| { | |
| "best_metric": 0.34081346423562414, | |
| "best_model_checkpoint": "videomae-base-finetuned-elder/checkpoint-145", | |
| "epoch": 3.2447916666666665, | |
| "eval_steps": 500, | |
| "global_step": 576, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 5.98492431640625, | |
| "learning_rate": 8.620689655172414e-06, | |
| "loss": 1.7608, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 5.645175457000732, | |
| "learning_rate": 1.7241379310344828e-05, | |
| "loss": 1.7351, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 5.5949578285217285, | |
| "learning_rate": 2.5862068965517244e-05, | |
| "loss": 1.6988, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 7.89724063873291, | |
| "learning_rate": 3.4482758620689657e-05, | |
| "loss": 1.6708, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 6.795271396636963, | |
| "learning_rate": 4.3103448275862066e-05, | |
| "loss": 1.7643, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 5.639424800872803, | |
| "learning_rate": 4.980694980694981e-05, | |
| "loss": 1.709, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 6.942084312438965, | |
| "learning_rate": 4.884169884169885e-05, | |
| "loss": 1.7576, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 6.221732139587402, | |
| "learning_rate": 4.787644787644788e-05, | |
| "loss": 1.728, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 5.884160041809082, | |
| "learning_rate": 4.6911196911196914e-05, | |
| "loss": 1.6656, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 5.812763690948486, | |
| "learning_rate": 4.594594594594595e-05, | |
| "loss": 1.7212, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 5.196298599243164, | |
| "learning_rate": 4.498069498069498e-05, | |
| "loss": 1.7729, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 6.1844162940979, | |
| "learning_rate": 4.401544401544402e-05, | |
| "loss": 1.7089, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 4.422025203704834, | |
| "learning_rate": 4.305019305019305e-05, | |
| "loss": 1.7591, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 4.016156196594238, | |
| "learning_rate": 4.2084942084942086e-05, | |
| "loss": 1.6792, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.34081346423562414, | |
| "eval_loss": 1.639670729637146, | |
| "eval_runtime": 914.1791, | |
| "eval_samples_per_second": 1.56, | |
| "eval_steps_per_second": 0.196, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 6.139647960662842, | |
| "learning_rate": 4.111969111969112e-05, | |
| "loss": 1.653, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 5.428959846496582, | |
| "learning_rate": 4.015444015444015e-05, | |
| "loss": 1.7568, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 4.396470069885254, | |
| "learning_rate": 3.918918918918919e-05, | |
| "loss": 1.7393, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 4.388951301574707, | |
| "learning_rate": 3.822393822393823e-05, | |
| "loss": 1.7956, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 9.291723251342773, | |
| "learning_rate": 3.725868725868726e-05, | |
| "loss": 1.7192, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 5.253334045410156, | |
| "learning_rate": 3.6293436293436295e-05, | |
| "loss": 1.6888, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 5.230763912200928, | |
| "learning_rate": 3.532818532818533e-05, | |
| "loss": 1.6972, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 3.834545612335205, | |
| "learning_rate": 3.436293436293436e-05, | |
| "loss": 1.7124, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 4.553481101989746, | |
| "learning_rate": 3.33976833976834e-05, | |
| "loss": 1.7011, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 4.672926425933838, | |
| "learning_rate": 3.2432432432432436e-05, | |
| "loss": 1.701, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 5.78378963470459, | |
| "learning_rate": 3.1467181467181466e-05, | |
| "loss": 1.597, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 4.538748741149902, | |
| "learning_rate": 3.0501930501930504e-05, | |
| "loss": 1.643, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 3.175865411758423, | |
| "learning_rate": 2.953667953667954e-05, | |
| "loss": 1.6941, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 5.939924240112305, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 1.5795, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 5.927539348602295, | |
| "learning_rate": 2.7606177606177608e-05, | |
| "loss": 1.6326, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy": 0.3232819074333801, | |
| "eval_loss": 1.6259315013885498, | |
| "eval_runtime": 1008.6021, | |
| "eval_samples_per_second": 1.414, | |
| "eval_steps_per_second": 0.177, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 5.333898067474365, | |
| "learning_rate": 2.6640926640926645e-05, | |
| "loss": 1.5935, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 3.408902406692505, | |
| "learning_rate": 2.5675675675675675e-05, | |
| "loss": 1.8192, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 4.679303169250488, | |
| "learning_rate": 2.4710424710424712e-05, | |
| "loss": 1.6555, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "grad_norm": 6.238588333129883, | |
| "learning_rate": 2.3745173745173746e-05, | |
| "loss": 1.6335, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "grad_norm": 7.497094631195068, | |
| "learning_rate": 2.277992277992278e-05, | |
| "loss": 1.6843, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 7.145444393157959, | |
| "learning_rate": 2.1814671814671817e-05, | |
| "loss": 1.6107, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 2.706979513168335, | |
| "learning_rate": 2.084942084942085e-05, | |
| "loss": 1.7367, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "grad_norm": 5.786703109741211, | |
| "learning_rate": 1.9884169884169884e-05, | |
| "loss": 1.6931, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 6.3389177322387695, | |
| "learning_rate": 1.891891891891892e-05, | |
| "loss": 1.5662, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "grad_norm": 3.2628817558288574, | |
| "learning_rate": 1.7953667953667955e-05, | |
| "loss": 1.6322, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "grad_norm": 4.778809547424316, | |
| "learning_rate": 1.698841698841699e-05, | |
| "loss": 1.675, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "grad_norm": 3.829134941101074, | |
| "learning_rate": 1.6023166023166026e-05, | |
| "loss": 1.66, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "grad_norm": 7.900679588317871, | |
| "learning_rate": 1.505791505791506e-05, | |
| "loss": 1.7465, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 4.327514171600342, | |
| "learning_rate": 1.4092664092664093e-05, | |
| "loss": 1.5989, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_accuracy": 0.34011220196353437, | |
| "eval_loss": 1.6231606006622314, | |
| "eval_runtime": 965.0554, | |
| "eval_samples_per_second": 1.478, | |
| "eval_steps_per_second": 0.185, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "grad_norm": 9.593939781188965, | |
| "learning_rate": 1.3127413127413127e-05, | |
| "loss": 1.688, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "grad_norm": 7.807051181793213, | |
| "learning_rate": 1.2162162162162164e-05, | |
| "loss": 1.6609, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "grad_norm": 12.353256225585938, | |
| "learning_rate": 1.1196911196911197e-05, | |
| "loss": 1.6091, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "grad_norm": 5.419424057006836, | |
| "learning_rate": 1.0231660231660233e-05, | |
| "loss": 1.6206, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "grad_norm": 4.162823677062988, | |
| "learning_rate": 9.266409266409266e-06, | |
| "loss": 1.64, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "grad_norm": 2.6399056911468506, | |
| "learning_rate": 8.301158301158302e-06, | |
| "loss": 1.4998, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "grad_norm": 7.833770751953125, | |
| "learning_rate": 7.335907335907337e-06, | |
| "loss": 1.5723, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "grad_norm": 9.628315925598145, | |
| "learning_rate": 6.370656370656371e-06, | |
| "loss": 1.6482, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "grad_norm": 5.782583236694336, | |
| "learning_rate": 5.405405405405406e-06, | |
| "loss": 1.5077, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "grad_norm": 5.132481575012207, | |
| "learning_rate": 4.4401544401544405e-06, | |
| "loss": 1.7713, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "grad_norm": 4.762849807739258, | |
| "learning_rate": 3.474903474903475e-06, | |
| "loss": 1.5803, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 4.8944315910339355, | |
| "learning_rate": 2.5096525096525096e-06, | |
| "loss": 1.7035, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "grad_norm": 4.528627872467041, | |
| "learning_rate": 1.5444015444015445e-06, | |
| "loss": 1.5533, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "grad_norm": 9.058985710144043, | |
| "learning_rate": 5.791505791505791e-07, | |
| "loss": 1.7029, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "eval_accuracy": 0.3288920056100982, | |
| "eval_loss": 1.6284162998199463, | |
| "eval_runtime": 971.7776, | |
| "eval_samples_per_second": 1.467, | |
| "eval_steps_per_second": 0.184, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "step": 576, | |
| "total_flos": 5.730855473985159e+18, | |
| "train_loss": 1.6746184544430838, | |
| "train_runtime": 9779.0761, | |
| "train_samples_per_second": 0.471, | |
| "train_steps_per_second": 0.059 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "eval_accuracy": 0.34811715481171546, | |
| "eval_loss": 1.6624772548675537, | |
| "eval_runtime": 751.8376, | |
| "eval_samples_per_second": 1.589, | |
| "eval_steps_per_second": 0.2, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "eval_accuracy": 0.34811715481171546, | |
| "eval_loss": 1.6624772548675537, | |
| "eval_runtime": 754.0286, | |
| "eval_samples_per_second": 1.585, | |
| "eval_steps_per_second": 0.199, | |
| "step": 576 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 576, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 5.730855473985159e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |