, { "epoch": 69.52892561983471, "eval_accuracy": 0.8487719004107637, "eval_auc": 0.8975541144199808, "eval_loss": 0.3885815143585205, "eval_runtime": 87.095, "eval_samples_per_second": 17.946, "eval_steps_per_second": 0.563, "step": 70 }, { "epoch": 70.52892561983471, "eval_accuracy": 0.8476486918482375, "eval_auc": 0.8951087258228319, "eval_loss": 0.3933103084564209, "eval_runtime": 87.43, "eval_samples_per_second": 17.877, "eval_steps_per_second": 0.56, "step": 71 }, { "epoch": 71.52892561983471, "eval_accuracy": 0.8505171838505172, "eval_auc": 0.8986224830157784, "eval_loss": 0.3884218633174896, "eval_runtime": 87.2605, "eval_samples_per_second": 17.912, "eval_steps_per_second": 0.562, "step": 72 }, { "epoch": 72.52892561983471, "eval_accuracy": 0.851218487394958, "eval_auc": 0.8991789100147513, "eval_loss": 0.3868821859359741, "eval_runtime": 87.4057, "eval_samples_per_second": 17.882, "eval_steps_per_second": 0.561, "step": 73 }, { "epoch": 73.52892561983471, "eval_accuracy": 0.8519613558757392, "eval_auc": 0.898218220649988, "eval_loss": 0.3877873122692108, "eval_runtime": 87.3717, "eval_samples_per_second": 17.889, "eval_steps_per_second": 0.561, "step": 74 }, { "epoch": 74.52892561983471, "eval_accuracy": 0.8548414376321353, "eval_auc": 0.9043920962719242, "eval_loss": 0.3716762959957123, "eval_runtime": 87.7248, "eval_samples_per_second": 17.817, "eval_steps_per_second": 0.559, "step": 75 }, { "epoch": 75.52892561983471, "eval_accuracy": 0.8507235338918507, "eval_auc": 0.9019998015352945, "eval_loss": 0.3796072006225586, "eval_runtime": 87.5861, "eval_samples_per_second": 17.845, "eval_steps_per_second": 0.559, "step": 76 }, { "epoch": 76.52892561983471, "eval_accuracy": 0.8552576630752526, "eval_auc": 0.9050678522215962, "eval_loss": 0.3757629692554474, "eval_runtime": 88.0061, "eval_samples_per_second": 17.76, "eval_steps_per_second": 0.557, "step": 77 }, { "epoch": 77.52892561983471, "eval_accuracy": 0.8553914389723419, "eval_auc": 0.9055021150936422, "eval_loss": 0.37119558453559875, "eval_runtime": 87.5028, "eval_samples_per_second": 17.862, "eval_steps_per_second": 0.56, "step": 78 }, { "epoch": 78.52892561983471, "eval_accuracy": 0.8529289225897841, "eval_auc": 0.9042613508439051, "eval_loss": 0.3714446425437927, "eval_runtime": 87.2641, "eval_samples_per_second": 17.911, "eval_steps_per_second": 0.562, "step": 79 }, { "epoch": 79.52892561983471, "eval_accuracy": 0.8507856693903205, "eval_auc": 0.9015082574820903, "eval_loss": 0.3804471492767334, "eval_runtime": 87.3664, "eval_samples_per_second": 17.89, "eval_steps_per_second": 0.561, "step": 80 }, { "epoch": 80.52892561983471, "eval_accuracy": 0.8524967561006237, "eval_auc": 0.9033352494220062, "eval_loss": 0.3733759820461273, "eval_runtime": 87.4052, "eval_samples_per_second": 17.882, "eval_steps_per_second": 0.561, "step": 81 }, { "epoch": 81.52892561983471, "eval_accuracy": 0.8495783157806402, "eval_auc": 0.9056206015902386, "eval_loss": 0.3749751150608063, "eval_runtime": 87.2115, "eval_samples_per_second": 17.922, "eval_steps_per_second": 0.562, "step": 82 }, { "epoch": 82.52892561983471, "eval_accuracy": 0.8469255528152824, "eval_auc": 0.9015017576251956, "eval_loss": 0.37824445962905884, "eval_runtime": 87.3018, "eval_samples_per_second": 17.903, "eval_steps_per_second": 0.561, "step": 83 }, { "epoch": 83.52892561983471, "eval_accuracy": 0.851901323204074, "eval_auc": 0.904959278213227, "eval_loss": 0.37339141964912415, "eval_runtime": 87.5274, "eval_samples_per_second": 17.857, "eval_steps_per_second": 0.56, "step": 84 }, { "epoch": 84.52892561983471, "eval_accuracy": 0.8520324519736012, "eval_auc": 0.9043750712310512, "eval_loss": 0.37398338317871094, "eval_runtime": 87.9354, "eval_samples_per_second": 17.774, "eval_steps_per_second": 0.557, "step": 85 }, { "epoch": 85.52892561983471, "eval_accuracy": 0.8538973264716957, "eval_auc": 0.9069493908976312, "eval_loss": 0.37228140234947205, "eval_runtime": 87.9449, "eval_samples_per_second": 17.772, "eval_steps_per_second": 0.557, "step": 86 }, { "epoch": 86.52892561983471, "eval_accuracy": 0.8509990405873274, "eval_auc": 0.9069128627267412, "eval_loss": 0.3711836338043213, "eval_runtime": 87.5107, "eval_samples_per_second": 17.861, "eval_steps_per_second": 0.56, "step": 87 }, { "epoch": 87.52892561983471, "eval_accuracy": 0.8546714238300697, "eval_auc": 0.9058326445962316, "eval_loss": 0.3642977178096771, "eval_runtime": 87.7755, "eval_samples_per_second": 17.807, "eval_steps_per_second": 0.558, "step": 88 }, { "epoch": 88.52892561983471, "eval_accuracy": 0.8579306280518606, "eval_auc": 0.9092894250442615, "eval_loss": 0.36133790016174316, "eval_runtime": 87.6348, "eval_samples_per_second": 17.835, "eval_steps_per_second": 0.559, "step": 89 }, { "epoch": 89.52892561983471, "eval_accuracy": 0.8563854214503402, "eval_auc": 0.9109548936444647, "eval_loss": 0.36236608028411865, "eval_runtime": 87.4485, "eval_samples_per_second": 17.873, "eval_steps_per_second": 0.56, "step": 90 }, { "epoch": 90.52892561983471, "eval_accuracy": 0.8541448058761805, "eval_auc": 0.9055844765532028, "eval_loss": 0.364606648683548, "eval_runtime": 87.7842, "eval_samples_per_second": 17.805, "eval_steps_per_second": 0.558, "step": 91 }, { "epoch": 91.52892561983471, "eval_accuracy": 0.8555063132368927, "eval_auc": 0.9095905111982248, "eval_loss": 0.36065495014190674, "eval_runtime": 87.8589, "eval_samples_per_second": 17.79, "eval_steps_per_second": 0.558, "step": 92 }, { "epoch": 92.52892561983471, "eval_accuracy": 0.8537793259747345, "eval_auc": 0.9075183954759425, "eval_loss": 0.3644067347049713, "eval_runtime": 87.4575, "eval_samples_per_second": 17.872, "eval_steps_per_second": 0.56, "step": 93 }, { "epoch": 93.52892561983471, "eval_accuracy": 0.8566125290023202, "eval_auc": 0.9105956199515519, "eval_loss": 0.3642030656337738, "eval_runtime": 87.9636, "eval_samples_per_second": 17.769, "eval_steps_per_second": 0.557, "step": 94 }, { "epoch": 94.52892561983471, "eval_accuracy": 0.8580002500729379, "eval_auc": 0.9118745580382054, "eval_loss": 0.35949909687042236, "eval_runtime": 87.3425, "eval_samples_per_second": 17.895, "eval_steps_per_second": 0.561, "step": 95 }, { "epoch": 95.52892561983471, "eval_accuracy": 0.8576235541535226, "eval_auc": 0.9098413741505762, "eval_loss": 0.3638646602630615, "eval_runtime": 87.708, "eval_samples_per_second": 17.82, "eval_steps_per_second": 0.559, "step": 96 }, { "epoch": 96.52892561983471, "eval_accuracy": 0.85633238778575, "eval_auc": 0.9106240561108658, "eval_loss": 0.3620871901512146, "eval_runtime": 87.4841, "eval_samples_per_second": 17.866, "eval_steps_per_second": 0.56, "step": 97 }, { "epoch": 97.52892561983471, "eval_accuracy": 0.8512826919873396, "eval_auc": 0.9098123479022083, "eval_loss": 0.36590248346328735, "eval_runtime": 87.3427, "eval_samples_per_second": 17.895, "eval_steps_per_second": 0.561, "step": 98 }, { "epoch": 98.52892561983471, "eval_accuracy": 0.8521421983734384, "eval_auc": 0.9058724695907405, "eval_loss": 0.3740386664867401, "eval_runtime": 87.6579, "eval_samples_per_second": 17.831, "eval_steps_per_second": 0.559, "step": 99 }, { "epoch": 99.52892561983471, "eval_accuracy": 0.85401096163428, "eval_auc": 0.9065855978572865, "eval_loss": 0.37084951996803284, "eval_runtime": 87.5494, "eval_samples_per_second": 17.853, "eval_steps_per_second": 0.56, "step": 100 }, { "epoch": 99.52892561983471, "step": 100, "total_flos": 1.3065819223244145e+18, "train_loss": 0.5646095657348633, "train_runtime": 38955.3575, "train_samples_per_second": 9.914, "train_steps_per_second": 0.003 } ], "logging_steps": 500, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 100, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.3065819223244145e+18, "train_batch_size": 16, "trial_name": null, "trial_params": null }