| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9957679860592482, | |
| "eval_steps": 250, | |
| "global_step": 3500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0028450513887407092, | |
| "grad_norm": 0.2809712886810303, | |
| "learning_rate": 4.445629945763315e-08, | |
| "loss": 0.0202, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0056901027774814185, | |
| "grad_norm": 0.2773303985595703, | |
| "learning_rate": 8.89125989152663e-08, | |
| "loss": 0.0184, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008535154166222128, | |
| "grad_norm": 0.28651171922683716, | |
| "learning_rate": 1.3336889837289946e-07, | |
| "loss": 0.018, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011380205554962837, | |
| "grad_norm": 0.24912181496620178, | |
| "learning_rate": 1.778251978305326e-07, | |
| "loss": 0.0173, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.014225256943703546, | |
| "grad_norm": 0.2654182016849518, | |
| "learning_rate": 2.2228149728816572e-07, | |
| "loss": 0.0193, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.017070308332444255, | |
| "grad_norm": 0.2645716965198517, | |
| "learning_rate": 2.667377967457989e-07, | |
| "loss": 0.0158, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.019915359721184963, | |
| "grad_norm": 0.28719639778137207, | |
| "learning_rate": 3.1119409620343207e-07, | |
| "loss": 0.016, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.022760411109925674, | |
| "grad_norm": 0.24205148220062256, | |
| "learning_rate": 3.556503956610652e-07, | |
| "loss": 0.0139, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.02560546249866638, | |
| "grad_norm": 0.1541828215122223, | |
| "learning_rate": 4.0010669511869836e-07, | |
| "loss": 0.0143, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.028450513887407092, | |
| "grad_norm": 0.24321648478507996, | |
| "learning_rate": 4.4456299457633145e-07, | |
| "loss": 0.0138, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0312955652761478, | |
| "grad_norm": 0.13496069610118866, | |
| "learning_rate": 4.890192940339646e-07, | |
| "loss": 0.0127, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.03414061666488851, | |
| "grad_norm": 0.1574280858039856, | |
| "learning_rate": 5.334755934915978e-07, | |
| "loss": 0.0115, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03698566805362922, | |
| "grad_norm": 0.16117185354232788, | |
| "learning_rate": 5.779318929492309e-07, | |
| "loss": 0.0117, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.039830719442369926, | |
| "grad_norm": 0.11417609453201294, | |
| "learning_rate": 6.223881924068641e-07, | |
| "loss": 0.0111, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.04267577083111064, | |
| "grad_norm": 0.13975922763347626, | |
| "learning_rate": 6.668444918644972e-07, | |
| "loss": 0.0111, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.04552082221985135, | |
| "grad_norm": 0.10122673958539963, | |
| "learning_rate": 7.113007913221304e-07, | |
| "loss": 0.0106, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.048365873608592055, | |
| "grad_norm": 0.10620034486055374, | |
| "learning_rate": 7.557570907797635e-07, | |
| "loss": 0.01, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.05121092499733276, | |
| "grad_norm": 0.10404311865568161, | |
| "learning_rate": 8.002133902373967e-07, | |
| "loss": 0.0103, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.05405597638607347, | |
| "grad_norm": 0.09400220960378647, | |
| "learning_rate": 8.446696896950297e-07, | |
| "loss": 0.0106, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.056901027774814185, | |
| "grad_norm": 0.0968412309885025, | |
| "learning_rate": 8.891259891526629e-07, | |
| "loss": 0.0102, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05974607916355489, | |
| "grad_norm": 0.10527963936328888, | |
| "learning_rate": 9.335822886102961e-07, | |
| "loss": 0.0103, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.0625911305522956, | |
| "grad_norm": 0.11160361021757126, | |
| "learning_rate": 9.780385880679293e-07, | |
| "loss": 0.0109, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.06543618194103631, | |
| "grad_norm": 0.09594683349132538, | |
| "learning_rate": 1.0224948875255625e-06, | |
| "loss": 0.0099, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.06828123332977702, | |
| "grad_norm": 0.09191753715276718, | |
| "learning_rate": 1.0669511869831957e-06, | |
| "loss": 0.0086, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.07112628471851773, | |
| "grad_norm": 0.10616082698106766, | |
| "learning_rate": 1.1114074864408287e-06, | |
| "loss": 0.01, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.07112628471851773, | |
| "eval_loss": 0.04481230676174164, | |
| "eval_runtime": 8.9152, | |
| "eval_samples_per_second": 168.253, | |
| "eval_steps_per_second": 10.544, | |
| "eval_sts_dev_pearson_cosine": 0.7566652114171531, | |
| "eval_sts_dev_pearson_dot": 0.6030696212508195, | |
| "eval_sts_dev_pearson_euclidean": 0.723338411802702, | |
| "eval_sts_dev_pearson_manhattan": 0.7229820157274984, | |
| "eval_sts_dev_pearson_max": 0.7566652114171531, | |
| "eval_sts_dev_spearman_cosine": 0.7641649126837959, | |
| "eval_sts_dev_spearman_dot": 0.5924781561865081, | |
| "eval_sts_dev_spearman_euclidean": 0.7161218303280887, | |
| "eval_sts_dev_spearman_manhattan": 0.7161351439672354, | |
| "eval_sts_dev_spearman_max": 0.7641649126837959, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.07397133610725844, | |
| "grad_norm": 0.09024439752101898, | |
| "learning_rate": 1.1558637858984619e-06, | |
| "loss": 0.0098, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.07681638749599914, | |
| "grad_norm": 0.10580305010080338, | |
| "learning_rate": 1.200320085356095e-06, | |
| "loss": 0.0094, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.07966143888473985, | |
| "grad_norm": 0.07469004392623901, | |
| "learning_rate": 1.2447763848137283e-06, | |
| "loss": 0.0097, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.08250649027348056, | |
| "grad_norm": 0.08532268553972244, | |
| "learning_rate": 1.2892326842713615e-06, | |
| "loss": 0.0094, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.08535154166222128, | |
| "grad_norm": 0.11069530993700027, | |
| "learning_rate": 1.3336889837289944e-06, | |
| "loss": 0.0095, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.08819659305096199, | |
| "grad_norm": 0.14181849360466003, | |
| "learning_rate": 1.3781452831866276e-06, | |
| "loss": 0.0098, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.0910416444397027, | |
| "grad_norm": 0.10291895270347595, | |
| "learning_rate": 1.4226015826442608e-06, | |
| "loss": 0.0092, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.0938866958284434, | |
| "grad_norm": 0.09878888726234436, | |
| "learning_rate": 1.467057882101894e-06, | |
| "loss": 0.0095, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.09673174721718411, | |
| "grad_norm": 0.11313822865486145, | |
| "learning_rate": 1.511514181559527e-06, | |
| "loss": 0.0103, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.09957679860592482, | |
| "grad_norm": 0.10922758281230927, | |
| "learning_rate": 1.5559704810171602e-06, | |
| "loss": 0.0097, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.10242184999466553, | |
| "grad_norm": 0.09477540105581284, | |
| "learning_rate": 1.6004267804747934e-06, | |
| "loss": 0.0091, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.10526690138340623, | |
| "grad_norm": 0.11776648461818695, | |
| "learning_rate": 1.6448830799324264e-06, | |
| "loss": 0.0094, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.10811195277214694, | |
| "grad_norm": 0.10813190042972565, | |
| "learning_rate": 1.6893393793900594e-06, | |
| "loss": 0.0088, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.11095700416088766, | |
| "grad_norm": 0.0988766998052597, | |
| "learning_rate": 1.7337956788476928e-06, | |
| "loss": 0.009, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.11380205554962837, | |
| "grad_norm": 0.11297037452459335, | |
| "learning_rate": 1.7782519783053258e-06, | |
| "loss": 0.0098, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.11664710693836908, | |
| "grad_norm": 0.11383142322301865, | |
| "learning_rate": 1.8227082777629592e-06, | |
| "loss": 0.0083, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.11949215832710978, | |
| "grad_norm": 0.09991955757141113, | |
| "learning_rate": 1.8671645772205922e-06, | |
| "loss": 0.0099, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.12233720971585049, | |
| "grad_norm": 0.12355756759643555, | |
| "learning_rate": 1.911620876678225e-06, | |
| "loss": 0.0094, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.1251822611045912, | |
| "grad_norm": 0.13183994591236115, | |
| "learning_rate": 1.9560771761358586e-06, | |
| "loss": 0.0092, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.1280273124933319, | |
| "grad_norm": 0.09731684625148773, | |
| "learning_rate": 2.0005334755934916e-06, | |
| "loss": 0.009, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.13087236388207263, | |
| "grad_norm": 0.10299917310476303, | |
| "learning_rate": 2.044989775051125e-06, | |
| "loss": 0.0088, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.13371741527081332, | |
| "grad_norm": 0.10299093276262283, | |
| "learning_rate": 2.089446074508758e-06, | |
| "loss": 0.0092, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.13656246665955404, | |
| "grad_norm": 0.10356424003839493, | |
| "learning_rate": 2.1339023739663914e-06, | |
| "loss": 0.0083, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.13940751804829474, | |
| "grad_norm": 0.09914368391036987, | |
| "learning_rate": 2.1783586734240244e-06, | |
| "loss": 0.0089, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.14225256943703546, | |
| "grad_norm": 0.09933792054653168, | |
| "learning_rate": 2.2228149728816573e-06, | |
| "loss": 0.0089, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.14225256943703546, | |
| "eval_loss": 0.044373366981744766, | |
| "eval_runtime": 9.347, | |
| "eval_samples_per_second": 160.479, | |
| "eval_steps_per_second": 10.057, | |
| "eval_sts_dev_pearson_cosine": 0.7648120608553326, | |
| "eval_sts_dev_pearson_dot": 0.5968017368208518, | |
| "eval_sts_dev_pearson_euclidean": 0.7279404616700573, | |
| "eval_sts_dev_pearson_manhattan": 0.7275721595620177, | |
| "eval_sts_dev_pearson_max": 0.7648120608553326, | |
| "eval_sts_dev_spearman_cosine": 0.7725220548635785, | |
| "eval_sts_dev_spearman_dot": 0.5821758472972447, | |
| "eval_sts_dev_spearman_euclidean": 0.7216429612052142, | |
| "eval_sts_dev_spearman_manhattan": 0.7215280543286006, | |
| "eval_sts_dev_spearman_max": 0.7725220548635785, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.14509762082577615, | |
| "grad_norm": 0.09889407455921173, | |
| "learning_rate": 2.2672712723392908e-06, | |
| "loss": 0.0095, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.14794267221451687, | |
| "grad_norm": 0.08651946485042572, | |
| "learning_rate": 2.3117275717969237e-06, | |
| "loss": 0.0095, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.1507877236032576, | |
| "grad_norm": 0.11702941358089447, | |
| "learning_rate": 2.356183871254557e-06, | |
| "loss": 0.0091, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.1536327749919983, | |
| "grad_norm": 0.0989551842212677, | |
| "learning_rate": 2.40064017071219e-06, | |
| "loss": 0.0082, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.156477826380739, | |
| "grad_norm": 0.13362008333206177, | |
| "learning_rate": 2.445096470169823e-06, | |
| "loss": 0.0091, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.1593228777694797, | |
| "grad_norm": 0.09574282169342041, | |
| "learning_rate": 2.4895527696274565e-06, | |
| "loss": 0.0086, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.16216792915822043, | |
| "grad_norm": 0.10629838705062866, | |
| "learning_rate": 2.5340090690850895e-06, | |
| "loss": 0.009, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.16501298054696112, | |
| "grad_norm": 0.09541832655668259, | |
| "learning_rate": 2.578465368542723e-06, | |
| "loss": 0.0088, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.16785803193570184, | |
| "grad_norm": 0.1058318167924881, | |
| "learning_rate": 2.622921668000356e-06, | |
| "loss": 0.0087, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.17070308332444256, | |
| "grad_norm": 0.09181062877178192, | |
| "learning_rate": 2.667377967457989e-06, | |
| "loss": 0.0089, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.17354813471318326, | |
| "grad_norm": 0.1417740136384964, | |
| "learning_rate": 2.7118342669156223e-06, | |
| "loss": 0.009, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.17639318610192398, | |
| "grad_norm": 0.11063350737094879, | |
| "learning_rate": 2.7562905663732553e-06, | |
| "loss": 0.0088, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.17923823749066467, | |
| "grad_norm": 0.09422960132360458, | |
| "learning_rate": 2.8007468658308887e-06, | |
| "loss": 0.0088, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.1820832888794054, | |
| "grad_norm": 0.08875516802072525, | |
| "learning_rate": 2.8452031652885217e-06, | |
| "loss": 0.0081, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.18492834026814609, | |
| "grad_norm": 0.08624540269374847, | |
| "learning_rate": 2.8896594647461547e-06, | |
| "loss": 0.0082, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.1877733916568868, | |
| "grad_norm": 0.09943191707134247, | |
| "learning_rate": 2.934115764203788e-06, | |
| "loss": 0.0088, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.1906184430456275, | |
| "grad_norm": 0.08673301339149475, | |
| "learning_rate": 2.978572063661421e-06, | |
| "loss": 0.0086, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.19346349443436822, | |
| "grad_norm": 0.090702585875988, | |
| "learning_rate": 3.023028363119054e-06, | |
| "loss": 0.0085, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.19630854582310894, | |
| "grad_norm": 0.08411288261413574, | |
| "learning_rate": 3.067484662576687e-06, | |
| "loss": 0.009, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.19915359721184964, | |
| "grad_norm": 0.09590886533260345, | |
| "learning_rate": 3.1119409620343205e-06, | |
| "loss": 0.0083, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.20199864860059036, | |
| "grad_norm": 0.12336103618144989, | |
| "learning_rate": 3.1563972614919534e-06, | |
| "loss": 0.0088, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.20484369998933105, | |
| "grad_norm": 0.08143921196460724, | |
| "learning_rate": 3.200853560949587e-06, | |
| "loss": 0.0088, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.20768875137807177, | |
| "grad_norm": 0.09164416790008545, | |
| "learning_rate": 3.24530986040722e-06, | |
| "loss": 0.0087, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.21053380276681247, | |
| "grad_norm": 0.1068928986787796, | |
| "learning_rate": 3.289766159864853e-06, | |
| "loss": 0.0088, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.2133788541555532, | |
| "grad_norm": 0.08625414967536926, | |
| "learning_rate": 3.3342224593224862e-06, | |
| "loss": 0.008, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.2133788541555532, | |
| "eval_loss": 0.04651115834712982, | |
| "eval_runtime": 9.062, | |
| "eval_samples_per_second": 165.526, | |
| "eval_steps_per_second": 10.373, | |
| "eval_sts_dev_pearson_cosine": 0.769180082275811, | |
| "eval_sts_dev_pearson_dot": 0.5978598585684491, | |
| "eval_sts_dev_pearson_euclidean": 0.7336764223199792, | |
| "eval_sts_dev_pearson_manhattan": 0.7333470603433799, | |
| "eval_sts_dev_pearson_max": 0.769180082275811, | |
| "eval_sts_dev_spearman_cosine": 0.779812353514179, | |
| "eval_sts_dev_spearman_dot": 0.5813102081634336, | |
| "eval_sts_dev_spearman_euclidean": 0.7286880899787377, | |
| "eval_sts_dev_spearman_manhattan": 0.728602343078262, | |
| "eval_sts_dev_spearman_max": 0.779812353514179, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.21622390554429388, | |
| "grad_norm": 0.13600626587867737, | |
| "learning_rate": 3.378678758780119e-06, | |
| "loss": 0.0087, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.2190689569330346, | |
| "grad_norm": 0.14500027894973755, | |
| "learning_rate": 3.423135058237752e-06, | |
| "loss": 0.0087, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.22191400832177532, | |
| "grad_norm": 0.10052921622991562, | |
| "learning_rate": 3.4675913576953856e-06, | |
| "loss": 0.009, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.22475905971051602, | |
| "grad_norm": 0.08056453615427017, | |
| "learning_rate": 3.512047657153019e-06, | |
| "loss": 0.0085, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.22760411109925674, | |
| "grad_norm": 0.08645027875900269, | |
| "learning_rate": 3.5565039566106516e-06, | |
| "loss": 0.009, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.23044916248799743, | |
| "grad_norm": 0.12497828155755997, | |
| "learning_rate": 3.600960256068285e-06, | |
| "loss": 0.0082, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.23329421387673815, | |
| "grad_norm": 0.06854041665792465, | |
| "learning_rate": 3.6454165555259184e-06, | |
| "loss": 0.0073, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.23613926526547885, | |
| "grad_norm": 0.0781393051147461, | |
| "learning_rate": 3.689872854983551e-06, | |
| "loss": 0.0078, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.23898431665421957, | |
| "grad_norm": 0.09048033505678177, | |
| "learning_rate": 3.7343291544411844e-06, | |
| "loss": 0.0088, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.24182936804296026, | |
| "grad_norm": 0.10866343975067139, | |
| "learning_rate": 3.7787854538988178e-06, | |
| "loss": 0.0077, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.24467441943170098, | |
| "grad_norm": 0.08551909774541855, | |
| "learning_rate": 3.82324175335645e-06, | |
| "loss": 0.008, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.2475194708204417, | |
| "grad_norm": 0.10334528237581253, | |
| "learning_rate": 3.867698052814084e-06, | |
| "loss": 0.008, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.2503645222091824, | |
| "grad_norm": 0.10668737441301346, | |
| "learning_rate": 3.912154352271717e-06, | |
| "loss": 0.0086, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.2532095735979231, | |
| "grad_norm": 0.09555123746395111, | |
| "learning_rate": 3.9566106517293506e-06, | |
| "loss": 0.0083, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.2560546249866638, | |
| "grad_norm": 0.09091876447200775, | |
| "learning_rate": 4.001066951186983e-06, | |
| "loss": 0.0081, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.2588996763754045, | |
| "grad_norm": 0.10903967916965485, | |
| "learning_rate": 4.0455232506446165e-06, | |
| "loss": 0.0081, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.26174472776414526, | |
| "grad_norm": 0.0973634123802185, | |
| "learning_rate": 4.08997955010225e-06, | |
| "loss": 0.0077, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.26458977915288595, | |
| "grad_norm": 0.10415139049291611, | |
| "learning_rate": 4.1344358495598825e-06, | |
| "loss": 0.0083, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.26743483054162664, | |
| "grad_norm": 0.07658711075782776, | |
| "learning_rate": 4.178892149017516e-06, | |
| "loss": 0.0081, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.2702798819303674, | |
| "grad_norm": 0.08397387713193893, | |
| "learning_rate": 4.223348448475149e-06, | |
| "loss": 0.0069, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.2731249333191081, | |
| "grad_norm": 0.07437604665756226, | |
| "learning_rate": 4.267804747932783e-06, | |
| "loss": 0.0084, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.2759699847078488, | |
| "grad_norm": 0.08432639390230179, | |
| "learning_rate": 4.312261047390415e-06, | |
| "loss": 0.0075, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.2788150360965895, | |
| "grad_norm": 0.10041897743940353, | |
| "learning_rate": 4.356717346848049e-06, | |
| "loss": 0.0081, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.2816600874853302, | |
| "grad_norm": 0.08802913874387741, | |
| "learning_rate": 4.401173646305682e-06, | |
| "loss": 0.0086, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.2845051388740709, | |
| "grad_norm": 0.10163892060518265, | |
| "learning_rate": 4.445629945763315e-06, | |
| "loss": 0.0079, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2845051388740709, | |
| "eval_loss": 0.047278326004743576, | |
| "eval_runtime": 8.8427, | |
| "eval_samples_per_second": 169.631, | |
| "eval_steps_per_second": 10.63, | |
| "eval_sts_dev_pearson_cosine": 0.7757447848847815, | |
| "eval_sts_dev_pearson_dot": 0.6005493714862752, | |
| "eval_sts_dev_pearson_euclidean": 0.7410592947515149, | |
| "eval_sts_dev_pearson_manhattan": 0.7408111418700313, | |
| "eval_sts_dev_pearson_max": 0.7757447848847815, | |
| "eval_sts_dev_spearman_cosine": 0.78547452833307, | |
| "eval_sts_dev_spearman_dot": 0.582949767142449, | |
| "eval_sts_dev_spearman_euclidean": 0.7377389195713249, | |
| "eval_sts_dev_spearman_manhattan": 0.7378881505306938, | |
| "eval_sts_dev_spearman_max": 0.78547452833307, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2873501902628116, | |
| "grad_norm": 0.08119315654039383, | |
| "learning_rate": 4.490086245220948e-06, | |
| "loss": 0.0088, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.2901952416515523, | |
| "grad_norm": 0.10737801343202591, | |
| "learning_rate": 4.5345425446785815e-06, | |
| "loss": 0.0073, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.29304029304029305, | |
| "grad_norm": 0.08908016234636307, | |
| "learning_rate": 4.578998844136214e-06, | |
| "loss": 0.008, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.29588534442903375, | |
| "grad_norm": 0.08246352523565292, | |
| "learning_rate": 4.6234551435938475e-06, | |
| "loss": 0.0073, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.29873039581777444, | |
| "grad_norm": 0.08022474497556686, | |
| "learning_rate": 4.667911443051481e-06, | |
| "loss": 0.008, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.3015754472065152, | |
| "grad_norm": 0.07938782870769501, | |
| "learning_rate": 4.712367742509114e-06, | |
| "loss": 0.0074, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.3044204985952559, | |
| "grad_norm": 0.07806035876274109, | |
| "learning_rate": 4.756824041966747e-06, | |
| "loss": 0.007, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.3072655499839966, | |
| "grad_norm": 0.08204073458909988, | |
| "learning_rate": 4.80128034142438e-06, | |
| "loss": 0.0075, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.31011060137273727, | |
| "grad_norm": 0.07709292322397232, | |
| "learning_rate": 4.845736640882014e-06, | |
| "loss": 0.0077, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.312955652761478, | |
| "grad_norm": 0.09081903845071793, | |
| "learning_rate": 4.890192940339646e-06, | |
| "loss": 0.0076, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.3158007041502187, | |
| "grad_norm": 0.0967966839671135, | |
| "learning_rate": 4.93464923979728e-06, | |
| "loss": 0.0082, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.3186457555389594, | |
| "grad_norm": 0.07934273034334183, | |
| "learning_rate": 4.979105539254913e-06, | |
| "loss": 0.0073, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.32149080692770016, | |
| "grad_norm": 0.07694579660892487, | |
| "learning_rate": 5.023561838712546e-06, | |
| "loss": 0.007, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.32433585831644085, | |
| "grad_norm": 0.07895845174789429, | |
| "learning_rate": 5.068018138170179e-06, | |
| "loss": 0.0077, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.32718090970518154, | |
| "grad_norm": 0.07453285902738571, | |
| "learning_rate": 5.1124744376278124e-06, | |
| "loss": 0.0074, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.33002596109392224, | |
| "grad_norm": 0.08011069148778915, | |
| "learning_rate": 5.156930737085446e-06, | |
| "loss": 0.0076, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.332871012482663, | |
| "grad_norm": 0.08325564116239548, | |
| "learning_rate": 5.201387036543078e-06, | |
| "loss": 0.0078, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.3357160638714037, | |
| "grad_norm": 0.08292325586080551, | |
| "learning_rate": 5.245843336000712e-06, | |
| "loss": 0.0073, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.3385611152601444, | |
| "grad_norm": 0.08605830371379852, | |
| "learning_rate": 5.290299635458345e-06, | |
| "loss": 0.0077, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.3414061666488851, | |
| "grad_norm": 0.08384672552347183, | |
| "learning_rate": 5.334755934915978e-06, | |
| "loss": 0.0068, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.3442512180376258, | |
| "grad_norm": 0.10930886119604111, | |
| "learning_rate": 5.379212234373611e-06, | |
| "loss": 0.0079, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.3470962694263665, | |
| "grad_norm": 0.09999439120292664, | |
| "learning_rate": 5.423668533831245e-06, | |
| "loss": 0.0073, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.3499413208151072, | |
| "grad_norm": 0.0711401030421257, | |
| "learning_rate": 5.468124833288877e-06, | |
| "loss": 0.0075, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.35278637220384795, | |
| "grad_norm": 0.12141191959381104, | |
| "learning_rate": 5.512581132746511e-06, | |
| "loss": 0.0078, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.35563142359258865, | |
| "grad_norm": 0.08158909529447556, | |
| "learning_rate": 5.557037432204144e-06, | |
| "loss": 0.0073, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.35563142359258865, | |
| "eval_loss": 0.04716332256793976, | |
| "eval_runtime": 9.2017, | |
| "eval_samples_per_second": 163.013, | |
| "eval_steps_per_second": 10.215, | |
| "eval_sts_dev_pearson_cosine": 0.7745797315927636, | |
| "eval_sts_dev_pearson_dot": 0.6045460896217866, | |
| "eval_sts_dev_pearson_euclidean": 0.7454842399458257, | |
| "eval_sts_dev_pearson_manhattan": 0.7450723972536097, | |
| "eval_sts_dev_pearson_max": 0.7745797315927636, | |
| "eval_sts_dev_spearman_cosine": 0.7854745787288134, | |
| "eval_sts_dev_spearman_dot": 0.5869807295128947, | |
| "eval_sts_dev_spearman_euclidean": 0.7432930573697278, | |
| "eval_sts_dev_spearman_manhattan": 0.7431996603127268, | |
| "eval_sts_dev_spearman_max": 0.7854745787288134, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.35847647498132934, | |
| "grad_norm": 0.07299906015396118, | |
| "learning_rate": 5.601493731661777e-06, | |
| "loss": 0.0073, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.36132152637007003, | |
| "grad_norm": 0.08581911772489548, | |
| "learning_rate": 5.64595003111941e-06, | |
| "loss": 0.007, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.3641665777588108, | |
| "grad_norm": 0.08339793235063553, | |
| "learning_rate": 5.690406330577043e-06, | |
| "loss": 0.0068, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.3670116291475515, | |
| "grad_norm": 0.08051007241010666, | |
| "learning_rate": 5.734862630034677e-06, | |
| "loss": 0.0067, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.36985668053629217, | |
| "grad_norm": 0.08804050087928772, | |
| "learning_rate": 5.779318929492309e-06, | |
| "loss": 0.0078, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.3727017319250329, | |
| "grad_norm": 0.07765672355890274, | |
| "learning_rate": 5.823775228949943e-06, | |
| "loss": 0.0072, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.3755467833137736, | |
| "grad_norm": 0.08375009894371033, | |
| "learning_rate": 5.868231528407576e-06, | |
| "loss": 0.0071, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.3783918347025143, | |
| "grad_norm": 0.07235526293516159, | |
| "learning_rate": 5.912687827865209e-06, | |
| "loss": 0.0068, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.381236886091255, | |
| "grad_norm": 0.08521237969398499, | |
| "learning_rate": 5.957144127322842e-06, | |
| "loss": 0.0068, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.38408193747999575, | |
| "grad_norm": 0.08466946333646774, | |
| "learning_rate": 6.001600426780475e-06, | |
| "loss": 0.0074, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.38692698886873644, | |
| "grad_norm": 0.08605194091796875, | |
| "learning_rate": 6.046056726238108e-06, | |
| "loss": 0.0074, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.38977204025747714, | |
| "grad_norm": 0.10898251086473465, | |
| "learning_rate": 6.0905130256957415e-06, | |
| "loss": 0.0077, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.3926170916462179, | |
| "grad_norm": 0.07759184390306473, | |
| "learning_rate": 6.134969325153374e-06, | |
| "loss": 0.0069, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.3954621430349586, | |
| "grad_norm": 0.09418889880180359, | |
| "learning_rate": 6.1794256246110075e-06, | |
| "loss": 0.0079, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.3983071944236993, | |
| "grad_norm": 0.07198388129472733, | |
| "learning_rate": 6.223881924068641e-06, | |
| "loss": 0.0066, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.40115224581243997, | |
| "grad_norm": 0.1127256527543068, | |
| "learning_rate": 6.2683382235262735e-06, | |
| "loss": 0.008, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.4039972972011807, | |
| "grad_norm": 0.09208247065544128, | |
| "learning_rate": 6.312794522983907e-06, | |
| "loss": 0.008, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.4068423485899214, | |
| "grad_norm": 0.08608128875494003, | |
| "learning_rate": 6.35725082244154e-06, | |
| "loss": 0.0071, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.4096873999786621, | |
| "grad_norm": 0.09031302481889725, | |
| "learning_rate": 6.401707121899174e-06, | |
| "loss": 0.0066, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.4125324513674028, | |
| "grad_norm": 0.08052125573158264, | |
| "learning_rate": 6.446163421356806e-06, | |
| "loss": 0.0079, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.41537750275614355, | |
| "grad_norm": 0.07241199910640717, | |
| "learning_rate": 6.49061972081444e-06, | |
| "loss": 0.0075, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.41822255414488424, | |
| "grad_norm": 0.10164492577314377, | |
| "learning_rate": 6.535076020272072e-06, | |
| "loss": 0.0066, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.42106760553362493, | |
| "grad_norm": 0.08544593304395676, | |
| "learning_rate": 6.579532319729706e-06, | |
| "loss": 0.007, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.4239126569223657, | |
| "grad_norm": 0.11136358976364136, | |
| "learning_rate": 6.623988619187339e-06, | |
| "loss": 0.0066, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.4267577083111064, | |
| "grad_norm": 0.07907264679670334, | |
| "learning_rate": 6.6684449186449725e-06, | |
| "loss": 0.0066, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4267577083111064, | |
| "eval_loss": 0.04738680273294449, | |
| "eval_runtime": 8.8516, | |
| "eval_samples_per_second": 169.462, | |
| "eval_steps_per_second": 10.62, | |
| "eval_sts_dev_pearson_cosine": 0.7790001769076627, | |
| "eval_sts_dev_pearson_dot": 0.6181753135926376, | |
| "eval_sts_dev_pearson_euclidean": 0.7499901311425706, | |
| "eval_sts_dev_pearson_manhattan": 0.7495768624913272, | |
| "eval_sts_dev_pearson_max": 0.7790001769076627, | |
| "eval_sts_dev_spearman_cosine": 0.7907671099319872, | |
| "eval_sts_dev_spearman_dot": 0.5999468232206078, | |
| "eval_sts_dev_spearman_euclidean": 0.7486926337135288, | |
| "eval_sts_dev_spearman_manhattan": 0.7484812166973952, | |
| "eval_sts_dev_spearman_max": 0.7907671099319872, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.42960275969984707, | |
| "grad_norm": 0.0868421345949173, | |
| "learning_rate": 6.712901218102606e-06, | |
| "loss": 0.0075, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.43244781108858776, | |
| "grad_norm": 0.08232498168945312, | |
| "learning_rate": 6.757357517560238e-06, | |
| "loss": 0.0072, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.4352928624773285, | |
| "grad_norm": 0.08831491321325302, | |
| "learning_rate": 6.801813817017871e-06, | |
| "loss": 0.0072, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.4381379138660692, | |
| "grad_norm": 0.09035244584083557, | |
| "learning_rate": 6.846270116475504e-06, | |
| "loss": 0.0067, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.4409829652548099, | |
| "grad_norm": 0.09386060386896133, | |
| "learning_rate": 6.890726415933138e-06, | |
| "loss": 0.0073, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.44382801664355065, | |
| "grad_norm": 0.07013905048370361, | |
| "learning_rate": 6.935182715390771e-06, | |
| "loss": 0.0066, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.44667306803229134, | |
| "grad_norm": 0.09007762372493744, | |
| "learning_rate": 6.979639014848405e-06, | |
| "loss": 0.0063, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.44951811942103204, | |
| "grad_norm": 0.08053620904684067, | |
| "learning_rate": 7.024095314306038e-06, | |
| "loss": 0.0074, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.45236317080977273, | |
| "grad_norm": 0.09655388444662094, | |
| "learning_rate": 7.06855161376367e-06, | |
| "loss": 0.0075, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.4552082221985135, | |
| "grad_norm": 0.07398466765880585, | |
| "learning_rate": 7.113007913221303e-06, | |
| "loss": 0.0069, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.4580532735872542, | |
| "grad_norm": 0.08047506213188171, | |
| "learning_rate": 7.1574642126789366e-06, | |
| "loss": 0.0065, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.46089832497599487, | |
| "grad_norm": 0.09212318807840347, | |
| "learning_rate": 7.20192051213657e-06, | |
| "loss": 0.007, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.4637433763647356, | |
| "grad_norm": 0.08342114090919495, | |
| "learning_rate": 7.246376811594203e-06, | |
| "loss": 0.0067, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.4665884277534763, | |
| "grad_norm": 0.06753776967525482, | |
| "learning_rate": 7.290833111051837e-06, | |
| "loss": 0.0067, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.469433479142217, | |
| "grad_norm": 0.06800476461648941, | |
| "learning_rate": 7.33528941050947e-06, | |
| "loss": 0.0072, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.4722785305309577, | |
| "grad_norm": 0.08325930684804916, | |
| "learning_rate": 7.379745709967102e-06, | |
| "loss": 0.007, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.47512358191969845, | |
| "grad_norm": 0.0933527797460556, | |
| "learning_rate": 7.424202009424735e-06, | |
| "loss": 0.0078, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.47796863330843914, | |
| "grad_norm": 0.08404399454593658, | |
| "learning_rate": 7.468658308882369e-06, | |
| "loss": 0.0069, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.48081368469717983, | |
| "grad_norm": 0.08951716870069504, | |
| "learning_rate": 7.513114608340002e-06, | |
| "loss": 0.0067, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.4836587360859205, | |
| "grad_norm": 0.0985400453209877, | |
| "learning_rate": 7.5575709077976356e-06, | |
| "loss": 0.0072, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.4865037874746613, | |
| "grad_norm": 0.08860517293214798, | |
| "learning_rate": 7.602027207255269e-06, | |
| "loss": 0.0071, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.48934883886340197, | |
| "grad_norm": 0.09596813470125198, | |
| "learning_rate": 7.6464835067129e-06, | |
| "loss": 0.0069, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.49219389025214266, | |
| "grad_norm": 0.08169304579496384, | |
| "learning_rate": 7.690939806170534e-06, | |
| "loss": 0.0074, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.4950389416408834, | |
| "grad_norm": 0.08802200853824615, | |
| "learning_rate": 7.735396105628168e-06, | |
| "loss": 0.0073, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.4978839930296241, | |
| "grad_norm": 0.10039868205785751, | |
| "learning_rate": 7.779852405085801e-06, | |
| "loss": 0.0064, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.4978839930296241, | |
| "eval_loss": 0.04991479963064194, | |
| "eval_runtime": 9.5702, | |
| "eval_samples_per_second": 156.737, | |
| "eval_steps_per_second": 9.822, | |
| "eval_sts_dev_pearson_cosine": 0.7809326345755484, | |
| "eval_sts_dev_pearson_dot": 0.6075613489678238, | |
| "eval_sts_dev_pearson_euclidean": 0.7492249179863018, | |
| "eval_sts_dev_pearson_manhattan": 0.748824124010157, | |
| "eval_sts_dev_pearson_max": 0.7809326345755484, | |
| "eval_sts_dev_spearman_cosine": 0.7937663255592566, | |
| "eval_sts_dev_spearman_dot": 0.5920294462594152, | |
| "eval_sts_dev_spearman_euclidean": 0.7488717447673626, | |
| "eval_sts_dev_spearman_manhattan": 0.7486136956534813, | |
| "eval_sts_dev_spearman_max": 0.7937663255592566, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.5007290444183649, | |
| "grad_norm": 0.08260150998830795, | |
| "learning_rate": 7.824308704543434e-06, | |
| "loss": 0.0064, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.5035740958071055, | |
| "grad_norm": 0.05973382294178009, | |
| "learning_rate": 7.868765004001068e-06, | |
| "loss": 0.0068, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.5064191471958462, | |
| "grad_norm": 0.08796348422765732, | |
| "learning_rate": 7.913221303458701e-06, | |
| "loss": 0.007, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.5092641985845869, | |
| "grad_norm": 0.10702888667583466, | |
| "learning_rate": 7.957677602916333e-06, | |
| "loss": 0.0065, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.5121092499733276, | |
| "grad_norm": 0.07452105730772018, | |
| "learning_rate": 8.002133902373966e-06, | |
| "loss": 0.0073, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.5149543013620683, | |
| "grad_norm": 0.07454142719507217, | |
| "learning_rate": 8.0465902018316e-06, | |
| "loss": 0.0061, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.517799352750809, | |
| "grad_norm": 0.08079402148723602, | |
| "learning_rate": 8.091046501289233e-06, | |
| "loss": 0.0071, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.5206444041395498, | |
| "grad_norm": 0.05563436076045036, | |
| "learning_rate": 8.135502800746867e-06, | |
| "loss": 0.0058, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.5234894555282905, | |
| "grad_norm": 0.08133077621459961, | |
| "learning_rate": 8.1799591002045e-06, | |
| "loss": 0.0065, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.5263345069170312, | |
| "grad_norm": 0.06776826083660126, | |
| "learning_rate": 8.224415399662133e-06, | |
| "loss": 0.0067, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.5291795583057719, | |
| "grad_norm": 0.07137738913297653, | |
| "learning_rate": 8.268871699119765e-06, | |
| "loss": 0.0063, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.5320246096945126, | |
| "grad_norm": 0.08924838155508041, | |
| "learning_rate": 8.313327998577398e-06, | |
| "loss": 0.007, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.5348696610832533, | |
| "grad_norm": 0.10980788618326187, | |
| "learning_rate": 8.357784298035032e-06, | |
| "loss": 0.0069, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.537714712471994, | |
| "grad_norm": 0.10096590220928192, | |
| "learning_rate": 8.402240597492665e-06, | |
| "loss": 0.0073, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.5405597638607348, | |
| "grad_norm": 0.06633611768484116, | |
| "learning_rate": 8.446696896950299e-06, | |
| "loss": 0.0067, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.5434048152494755, | |
| "grad_norm": 0.0696336105465889, | |
| "learning_rate": 8.491153196407932e-06, | |
| "loss": 0.0068, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.5462498666382162, | |
| "grad_norm": 0.0785793736577034, | |
| "learning_rate": 8.535609495865565e-06, | |
| "loss": 0.0066, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.5490949180269569, | |
| "grad_norm": 0.10194658488035202, | |
| "learning_rate": 8.580065795323197e-06, | |
| "loss": 0.007, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.5519399694156976, | |
| "grad_norm": 0.07388205081224442, | |
| "learning_rate": 8.62452209478083e-06, | |
| "loss": 0.006, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.5547850208044383, | |
| "grad_norm": 0.09130030125379562, | |
| "learning_rate": 8.668978394238464e-06, | |
| "loss": 0.0062, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.557630072193179, | |
| "grad_norm": 0.06957433372735977, | |
| "learning_rate": 8.713434693696097e-06, | |
| "loss": 0.0062, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.5604751235819196, | |
| "grad_norm": 0.07989591360092163, | |
| "learning_rate": 8.75789099315373e-06, | |
| "loss": 0.0067, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.5633201749706604, | |
| "grad_norm": 0.06442303210496902, | |
| "learning_rate": 8.802347292611364e-06, | |
| "loss": 0.0063, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.5661652263594011, | |
| "grad_norm": 0.0740804597735405, | |
| "learning_rate": 8.846803592068996e-06, | |
| "loss": 0.006, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.5690102777481418, | |
| "grad_norm": 0.09938943386077881, | |
| "learning_rate": 8.89125989152663e-06, | |
| "loss": 0.0067, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5690102777481418, | |
| "eval_loss": 0.04781487584114075, | |
| "eval_runtime": 9.1274, | |
| "eval_samples_per_second": 164.341, | |
| "eval_steps_per_second": 10.299, | |
| "eval_sts_dev_pearson_cosine": 0.7835655100602283, | |
| "eval_sts_dev_pearson_dot": 0.6140666203682124, | |
| "eval_sts_dev_pearson_euclidean": 0.7549529684333918, | |
| "eval_sts_dev_pearson_manhattan": 0.7544779011570287, | |
| "eval_sts_dev_pearson_max": 0.7835655100602283, | |
| "eval_sts_dev_spearman_cosine": 0.7943462202168604, | |
| "eval_sts_dev_spearman_dot": 0.5976362907741744, | |
| "eval_sts_dev_spearman_euclidean": 0.7553189959320907, | |
| "eval_sts_dev_spearman_manhattan": 0.7548879863357982, | |
| "eval_sts_dev_spearman_max": 0.7943462202168604, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5718553291368825, | |
| "grad_norm": 0.08203410357236862, | |
| "learning_rate": 8.935716190984263e-06, | |
| "loss": 0.0076, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.5747003805256232, | |
| "grad_norm": 0.06707337498664856, | |
| "learning_rate": 8.980172490441896e-06, | |
| "loss": 0.0069, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.5775454319143639, | |
| "grad_norm": 0.07895516604185104, | |
| "learning_rate": 9.02462878989953e-06, | |
| "loss": 0.0065, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.5803904833031046, | |
| "grad_norm": 0.08560437709093094, | |
| "learning_rate": 9.069085089357163e-06, | |
| "loss": 0.007, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.5832355346918454, | |
| "grad_norm": 0.07935027033090591, | |
| "learning_rate": 9.113541388814796e-06, | |
| "loss": 0.006, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.5860805860805861, | |
| "grad_norm": 0.07242047786712646, | |
| "learning_rate": 9.157997688272428e-06, | |
| "loss": 0.0064, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.5889256374693268, | |
| "grad_norm": 0.067719466984272, | |
| "learning_rate": 9.202453987730062e-06, | |
| "loss": 0.0063, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.5917706888580675, | |
| "grad_norm": 0.06705283373594284, | |
| "learning_rate": 9.246910287187695e-06, | |
| "loss": 0.0067, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.5946157402468082, | |
| "grad_norm": 0.07053534686565399, | |
| "learning_rate": 9.291366586645328e-06, | |
| "loss": 0.0064, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.5974607916355489, | |
| "grad_norm": 0.07750871032476425, | |
| "learning_rate": 9.335822886102962e-06, | |
| "loss": 0.0062, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.6003058430242896, | |
| "grad_norm": 0.0752708688378334, | |
| "learning_rate": 9.380279185560595e-06, | |
| "loss": 0.0063, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.6031508944130304, | |
| "grad_norm": 0.06802825629711151, | |
| "learning_rate": 9.424735485018229e-06, | |
| "loss": 0.0063, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.6059959458017711, | |
| "grad_norm": 0.08155028522014618, | |
| "learning_rate": 9.46919178447586e-06, | |
| "loss": 0.0074, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.6088409971905118, | |
| "grad_norm": 0.09067688137292862, | |
| "learning_rate": 9.513648083933494e-06, | |
| "loss": 0.0067, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.6116860485792525, | |
| "grad_norm": 0.06688214093446732, | |
| "learning_rate": 9.558104383391127e-06, | |
| "loss": 0.006, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.6145310999679932, | |
| "grad_norm": 0.07848970592021942, | |
| "learning_rate": 9.60256068284876e-06, | |
| "loss": 0.0062, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.6173761513567338, | |
| "grad_norm": 0.07614806294441223, | |
| "learning_rate": 9.647016982306394e-06, | |
| "loss": 0.007, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.6202212027454745, | |
| "grad_norm": 0.07507840543985367, | |
| "learning_rate": 9.691473281764027e-06, | |
| "loss": 0.0069, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.6230662541342153, | |
| "grad_norm": 0.08833298087120056, | |
| "learning_rate": 9.73592958122166e-06, | |
| "loss": 0.007, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.625911305522956, | |
| "grad_norm": 0.07082614302635193, | |
| "learning_rate": 9.780385880679292e-06, | |
| "loss": 0.0065, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.6287563569116967, | |
| "grad_norm": 0.0823511853814125, | |
| "learning_rate": 9.824842180136926e-06, | |
| "loss": 0.0071, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.6316014083004374, | |
| "grad_norm": 0.06206200271844864, | |
| "learning_rate": 9.86929847959456e-06, | |
| "loss": 0.007, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.6344464596891781, | |
| "grad_norm": 0.0808667540550232, | |
| "learning_rate": 9.913754779052193e-06, | |
| "loss": 0.0064, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.6372915110779188, | |
| "grad_norm": 0.06442642211914062, | |
| "learning_rate": 9.958211078509826e-06, | |
| "loss": 0.0061, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.6401365624666595, | |
| "grad_norm": 0.07416217774152756, | |
| "learning_rate": 1.000266737796746e-05, | |
| "loss": 0.0062, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.6401365624666595, | |
| "eval_loss": 0.04642986133694649, | |
| "eval_runtime": 9.625, | |
| "eval_samples_per_second": 155.844, | |
| "eval_steps_per_second": 9.766, | |
| "eval_sts_dev_pearson_cosine": 0.7855623274467606, | |
| "eval_sts_dev_pearson_dot": 0.5924008322873175, | |
| "eval_sts_dev_pearson_euclidean": 0.7567766160311133, | |
| "eval_sts_dev_pearson_manhattan": 0.7563225529205405, | |
| "eval_sts_dev_pearson_max": 0.7855623274467606, | |
| "eval_sts_dev_spearman_cosine": 0.7934736270810029, | |
| "eval_sts_dev_spearman_dot": 0.5798196487719647, | |
| "eval_sts_dev_spearman_euclidean": 0.7571185706646215, | |
| "eval_sts_dev_spearman_manhattan": 0.7567665724312764, | |
| "eval_sts_dev_spearman_max": 0.7934736270810029, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.6429816138554003, | |
| "grad_norm": 0.09135396778583527, | |
| "learning_rate": 1.0047123677425091e-05, | |
| "loss": 0.0069, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.645826665244141, | |
| "grad_norm": 0.08974805474281311, | |
| "learning_rate": 1.0091579976882725e-05, | |
| "loss": 0.0062, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.6486717166328817, | |
| "grad_norm": 0.07147160917520523, | |
| "learning_rate": 1.0136036276340358e-05, | |
| "loss": 0.0063, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.6515167680216224, | |
| "grad_norm": 0.0677226111292839, | |
| "learning_rate": 1.0180492575797991e-05, | |
| "loss": 0.0063, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.6543618194103631, | |
| "grad_norm": 0.06699724495410919, | |
| "learning_rate": 1.0224948875255625e-05, | |
| "loss": 0.006, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.6572068707991038, | |
| "grad_norm": 0.07739193737506866, | |
| "learning_rate": 1.0269405174713258e-05, | |
| "loss": 0.0064, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.6600519221878445, | |
| "grad_norm": 0.04876289144158363, | |
| "learning_rate": 1.0313861474170892e-05, | |
| "loss": 0.0061, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.6628969735765853, | |
| "grad_norm": 0.0824015662074089, | |
| "learning_rate": 1.0358317773628523e-05, | |
| "loss": 0.0065, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.665742024965326, | |
| "grad_norm": 0.06627832353115082, | |
| "learning_rate": 1.0402774073086157e-05, | |
| "loss": 0.0061, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.6685870763540667, | |
| "grad_norm": 0.0926406979560852, | |
| "learning_rate": 1.044723037254379e-05, | |
| "loss": 0.0067, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.6714321277428074, | |
| "grad_norm": 0.06944271177053452, | |
| "learning_rate": 1.0491686672001424e-05, | |
| "loss": 0.0066, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.674277179131548, | |
| "grad_norm": 0.07248842716217041, | |
| "learning_rate": 1.0536142971459057e-05, | |
| "loss": 0.0068, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.6771222305202887, | |
| "grad_norm": 0.07560228556394577, | |
| "learning_rate": 1.058059927091669e-05, | |
| "loss": 0.0071, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.6799672819090294, | |
| "grad_norm": 0.07752121984958649, | |
| "learning_rate": 1.0625055570374324e-05, | |
| "loss": 0.0064, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.6828123332977702, | |
| "grad_norm": 0.091914102435112, | |
| "learning_rate": 1.0669511869831956e-05, | |
| "loss": 0.0064, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.6856573846865109, | |
| "grad_norm": 0.08635730296373367, | |
| "learning_rate": 1.0713968169289589e-05, | |
| "loss": 0.0064, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.6885024360752516, | |
| "grad_norm": 0.06619139015674591, | |
| "learning_rate": 1.0758424468747222e-05, | |
| "loss": 0.0064, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.6913474874639923, | |
| "grad_norm": 0.08025142550468445, | |
| "learning_rate": 1.0802880768204856e-05, | |
| "loss": 0.0062, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.694192538852733, | |
| "grad_norm": 0.07627130299806595, | |
| "learning_rate": 1.084733706766249e-05, | |
| "loss": 0.0067, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.6970375902414737, | |
| "grad_norm": 0.0778108760714531, | |
| "learning_rate": 1.0891793367120123e-05, | |
| "loss": 0.0062, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.6998826416302144, | |
| "grad_norm": 0.06801705807447433, | |
| "learning_rate": 1.0936249666577754e-05, | |
| "loss": 0.0059, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.7027276930189551, | |
| "grad_norm": 0.06568338721990585, | |
| "learning_rate": 1.0980705966035388e-05, | |
| "loss": 0.0063, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.7055727444076959, | |
| "grad_norm": 0.07497888058423996, | |
| "learning_rate": 1.1025162265493021e-05, | |
| "loss": 0.0055, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.7084177957964366, | |
| "grad_norm": 0.0807732567191124, | |
| "learning_rate": 1.1069618564950655e-05, | |
| "loss": 0.0074, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.7112628471851773, | |
| "grad_norm": 0.070890873670578, | |
| "learning_rate": 1.1114074864408288e-05, | |
| "loss": 0.0064, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.7112628471851773, | |
| "eval_loss": 0.04881654307246208, | |
| "eval_runtime": 9.0782, | |
| "eval_samples_per_second": 165.231, | |
| "eval_steps_per_second": 10.354, | |
| "eval_sts_dev_pearson_cosine": 0.7833801585647451, | |
| "eval_sts_dev_pearson_dot": 0.6099273388035109, | |
| "eval_sts_dev_pearson_euclidean": 0.7555637908097597, | |
| "eval_sts_dev_pearson_manhattan": 0.755336974018684, | |
| "eval_sts_dev_pearson_max": 0.7833801585647451, | |
| "eval_sts_dev_spearman_cosine": 0.7938690229216494, | |
| "eval_sts_dev_spearman_dot": 0.5921480251455608, | |
| "eval_sts_dev_spearman_euclidean": 0.7551889084831053, | |
| "eval_sts_dev_spearman_manhattan": 0.7549767859265626, | |
| "eval_sts_dev_spearman_max": 0.7938690229216494, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.714107898573918, | |
| "grad_norm": 0.06863918155431747, | |
| "learning_rate": 1.1158531163865921e-05, | |
| "loss": 0.006, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.7169529499626587, | |
| "grad_norm": 0.07372977584600449, | |
| "learning_rate": 1.1202987463323555e-05, | |
| "loss": 0.0061, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.7197980013513994, | |
| "grad_norm": 0.06173211336135864, | |
| "learning_rate": 1.1247443762781187e-05, | |
| "loss": 0.0064, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.7226430527401401, | |
| "grad_norm": 0.0746549442410469, | |
| "learning_rate": 1.129190006223882e-05, | |
| "loss": 0.0059, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.7254881041288809, | |
| "grad_norm": 0.07160431891679764, | |
| "learning_rate": 1.1336356361696453e-05, | |
| "loss": 0.0064, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.7283331555176216, | |
| "grad_norm": 0.07895245403051376, | |
| "learning_rate": 1.1380812661154087e-05, | |
| "loss": 0.0061, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.7311782069063623, | |
| "grad_norm": 0.06770409643650055, | |
| "learning_rate": 1.142526896061172e-05, | |
| "loss": 0.0062, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.734023258295103, | |
| "grad_norm": 0.07894620299339294, | |
| "learning_rate": 1.1469725260069354e-05, | |
| "loss": 0.0068, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.7368683096838436, | |
| "grad_norm": 0.07674427330493927, | |
| "learning_rate": 1.1514181559526985e-05, | |
| "loss": 0.0061, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.7397133610725843, | |
| "grad_norm": 0.09392740577459335, | |
| "learning_rate": 1.1558637858984619e-05, | |
| "loss": 0.0065, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.742558412461325, | |
| "grad_norm": 0.06918327510356903, | |
| "learning_rate": 1.1603094158442252e-05, | |
| "loss": 0.0055, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.7454034638500658, | |
| "grad_norm": 0.0910848081111908, | |
| "learning_rate": 1.1647550457899886e-05, | |
| "loss": 0.0057, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.7482485152388065, | |
| "grad_norm": 0.06995029747486115, | |
| "learning_rate": 1.1692006757357519e-05, | |
| "loss": 0.0064, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.7510935666275472, | |
| "grad_norm": 0.06808440387248993, | |
| "learning_rate": 1.1736463056815152e-05, | |
| "loss": 0.0056, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.7539386180162879, | |
| "grad_norm": 0.06680841743946075, | |
| "learning_rate": 1.1780919356272784e-05, | |
| "loss": 0.0059, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.7567836694050286, | |
| "grad_norm": 0.07254023104906082, | |
| "learning_rate": 1.1825375655730417e-05, | |
| "loss": 0.0059, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.7596287207937693, | |
| "grad_norm": 0.06777305901050568, | |
| "learning_rate": 1.1869831955188051e-05, | |
| "loss": 0.0064, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.76247377218251, | |
| "grad_norm": 0.07384537160396576, | |
| "learning_rate": 1.1914288254645684e-05, | |
| "loss": 0.0067, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.7653188235712508, | |
| "grad_norm": 0.07408931851387024, | |
| "learning_rate": 1.1958744554103318e-05, | |
| "loss": 0.0062, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.7681638749599915, | |
| "grad_norm": 0.0712476596236229, | |
| "learning_rate": 1.200320085356095e-05, | |
| "loss": 0.0056, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.7710089263487322, | |
| "grad_norm": 0.07831274718046188, | |
| "learning_rate": 1.2047657153018583e-05, | |
| "loss": 0.0063, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.7738539777374729, | |
| "grad_norm": 0.08914618194103241, | |
| "learning_rate": 1.2092113452476216e-05, | |
| "loss": 0.0064, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.7766990291262136, | |
| "grad_norm": 0.05413926765322685, | |
| "learning_rate": 1.213656975193385e-05, | |
| "loss": 0.0063, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.7795440805149543, | |
| "grad_norm": 0.07458141446113586, | |
| "learning_rate": 1.2181026051391483e-05, | |
| "loss": 0.0062, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.782389131903695, | |
| "grad_norm": 0.06790082156658173, | |
| "learning_rate": 1.2225482350849116e-05, | |
| "loss": 0.0058, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.782389131903695, | |
| "eval_loss": 0.047921594232320786, | |
| "eval_runtime": 9.1598, | |
| "eval_samples_per_second": 163.759, | |
| "eval_steps_per_second": 10.262, | |
| "eval_sts_dev_pearson_cosine": 0.7890077878318924, | |
| "eval_sts_dev_pearson_dot": 0.6145569918459842, | |
| "eval_sts_dev_pearson_euclidean": 0.7622940567617165, | |
| "eval_sts_dev_pearson_manhattan": 0.7619872460429895, | |
| "eval_sts_dev_pearson_max": 0.7890077878318924, | |
| "eval_sts_dev_spearman_cosine": 0.7986960426836712, | |
| "eval_sts_dev_spearman_dot": 0.5995859874295417, | |
| "eval_sts_dev_spearman_euclidean": 0.7620718720832805, | |
| "eval_sts_dev_spearman_manhattan": 0.7619175969681303, | |
| "eval_sts_dev_spearman_max": 0.7986960426836712, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.7852341832924358, | |
| "grad_norm": 0.07279020547866821, | |
| "learning_rate": 1.2269938650306748e-05, | |
| "loss": 0.0063, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.7880792346811765, | |
| "grad_norm": 0.07638818025588989, | |
| "learning_rate": 1.2314394949764382e-05, | |
| "loss": 0.0061, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.7909242860699172, | |
| "grad_norm": 0.07741549611091614, | |
| "learning_rate": 1.2358851249222015e-05, | |
| "loss": 0.0059, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.7937693374586579, | |
| "grad_norm": 0.07450976967811584, | |
| "learning_rate": 1.2403307548679648e-05, | |
| "loss": 0.0061, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.7966143888473985, | |
| "grad_norm": 0.07069046795368195, | |
| "learning_rate": 1.2447763848137282e-05, | |
| "loss": 0.0059, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.7994594402361392, | |
| "grad_norm": 0.07043927907943726, | |
| "learning_rate": 1.2492220147594915e-05, | |
| "loss": 0.0058, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.8023044916248799, | |
| "grad_norm": 0.06363347172737122, | |
| "learning_rate": 1.2536676447052547e-05, | |
| "loss": 0.0057, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.8051495430136207, | |
| "grad_norm": 0.0633586049079895, | |
| "learning_rate": 1.2581132746510182e-05, | |
| "loss": 0.0059, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.8079945944023614, | |
| "grad_norm": 0.0656353160738945, | |
| "learning_rate": 1.2625589045967814e-05, | |
| "loss": 0.0058, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.8108396457911021, | |
| "grad_norm": 0.05306802690029144, | |
| "learning_rate": 1.2670045345425447e-05, | |
| "loss": 0.0068, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.8136846971798428, | |
| "grad_norm": 0.06369970738887787, | |
| "learning_rate": 1.271450164488308e-05, | |
| "loss": 0.006, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.8165297485685835, | |
| "grad_norm": 0.059002261608839035, | |
| "learning_rate": 1.2758957944340712e-05, | |
| "loss": 0.0058, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.8193747999573242, | |
| "grad_norm": 0.06396970897912979, | |
| "learning_rate": 1.2803414243798347e-05, | |
| "loss": 0.0061, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.8222198513460649, | |
| "grad_norm": 0.06522241234779358, | |
| "learning_rate": 1.2847870543255979e-05, | |
| "loss": 0.0058, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.8250649027348056, | |
| "grad_norm": 0.07420309633016586, | |
| "learning_rate": 1.2892326842713613e-05, | |
| "loss": 0.0055, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.8279099541235464, | |
| "grad_norm": 0.0638047531247139, | |
| "learning_rate": 1.2936783142171246e-05, | |
| "loss": 0.006, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.8307550055122871, | |
| "grad_norm": 0.06835135072469711, | |
| "learning_rate": 1.298123944162888e-05, | |
| "loss": 0.0063, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.8336000569010278, | |
| "grad_norm": 0.07669410854578018, | |
| "learning_rate": 1.3025695741086513e-05, | |
| "loss": 0.0066, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.8364451082897685, | |
| "grad_norm": 0.0799371749162674, | |
| "learning_rate": 1.3070152040544144e-05, | |
| "loss": 0.0059, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.8392901596785092, | |
| "grad_norm": 0.06452161073684692, | |
| "learning_rate": 1.311460834000178e-05, | |
| "loss": 0.0056, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.8421352110672499, | |
| "grad_norm": 0.08192815631628036, | |
| "learning_rate": 1.3159064639459411e-05, | |
| "loss": 0.006, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.8449802624559906, | |
| "grad_norm": 0.08512122929096222, | |
| "learning_rate": 1.3203520938917045e-05, | |
| "loss": 0.0058, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.8478253138447314, | |
| "grad_norm": 0.05736185237765312, | |
| "learning_rate": 1.3247977238374678e-05, | |
| "loss": 0.006, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.8506703652334721, | |
| "grad_norm": 0.056353483349084854, | |
| "learning_rate": 1.329243353783231e-05, | |
| "loss": 0.0056, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.8535154166222128, | |
| "grad_norm": 0.07176116853952408, | |
| "learning_rate": 1.3336889837289945e-05, | |
| "loss": 0.0062, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.8535154166222128, | |
| "eval_loss": 0.05112998187541962, | |
| "eval_runtime": 8.8822, | |
| "eval_samples_per_second": 168.877, | |
| "eval_steps_per_second": 10.583, | |
| "eval_sts_dev_pearson_cosine": 0.7899474758938174, | |
| "eval_sts_dev_pearson_dot": 0.601477379904751, | |
| "eval_sts_dev_pearson_euclidean": 0.7631393093085868, | |
| "eval_sts_dev_pearson_manhattan": 0.762660331965514, | |
| "eval_sts_dev_pearson_max": 0.7899474758938174, | |
| "eval_sts_dev_spearman_cosine": 0.7996334507041041, | |
| "eval_sts_dev_spearman_dot": 0.5888332407477099, | |
| "eval_sts_dev_spearman_euclidean": 0.7632786368314162, | |
| "eval_sts_dev_spearman_manhattan": 0.7624223584443209, | |
| "eval_sts_dev_spearman_max": 0.7996334507041041, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.8563604680109534, | |
| "grad_norm": 0.07095087319612503, | |
| "learning_rate": 1.3381346136747577e-05, | |
| "loss": 0.0059, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.8592055193996941, | |
| "grad_norm": 0.06647340953350067, | |
| "learning_rate": 1.3425802436205212e-05, | |
| "loss": 0.0064, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.8620505707884348, | |
| "grad_norm": 0.069040946662426, | |
| "learning_rate": 1.3470258735662843e-05, | |
| "loss": 0.0064, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.8648956221771755, | |
| "grad_norm": 0.05208707973361015, | |
| "learning_rate": 1.3514715035120475e-05, | |
| "loss": 0.006, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.8677406735659163, | |
| "grad_norm": 0.058777816593647, | |
| "learning_rate": 1.355917133457811e-05, | |
| "loss": 0.0059, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.870585724954657, | |
| "grad_norm": 0.0731450691819191, | |
| "learning_rate": 1.3603627634035742e-05, | |
| "loss": 0.0055, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.8734307763433977, | |
| "grad_norm": 0.08497700840234756, | |
| "learning_rate": 1.3648083933493377e-05, | |
| "loss": 0.0056, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.8762758277321384, | |
| "grad_norm": 0.06076115369796753, | |
| "learning_rate": 1.3692540232951009e-05, | |
| "loss": 0.0058, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.8791208791208791, | |
| "grad_norm": 0.05804910510778427, | |
| "learning_rate": 1.3736996532408644e-05, | |
| "loss": 0.0057, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.8819659305096198, | |
| "grad_norm": 0.06687209010124207, | |
| "learning_rate": 1.3781452831866276e-05, | |
| "loss": 0.0058, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.8848109818983605, | |
| "grad_norm": 0.06274023652076721, | |
| "learning_rate": 1.3825909131323907e-05, | |
| "loss": 0.0062, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.8876560332871013, | |
| "grad_norm": 0.06041685864329338, | |
| "learning_rate": 1.3870365430781542e-05, | |
| "loss": 0.0058, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.890501084675842, | |
| "grad_norm": 0.07634738087654114, | |
| "learning_rate": 1.3914821730239174e-05, | |
| "loss": 0.0058, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.8933461360645827, | |
| "grad_norm": 0.05441463738679886, | |
| "learning_rate": 1.395927802969681e-05, | |
| "loss": 0.0055, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.8961911874533234, | |
| "grad_norm": 0.08034619688987732, | |
| "learning_rate": 1.4003734329154441e-05, | |
| "loss": 0.0056, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.8990362388420641, | |
| "grad_norm": 0.05668621510267258, | |
| "learning_rate": 1.4048190628612076e-05, | |
| "loss": 0.0055, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.9018812902308048, | |
| "grad_norm": 0.0647374764084816, | |
| "learning_rate": 1.4092646928069708e-05, | |
| "loss": 0.0054, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.9047263416195455, | |
| "grad_norm": 0.06342489272356033, | |
| "learning_rate": 1.413710322752734e-05, | |
| "loss": 0.0059, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.9075713930082863, | |
| "grad_norm": 0.05244365334510803, | |
| "learning_rate": 1.4181559526984975e-05, | |
| "loss": 0.0056, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.910416444397027, | |
| "grad_norm": 0.06412120163440704, | |
| "learning_rate": 1.4226015826442606e-05, | |
| "loss": 0.0057, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.9132614957857677, | |
| "grad_norm": 0.06194351613521576, | |
| "learning_rate": 1.4270472125900241e-05, | |
| "loss": 0.0055, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 0.9161065471745083, | |
| "grad_norm": 0.06416637450456619, | |
| "learning_rate": 1.4314928425357873e-05, | |
| "loss": 0.0061, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.918951598563249, | |
| "grad_norm": 0.05956665053963661, | |
| "learning_rate": 1.4359384724815508e-05, | |
| "loss": 0.0055, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 0.9217966499519897, | |
| "grad_norm": 0.055366478860378265, | |
| "learning_rate": 1.440384102427314e-05, | |
| "loss": 0.0062, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.9246417013407304, | |
| "grad_norm": 0.065581776201725, | |
| "learning_rate": 1.4448297323730772e-05, | |
| "loss": 0.006, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.9246417013407304, | |
| "eval_loss": 0.050821732729673386, | |
| "eval_runtime": 9.0965, | |
| "eval_samples_per_second": 164.898, | |
| "eval_steps_per_second": 10.334, | |
| "eval_sts_dev_pearson_cosine": 0.7909511151327651, | |
| "eval_sts_dev_pearson_dot": 0.6053394742010075, | |
| "eval_sts_dev_pearson_euclidean": 0.7648214403760886, | |
| "eval_sts_dev_pearson_manhattan": 0.7646742286120747, | |
| "eval_sts_dev_pearson_max": 0.7909511151327651, | |
| "eval_sts_dev_spearman_cosine": 0.7988801832352788, | |
| "eval_sts_dev_spearman_dot": 0.5877204065924448, | |
| "eval_sts_dev_spearman_euclidean": 0.7657836560350672, | |
| "eval_sts_dev_spearman_manhattan": 0.7656908568548414, | |
| "eval_sts_dev_spearman_max": 0.7988801832352788, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.9274867527294712, | |
| "grad_norm": 0.07194357365369797, | |
| "learning_rate": 1.4492753623188407e-05, | |
| "loss": 0.0058, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.9303318041182119, | |
| "grad_norm": 0.07017621397972107, | |
| "learning_rate": 1.4537209922646039e-05, | |
| "loss": 0.0053, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 0.9331768555069526, | |
| "grad_norm": 0.0723465159535408, | |
| "learning_rate": 1.4581666222103674e-05, | |
| "loss": 0.0064, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.9360219068956933, | |
| "grad_norm": 0.07010278105735779, | |
| "learning_rate": 1.4626122521561305e-05, | |
| "loss": 0.006, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 0.938866958284434, | |
| "grad_norm": 0.06073617562651634, | |
| "learning_rate": 1.467057882101894e-05, | |
| "loss": 0.0057, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.9417120096731747, | |
| "grad_norm": 0.05822043493390083, | |
| "learning_rate": 1.4715035120476572e-05, | |
| "loss": 0.0059, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 0.9445570610619154, | |
| "grad_norm": 0.05081350356340408, | |
| "learning_rate": 1.4759491419934204e-05, | |
| "loss": 0.0057, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.9474021124506561, | |
| "grad_norm": 0.0619865357875824, | |
| "learning_rate": 1.4803947719391839e-05, | |
| "loss": 0.0056, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 0.9502471638393969, | |
| "grad_norm": 0.06353365629911423, | |
| "learning_rate": 1.484840401884947e-05, | |
| "loss": 0.0056, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.9530922152281376, | |
| "grad_norm": 0.07539238780736923, | |
| "learning_rate": 1.4892860318307106e-05, | |
| "loss": 0.0061, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.9559372666168783, | |
| "grad_norm": 0.06994681805372238, | |
| "learning_rate": 1.4937316617764737e-05, | |
| "loss": 0.0053, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.958782318005619, | |
| "grad_norm": 0.05879216268658638, | |
| "learning_rate": 1.498177291722237e-05, | |
| "loss": 0.0056, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 0.9616273693943597, | |
| "grad_norm": 0.0628664419054985, | |
| "learning_rate": 1.5026229216680004e-05, | |
| "loss": 0.006, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.9644724207831004, | |
| "grad_norm": 0.07300525158643723, | |
| "learning_rate": 1.5070685516137636e-05, | |
| "loss": 0.0066, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 0.967317472171841, | |
| "grad_norm": 0.09258022159337997, | |
| "learning_rate": 1.5115141815595271e-05, | |
| "loss": 0.0062, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.9701625235605819, | |
| "grad_norm": 0.05411943048238754, | |
| "learning_rate": 1.5159598115052903e-05, | |
| "loss": 0.0053, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 0.9730075749493226, | |
| "grad_norm": 0.06785852462053299, | |
| "learning_rate": 1.5204054414510538e-05, | |
| "loss": 0.0062, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.9758526263380632, | |
| "grad_norm": 0.04845158010721207, | |
| "learning_rate": 1.524851071396817e-05, | |
| "loss": 0.0057, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 0.9786976777268039, | |
| "grad_norm": 0.07520108669996262, | |
| "learning_rate": 1.52929670134258e-05, | |
| "loss": 0.0059, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.9815427291155446, | |
| "grad_norm": 0.0539853572845459, | |
| "learning_rate": 1.5337423312883436e-05, | |
| "loss": 0.0061, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.9843877805042853, | |
| "grad_norm": 0.0653446614742279, | |
| "learning_rate": 1.5381879612341068e-05, | |
| "loss": 0.0057, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.987232831893026, | |
| "grad_norm": 0.0627661645412445, | |
| "learning_rate": 1.5426335911798703e-05, | |
| "loss": 0.0054, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 0.9900778832817668, | |
| "grad_norm": 0.05211208760738373, | |
| "learning_rate": 1.5470792211256335e-05, | |
| "loss": 0.0054, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.9929229346705075, | |
| "grad_norm": 0.06061340123414993, | |
| "learning_rate": 1.551524851071397e-05, | |
| "loss": 0.0057, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 0.9957679860592482, | |
| "grad_norm": 0.06133125722408295, | |
| "learning_rate": 1.5559704810171602e-05, | |
| "loss": 0.0056, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.9957679860592482, | |
| "eval_loss": 0.04846322536468506, | |
| "eval_runtime": 9.4808, | |
| "eval_samples_per_second": 158.214, | |
| "eval_steps_per_second": 9.915, | |
| "eval_sts_dev_pearson_cosine": 0.7873863893875668, | |
| "eval_sts_dev_pearson_dot": 0.590451098760234, | |
| "eval_sts_dev_pearson_euclidean": 0.7578432355248655, | |
| "eval_sts_dev_pearson_manhattan": 0.7576106133017201, | |
| "eval_sts_dev_pearson_max": 0.7873863893875668, | |
| "eval_sts_dev_spearman_cosine": 0.7957546813665759, | |
| "eval_sts_dev_spearman_dot": 0.5781029293331612, | |
| "eval_sts_dev_spearman_euclidean": 0.7559256690552184, | |
| "eval_sts_dev_spearman_manhattan": 0.7557621348675576, | |
| "eval_sts_dev_spearman_max": 0.7957546813665759, | |
| "step": 3500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 7028, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 3500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |