| { | |
| "best_metric": 0.08124219626188278, | |
| "best_model_checkpoint": "/home1/datawork/mcontini/models/multilabel/huggingface/dinov2-large-2024_01_05-kornia_img-size518_batch-size32_epochs70_freeze/checkpoint-28496", | |
| "epoch": 114.0, | |
| "eval_steps": 500, | |
| "global_step": 31236, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.44556873691556176, | |
| "eval_f1_macro": 0.5755948244574681, | |
| "eval_f1_micro": 0.7376394107473012, | |
| "eval_loss": 0.13577787578105927, | |
| "eval_roc_auc": 0.8276012534175776, | |
| "eval_runtime": 686.0469, | |
| "eval_samples_per_second": 4.178, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.01, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.01, | |
| "loss": 0.1895, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4357990230286113, | |
| "eval_f1_macro": 0.6131029690652663, | |
| "eval_f1_micro": 0.7463369963369964, | |
| "eval_loss": 0.14224015176296234, | |
| "eval_roc_auc": 0.8432701847378548, | |
| "eval_runtime": 679.513, | |
| "eval_samples_per_second": 4.218, | |
| "eval_steps_per_second": 0.132, | |
| "learning_rate": 0.01, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.38415910676901605, | |
| "eval_f1_macro": 0.5242425898328716, | |
| "eval_f1_micro": 0.7273147345925026, | |
| "eval_loss": 0.21337130665779114, | |
| "eval_roc_auc": 0.8305454415797603, | |
| "eval_runtime": 681.6164, | |
| "eval_samples_per_second": 4.205, | |
| "eval_steps_per_second": 0.132, | |
| "learning_rate": 0.01, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 0.01, | |
| "loss": 0.1668, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4438241451500349, | |
| "eval_f1_macro": 0.5474301561230492, | |
| "eval_f1_micro": 0.7034210860994532, | |
| "eval_loss": 0.14501234889030457, | |
| "eval_roc_auc": 0.7947377699358407, | |
| "eval_runtime": 676.7895, | |
| "eval_samples_per_second": 4.235, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.01, | |
| "step": 1096 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.4438241451500349, | |
| "eval_f1_macro": 0.6194844495540315, | |
| "eval_f1_micro": 0.7611423380457615, | |
| "eval_loss": 0.13293854892253876, | |
| "eval_roc_auc": 0.8535844928345971, | |
| "eval_runtime": 676.1205, | |
| "eval_samples_per_second": 4.239, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.01, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 0.01, | |
| "loss": 0.1666, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.44452198185624564, | |
| "eval_f1_macro": 0.5624987041776927, | |
| "eval_f1_micro": 0.752847713067352, | |
| "eval_loss": 0.13243332505226135, | |
| "eval_roc_auc": 0.8411441150969292, | |
| "eval_runtime": 676.3907, | |
| "eval_samples_per_second": 4.237, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.01, | |
| "step": 1644 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.43126308443824146, | |
| "eval_f1_macro": 0.5689553622505643, | |
| "eval_f1_micro": 0.7496488764044945, | |
| "eval_loss": 0.13447266817092896, | |
| "eval_roc_auc": 0.838952950800037, | |
| "eval_runtime": 675.7851, | |
| "eval_samples_per_second": 4.241, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.01, | |
| "step": 1918 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 0.01, | |
| "loss": 0.1664, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4323098394975576, | |
| "eval_f1_macro": 0.5627920395195278, | |
| "eval_f1_micro": 0.7502482911725186, | |
| "eval_loss": 0.13808754086494446, | |
| "eval_roc_auc": 0.8397325865953646, | |
| "eval_runtime": 681.8119, | |
| "eval_samples_per_second": 4.204, | |
| "eval_steps_per_second": 0.132, | |
| "learning_rate": 0.01, | |
| "step": 2192 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.44033496161898117, | |
| "eval_f1_macro": 0.5492251158735639, | |
| "eval_f1_micro": 0.7395667604944316, | |
| "eval_loss": 0.13694943487644196, | |
| "eval_roc_auc": 0.8219722316265465, | |
| "eval_runtime": 674.9771, | |
| "eval_samples_per_second": 4.246, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.01, | |
| "step": 2466 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 0.01, | |
| "loss": 0.1656, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.4424284717376134, | |
| "eval_f1_macro": 0.528180519175626, | |
| "eval_f1_micro": 0.7326552851434799, | |
| "eval_loss": 0.13609227538108826, | |
| "eval_roc_auc": 0.821178691278072, | |
| "eval_runtime": 674.2621, | |
| "eval_samples_per_second": 4.251, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.01, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 10.95, | |
| "learning_rate": 0.01, | |
| "loss": 0.166, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.4277739009071877, | |
| "eval_f1_macro": 0.5428317486981787, | |
| "eval_f1_micro": 0.7434225844004656, | |
| "eval_loss": 0.1380929797887802, | |
| "eval_roc_auc": 0.8371006883503846, | |
| "eval_runtime": 676.158, | |
| "eval_samples_per_second": 4.239, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.01, | |
| "step": 3014 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.444870900209351, | |
| "eval_f1_macro": 0.5618568055480317, | |
| "eval_f1_micro": 0.7354685646500594, | |
| "eval_loss": 0.1344844251871109, | |
| "eval_roc_auc": 0.827911942291835, | |
| "eval_runtime": 683.7162, | |
| "eval_samples_per_second": 4.192, | |
| "eval_steps_per_second": 0.132, | |
| "learning_rate": 0.01, | |
| "step": 3288 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "learning_rate": 0.001, | |
| "loss": 0.1585, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.49023028611304953, | |
| "eval_f1_macro": 0.650060261894195, | |
| "eval_f1_micro": 0.8009333029820168, | |
| "eval_loss": 0.11546628922224045, | |
| "eval_roc_auc": 0.8745955707824836, | |
| "eval_runtime": 679.0864, | |
| "eval_samples_per_second": 4.22, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.001, | |
| "step": 3562 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.5041870202372645, | |
| "eval_f1_macro": 0.6697333276095331, | |
| "eval_f1_micro": 0.8079378774805867, | |
| "eval_loss": 0.11155486851930618, | |
| "eval_roc_auc": 0.8750976636196655, | |
| "eval_runtime": 676.6891, | |
| "eval_samples_per_second": 4.235, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.001, | |
| "step": 3836 | |
| }, | |
| { | |
| "epoch": 14.6, | |
| "learning_rate": 0.001, | |
| "loss": 0.133, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.5181437543614794, | |
| "eval_f1_macro": 0.6736053030113935, | |
| "eval_f1_micro": 0.814943326393708, | |
| "eval_loss": 0.10734836012125015, | |
| "eval_roc_auc": 0.877205285207194, | |
| "eval_runtime": 677.4924, | |
| "eval_samples_per_second": 4.23, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.001, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5083740404745289, | |
| "eval_f1_macro": 0.7055616874566738, | |
| "eval_f1_micro": 0.8238276299112801, | |
| "eval_loss": 0.10476414114236832, | |
| "eval_roc_auc": 0.8975418625131631, | |
| "eval_runtime": 687.0217, | |
| "eval_samples_per_second": 4.172, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.001, | |
| "step": 4384 | |
| }, | |
| { | |
| "epoch": 16.42, | |
| "learning_rate": 0.001, | |
| "loss": 0.1289, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5244242847173761, | |
| "eval_f1_macro": 0.6896485755961196, | |
| "eval_f1_micro": 0.820858825547487, | |
| "eval_loss": 0.10253454744815826, | |
| "eval_roc_auc": 0.8839468587595108, | |
| "eval_runtime": 684.6037, | |
| "eval_samples_per_second": 4.186, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.001, | |
| "step": 4658 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.5321004884856944, | |
| "eval_f1_macro": 0.7045003592264228, | |
| "eval_f1_micro": 0.8289563051845145, | |
| "eval_loss": 0.10259302705526352, | |
| "eval_roc_auc": 0.8916264271206406, | |
| "eval_runtime": 685.7262, | |
| "eval_samples_per_second": 4.18, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.001, | |
| "step": 4932 | |
| }, | |
| { | |
| "epoch": 18.25, | |
| "learning_rate": 0.001, | |
| "loss": 0.1227, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.5279134682484299, | |
| "eval_f1_macro": 0.6905367219275804, | |
| "eval_f1_micro": 0.8306010928961749, | |
| "eval_loss": 0.10123815387487411, | |
| "eval_roc_auc": 0.8940566516497492, | |
| "eval_runtime": 685.5377, | |
| "eval_samples_per_second": 4.181, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.001, | |
| "step": 5206 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5216329378925332, | |
| "eval_f1_macro": 0.6830881274898382, | |
| "eval_f1_micro": 0.8280441143371596, | |
| "eval_loss": 0.09970748424530029, | |
| "eval_roc_auc": 0.8930346669934526, | |
| "eval_runtime": 686.9199, | |
| "eval_samples_per_second": 4.172, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.001, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 20.07, | |
| "learning_rate": 0.001, | |
| "loss": 0.1202, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.5352407536636427, | |
| "eval_f1_macro": 0.6926783323821563, | |
| "eval_f1_micro": 0.8300336623495178, | |
| "eval_loss": 0.09886988252401352, | |
| "eval_roc_auc": 0.8896211857387517, | |
| "eval_runtime": 684.9162, | |
| "eval_samples_per_second": 4.184, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.001, | |
| "step": 5754 | |
| }, | |
| { | |
| "epoch": 21.9, | |
| "learning_rate": 0.001, | |
| "loss": 0.12, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.5209351011863224, | |
| "eval_f1_macro": 0.6961228606859606, | |
| "eval_f1_micro": 0.8279826958105646, | |
| "eval_loss": 0.09963646531105042, | |
| "eval_roc_auc": 0.8892587586568824, | |
| "eval_runtime": 686.1389, | |
| "eval_samples_per_second": 4.177, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.001, | |
| "step": 6028 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.5195394277739009, | |
| "eval_f1_macro": 0.6958628426894405, | |
| "eval_f1_micro": 0.831919078392807, | |
| "eval_loss": 0.09720779210329056, | |
| "eval_roc_auc": 0.8955944894582717, | |
| "eval_runtime": 693.3459, | |
| "eval_samples_per_second": 4.134, | |
| "eval_steps_per_second": 0.13, | |
| "learning_rate": 0.001, | |
| "step": 6302 | |
| }, | |
| { | |
| "epoch": 23.72, | |
| "learning_rate": 0.001, | |
| "loss": 0.1179, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.5212840195394278, | |
| "eval_f1_macro": 0.6881053152313114, | |
| "eval_f1_micro": 0.8270608813406306, | |
| "eval_loss": 0.10082241147756577, | |
| "eval_roc_auc": 0.8915954736236973, | |
| "eval_runtime": 682.9894, | |
| "eval_samples_per_second": 4.196, | |
| "eval_steps_per_second": 0.132, | |
| "learning_rate": 0.001, | |
| "step": 6576 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.5268667131891137, | |
| "eval_f1_macro": 0.6859679989625925, | |
| "eval_f1_micro": 0.8283316086006668, | |
| "eval_loss": 0.09828384965658188, | |
| "eval_roc_auc": 0.8862551588199984, | |
| "eval_runtime": 673.7378, | |
| "eval_samples_per_second": 4.254, | |
| "eval_steps_per_second": 0.134, | |
| "learning_rate": 0.001, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 25.55, | |
| "learning_rate": 0.001, | |
| "loss": 0.1166, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.5310537334263782, | |
| "eval_f1_macro": 0.6805616825898689, | |
| "eval_f1_micro": 0.8284274424464553, | |
| "eval_loss": 0.09853371977806091, | |
| "eval_roc_auc": 0.8875551335725609, | |
| "eval_runtime": 679.0226, | |
| "eval_samples_per_second": 4.221, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.001, | |
| "step": 7124 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.5324494068387997, | |
| "eval_f1_macro": 0.6901040821549612, | |
| "eval_f1_micro": 0.8305464575073264, | |
| "eval_loss": 0.09571811556816101, | |
| "eval_roc_auc": 0.887615396252071, | |
| "eval_runtime": 672.1908, | |
| "eval_samples_per_second": 4.264, | |
| "eval_steps_per_second": 0.134, | |
| "learning_rate": 0.001, | |
| "step": 7398 | |
| }, | |
| { | |
| "epoch": 27.37, | |
| "learning_rate": 0.001, | |
| "loss": 0.1158, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5177948360083741, | |
| "eval_f1_macro": 0.7054421966314011, | |
| "eval_f1_micro": 0.8292325882551658, | |
| "eval_loss": 0.09954769909381866, | |
| "eval_roc_auc": 0.8934873150088631, | |
| "eval_runtime": 681.7881, | |
| "eval_samples_per_second": 4.204, | |
| "eval_steps_per_second": 0.132, | |
| "learning_rate": 0.001, | |
| "step": 7672 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.5334961618981159, | |
| "eval_f1_macro": 0.7026467347883069, | |
| "eval_f1_micro": 0.8363861804655357, | |
| "eval_loss": 0.09332505613565445, | |
| "eval_roc_auc": 0.8970916521216963, | |
| "eval_runtime": 684.6938, | |
| "eval_samples_per_second": 4.186, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.001, | |
| "step": 7946 | |
| }, | |
| { | |
| "epoch": 29.2, | |
| "learning_rate": 0.001, | |
| "loss": 0.114, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.5258199581297976, | |
| "eval_f1_macro": 0.7109768073155117, | |
| "eval_f1_micro": 0.8351258454374099, | |
| "eval_loss": 0.09473367780447006, | |
| "eval_roc_auc": 0.901874991489952, | |
| "eval_runtime": 677.918, | |
| "eval_samples_per_second": 4.228, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.001, | |
| "step": 8220 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.5331472435450104, | |
| "eval_f1_macro": 0.7175382540523837, | |
| "eval_f1_micro": 0.8365119611950171, | |
| "eval_loss": 0.09674925357103348, | |
| "eval_roc_auc": 0.9045853985344947, | |
| "eval_runtime": 675.0971, | |
| "eval_samples_per_second": 4.245, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.001, | |
| "step": 8494 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "learning_rate": 0.001, | |
| "loss": 0.1134, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.5324494068387997, | |
| "eval_f1_macro": 0.6932594476375145, | |
| "eval_f1_micro": 0.8353541076487252, | |
| "eval_loss": 0.09490892291069031, | |
| "eval_roc_auc": 0.8947967085095635, | |
| "eval_runtime": 677.2028, | |
| "eval_samples_per_second": 4.232, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.001, | |
| "step": 8768 | |
| }, | |
| { | |
| "epoch": 32.85, | |
| "learning_rate": 0.001, | |
| "loss": 0.113, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.5362875087229588, | |
| "eval_f1_macro": 0.6973292248077614, | |
| "eval_f1_micro": 0.8367208672086721, | |
| "eval_loss": 0.09511947631835938, | |
| "eval_roc_auc": 0.8966987186810037, | |
| "eval_runtime": 679.2015, | |
| "eval_samples_per_second": 4.22, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.001, | |
| "step": 9042 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.5380321004884857, | |
| "eval_f1_macro": 0.6878227037845351, | |
| "eval_f1_micro": 0.8334680679062246, | |
| "eval_loss": 0.09364539384841919, | |
| "eval_roc_auc": 0.8876181367760314, | |
| "eval_runtime": 675.0346, | |
| "eval_samples_per_second": 4.246, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.001, | |
| "step": 9316 | |
| }, | |
| { | |
| "epoch": 34.67, | |
| "learning_rate": 0.001, | |
| "loss": 0.1124, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.5310537334263782, | |
| "eval_f1_macro": 0.6856042645068489, | |
| "eval_f1_micro": 0.833974649162517, | |
| "eval_loss": 0.09358564764261246, | |
| "eval_roc_auc": 0.8944494841237697, | |
| "eval_runtime": 678.2782, | |
| "eval_samples_per_second": 4.225, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.001, | |
| "step": 9590 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.5453593859036985, | |
| "eval_f1_macro": 0.729828782855425, | |
| "eval_f1_micro": 0.8455960879096174, | |
| "eval_loss": 0.09342356771230698, | |
| "eval_roc_auc": 0.9030647539078717, | |
| "eval_runtime": 674.7512, | |
| "eval_samples_per_second": 4.247, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 9864 | |
| }, | |
| { | |
| "epoch": 36.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1083, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.54675505931612, | |
| "eval_f1_macro": 0.7188765655113909, | |
| "eval_f1_micro": 0.8456650022696323, | |
| "eval_loss": 0.09240464121103287, | |
| "eval_roc_auc": 0.8999478550409371, | |
| "eval_runtime": 674.676, | |
| "eval_samples_per_second": 4.248, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 10138 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.5450104675505931, | |
| "eval_f1_macro": 0.7089159960142193, | |
| "eval_f1_micro": 0.8449173647271904, | |
| "eval_loss": 0.09147636592388153, | |
| "eval_roc_auc": 0.9003695495594045, | |
| "eval_runtime": 675.4085, | |
| "eval_samples_per_second": 4.243, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 10412 | |
| }, | |
| { | |
| "epoch": 38.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1034, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.5484996510816469, | |
| "eval_f1_macro": 0.725215575661352, | |
| "eval_f1_micro": 0.8487853799866281, | |
| "eval_loss": 0.09022974222898483, | |
| "eval_roc_auc": 0.9078051247451889, | |
| "eval_runtime": 672.7306, | |
| "eval_samples_per_second": 4.26, | |
| "eval_steps_per_second": 0.134, | |
| "learning_rate": 0.0001, | |
| "step": 10686 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.5495464061409631, | |
| "eval_f1_macro": 0.7182446688615595, | |
| "eval_f1_micro": 0.8458797579322437, | |
| "eval_loss": 0.09058264642953873, | |
| "eval_roc_auc": 0.9011424061638826, | |
| "eval_runtime": 678.9298, | |
| "eval_samples_per_second": 4.221, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 10960 | |
| }, | |
| { | |
| "epoch": 40.15, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1024, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.5505931612002791, | |
| "eval_f1_macro": 0.7130026819185953, | |
| "eval_f1_micro": 0.8481005491705826, | |
| "eval_loss": 0.08943015336990356, | |
| "eval_roc_auc": 0.902018393012137, | |
| "eval_runtime": 676.4356, | |
| "eval_samples_per_second": 4.237, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 11234 | |
| }, | |
| { | |
| "epoch": 41.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1004, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.5519888346127007, | |
| "eval_f1_macro": 0.7148190184347656, | |
| "eval_f1_micro": 0.8457012282205084, | |
| "eval_loss": 0.08726447820663452, | |
| "eval_roc_auc": 0.8977194051943719, | |
| "eval_runtime": 677.9496, | |
| "eval_samples_per_second": 4.227, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 11508 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.5537334263782275, | |
| "eval_f1_macro": 0.71816969331258, | |
| "eval_f1_micro": 0.8494563389754511, | |
| "eval_loss": 0.08699071407318115, | |
| "eval_roc_auc": 0.906163507621426, | |
| "eval_runtime": 676.5268, | |
| "eval_samples_per_second": 4.236, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 11782 | |
| }, | |
| { | |
| "epoch": 43.8, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0998, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.5498953244940684, | |
| "eval_f1_macro": 0.7261208407998851, | |
| "eval_f1_micro": 0.8486114247008355, | |
| "eval_loss": 0.08676985651254654, | |
| "eval_roc_auc": 0.9033042612782081, | |
| "eval_runtime": 674.6536, | |
| "eval_samples_per_second": 4.248, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 12056 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.555129099790649, | |
| "eval_f1_macro": 0.7235580263821535, | |
| "eval_f1_micro": 0.8493258426966293, | |
| "eval_loss": 0.08680889010429382, | |
| "eval_roc_auc": 0.9052931027877648, | |
| "eval_runtime": 688.2557, | |
| "eval_samples_per_second": 4.164, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.0001, | |
| "step": 12330 | |
| }, | |
| { | |
| "epoch": 45.62, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0975, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.5512909979064898, | |
| "eval_f1_macro": 0.7317716716296281, | |
| "eval_f1_micro": 0.8489586241554526, | |
| "eval_loss": 0.0865492969751358, | |
| "eval_roc_auc": 0.9071607698668371, | |
| "eval_runtime": 684.0678, | |
| "eval_samples_per_second": 4.19, | |
| "eval_steps_per_second": 0.132, | |
| "learning_rate": 0.0001, | |
| "step": 12604 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.5547801814375436, | |
| "eval_f1_macro": 0.7390020274567815, | |
| "eval_f1_micro": 0.8512299882858259, | |
| "eval_loss": 0.08599700033664703, | |
| "eval_roc_auc": 0.908765101440927, | |
| "eval_runtime": 688.2365, | |
| "eval_samples_per_second": 4.164, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.0001, | |
| "step": 12878 | |
| }, | |
| { | |
| "epoch": 47.45, | |
| "learning_rate": 0.0001, | |
| "loss": 0.099, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5558269364968598, | |
| "eval_f1_macro": 0.7360003523455093, | |
| "eval_f1_micro": 0.8509512552065742, | |
| "eval_loss": 0.08596429973840714, | |
| "eval_roc_auc": 0.9055422308395834, | |
| "eval_runtime": 686.3198, | |
| "eval_samples_per_second": 4.176, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.0001, | |
| "step": 13152 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.5547801814375436, | |
| "eval_f1_macro": 0.7361919298080869, | |
| "eval_f1_micro": 0.849985959000281, | |
| "eval_loss": 0.08584348857402802, | |
| "eval_roc_auc": 0.9057525299940252, | |
| "eval_runtime": 688.3813, | |
| "eval_samples_per_second": 4.163, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.0001, | |
| "step": 13426 | |
| }, | |
| { | |
| "epoch": 49.27, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0972, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.5586182833217027, | |
| "eval_f1_macro": 0.725712332481399, | |
| "eval_f1_micro": 0.8505096262740656, | |
| "eval_loss": 0.08557379245758057, | |
| "eval_roc_auc": 0.9032805341102342, | |
| "eval_runtime": 685.8179, | |
| "eval_samples_per_second": 4.179, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.0001, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.557920446615492, | |
| "eval_f1_macro": 0.7408593608052999, | |
| "eval_f1_micro": 0.8500254194204373, | |
| "eval_loss": 0.08562461286783218, | |
| "eval_roc_auc": 0.9038335718454608, | |
| "eval_runtime": 683.3234, | |
| "eval_samples_per_second": 4.194, | |
| "eval_steps_per_second": 0.132, | |
| "learning_rate": 0.0001, | |
| "step": 13974 | |
| }, | |
| { | |
| "epoch": 51.09, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0957, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.5568736915561758, | |
| "eval_f1_macro": 0.7232142709265429, | |
| "eval_f1_micro": 0.8507868221442318, | |
| "eval_loss": 0.08591117709875107, | |
| "eval_roc_auc": 0.9035466101391771, | |
| "eval_runtime": 693.4248, | |
| "eval_samples_per_second": 4.133, | |
| "eval_steps_per_second": 0.13, | |
| "learning_rate": 0.0001, | |
| "step": 14248 | |
| }, | |
| { | |
| "epoch": 52.92, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0964, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.5628053035589672, | |
| "eval_f1_macro": 0.7275870481420489, | |
| "eval_f1_micro": 0.852056338028169, | |
| "eval_loss": 0.08490145951509476, | |
| "eval_roc_auc": 0.9058454914515268, | |
| "eval_runtime": 691.5127, | |
| "eval_samples_per_second": 4.145, | |
| "eval_steps_per_second": 0.13, | |
| "learning_rate": 0.0001, | |
| "step": 14522 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.5537334263782275, | |
| "eval_f1_macro": 0.7394514344990791, | |
| "eval_f1_micro": 0.85390386218394, | |
| "eval_loss": 0.08516541868448257, | |
| "eval_roc_auc": 0.9115532672468961, | |
| "eval_runtime": 698.0325, | |
| "eval_samples_per_second": 4.106, | |
| "eval_steps_per_second": 0.129, | |
| "learning_rate": 0.0001, | |
| "step": 14796 | |
| }, | |
| { | |
| "epoch": 54.74, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0955, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.5565247732030705, | |
| "eval_f1_macro": 0.7354184764103003, | |
| "eval_f1_micro": 0.8511167656205825, | |
| "eval_loss": 0.08514942973852158, | |
| "eval_roc_auc": 0.904089479088129, | |
| "eval_runtime": 681.3519, | |
| "eval_samples_per_second": 4.206, | |
| "eval_steps_per_second": 0.132, | |
| "learning_rate": 0.0001, | |
| "step": 15070 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.5572226099092812, | |
| "eval_f1_macro": 0.736739641327092, | |
| "eval_f1_micro": 0.8529461421576904, | |
| "eval_loss": 0.08491206169128418, | |
| "eval_roc_auc": 0.9066984002032717, | |
| "eval_runtime": 677.9791, | |
| "eval_samples_per_second": 4.227, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 15344 | |
| }, | |
| { | |
| "epoch": 56.57, | |
| "learning_rate": 0.0001, | |
| "loss": 0.095, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.5537334263782275, | |
| "eval_f1_macro": 0.7241830253482859, | |
| "eval_f1_micro": 0.8493824336688013, | |
| "eval_loss": 0.0848437026143074, | |
| "eval_roc_auc": 0.8993941682342463, | |
| "eval_runtime": 677.1333, | |
| "eval_samples_per_second": 4.233, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 15618 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.5593161200279134, | |
| "eval_f1_macro": 0.7363418087082886, | |
| "eval_f1_micro": 0.8511604153662826, | |
| "eval_loss": 0.08454328030347824, | |
| "eval_roc_auc": 0.9029315644433922, | |
| "eval_runtime": 675.3593, | |
| "eval_samples_per_second": 4.244, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 15892 | |
| }, | |
| { | |
| "epoch": 58.39, | |
| "learning_rate": 0.0001, | |
| "loss": 0.093, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.560711793440335, | |
| "eval_f1_macro": 0.73901392865669, | |
| "eval_f1_micro": 0.8530955471527739, | |
| "eval_loss": 0.08396653085947037, | |
| "eval_roc_auc": 0.9058246057741859, | |
| "eval_runtime": 679.8275, | |
| "eval_samples_per_second": 4.216, | |
| "eval_steps_per_second": 0.132, | |
| "learning_rate": 0.0001, | |
| "step": 16166 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.5561758548499651, | |
| "eval_f1_macro": 0.7472770304573509, | |
| "eval_f1_micro": 0.852848189028787, | |
| "eval_loss": 0.08474517613649368, | |
| "eval_roc_auc": 0.9116141789978706, | |
| "eval_runtime": 679.8207, | |
| "eval_samples_per_second": 4.216, | |
| "eval_steps_per_second": 0.132, | |
| "learning_rate": 0.0001, | |
| "step": 16440 | |
| }, | |
| { | |
| "epoch": 60.22, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0936, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.552337752965806, | |
| "eval_f1_macro": 0.7425280881449604, | |
| "eval_f1_micro": 0.8516569637259293, | |
| "eval_loss": 0.08434043824672699, | |
| "eval_roc_auc": 0.9078005379735077, | |
| "eval_runtime": 678.8837, | |
| "eval_samples_per_second": 4.222, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 16714 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.5540823447313329, | |
| "eval_f1_macro": 0.7455853496732745, | |
| "eval_f1_micro": 0.8515365097265295, | |
| "eval_loss": 0.08436089754104614, | |
| "eval_roc_auc": 0.905273313320008, | |
| "eval_runtime": 684.8061, | |
| "eval_samples_per_second": 4.185, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.0001, | |
| "step": 16988 | |
| }, | |
| { | |
| "epoch": 62.04, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0932, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.5575715282623867, | |
| "eval_f1_macro": 0.7344319075168565, | |
| "eval_f1_micro": 0.8535319341006545, | |
| "eval_loss": 0.0839960053563118, | |
| "eval_roc_auc": 0.9061600170593289, | |
| "eval_runtime": 676.8011, | |
| "eval_samples_per_second": 4.235, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 17262 | |
| }, | |
| { | |
| "epoch": 63.87, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0933, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.5614096301465457, | |
| "eval_f1_macro": 0.7405199466064576, | |
| "eval_f1_micro": 0.8543109759531453, | |
| "eval_loss": 0.08395348489284515, | |
| "eval_roc_auc": 0.907220383474883, | |
| "eval_runtime": 676.0097, | |
| "eval_samples_per_second": 4.24, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 17536 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.557920446615492, | |
| "eval_f1_macro": 0.7354221702015719, | |
| "eval_f1_micro": 0.8506689439225733, | |
| "eval_loss": 0.08403661847114563, | |
| "eval_roc_auc": 0.9015583167344123, | |
| "eval_runtime": 675.0487, | |
| "eval_samples_per_second": 4.246, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 17810 | |
| }, | |
| { | |
| "epoch": 65.69, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0921, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.5568736915561758, | |
| "eval_f1_macro": 0.7296578358578595, | |
| "eval_f1_micro": 0.852865023077789, | |
| "eval_loss": 0.08408054709434509, | |
| "eval_roc_auc": 0.9065963661690798, | |
| "eval_runtime": 680.0166, | |
| "eval_samples_per_second": 4.215, | |
| "eval_steps_per_second": 0.132, | |
| "learning_rate": 0.0001, | |
| "step": 18084 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.5540823447313329, | |
| "eval_f1_macro": 0.7392975848141861, | |
| "eval_f1_micro": 0.8539689628223736, | |
| "eval_loss": 0.08376849442720413, | |
| "eval_roc_auc": 0.9100385075348831, | |
| "eval_runtime": 675.941, | |
| "eval_samples_per_second": 4.24, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 18358 | |
| }, | |
| { | |
| "epoch": 67.52, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0913, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.5572226099092812, | |
| "eval_f1_macro": 0.7403483881006915, | |
| "eval_f1_micro": 0.854102492299076, | |
| "eval_loss": 0.08355987071990967, | |
| "eval_roc_auc": 0.9089826269243382, | |
| "eval_runtime": 676.7975, | |
| "eval_samples_per_second": 4.235, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 18632 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.5582693649685974, | |
| "eval_f1_macro": 0.7494443807338856, | |
| "eval_f1_micro": 0.8547792062604807, | |
| "eval_loss": 0.08346723765134811, | |
| "eval_roc_auc": 0.9100283387486087, | |
| "eval_runtime": 675.2406, | |
| "eval_samples_per_second": 4.244, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 18906 | |
| }, | |
| { | |
| "epoch": 69.34, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0911, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.5561758548499651, | |
| "eval_f1_macro": 0.7486606655073544, | |
| "eval_f1_micro": 0.8551793496480055, | |
| "eval_loss": 0.08306006342172623, | |
| "eval_roc_auc": 0.9104037761073852, | |
| "eval_runtime": 675.6626, | |
| "eval_samples_per_second": 4.242, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 0.0001, | |
| "step": 19180 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.557920446615492, | |
| "eval_f1_macro": 0.74841480686329, | |
| "eval_f1_micro": 0.8557041347283614, | |
| "eval_loss": 0.08348394185304642, | |
| "eval_roc_auc": 0.9102149107350765, | |
| "eval_runtime": 688.9991, | |
| "eval_samples_per_second": 4.16, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.0001, | |
| "step": 19454 | |
| }, | |
| { | |
| "epoch": 71.17, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0907, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.5610607117934403, | |
| "eval_f1_macro": 0.7445560004670461, | |
| "eval_f1_micro": 0.8531667140017041, | |
| "eval_loss": 0.08317266404628754, | |
| "eval_roc_auc": 0.9036835353705291, | |
| "eval_runtime": 686.0467, | |
| "eval_samples_per_second": 4.178, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.0001, | |
| "step": 19728 | |
| }, | |
| { | |
| "epoch": 72.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0905, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.5575715282623867, | |
| "eval_f1_macro": 0.7511661878734329, | |
| "eval_f1_micro": 0.8557848235754626, | |
| "eval_loss": 0.0826636552810669, | |
| "eval_roc_auc": 0.9104516775814524, | |
| "eval_runtime": 696.2462, | |
| "eval_samples_per_second": 4.116, | |
| "eval_steps_per_second": 0.129, | |
| "learning_rate": 0.0001, | |
| "step": 20002 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.5589672016748081, | |
| "eval_f1_macro": 0.7519078199055363, | |
| "eval_f1_micro": 0.8547880690737834, | |
| "eval_loss": 0.08345863223075867, | |
| "eval_roc_auc": 0.9089978296204139, | |
| "eval_runtime": 684.5044, | |
| "eval_samples_per_second": 4.187, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.0001, | |
| "step": 20276 | |
| }, | |
| { | |
| "epoch": 74.82, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0896, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.5565247732030705, | |
| "eval_f1_macro": 0.7427640048071817, | |
| "eval_f1_micro": 0.8535384963511908, | |
| "eval_loss": 0.08291995525360107, | |
| "eval_roc_auc": 0.9052642407433178, | |
| "eval_runtime": 693.0369, | |
| "eval_samples_per_second": 4.135, | |
| "eval_steps_per_second": 0.13, | |
| "learning_rate": 0.0001, | |
| "step": 20550 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.5642009769713887, | |
| "eval_f1_macro": 0.7449358839801685, | |
| "eval_f1_micro": 0.8560516708789666, | |
| "eval_loss": 0.08278567343950272, | |
| "eval_roc_auc": 0.9091009598641902, | |
| "eval_runtime": 689.5027, | |
| "eval_samples_per_second": 4.157, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 0.0001, | |
| "step": 20824 | |
| }, | |
| { | |
| "epoch": 76.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.089, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.5603628750872296, | |
| "eval_f1_macro": 0.7507123347472292, | |
| "eval_f1_micro": 0.8567585743106928, | |
| "eval_loss": 0.08268015086650848, | |
| "eval_roc_auc": 0.9102413784270108, | |
| "eval_runtime": 691.3385, | |
| "eval_samples_per_second": 4.146, | |
| "eval_steps_per_second": 0.13, | |
| "learning_rate": 0.0001, | |
| "step": 21098 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.557920446615492, | |
| "eval_f1_macro": 0.7435504236075495, | |
| "eval_f1_micro": 0.8528667079277555, | |
| "eval_loss": 0.0833190307021141, | |
| "eval_roc_auc": 0.9067310989812636, | |
| "eval_runtime": 698.1968, | |
| "eval_samples_per_second": 4.105, | |
| "eval_steps_per_second": 0.129, | |
| "learning_rate": 0.0001, | |
| "step": 21372 | |
| }, | |
| { | |
| "epoch": 78.47, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0892, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.5589672016748081, | |
| "eval_f1_macro": 0.7501683098189544, | |
| "eval_f1_micro": 0.8540393754243042, | |
| "eval_loss": 0.08301213383674622, | |
| "eval_roc_auc": 0.905519599881194, | |
| "eval_runtime": 693.3725, | |
| "eval_samples_per_second": 4.133, | |
| "eval_steps_per_second": 0.13, | |
| "learning_rate": 0.0001, | |
| "step": 21646 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.5600139567341242, | |
| "eval_f1_macro": 0.7461247141006309, | |
| "eval_f1_micro": 0.8548240635641317, | |
| "eval_loss": 0.08266153186559677, | |
| "eval_roc_auc": 0.9048757931076342, | |
| "eval_runtime": 692.1533, | |
| "eval_samples_per_second": 4.141, | |
| "eval_steps_per_second": 0.13, | |
| "learning_rate": 1e-05, | |
| "step": 21920 | |
| }, | |
| { | |
| "epoch": 80.29, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0879, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.560711793440335, | |
| "eval_f1_macro": 0.7542778186740821, | |
| "eval_f1_micro": 0.8576379185065117, | |
| "eval_loss": 0.08230110257863998, | |
| "eval_roc_auc": 0.9116332184274908, | |
| "eval_runtime": 691.9752, | |
| "eval_samples_per_second": 4.142, | |
| "eval_steps_per_second": 0.13, | |
| "learning_rate": 1e-05, | |
| "step": 22194 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.5631542219120725, | |
| "eval_f1_macro": 0.7536111063550082, | |
| "eval_f1_micro": 0.8576225654801881, | |
| "eval_loss": 0.08222728967666626, | |
| "eval_roc_auc": 0.9111816666216643, | |
| "eval_runtime": 688.2687, | |
| "eval_samples_per_second": 4.164, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 1e-05, | |
| "step": 22468 | |
| }, | |
| { | |
| "epoch": 82.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0867, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.5624563852058618, | |
| "eval_f1_macro": 0.7519980936807484, | |
| "eval_f1_micro": 0.8553623024191264, | |
| "eval_loss": 0.08224428445100784, | |
| "eval_roc_auc": 0.9057647902327958, | |
| "eval_runtime": 675.1087, | |
| "eval_samples_per_second": 4.245, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 1e-05, | |
| "step": 22742 | |
| }, | |
| { | |
| "epoch": 83.94, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0864, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.5638520586182834, | |
| "eval_f1_macro": 0.751088987860079, | |
| "eval_f1_micro": 0.8550642905481616, | |
| "eval_loss": 0.08214889466762543, | |
| "eval_roc_auc": 0.9071555340236915, | |
| "eval_runtime": 684.6287, | |
| "eval_samples_per_second": 4.186, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 1e-05, | |
| "step": 23016 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.5617585484996511, | |
| "eval_f1_macro": 0.7532850236770345, | |
| "eval_f1_micro": 0.8560117633751838, | |
| "eval_loss": 0.08197268098592758, | |
| "eval_roc_auc": 0.9067157953185159, | |
| "eval_runtime": 685.9962, | |
| "eval_samples_per_second": 4.178, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 1e-05, | |
| "step": 23290 | |
| }, | |
| { | |
| "epoch": 85.77, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0865, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.5600139567341242, | |
| "eval_f1_macro": 0.7495768803790436, | |
| "eval_f1_micro": 0.8553152949167893, | |
| "eval_loss": 0.0821395218372345, | |
| "eval_roc_auc": 0.9060269285615214, | |
| "eval_runtime": 676.0683, | |
| "eval_samples_per_second": 4.239, | |
| "eval_steps_per_second": 0.133, | |
| "learning_rate": 1e-05, | |
| "step": 23564 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.5586182833217027, | |
| "eval_f1_macro": 0.7518865385404515, | |
| "eval_f1_micro": 0.8558878188883257, | |
| "eval_loss": 0.08169202506542206, | |
| "eval_roc_auc": 0.9080884949227034, | |
| "eval_runtime": 683.932, | |
| "eval_samples_per_second": 4.19, | |
| "eval_steps_per_second": 0.132, | |
| "learning_rate": 1e-05, | |
| "step": 23838 | |
| }, | |
| { | |
| "epoch": 87.59, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0868, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.5621074668527565, | |
| "eval_f1_macro": 0.7526313975322289, | |
| "eval_f1_micro": 0.8558239036198839, | |
| "eval_loss": 0.08171343803405762, | |
| "eval_roc_auc": 0.9081685470699702, | |
| "eval_runtime": 687.6304, | |
| "eval_samples_per_second": 4.168, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 1e-05, | |
| "step": 24112 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.5638520586182834, | |
| "eval_f1_macro": 0.7535945449960157, | |
| "eval_f1_micro": 0.8569978572234127, | |
| "eval_loss": 0.08180436491966248, | |
| "eval_roc_auc": 0.9082570227224631, | |
| "eval_runtime": 685.8987, | |
| "eval_samples_per_second": 4.178, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 1e-05, | |
| "step": 24386 | |
| }, | |
| { | |
| "epoch": 89.42, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0857, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.5617585484996511, | |
| "eval_f1_macro": 0.7521712775972677, | |
| "eval_f1_micro": 0.8557914296976182, | |
| "eval_loss": 0.08184907585382462, | |
| "eval_roc_auc": 0.9080738403314199, | |
| "eval_runtime": 2199.2107, | |
| "eval_samples_per_second": 1.303, | |
| "eval_steps_per_second": 0.041, | |
| "learning_rate": 1e-05, | |
| "step": 24660 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.5631542219120725, | |
| "eval_f1_macro": 0.7496381590553177, | |
| "eval_f1_micro": 0.856868937514099, | |
| "eval_loss": 0.08175913989543915, | |
| "eval_roc_auc": 0.9081476613926293, | |
| "eval_runtime": 685.7142, | |
| "eval_samples_per_second": 4.18, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 1e-05, | |
| "step": 24934 | |
| }, | |
| { | |
| "epoch": 91.24, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0862, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.5648988136775994, | |
| "eval_f1_macro": 0.7551884126903309, | |
| "eval_f1_micro": 0.8566131025957974, | |
| "eval_loss": 0.08205177634954453, | |
| "eval_roc_auc": 0.9092762668547993, | |
| "eval_runtime": 688.0975, | |
| "eval_samples_per_second": 4.165, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 1e-05, | |
| "step": 25208 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.5628053035589672, | |
| "eval_f1_macro": 0.7579638727848569, | |
| "eval_f1_micro": 0.8588642195693407, | |
| "eval_loss": 0.08153587579727173, | |
| "eval_roc_auc": 0.9129889700545543, | |
| "eval_runtime": 686.4355, | |
| "eval_samples_per_second": 4.175, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 1e-05, | |
| "step": 25482 | |
| }, | |
| { | |
| "epoch": 93.07, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0851, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.5600139567341242, | |
| "eval_f1_macro": 0.7565755790887538, | |
| "eval_f1_micro": 0.8570630932439977, | |
| "eval_loss": 0.0816139355301857, | |
| "eval_roc_auc": 0.911680023691974, | |
| "eval_runtime": 686.9681, | |
| "eval_samples_per_second": 4.172, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 1e-05, | |
| "step": 25756 | |
| }, | |
| { | |
| "epoch": 94.89, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0854, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.5631542219120725, | |
| "eval_f1_macro": 0.7553215815461111, | |
| "eval_f1_micro": 0.8563582357226924, | |
| "eval_loss": 0.08153104782104492, | |
| "eval_roc_auc": 0.9100006738804182, | |
| "eval_runtime": 792.6719, | |
| "eval_samples_per_second": 3.616, | |
| "eval_steps_per_second": 0.114, | |
| "learning_rate": 1e-05, | |
| "step": 26030 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.5621074668527565, | |
| "eval_f1_macro": 0.7584737150271473, | |
| "eval_f1_micro": 0.8576208800401539, | |
| "eval_loss": 0.081536203622818, | |
| "eval_roc_auc": 0.9123942619313182, | |
| "eval_runtime": 689.1211, | |
| "eval_samples_per_second": 4.159, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 1e-05, | |
| "step": 26304 | |
| }, | |
| { | |
| "epoch": 96.72, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0854, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.5628053035589672, | |
| "eval_f1_macro": 0.7578675241138624, | |
| "eval_f1_micro": 0.8575591168889387, | |
| "eval_loss": 0.0817214846611023, | |
| "eval_roc_auc": 0.9107227875201963, | |
| "eval_runtime": 791.8215, | |
| "eval_samples_per_second": 3.62, | |
| "eval_steps_per_second": 0.114, | |
| "learning_rate": 1e-05, | |
| "step": 26578 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.5638520586182834, | |
| "eval_f1_macro": 0.7526862577512524, | |
| "eval_f1_micro": 0.8570947651910453, | |
| "eval_loss": 0.08161807805299759, | |
| "eval_roc_auc": 0.9100232038721354, | |
| "eval_runtime": 689.7672, | |
| "eval_samples_per_second": 4.155, | |
| "eval_steps_per_second": 0.13, | |
| "learning_rate": 1e-05, | |
| "step": 26852 | |
| }, | |
| { | |
| "epoch": 98.54, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0855, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.5642009769713887, | |
| "eval_f1_macro": 0.7556285126609241, | |
| "eval_f1_micro": 0.8578035986237239, | |
| "eval_loss": 0.08184286206960678, | |
| "eval_roc_auc": 0.9086036990034648, | |
| "eval_runtime": 685.3364, | |
| "eval_samples_per_second": 4.182, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 1e-05, | |
| "step": 27126 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.5631542219120725, | |
| "eval_f1_macro": 0.753319281703831, | |
| "eval_f1_micro": 0.857062242537103, | |
| "eval_loss": 0.08161789923906326, | |
| "eval_roc_auc": 0.9080422377630124, | |
| "eval_runtime": 680.1579, | |
| "eval_samples_per_second": 4.214, | |
| "eval_steps_per_second": 0.132, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 100.36, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.0837, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 101.0, | |
| "eval_accuracy": 0.5645498953244941, | |
| "eval_f1_macro": 0.7553159980269647, | |
| "eval_f1_micro": 0.8575286968264686, | |
| "eval_loss": 0.08142262697219849, | |
| "eval_roc_auc": 0.9092807526598085, | |
| "eval_runtime": 693.9432, | |
| "eval_samples_per_second": 4.13, | |
| "eval_steps_per_second": 0.13, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 27674 | |
| }, | |
| { | |
| "epoch": 102.0, | |
| "eval_accuracy": 0.5652477320307048, | |
| "eval_f1_macro": 0.7559444477928223, | |
| "eval_f1_micro": 0.8571749382438806, | |
| "eval_loss": 0.08143333345651627, | |
| "eval_roc_auc": 0.9098557722819599, | |
| "eval_runtime": 695.0171, | |
| "eval_samples_per_second": 4.124, | |
| "eval_steps_per_second": 0.129, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 27948 | |
| }, | |
| { | |
| "epoch": 102.19, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.085, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 103.0, | |
| "eval_accuracy": 0.5645498953244941, | |
| "eval_f1_macro": 0.7565514506209431, | |
| "eval_f1_micro": 0.8570462613399448, | |
| "eval_loss": 0.08157742768526077, | |
| "eval_roc_auc": 0.9085338156424723, | |
| "eval_runtime": 710.2061, | |
| "eval_samples_per_second": 4.035, | |
| "eval_steps_per_second": 0.127, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 28222 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "eval_accuracy": 0.5645498953244941, | |
| "eval_f1_macro": 0.7572978759334409, | |
| "eval_f1_micro": 0.857623884617543, | |
| "eval_loss": 0.08124219626188278, | |
| "eval_roc_auc": 0.9102385369363781, | |
| "eval_runtime": 703.8703, | |
| "eval_samples_per_second": 4.072, | |
| "eval_steps_per_second": 0.128, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 28496 | |
| }, | |
| { | |
| "epoch": 104.01, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.0844, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "eval_accuracy": 0.5603628750872296, | |
| "eval_f1_macro": 0.7588882568234135, | |
| "eval_f1_micro": 0.8571747004736696, | |
| "eval_loss": 0.08170615136623383, | |
| "eval_roc_auc": 0.9124156957134514, | |
| "eval_runtime": 693.4706, | |
| "eval_samples_per_second": 4.133, | |
| "eval_steps_per_second": 0.13, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 28770 | |
| }, | |
| { | |
| "epoch": 105.84, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.0845, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 106.0, | |
| "eval_accuracy": 0.5628053035589672, | |
| "eval_f1_macro": 0.7514055460147794, | |
| "eval_f1_micro": 0.8562891131532955, | |
| "eval_loss": 0.08144387602806091, | |
| "eval_roc_auc": 0.9079250010327448, | |
| "eval_runtime": 693.924, | |
| "eval_samples_per_second": 4.13, | |
| "eval_steps_per_second": 0.13, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 29044 | |
| }, | |
| { | |
| "epoch": 107.0, | |
| "eval_accuracy": 0.5635031402651779, | |
| "eval_f1_macro": 0.7490061784836257, | |
| "eval_f1_micro": 0.8557823129251702, | |
| "eval_loss": 0.08168599754571915, | |
| "eval_roc_auc": 0.9057833825242961, | |
| "eval_runtime": 697.3665, | |
| "eval_samples_per_second": 4.11, | |
| "eval_steps_per_second": 0.129, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 29318 | |
| }, | |
| { | |
| "epoch": 107.66, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.0854, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "eval_accuracy": 0.5642009769713887, | |
| "eval_f1_macro": 0.7569164155873785, | |
| "eval_f1_micro": 0.8569341425039335, | |
| "eval_loss": 0.08160943537950516, | |
| "eval_roc_auc": 0.9094149373671999, | |
| "eval_runtime": 692.7895, | |
| "eval_samples_per_second": 4.137, | |
| "eval_steps_per_second": 0.13, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 29592 | |
| }, | |
| { | |
| "epoch": 109.0, | |
| "eval_accuracy": 0.5652477320307048, | |
| "eval_f1_macro": 0.7558234898859766, | |
| "eval_f1_micro": 0.8573669467787115, | |
| "eval_loss": 0.08135490119457245, | |
| "eval_roc_auc": 0.9106934783376293, | |
| "eval_runtime": 695.7903, | |
| "eval_samples_per_second": 4.119, | |
| "eval_steps_per_second": 0.129, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 29866 | |
| }, | |
| { | |
| "epoch": 109.49, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.0854, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "eval_accuracy": 0.5638520586182834, | |
| "eval_f1_macro": 0.7564667466516518, | |
| "eval_f1_micro": 0.8577973962116557, | |
| "eval_loss": 0.08132224529981613, | |
| "eval_roc_auc": 0.9118372864958749, | |
| "eval_runtime": 682.0266, | |
| "eval_samples_per_second": 4.202, | |
| "eval_steps_per_second": 0.132, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 30140 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "eval_accuracy": 0.5638520586182834, | |
| "eval_f1_macro": 0.7579481466413214, | |
| "eval_f1_micro": 0.8576381122791322, | |
| "eval_loss": 0.0814104825258255, | |
| "eval_roc_auc": 0.911498485615307, | |
| "eval_runtime": 686.5544, | |
| "eval_samples_per_second": 4.174, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "step": 30414 | |
| }, | |
| { | |
| "epoch": 111.31, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "loss": 0.0851, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "eval_accuracy": 0.5631542219120725, | |
| "eval_f1_macro": 0.7575801018117111, | |
| "eval_f1_micro": 0.8580721134974485, | |
| "eval_loss": 0.08170080929994583, | |
| "eval_roc_auc": 0.91075603440298, | |
| "eval_runtime": 746.778, | |
| "eval_samples_per_second": 3.838, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "step": 30688 | |
| }, | |
| { | |
| "epoch": 113.0, | |
| "eval_accuracy": 0.5614096301465457, | |
| "eval_f1_macro": 0.7562692232145891, | |
| "eval_f1_micro": 0.8583059164668487, | |
| "eval_loss": 0.081505186855793, | |
| "eval_roc_auc": 0.912813663063945, | |
| "eval_runtime": 687.4479, | |
| "eval_samples_per_second": 4.169, | |
| "eval_steps_per_second": 0.131, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "step": 30962 | |
| }, | |
| { | |
| "epoch": 113.14, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "loss": 0.0848, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 114.0, | |
| "eval_accuracy": 0.5655966503838102, | |
| "eval_f1_macro": 0.7560403631861836, | |
| "eval_f1_micro": 0.8563654914408797, | |
| "eval_loss": 0.08186182379722595, | |
| "eval_roc_auc": 0.9061407756963643, | |
| "eval_runtime": 731.2304, | |
| "eval_samples_per_second": 3.919, | |
| "eval_steps_per_second": 0.123, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "step": 31236 | |
| }, | |
| { | |
| "epoch": 114.0, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "step": 31236, | |
| "total_flos": 1.4819663325231928e+21, | |
| "train_loss": 0.033337813025782426, | |
| "train_runtime": 131818.0427, | |
| "train_samples_per_second": 9.311, | |
| "train_steps_per_second": 0.291 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 38360, | |
| "num_train_epochs": 140, | |
| "save_steps": 500, | |
| "total_flos": 1.4819663325231928e+21, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |