| { | |
| "best_metric": 0.3492669463157654, | |
| "best_model_checkpoint": "/home/datawork-iot-nos/Seatizen/models/multilabel/drone/drone-DinoVdeau-produttoria_binary-probabilities-large-2024_11_03-batch-size64_freeze_probs/checkpoint-10498", | |
| "epoch": 68.0, | |
| "eval_steps": 500, | |
| "global_step": 12308, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_explained_variance": 0.3009445369243622, | |
| "eval_loss": 0.3794757127761841, | |
| "eval_mae": 0.14892756938934326, | |
| "eval_r2": 0.2894136607646942, | |
| "eval_rmse": 0.20668388903141022, | |
| "eval_runtime": 77.6082, | |
| "eval_samples_per_second": 49.531, | |
| "eval_steps_per_second": 0.786, | |
| "learning_rate": 0.001, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_explained_variance": 0.3548472821712494, | |
| "eval_loss": 0.3673744201660156, | |
| "eval_mae": 0.1374034583568573, | |
| "eval_r2": 0.35173478722572327, | |
| "eval_rmse": 0.198309525847435, | |
| "eval_runtime": 76.8329, | |
| "eval_samples_per_second": 50.031, | |
| "eval_steps_per_second": 0.794, | |
| "learning_rate": 0.001, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 2.7624309392265194, | |
| "grad_norm": 0.26878172159194946, | |
| "learning_rate": 0.001, | |
| "loss": 0.4416, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_explained_variance": 0.35690778493881226, | |
| "eval_loss": 0.3671453297138214, | |
| "eval_mae": 0.1413687765598297, | |
| "eval_r2": 0.35207054018974304, | |
| "eval_rmse": 0.198079913854599, | |
| "eval_runtime": 77.6227, | |
| "eval_samples_per_second": 49.522, | |
| "eval_steps_per_second": 0.786, | |
| "learning_rate": 0.001, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_explained_variance": 0.37491223216056824, | |
| "eval_loss": 0.36317145824432373, | |
| "eval_mae": 0.1391323208808899, | |
| "eval_r2": 0.3708474040031433, | |
| "eval_rmse": 0.19521364569664001, | |
| "eval_runtime": 77.1791, | |
| "eval_samples_per_second": 49.806, | |
| "eval_steps_per_second": 0.79, | |
| "learning_rate": 0.001, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_explained_variance": 0.3614368736743927, | |
| "eval_loss": 0.3678734302520752, | |
| "eval_mae": 0.141828715801239, | |
| "eval_r2": 0.3453221321105957, | |
| "eval_rmse": 0.19933271408081055, | |
| "eval_runtime": 79.1374, | |
| "eval_samples_per_second": 48.574, | |
| "eval_steps_per_second": 0.771, | |
| "learning_rate": 0.001, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 5.524861878453039, | |
| "grad_norm": 0.19997762143611908, | |
| "learning_rate": 0.001, | |
| "loss": 0.3813, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_explained_variance": 0.3743399381637573, | |
| "eval_loss": 0.36250030994415283, | |
| "eval_mae": 0.13803647458553314, | |
| "eval_r2": 0.37177884578704834, | |
| "eval_rmse": 0.19508354365825653, | |
| "eval_runtime": 77.2448, | |
| "eval_samples_per_second": 49.764, | |
| "eval_steps_per_second": 0.79, | |
| "learning_rate": 0.001, | |
| "step": 1086 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_explained_variance": 0.38368356227874756, | |
| "eval_loss": 0.36188462376594543, | |
| "eval_mae": 0.1347939670085907, | |
| "eval_r2": 0.3771490454673767, | |
| "eval_rmse": 0.19410446286201477, | |
| "eval_runtime": 77.3383, | |
| "eval_samples_per_second": 49.704, | |
| "eval_steps_per_second": 0.789, | |
| "learning_rate": 0.001, | |
| "step": 1267 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_explained_variance": 0.3808881640434265, | |
| "eval_loss": 0.36125126481056213, | |
| "eval_mae": 0.13681310415267944, | |
| "eval_r2": 0.37883251905441284, | |
| "eval_rmse": 0.19354337453842163, | |
| "eval_runtime": 80.1691, | |
| "eval_samples_per_second": 47.949, | |
| "eval_steps_per_second": 0.761, | |
| "learning_rate": 0.001, | |
| "step": 1448 | |
| }, | |
| { | |
| "epoch": 8.287292817679559, | |
| "grad_norm": 0.1677914261817932, | |
| "learning_rate": 0.001, | |
| "loss": 0.3785, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_explained_variance": 0.38331514596939087, | |
| "eval_loss": 0.3603876233100891, | |
| "eval_mae": 0.135352224111557, | |
| "eval_r2": 0.3812035918235779, | |
| "eval_rmse": 0.19339486956596375, | |
| "eval_runtime": 77.1781, | |
| "eval_samples_per_second": 49.807, | |
| "eval_steps_per_second": 0.79, | |
| "learning_rate": 0.001, | |
| "step": 1629 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_explained_variance": 0.3843615651130676, | |
| "eval_loss": 0.3612792491912842, | |
| "eval_mae": 0.13375206291675568, | |
| "eval_r2": 0.38122493028640747, | |
| "eval_rmse": 0.19321060180664062, | |
| "eval_runtime": 77.2138, | |
| "eval_samples_per_second": 49.784, | |
| "eval_steps_per_second": 0.79, | |
| "learning_rate": 0.001, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_explained_variance": 0.3856731057167053, | |
| "eval_loss": 0.3603772521018982, | |
| "eval_mae": 0.13226205110549927, | |
| "eval_r2": 0.3844555616378784, | |
| "eval_rmse": 0.19312407076358795, | |
| "eval_runtime": 77.7929, | |
| "eval_samples_per_second": 49.413, | |
| "eval_steps_per_second": 0.784, | |
| "learning_rate": 0.001, | |
| "step": 1991 | |
| }, | |
| { | |
| "epoch": 11.049723756906078, | |
| "grad_norm": 1.5252280235290527, | |
| "learning_rate": 0.001, | |
| "loss": 0.3743, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_explained_variance": 0.38444802165031433, | |
| "eval_loss": 0.361823707818985, | |
| "eval_mae": 0.13859649002552032, | |
| "eval_r2": 0.3774065375328064, | |
| "eval_rmse": 0.1941623091697693, | |
| "eval_runtime": 76.0433, | |
| "eval_samples_per_second": 50.55, | |
| "eval_steps_per_second": 0.802, | |
| "learning_rate": 0.001, | |
| "step": 2172 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_explained_variance": 0.3894338309764862, | |
| "eval_loss": 0.35931822657585144, | |
| "eval_mae": 0.13433586061000824, | |
| "eval_r2": 0.3875495195388794, | |
| "eval_rmse": 0.1924724578857422, | |
| "eval_runtime": 80.7793, | |
| "eval_samples_per_second": 47.586, | |
| "eval_steps_per_second": 0.755, | |
| "learning_rate": 0.001, | |
| "step": 2353 | |
| }, | |
| { | |
| "epoch": 13.812154696132596, | |
| "grad_norm": 0.13441379368305206, | |
| "learning_rate": 0.001, | |
| "loss": 0.3732, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_explained_variance": 0.3862605392932892, | |
| "eval_loss": 0.3604746460914612, | |
| "eval_mae": 0.13521355390548706, | |
| "eval_r2": 0.38306838274002075, | |
| "eval_rmse": 0.19319292902946472, | |
| "eval_runtime": 77.1543, | |
| "eval_samples_per_second": 49.822, | |
| "eval_steps_per_second": 0.791, | |
| "learning_rate": 0.001, | |
| "step": 2534 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_explained_variance": 0.3836004436016083, | |
| "eval_loss": 0.36050480604171753, | |
| "eval_mae": 0.13660094141960144, | |
| "eval_r2": 0.3816676735877991, | |
| "eval_rmse": 0.19354429841041565, | |
| "eval_runtime": 78.1543, | |
| "eval_samples_per_second": 49.185, | |
| "eval_steps_per_second": 0.781, | |
| "learning_rate": 0.001, | |
| "step": 2715 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_explained_variance": 0.39098840951919556, | |
| "eval_loss": 0.3599933683872223, | |
| "eval_mae": 0.13121920824050903, | |
| "eval_r2": 0.388213574886322, | |
| "eval_rmse": 0.1921611875295639, | |
| "eval_runtime": 78.6199, | |
| "eval_samples_per_second": 48.893, | |
| "eval_steps_per_second": 0.776, | |
| "learning_rate": 0.001, | |
| "step": 2896 | |
| }, | |
| { | |
| "epoch": 16.574585635359117, | |
| "grad_norm": 0.13405688107013702, | |
| "learning_rate": 0.001, | |
| "loss": 0.3733, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_explained_variance": 0.38817232847213745, | |
| "eval_loss": 0.3628774583339691, | |
| "eval_mae": 0.13783428072929382, | |
| "eval_r2": 0.38425371050834656, | |
| "eval_rmse": 0.1932491511106491, | |
| "eval_runtime": 80.2352, | |
| "eval_samples_per_second": 47.909, | |
| "eval_steps_per_second": 0.76, | |
| "learning_rate": 0.001, | |
| "step": 3077 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_explained_variance": 0.3839576840400696, | |
| "eval_loss": 0.36154037714004517, | |
| "eval_mae": 0.1323489546775818, | |
| "eval_r2": 0.37684857845306396, | |
| "eval_rmse": 0.19430074095726013, | |
| "eval_runtime": 85.0559, | |
| "eval_samples_per_second": 45.194, | |
| "eval_steps_per_second": 0.717, | |
| "learning_rate": 0.001, | |
| "step": 3258 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_explained_variance": 0.3911250829696655, | |
| "eval_loss": 0.3594801127910614, | |
| "eval_mae": 0.13296250998973846, | |
| "eval_r2": 0.38950252532958984, | |
| "eval_rmse": 0.19218452274799347, | |
| "eval_runtime": 83.3283, | |
| "eval_samples_per_second": 46.131, | |
| "eval_steps_per_second": 0.732, | |
| "learning_rate": 0.001, | |
| "step": 3439 | |
| }, | |
| { | |
| "epoch": 19.337016574585636, | |
| "grad_norm": 0.1141289696097374, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3723, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_explained_variance": 0.4041489064693451, | |
| "eval_loss": 0.3565874397754669, | |
| "eval_mae": 0.13302744925022125, | |
| "eval_r2": 0.40064936876296997, | |
| "eval_rmse": 0.19017010927200317, | |
| "eval_runtime": 81.1931, | |
| "eval_samples_per_second": 47.344, | |
| "eval_steps_per_second": 0.751, | |
| "learning_rate": 0.0001, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_explained_variance": 0.4089391827583313, | |
| "eval_loss": 0.35486647486686707, | |
| "eval_mae": 0.13062793016433716, | |
| "eval_r2": 0.40758493542671204, | |
| "eval_rmse": 0.18895885348320007, | |
| "eval_runtime": 83.1097, | |
| "eval_samples_per_second": 46.252, | |
| "eval_steps_per_second": 0.734, | |
| "learning_rate": 0.0001, | |
| "step": 3801 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_explained_variance": 0.41082069277763367, | |
| "eval_loss": 0.35447388887405396, | |
| "eval_mae": 0.13081100583076477, | |
| "eval_r2": 0.4096067547798157, | |
| "eval_rmse": 0.18863680958747864, | |
| "eval_runtime": 83.0406, | |
| "eval_samples_per_second": 46.291, | |
| "eval_steps_per_second": 0.735, | |
| "learning_rate": 0.0001, | |
| "step": 3982 | |
| }, | |
| { | |
| "epoch": 22.099447513812155, | |
| "grad_norm": 0.1349981278181076, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3683, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_explained_variance": 0.4124269485473633, | |
| "eval_loss": 0.3544616997241974, | |
| "eval_mae": 0.13033078610897064, | |
| "eval_r2": 0.411631315946579, | |
| "eval_rmse": 0.18823565542697906, | |
| "eval_runtime": 84.9131, | |
| "eval_samples_per_second": 45.27, | |
| "eval_steps_per_second": 0.718, | |
| "learning_rate": 0.0001, | |
| "step": 4163 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_explained_variance": 0.4130716025829315, | |
| "eval_loss": 0.3539991080760956, | |
| "eval_mae": 0.1316699981689453, | |
| "eval_r2": 0.4120980501174927, | |
| "eval_rmse": 0.1881898045539856, | |
| "eval_runtime": 83.8568, | |
| "eval_samples_per_second": 45.84, | |
| "eval_steps_per_second": 0.727, | |
| "learning_rate": 0.0001, | |
| "step": 4344 | |
| }, | |
| { | |
| "epoch": 24.861878453038674, | |
| "grad_norm": 0.10933272540569305, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3654, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_explained_variance": 0.4125872850418091, | |
| "eval_loss": 0.3545873463153839, | |
| "eval_mae": 0.12844440340995789, | |
| "eval_r2": 0.41126883029937744, | |
| "eval_rmse": 0.18831981718540192, | |
| "eval_runtime": 83.2028, | |
| "eval_samples_per_second": 46.2, | |
| "eval_steps_per_second": 0.733, | |
| "learning_rate": 0.0001, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_explained_variance": 0.4165402948856354, | |
| "eval_loss": 0.3529074192047119, | |
| "eval_mae": 0.1263934224843979, | |
| "eval_r2": 0.4154190421104431, | |
| "eval_rmse": 0.18757320940494537, | |
| "eval_runtime": 81.7389, | |
| "eval_samples_per_second": 47.028, | |
| "eval_steps_per_second": 0.746, | |
| "learning_rate": 0.0001, | |
| "step": 4706 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_explained_variance": 0.4176566004753113, | |
| "eval_loss": 0.3532767593860626, | |
| "eval_mae": 0.129387766122818, | |
| "eval_r2": 0.41658732295036316, | |
| "eval_rmse": 0.187411367893219, | |
| "eval_runtime": 81.9775, | |
| "eval_samples_per_second": 46.891, | |
| "eval_steps_per_second": 0.744, | |
| "learning_rate": 0.0001, | |
| "step": 4887 | |
| }, | |
| { | |
| "epoch": 27.624309392265193, | |
| "grad_norm": 0.11634723842144012, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3652, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_explained_variance": 0.41691651940345764, | |
| "eval_loss": 0.3532498776912689, | |
| "eval_mae": 0.12938687205314636, | |
| "eval_r2": 0.41600102186203003, | |
| "eval_rmse": 0.18755248188972473, | |
| "eval_runtime": 84.518, | |
| "eval_samples_per_second": 45.481, | |
| "eval_steps_per_second": 0.722, | |
| "learning_rate": 0.0001, | |
| "step": 5068 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_explained_variance": 0.41915032267570496, | |
| "eval_loss": 0.35306474566459656, | |
| "eval_mae": 0.1302015781402588, | |
| "eval_r2": 0.41835859417915344, | |
| "eval_rmse": 0.1871432662010193, | |
| "eval_runtime": 81.5924, | |
| "eval_samples_per_second": 47.112, | |
| "eval_steps_per_second": 0.748, | |
| "learning_rate": 0.0001, | |
| "step": 5249 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_explained_variance": 0.4160480499267578, | |
| "eval_loss": 0.3536038398742676, | |
| "eval_mae": 0.1291646808385849, | |
| "eval_r2": 0.414754718542099, | |
| "eval_rmse": 0.18775980174541473, | |
| "eval_runtime": 81.1332, | |
| "eval_samples_per_second": 47.379, | |
| "eval_steps_per_second": 0.752, | |
| "learning_rate": 0.0001, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 30.386740331491712, | |
| "grad_norm": 0.12858645617961884, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3628, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_explained_variance": 0.41752102971076965, | |
| "eval_loss": 0.3530591130256653, | |
| "eval_mae": 0.1267225444316864, | |
| "eval_r2": 0.415239542722702, | |
| "eval_rmse": 0.1876552253961563, | |
| "eval_runtime": 82.6896, | |
| "eval_samples_per_second": 46.487, | |
| "eval_steps_per_second": 0.738, | |
| "learning_rate": 0.0001, | |
| "step": 5611 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_explained_variance": 0.4167982339859009, | |
| "eval_loss": 0.3528367877006531, | |
| "eval_mae": 0.12877780199050903, | |
| "eval_r2": 0.4161965548992157, | |
| "eval_rmse": 0.18764065206050873, | |
| "eval_runtime": 81.5086, | |
| "eval_samples_per_second": 47.161, | |
| "eval_steps_per_second": 0.748, | |
| "learning_rate": 0.0001, | |
| "step": 5792 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_explained_variance": 0.4230208098888397, | |
| "eval_loss": 0.35152381658554077, | |
| "eval_mae": 0.12729588150978088, | |
| "eval_r2": 0.4225224256515503, | |
| "eval_rmse": 0.18640562891960144, | |
| "eval_runtime": 83.3119, | |
| "eval_samples_per_second": 46.14, | |
| "eval_steps_per_second": 0.732, | |
| "learning_rate": 0.0001, | |
| "step": 5973 | |
| }, | |
| { | |
| "epoch": 33.149171270718234, | |
| "grad_norm": 0.12355350703001022, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3638, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_explained_variance": 0.4216320216655731, | |
| "eval_loss": 0.35195404291152954, | |
| "eval_mae": 0.12629321217536926, | |
| "eval_r2": 0.4202421009540558, | |
| "eval_rmse": 0.18677598237991333, | |
| "eval_runtime": 81.9599, | |
| "eval_samples_per_second": 46.901, | |
| "eval_steps_per_second": 0.744, | |
| "learning_rate": 0.0001, | |
| "step": 6154 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_explained_variance": 0.42201581597328186, | |
| "eval_loss": 0.35178276896476746, | |
| "eval_mae": 0.12782610952854156, | |
| "eval_r2": 0.42147499322891235, | |
| "eval_rmse": 0.18657900393009186, | |
| "eval_runtime": 82.9654, | |
| "eval_samples_per_second": 46.333, | |
| "eval_steps_per_second": 0.735, | |
| "learning_rate": 0.0001, | |
| "step": 6335 | |
| }, | |
| { | |
| "epoch": 35.91160220994475, | |
| "grad_norm": 0.12306394428014755, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3618, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_explained_variance": 0.41956183314323425, | |
| "eval_loss": 0.35231974720954895, | |
| "eval_mae": 0.12849368155002594, | |
| "eval_r2": 0.4192589223384857, | |
| "eval_rmse": 0.18713095784187317, | |
| "eval_runtime": 81.841, | |
| "eval_samples_per_second": 46.969, | |
| "eval_steps_per_second": 0.745, | |
| "learning_rate": 0.0001, | |
| "step": 6516 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_explained_variance": 0.4224753677845001, | |
| "eval_loss": 0.3515876829624176, | |
| "eval_mae": 0.12726719677448273, | |
| "eval_r2": 0.4216739237308502, | |
| "eval_rmse": 0.18659605085849762, | |
| "eval_runtime": 81.3618, | |
| "eval_samples_per_second": 47.246, | |
| "eval_steps_per_second": 0.75, | |
| "learning_rate": 0.0001, | |
| "step": 6697 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_explained_variance": 0.4183831810951233, | |
| "eval_loss": 0.35274896025657654, | |
| "eval_mae": 0.12742024660110474, | |
| "eval_r2": 0.41570571064949036, | |
| "eval_rmse": 0.1878250390291214, | |
| "eval_runtime": 82.5613, | |
| "eval_samples_per_second": 46.559, | |
| "eval_steps_per_second": 0.739, | |
| "learning_rate": 0.0001, | |
| "step": 6878 | |
| }, | |
| { | |
| "epoch": 38.67403314917127, | |
| "grad_norm": 0.12681056559085846, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3611, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_explained_variance": 0.42493724822998047, | |
| "eval_loss": 0.35124146938323975, | |
| "eval_mae": 0.12662582099437714, | |
| "eval_r2": 0.4241558611392975, | |
| "eval_rmse": 0.18624022603034973, | |
| "eval_runtime": 83.3424, | |
| "eval_samples_per_second": 46.123, | |
| "eval_steps_per_second": 0.732, | |
| "learning_rate": 0.0001, | |
| "step": 7059 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_explained_variance": 0.42367231845855713, | |
| "eval_loss": 0.35209622979164124, | |
| "eval_mae": 0.13019172847270966, | |
| "eval_r2": 0.4224165081977844, | |
| "eval_rmse": 0.18663105368614197, | |
| "eval_runtime": 82.8483, | |
| "eval_samples_per_second": 46.398, | |
| "eval_steps_per_second": 0.736, | |
| "learning_rate": 0.0001, | |
| "step": 7240 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_explained_variance": 0.4274601340293884, | |
| "eval_loss": 0.35067644715309143, | |
| "eval_mae": 0.1265629082918167, | |
| "eval_r2": 0.42641735076904297, | |
| "eval_rmse": 0.18584123253822327, | |
| "eval_runtime": 83.6418, | |
| "eval_samples_per_second": 45.958, | |
| "eval_steps_per_second": 0.729, | |
| "learning_rate": 0.0001, | |
| "step": 7421 | |
| }, | |
| { | |
| "epoch": 41.43646408839779, | |
| "grad_norm": 0.13862788677215576, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3613, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_explained_variance": 0.4272458851337433, | |
| "eval_loss": 0.3512935936450958, | |
| "eval_mae": 0.12775851786136627, | |
| "eval_r2": 0.4262687563896179, | |
| "eval_rmse": 0.18596960604190826, | |
| "eval_runtime": 83.9115, | |
| "eval_samples_per_second": 45.81, | |
| "eval_steps_per_second": 0.727, | |
| "learning_rate": 0.0001, | |
| "step": 7602 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_explained_variance": 0.4272707402706146, | |
| "eval_loss": 0.3510710895061493, | |
| "eval_mae": 0.12741515040397644, | |
| "eval_r2": 0.42624664306640625, | |
| "eval_rmse": 0.1859511435031891, | |
| "eval_runtime": 82.5626, | |
| "eval_samples_per_second": 46.559, | |
| "eval_steps_per_second": 0.739, | |
| "learning_rate": 0.0001, | |
| "step": 7783 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_explained_variance": 0.42821547389030457, | |
| "eval_loss": 0.35139599442481995, | |
| "eval_mae": 0.12441141903400421, | |
| "eval_r2": 0.4265681505203247, | |
| "eval_rmse": 0.18587811291217804, | |
| "eval_runtime": 82.7673, | |
| "eval_samples_per_second": 46.443, | |
| "eval_steps_per_second": 0.737, | |
| "learning_rate": 0.0001, | |
| "step": 7964 | |
| }, | |
| { | |
| "epoch": 44.19889502762431, | |
| "grad_norm": 0.15475843846797943, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3603, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_explained_variance": 0.42755335569381714, | |
| "eval_loss": 0.35247302055358887, | |
| "eval_mae": 0.127328023314476, | |
| "eval_r2": 0.42492759227752686, | |
| "eval_rmse": 0.18626871705055237, | |
| "eval_runtime": 84.2463, | |
| "eval_samples_per_second": 45.628, | |
| "eval_steps_per_second": 0.724, | |
| "learning_rate": 0.0001, | |
| "step": 8145 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_explained_variance": 0.4285746216773987, | |
| "eval_loss": 0.3505423069000244, | |
| "eval_mae": 0.12581512331962585, | |
| "eval_r2": 0.4274958372116089, | |
| "eval_rmse": 0.18559609353542328, | |
| "eval_runtime": 82.9445, | |
| "eval_samples_per_second": 46.344, | |
| "eval_steps_per_second": 0.735, | |
| "learning_rate": 0.0001, | |
| "step": 8326 | |
| }, | |
| { | |
| "epoch": 46.96132596685083, | |
| "grad_norm": 0.172088161110878, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3603, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_explained_variance": 0.42584168910980225, | |
| "eval_loss": 0.3517468571662903, | |
| "eval_mae": 0.1250177025794983, | |
| "eval_r2": 0.4231443405151367, | |
| "eval_rmse": 0.18658187985420227, | |
| "eval_runtime": 84.7488, | |
| "eval_samples_per_second": 45.358, | |
| "eval_steps_per_second": 0.72, | |
| "learning_rate": 0.0001, | |
| "step": 8507 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_explained_variance": 0.4292495548725128, | |
| "eval_loss": 0.35043978691101074, | |
| "eval_mae": 0.12591718137264252, | |
| "eval_r2": 0.42857199907302856, | |
| "eval_rmse": 0.18564504384994507, | |
| "eval_runtime": 80.6864, | |
| "eval_samples_per_second": 47.641, | |
| "eval_steps_per_second": 0.756, | |
| "learning_rate": 0.0001, | |
| "step": 8688 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_explained_variance": 0.42835286259651184, | |
| "eval_loss": 0.35074281692504883, | |
| "eval_mae": 0.12717720866203308, | |
| "eval_r2": 0.4274061322212219, | |
| "eval_rmse": 0.1857146918773651, | |
| "eval_runtime": 81.6357, | |
| "eval_samples_per_second": 47.087, | |
| "eval_steps_per_second": 0.747, | |
| "learning_rate": 0.0001, | |
| "step": 8869 | |
| }, | |
| { | |
| "epoch": 49.72375690607735, | |
| "grad_norm": 0.17033293843269348, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3604, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_explained_variance": 0.42889854311943054, | |
| "eval_loss": 0.3515849709510803, | |
| "eval_mae": 0.1283276230096817, | |
| "eval_r2": 0.42797213792800903, | |
| "eval_rmse": 0.1857057511806488, | |
| "eval_runtime": 82.7487, | |
| "eval_samples_per_second": 46.454, | |
| "eval_steps_per_second": 0.737, | |
| "learning_rate": 0.0001, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_explained_variance": 0.4282180070877075, | |
| "eval_loss": 0.35289809107780457, | |
| "eval_mae": 0.1288221776485443, | |
| "eval_r2": 0.42265036702156067, | |
| "eval_rmse": 0.1866857409477234, | |
| "eval_runtime": 83.8305, | |
| "eval_samples_per_second": 45.854, | |
| "eval_steps_per_second": 0.728, | |
| "learning_rate": 0.0001, | |
| "step": 9231 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_explained_variance": 0.42951008677482605, | |
| "eval_loss": 0.3505743443965912, | |
| "eval_mae": 0.12677451968193054, | |
| "eval_r2": 0.4281761944293976, | |
| "eval_rmse": 0.18569740653038025, | |
| "eval_runtime": 83.1138, | |
| "eval_samples_per_second": 46.25, | |
| "eval_steps_per_second": 0.734, | |
| "learning_rate": 0.0001, | |
| "step": 9412 | |
| }, | |
| { | |
| "epoch": 52.48618784530387, | |
| "grad_norm": 0.19461286067962646, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3592, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_explained_variance": 0.4302181005477905, | |
| "eval_loss": 0.35052910447120667, | |
| "eval_mae": 0.1273086667060852, | |
| "eval_r2": 0.4285990595817566, | |
| "eval_rmse": 0.18561594188213348, | |
| "eval_runtime": 82.8342, | |
| "eval_samples_per_second": 46.406, | |
| "eval_steps_per_second": 0.736, | |
| "learning_rate": 0.0001, | |
| "step": 9593 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_explained_variance": 0.43035173416137695, | |
| "eval_loss": 0.35016006231307983, | |
| "eval_mae": 0.12655657529830933, | |
| "eval_r2": 0.4299810826778412, | |
| "eval_rmse": 0.1853920817375183, | |
| "eval_runtime": 83.2383, | |
| "eval_samples_per_second": 46.181, | |
| "eval_steps_per_second": 0.733, | |
| "learning_rate": 0.0001, | |
| "step": 9774 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_explained_variance": 0.4318656921386719, | |
| "eval_loss": 0.35006165504455566, | |
| "eval_mae": 0.12509843707084656, | |
| "eval_r2": 0.42986157536506653, | |
| "eval_rmse": 0.18541744351387024, | |
| "eval_runtime": 82.8153, | |
| "eval_samples_per_second": 46.417, | |
| "eval_steps_per_second": 0.737, | |
| "learning_rate": 0.0001, | |
| "step": 9955 | |
| }, | |
| { | |
| "epoch": 55.248618784530386, | |
| "grad_norm": 0.179665207862854, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3601, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_explained_variance": 0.42942577600479126, | |
| "eval_loss": 0.35072585940361023, | |
| "eval_mae": 0.12430255115032196, | |
| "eval_r2": 0.4273306131362915, | |
| "eval_rmse": 0.18582786619663239, | |
| "eval_runtime": 83.8049, | |
| "eval_samples_per_second": 45.868, | |
| "eval_steps_per_second": 0.728, | |
| "learning_rate": 0.0001, | |
| "step": 10136 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_explained_variance": 0.42968177795410156, | |
| "eval_loss": 0.3508891463279724, | |
| "eval_mae": 0.12534378468990326, | |
| "eval_r2": 0.4273567497730255, | |
| "eval_rmse": 0.18598994612693787, | |
| "eval_runtime": 86.999, | |
| "eval_samples_per_second": 44.184, | |
| "eval_steps_per_second": 0.701, | |
| "learning_rate": 0.0001, | |
| "step": 10317 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_explained_variance": 0.43535250425338745, | |
| "eval_loss": 0.3492669463157654, | |
| "eval_mae": 0.12510134279727936, | |
| "eval_r2": 0.4338167607784271, | |
| "eval_rmse": 0.1846422404050827, | |
| "eval_runtime": 84.7392, | |
| "eval_samples_per_second": 45.363, | |
| "eval_steps_per_second": 0.72, | |
| "learning_rate": 0.0001, | |
| "step": 10498 | |
| }, | |
| { | |
| "epoch": 58.011049723756905, | |
| "grad_norm": 0.23822635412216187, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3601, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_explained_variance": 0.42991289496421814, | |
| "eval_loss": 0.3500733971595764, | |
| "eval_mae": 0.12414979934692383, | |
| "eval_r2": 0.42818644642829895, | |
| "eval_rmse": 0.18548892438411713, | |
| "eval_runtime": 83.0713, | |
| "eval_samples_per_second": 46.274, | |
| "eval_steps_per_second": 0.734, | |
| "learning_rate": 0.0001, | |
| "step": 10679 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_explained_variance": 0.43251222372055054, | |
| "eval_loss": 0.350059449672699, | |
| "eval_mae": 0.12591439485549927, | |
| "eval_r2": 0.43032628297805786, | |
| "eval_rmse": 0.18521927297115326, | |
| "eval_runtime": 82.5828, | |
| "eval_samples_per_second": 46.547, | |
| "eval_steps_per_second": 0.739, | |
| "learning_rate": 0.0001, | |
| "step": 10860 | |
| }, | |
| { | |
| "epoch": 60.773480662983424, | |
| "grad_norm": 0.2104698270559311, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3588, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_explained_variance": 0.4309556186199188, | |
| "eval_loss": 0.34978389739990234, | |
| "eval_mae": 0.126389279961586, | |
| "eval_r2": 0.43050628900527954, | |
| "eval_rmse": 0.18503333628177643, | |
| "eval_runtime": 84.1032, | |
| "eval_samples_per_second": 45.706, | |
| "eval_steps_per_second": 0.725, | |
| "learning_rate": 0.0001, | |
| "step": 11041 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_explained_variance": 0.43332165479660034, | |
| "eval_loss": 0.34984564781188965, | |
| "eval_mae": 0.1265084147453308, | |
| "eval_r2": 0.4322562515735626, | |
| "eval_rmse": 0.18499605357646942, | |
| "eval_runtime": 83.3683, | |
| "eval_samples_per_second": 46.109, | |
| "eval_steps_per_second": 0.732, | |
| "learning_rate": 0.0001, | |
| "step": 11222 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_explained_variance": 0.4338870644569397, | |
| "eval_loss": 0.35018646717071533, | |
| "eval_mae": 0.1270289421081543, | |
| "eval_r2": 0.4321424067020416, | |
| "eval_rmse": 0.18513011932373047, | |
| "eval_runtime": 82.3267, | |
| "eval_samples_per_second": 46.692, | |
| "eval_steps_per_second": 0.741, | |
| "learning_rate": 0.0001, | |
| "step": 11403 | |
| }, | |
| { | |
| "epoch": 63.53591160220994, | |
| "grad_norm": 0.18755941092967987, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3579, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_explained_variance": 0.43124625086784363, | |
| "eval_loss": 0.34996479749679565, | |
| "eval_mae": 0.12558279931545258, | |
| "eval_r2": 0.43004974722862244, | |
| "eval_rmse": 0.1853456199169159, | |
| "eval_runtime": 82.1284, | |
| "eval_samples_per_second": 46.805, | |
| "eval_steps_per_second": 0.743, | |
| "learning_rate": 0.0001, | |
| "step": 11584 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_explained_variance": 0.4304056167602539, | |
| "eval_loss": 0.3501463234424591, | |
| "eval_mae": 0.1280103474855423, | |
| "eval_r2": 0.42989540100097656, | |
| "eval_rmse": 0.1853969395160675, | |
| "eval_runtime": 83.5593, | |
| "eval_samples_per_second": 46.003, | |
| "eval_steps_per_second": 0.73, | |
| "learning_rate": 1e-05, | |
| "step": 11765 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_explained_variance": 0.43423348665237427, | |
| "eval_loss": 0.34930846095085144, | |
| "eval_mae": 0.1253172904253006, | |
| "eval_r2": 0.43362313508987427, | |
| "eval_rmse": 0.1847212016582489, | |
| "eval_runtime": 82.5157, | |
| "eval_samples_per_second": 46.585, | |
| "eval_steps_per_second": 0.739, | |
| "learning_rate": 1e-05, | |
| "step": 11946 | |
| }, | |
| { | |
| "epoch": 66.29834254143647, | |
| "grad_norm": 0.23534314334392548, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3564, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_explained_variance": 0.43399736285209656, | |
| "eval_loss": 0.3493542969226837, | |
| "eval_mae": 0.12613731622695923, | |
| "eval_r2": 0.43344247341156006, | |
| "eval_rmse": 0.18472003936767578, | |
| "eval_runtime": 83.448, | |
| "eval_samples_per_second": 46.065, | |
| "eval_steps_per_second": 0.731, | |
| "learning_rate": 1e-05, | |
| "step": 12127 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_explained_variance": 0.4307097792625427, | |
| "eval_loss": 0.3500206172466278, | |
| "eval_mae": 0.12607118487358093, | |
| "eval_r2": 0.4291488826274872, | |
| "eval_rmse": 0.18558326363563538, | |
| "eval_runtime": 81.73, | |
| "eval_samples_per_second": 47.033, | |
| "eval_steps_per_second": 0.746, | |
| "learning_rate": 1e-05, | |
| "step": 12308 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "learning_rate": 1e-05, | |
| "step": 12308, | |
| "total_flos": 1.159646636554683e+20, | |
| "train_loss": 0.36796005863937264, | |
| "train_runtime": 25085.7825, | |
| "train_samples_per_second": 68.896, | |
| "train_steps_per_second": 1.082 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 27150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 150, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 10, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.159646636554683e+20, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |