| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "YAHIA/ViViT-b-16x2-ShopLifting-Dataset\\checkpoint-596", | |
| "epoch": 1.4983221476510067, | |
| "eval_steps": 500, | |
| "global_step": 596, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 10.692367553710938, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.7508, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 15.156712532043457, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.5978, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 1.6303211450576782, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.6351, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 41.47138214111328, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.9622, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.7870268821716309, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.3437, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.17213623225688934, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4405, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.06276705861091614, | |
| "learning_rate": 4.906716417910448e-05, | |
| "loss": 0.2694, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 1.269716501235962, | |
| "learning_rate": 4.813432835820896e-05, | |
| "loss": 0.6896, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 30.071969985961914, | |
| "learning_rate": 4.7201492537313436e-05, | |
| "loss": 1.224, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 11.760859489440918, | |
| "learning_rate": 4.626865671641791e-05, | |
| "loss": 0.6247, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.22317390143871307, | |
| "learning_rate": 4.5335820895522394e-05, | |
| "loss": 0.2921, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 27.252477645874023, | |
| "learning_rate": 4.440298507462687e-05, | |
| "loss": 0.6916, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.2607596814632416, | |
| "learning_rate": 4.3470149253731345e-05, | |
| "loss": 0.2637, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 25.883403778076172, | |
| "learning_rate": 4.253731343283582e-05, | |
| "loss": 0.3661, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.009978611953556538, | |
| "learning_rate": 4.16044776119403e-05, | |
| "loss": 0.2078, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 28.141712188720703, | |
| "learning_rate": 4.067164179104478e-05, | |
| "loss": 0.4631, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.08477218449115753, | |
| "learning_rate": 3.9738805970149254e-05, | |
| "loss": 0.7177, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.6206006407737732, | |
| "learning_rate": 3.8805970149253736e-05, | |
| "loss": 0.0064, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 22.071073532104492, | |
| "learning_rate": 3.787313432835821e-05, | |
| "loss": 0.7343, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 134.8112335205078, | |
| "learning_rate": 3.694029850746269e-05, | |
| "loss": 0.1803, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 54.530120849609375, | |
| "learning_rate": 3.600746268656717e-05, | |
| "loss": 0.135, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.017338775098323822, | |
| "learning_rate": 3.5074626865671645e-05, | |
| "loss": 0.0485, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.008222455158829689, | |
| "learning_rate": 3.414179104477612e-05, | |
| "loss": 0.311, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.012648209929466248, | |
| "learning_rate": 3.32089552238806e-05, | |
| "loss": 0.253, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.00926213525235653, | |
| "learning_rate": 3.227611940298508e-05, | |
| "loss": 0.0245, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 1.1042240858078003, | |
| "learning_rate": 3.1343283582089554e-05, | |
| "loss": 0.2106, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.034143492579460144, | |
| "learning_rate": 3.0410447761194033e-05, | |
| "loss": 0.268, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.12180909514427185, | |
| "learning_rate": 2.9477611940298512e-05, | |
| "loss": 0.0042, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.00459245964884758, | |
| "learning_rate": 2.8544776119402988e-05, | |
| "loss": 0.0004, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.952755905511811, | |
| "eval_loss": 0.26606377959251404, | |
| "eval_runtime": 510.7369, | |
| "eval_samples_per_second": 0.249, | |
| "eval_steps_per_second": 0.125, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.006104098167270422, | |
| "learning_rate": 2.7611940298507467e-05, | |
| "loss": 0.0002, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 37.364593505859375, | |
| "learning_rate": 2.6679104477611942e-05, | |
| "loss": 0.046, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.030606430023908615, | |
| "learning_rate": 2.574626865671642e-05, | |
| "loss": 0.0002, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.3013696074485779, | |
| "learning_rate": 2.4813432835820897e-05, | |
| "loss": 0.5804, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.003663327544927597, | |
| "learning_rate": 2.3880597014925373e-05, | |
| "loss": 0.0001, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.004311152268201113, | |
| "learning_rate": 2.294776119402985e-05, | |
| "loss": 0.0004, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.04659305512905121, | |
| "learning_rate": 2.201492537313433e-05, | |
| "loss": 0.0002, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.037149786949157715, | |
| "learning_rate": 2.1082089552238806e-05, | |
| "loss": 0.001, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.03413153439760208, | |
| "learning_rate": 2.0149253731343285e-05, | |
| "loss": 0.0004, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.041676830500364304, | |
| "learning_rate": 1.921641791044776e-05, | |
| "loss": 0.0056, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.0016505724051967263, | |
| "learning_rate": 1.828358208955224e-05, | |
| "loss": 0.0002, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.0031964355148375034, | |
| "learning_rate": 1.735074626865672e-05, | |
| "loss": 0.0001, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.004493652377277613, | |
| "learning_rate": 1.6417910447761194e-05, | |
| "loss": 0.0001, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.0042636813595891, | |
| "learning_rate": 1.5485074626865673e-05, | |
| "loss": 0.0001, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.028110649436712265, | |
| "learning_rate": 1.455223880597015e-05, | |
| "loss": 0.0003, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.0027514537796378136, | |
| "learning_rate": 1.3619402985074628e-05, | |
| "loss": 0.0001, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.003923814278095961, | |
| "learning_rate": 1.2686567164179105e-05, | |
| "loss": 0.0013, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.001681660651229322, | |
| "learning_rate": 1.1753731343283584e-05, | |
| "loss": 0.1662, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.00280452030710876, | |
| "learning_rate": 1.082089552238806e-05, | |
| "loss": 0.0037, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.03961377218365669, | |
| "learning_rate": 9.888059701492537e-06, | |
| "loss": 0.0002, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.0012254673056304455, | |
| "learning_rate": 8.955223880597016e-06, | |
| "loss": 0.0076, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.0026522520929574966, | |
| "learning_rate": 8.022388059701493e-06, | |
| "loss": 0.0003, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.017898578196763992, | |
| "learning_rate": 7.08955223880597e-06, | |
| "loss": 0.0005, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.001244415994733572, | |
| "learning_rate": 6.156716417910448e-06, | |
| "loss": 0.0002, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.0038874938618391752, | |
| "learning_rate": 5.2238805970149255e-06, | |
| "loss": 0.0001, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.0015441217692568898, | |
| "learning_rate": 4.291044776119403e-06, | |
| "loss": 0.0001, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.002049211412668228, | |
| "learning_rate": 3.358208955223881e-06, | |
| "loss": 0.0001, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.09079094976186752, | |
| "learning_rate": 2.4253731343283585e-06, | |
| "loss": 0.0004, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.00330289825797081, | |
| "learning_rate": 1.4925373134328358e-06, | |
| "loss": 0.0001, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.002893247874453664, | |
| "learning_rate": 5.597014925373135e-07, | |
| "loss": 0.0001, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.00015069438086356968, | |
| "eval_runtime": 601.9366, | |
| "eval_samples_per_second": 0.211, | |
| "eval_steps_per_second": 0.106, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "step": 596, | |
| "total_flos": 3.0513984388253614e+18, | |
| "train_loss": 0.21028166316409014, | |
| "train_runtime": 8990.1785, | |
| "train_samples_per_second": 0.133, | |
| "train_steps_per_second": 0.066 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0027257483452558517, | |
| "eval_runtime": 678.7878, | |
| "eval_samples_per_second": 0.206, | |
| "eval_steps_per_second": 0.103, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.002725747646763921, | |
| "eval_runtime": 663.5855, | |
| "eval_samples_per_second": 0.211, | |
| "eval_steps_per_second": 0.105, | |
| "step": 596 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 596, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 3.0513984388253614e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |