| { | |
| "best_global_step": 686, | |
| "best_metric": 0.893740902474527, | |
| "best_model_checkpoint": "deepfake_model_Video-MAE/checkpoint-686", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 686, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014577259475218658, | |
| "grad_norm": 10.114992141723633, | |
| "learning_rate": 6.521739130434782e-05, | |
| "loss": 0.678, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029154518950437316, | |
| "grad_norm": 9.3939208984375, | |
| "learning_rate": 0.00013768115942028986, | |
| "loss": 0.6897, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.043731778425655975, | |
| "grad_norm": 0.7003632187843323, | |
| "learning_rate": 0.00021014492753623187, | |
| "loss": 0.3415, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05830903790087463, | |
| "grad_norm": 1.3577806949615479, | |
| "learning_rate": 0.0002826086956521739, | |
| "loss": 0.4874, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0728862973760933, | |
| "grad_norm": 0.14603275060653687, | |
| "learning_rate": 0.000355072463768116, | |
| "loss": 0.2387, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08746355685131195, | |
| "grad_norm": 1.7231674194335938, | |
| "learning_rate": 0.00042753623188405797, | |
| "loss": 0.6708, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.10204081632653061, | |
| "grad_norm": 0.02966398000717163, | |
| "learning_rate": 0.0005, | |
| "loss": 0.199, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.11661807580174927, | |
| "grad_norm": 3.2460460662841797, | |
| "learning_rate": 0.0004918962722852512, | |
| "loss": 0.7523, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.13119533527696792, | |
| "grad_norm": 0.2528744339942932, | |
| "learning_rate": 0.00048379254457050244, | |
| "loss": 0.2366, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1457725947521866, | |
| "grad_norm": 33.31367874145508, | |
| "learning_rate": 0.00047568881685575365, | |
| "loss": 0.8824, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16034985422740525, | |
| "grad_norm": 1.4266624450683594, | |
| "learning_rate": 0.00046758508914100487, | |
| "loss": 0.6016, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1749271137026239, | |
| "grad_norm": 3.168113946914673, | |
| "learning_rate": 0.0004594813614262561, | |
| "loss": 0.5234, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.18950437317784258, | |
| "grad_norm": 10.061539649963379, | |
| "learning_rate": 0.0004513776337115073, | |
| "loss": 0.7816, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 3.8101446628570557, | |
| "learning_rate": 0.00044327390599675857, | |
| "loss": 0.4259, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.21865889212827988, | |
| "grad_norm": 1.071272611618042, | |
| "learning_rate": 0.00043517017828200973, | |
| "loss": 0.2919, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.23323615160349853, | |
| "grad_norm": 14.386910438537598, | |
| "learning_rate": 0.00042706645056726094, | |
| "loss": 0.8595, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2478134110787172, | |
| "grad_norm": 0.7727123498916626, | |
| "learning_rate": 0.0004189627228525122, | |
| "loss": 0.431, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.26239067055393583, | |
| "grad_norm": 12.667505264282227, | |
| "learning_rate": 0.0004108589951377634, | |
| "loss": 0.4498, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.27696793002915454, | |
| "grad_norm": 0.17680327594280243, | |
| "learning_rate": 0.0004027552674230146, | |
| "loss": 0.2294, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.2915451895043732, | |
| "grad_norm": 0.14837072789669037, | |
| "learning_rate": 0.0003946515397082658, | |
| "loss": 0.3823, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.30612244897959184, | |
| "grad_norm": 0.4582265317440033, | |
| "learning_rate": 0.000386547811993517, | |
| "loss": 0.7998, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.3206997084548105, | |
| "grad_norm": 3.193190097808838, | |
| "learning_rate": 0.00037844408427876823, | |
| "loss": 0.3674, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.33527696793002915, | |
| "grad_norm": 0.8008913993835449, | |
| "learning_rate": 0.00037034035656401945, | |
| "loss": 0.4262, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.3498542274052478, | |
| "grad_norm": 0.4414026439189911, | |
| "learning_rate": 0.00036223662884927066, | |
| "loss": 0.1923, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.36443148688046645, | |
| "grad_norm": 0.18563510477542877, | |
| "learning_rate": 0.0003541329011345219, | |
| "loss": 0.2135, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.37900874635568516, | |
| "grad_norm": 0.15868167579174042, | |
| "learning_rate": 0.0003460291734197731, | |
| "loss": 0.3817, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.3935860058309038, | |
| "grad_norm": 0.3220128118991852, | |
| "learning_rate": 0.0003379254457050243, | |
| "loss": 0.3343, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 3.0862722396850586, | |
| "learning_rate": 0.0003298217179902755, | |
| "loss": 0.5447, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.4227405247813411, | |
| "grad_norm": 0.8935511112213135, | |
| "learning_rate": 0.00032171799027552674, | |
| "loss": 0.3427, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.43731778425655976, | |
| "grad_norm": 0.4812289774417877, | |
| "learning_rate": 0.00031361426256077795, | |
| "loss": 0.3456, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4518950437317784, | |
| "grad_norm": 0.29880422353744507, | |
| "learning_rate": 0.0003055105348460292, | |
| "loss": 0.5071, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.46647230320699706, | |
| "grad_norm": 0.364977091550827, | |
| "learning_rate": 0.0002974068071312804, | |
| "loss": 0.4138, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.48104956268221577, | |
| "grad_norm": 3.404712677001953, | |
| "learning_rate": 0.0002893030794165316, | |
| "loss": 0.2998, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.4956268221574344, | |
| "grad_norm": 0.4116116762161255, | |
| "learning_rate": 0.00028119935170178287, | |
| "loss": 0.2075, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.5102040816326531, | |
| "grad_norm": 0.44058191776275635, | |
| "learning_rate": 0.000273095623987034, | |
| "loss": 0.4849, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5247813411078717, | |
| "grad_norm": 0.39467599987983704, | |
| "learning_rate": 0.00026499189627228524, | |
| "loss": 0.1196, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.5393586005830904, | |
| "grad_norm": 0.17219886183738708, | |
| "learning_rate": 0.0002568881685575365, | |
| "loss": 0.2312, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.5539358600583091, | |
| "grad_norm": 0.4066016972064972, | |
| "learning_rate": 0.00024878444084278767, | |
| "loss": 0.992, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.5685131195335277, | |
| "grad_norm": 1.068954586982727, | |
| "learning_rate": 0.0002406807131280389, | |
| "loss": 0.3642, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.5830903790087464, | |
| "grad_norm": 0.7630329132080078, | |
| "learning_rate": 0.00023257698541329013, | |
| "loss": 0.4141, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.597667638483965, | |
| "grad_norm": 0.421441912651062, | |
| "learning_rate": 0.00022447325769854132, | |
| "loss": 0.2082, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.6122448979591837, | |
| "grad_norm": 3.339907169342041, | |
| "learning_rate": 0.00021636952998379256, | |
| "loss": 0.3963, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.6268221574344023, | |
| "grad_norm": 3.2065327167510986, | |
| "learning_rate": 0.00020826580226904377, | |
| "loss": 0.2974, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.641399416909621, | |
| "grad_norm": 0.5350266695022583, | |
| "learning_rate": 0.00020016207455429496, | |
| "loss": 0.4629, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.6559766763848397, | |
| "grad_norm": 3.20794677734375, | |
| "learning_rate": 0.0001920583468395462, | |
| "loss": 0.3801, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.6705539358600583, | |
| "grad_norm": 0.5933449268341064, | |
| "learning_rate": 0.00018395461912479742, | |
| "loss": 0.5355, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.685131195335277, | |
| "grad_norm": 2.230889320373535, | |
| "learning_rate": 0.00017585089141004863, | |
| "loss": 0.5586, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.6997084548104956, | |
| "grad_norm": 1.0690261125564575, | |
| "learning_rate": 0.00016774716369529985, | |
| "loss": 0.2688, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.6528918743133545, | |
| "learning_rate": 0.00015964343598055106, | |
| "loss": 0.353, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.7288629737609329, | |
| "grad_norm": 0.5949012041091919, | |
| "learning_rate": 0.00015153970826580228, | |
| "loss": 0.3549, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7434402332361516, | |
| "grad_norm": 0.618296205997467, | |
| "learning_rate": 0.00014343598055105346, | |
| "loss": 0.2767, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.7580174927113703, | |
| "grad_norm": 6.370248317718506, | |
| "learning_rate": 0.0001353322528363047, | |
| "loss": 0.6683, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.7725947521865889, | |
| "grad_norm": 0.6621841192245483, | |
| "learning_rate": 0.00012722852512155592, | |
| "loss": 0.2791, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.7871720116618076, | |
| "grad_norm": 0.6956811547279358, | |
| "learning_rate": 0.00011912479740680714, | |
| "loss": 0.427, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.8017492711370262, | |
| "grad_norm": 0.6581380367279053, | |
| "learning_rate": 0.00011102106969205834, | |
| "loss": 0.4249, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 0.6463478207588196, | |
| "learning_rate": 0.00010291734197730957, | |
| "loss": 0.2741, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.8309037900874635, | |
| "grad_norm": 0.6070910692214966, | |
| "learning_rate": 9.481361426256078e-05, | |
| "loss": 0.6631, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.8454810495626822, | |
| "grad_norm": 0.67457515001297, | |
| "learning_rate": 8.6709886547812e-05, | |
| "loss": 0.3493, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.8600583090379009, | |
| "grad_norm": 0.5490952134132385, | |
| "learning_rate": 7.860615883306321e-05, | |
| "loss": 0.202, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.8746355685131195, | |
| "grad_norm": 0.48928898572921753, | |
| "learning_rate": 7.050243111831443e-05, | |
| "loss": 0.2817, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8892128279883382, | |
| "grad_norm": 3.0225210189819336, | |
| "learning_rate": 6.239870340356564e-05, | |
| "loss": 0.451, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.9037900874635568, | |
| "grad_norm": 0.5548423528671265, | |
| "learning_rate": 5.4294975688816855e-05, | |
| "loss": 0.4454, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.9183673469387755, | |
| "grad_norm": 2.7942357063293457, | |
| "learning_rate": 4.619124797406808e-05, | |
| "loss": 0.5088, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.9329446064139941, | |
| "grad_norm": 0.6783173680305481, | |
| "learning_rate": 3.808752025931929e-05, | |
| "loss": 0.2772, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.9475218658892128, | |
| "grad_norm": 0.6532724499702454, | |
| "learning_rate": 2.9983792544570503e-05, | |
| "loss": 0.2725, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.9620991253644315, | |
| "grad_norm": 0.638654887676239, | |
| "learning_rate": 2.188006482982172e-05, | |
| "loss": 0.3508, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.9766763848396501, | |
| "grad_norm": 0.6031071543693542, | |
| "learning_rate": 1.3776337115072934e-05, | |
| "loss": 0.3531, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.9912536443148688, | |
| "grad_norm": 0.5881929993629456, | |
| "learning_rate": 5.672609400324149e-06, | |
| "loss": 0.1978, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.893740902474527, | |
| "eval_loss": 0.37430018186569214, | |
| "eval_runtime": 445.434, | |
| "eval_samples_per_second": 1.542, | |
| "eval_steps_per_second": 0.386, | |
| "step": 686 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 686, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 3.4192012335104655e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |