| { | |
| "best_global_step": 686, | |
| "best_metric": 0.9082969432314411, | |
| "best_model_checkpoint": "deepfake_model_Video/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": 5.51993465423584, | |
| "learning_rate": 2.608695652173913e-05, | |
| "loss": 0.5063, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029154518950437316, | |
| "grad_norm": 1.5133640766143799, | |
| "learning_rate": 5.507246376811594e-05, | |
| "loss": 0.3601, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.043731778425655975, | |
| "grad_norm": 0.24475030601024628, | |
| "learning_rate": 8.405797101449276e-05, | |
| "loss": 0.4217, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05830903790087463, | |
| "grad_norm": 5.526345729827881, | |
| "learning_rate": 0.00011304347826086956, | |
| "loss": 0.6438, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0728862973760933, | |
| "grad_norm": 5.993589878082275, | |
| "learning_rate": 0.00014202898550724638, | |
| "loss": 0.4652, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08746355685131195, | |
| "grad_norm": 3.286891222000122, | |
| "learning_rate": 0.0001710144927536232, | |
| "loss": 0.5641, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.10204081632653061, | |
| "grad_norm": 3.020139455795288, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4536, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.11661807580174927, | |
| "grad_norm": 10.138672828674316, | |
| "learning_rate": 0.0001967585089141005, | |
| "loss": 0.6045, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.13119533527696792, | |
| "grad_norm": 5.395774841308594, | |
| "learning_rate": 0.00019351701782820098, | |
| "loss": 0.3213, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1457725947521866, | |
| "grad_norm": 5.402332782745361, | |
| "learning_rate": 0.00019027552674230147, | |
| "loss": 0.4816, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16034985422740525, | |
| "grad_norm": 0.875799298286438, | |
| "learning_rate": 0.00018703403565640197, | |
| "loss": 0.3053, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1749271137026239, | |
| "grad_norm": 5.320566654205322, | |
| "learning_rate": 0.00018379254457050244, | |
| "loss": 0.5368, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.18950437317784258, | |
| "grad_norm": 5.179769992828369, | |
| "learning_rate": 0.00018055105348460294, | |
| "loss": 0.426, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 4.881013870239258, | |
| "learning_rate": 0.00017730956239870343, | |
| "loss": 0.6606, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.21865889212827988, | |
| "grad_norm": 5.195320129394531, | |
| "learning_rate": 0.0001740680713128039, | |
| "loss": 0.3117, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.23323615160349853, | |
| "grad_norm": 10.992500305175781, | |
| "learning_rate": 0.0001708265802269044, | |
| "loss": 0.5319, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2478134110787172, | |
| "grad_norm": 0.5826265215873718, | |
| "learning_rate": 0.00016758508914100487, | |
| "loss": 0.2159, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.26239067055393583, | |
| "grad_norm": 0.3476707339286804, | |
| "learning_rate": 0.00016434359805510534, | |
| "loss": 0.526, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.27696793002915454, | |
| "grad_norm": 5.252254009246826, | |
| "learning_rate": 0.00016110210696920584, | |
| "loss": 0.4294, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.2915451895043732, | |
| "grad_norm": 5.178494453430176, | |
| "learning_rate": 0.0001578606158833063, | |
| "loss": 0.3978, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.30612244897959184, | |
| "grad_norm": 0.4493197202682495, | |
| "learning_rate": 0.0001546191247974068, | |
| "loss": 0.2959, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.3206997084548105, | |
| "grad_norm": 0.6956782937049866, | |
| "learning_rate": 0.0001513776337115073, | |
| "loss": 0.7341, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.33527696793002915, | |
| "grad_norm": 0.7863760590553284, | |
| "learning_rate": 0.00014813614262560777, | |
| "loss": 0.3599, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.3498542274052478, | |
| "grad_norm": 0.3753291964530945, | |
| "learning_rate": 0.00014489465153970827, | |
| "loss": 0.3036, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.36443148688046645, | |
| "grad_norm": 0.45708099007606506, | |
| "learning_rate": 0.00014165316045380876, | |
| "loss": 0.3175, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.37900874635568516, | |
| "grad_norm": 0.4891352355480194, | |
| "learning_rate": 0.00013841166936790923, | |
| "loss": 0.6339, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.3935860058309038, | |
| "grad_norm": 5.203697204589844, | |
| "learning_rate": 0.00013517017828200973, | |
| "loss": 0.3162, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 5.238792419433594, | |
| "learning_rate": 0.00013192868719611023, | |
| "loss": 0.3201, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.4227405247813411, | |
| "grad_norm": 0.4989798367023468, | |
| "learning_rate": 0.0001286871961102107, | |
| "loss": 0.7276, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.43731778425655976, | |
| "grad_norm": 0.5836043357849121, | |
| "learning_rate": 0.0001254457050243112, | |
| "loss": 0.2891, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4518950437317784, | |
| "grad_norm": 0.558556079864502, | |
| "learning_rate": 0.0001222042139384117, | |
| "loss": 0.3987, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.46647230320699706, | |
| "grad_norm": 5.141500949859619, | |
| "learning_rate": 0.00011896272285251216, | |
| "loss": 0.4808, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.48104956268221577, | |
| "grad_norm": 5.160377025604248, | |
| "learning_rate": 0.00011572123176661264, | |
| "loss": 0.5713, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.4956268221574344, | |
| "grad_norm": 0.4454505443572998, | |
| "learning_rate": 0.00011247974068071314, | |
| "loss": 0.203, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.5102040816326531, | |
| "grad_norm": 5.493250370025635, | |
| "learning_rate": 0.00010923824959481361, | |
| "loss": 0.2357, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5247813411078717, | |
| "grad_norm": 0.41081610321998596, | |
| "learning_rate": 0.0001059967585089141, | |
| "loss": 0.5735, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.5393586005830904, | |
| "grad_norm": 0.6018832921981812, | |
| "learning_rate": 0.0001027552674230146, | |
| "loss": 0.4961, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.5539358600583091, | |
| "grad_norm": 5.193027496337891, | |
| "learning_rate": 9.951377633711507e-05, | |
| "loss": 0.2182, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.5685131195335277, | |
| "grad_norm": 5.439088344573975, | |
| "learning_rate": 9.627228525121557e-05, | |
| "loss": 0.3472, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.5830903790087464, | |
| "grad_norm": 0.3489497900009155, | |
| "learning_rate": 9.303079416531605e-05, | |
| "loss": 0.2154, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.597667638483965, | |
| "grad_norm": 0.35388824343681335, | |
| "learning_rate": 8.978930307941653e-05, | |
| "loss": 0.4423, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.6122448979591837, | |
| "grad_norm": 0.3389256000518799, | |
| "learning_rate": 8.654781199351703e-05, | |
| "loss": 0.22, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.6268221574344023, | |
| "grad_norm": 5.2634806632995605, | |
| "learning_rate": 8.330632090761751e-05, | |
| "loss": 0.5363, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.641399416909621, | |
| "grad_norm": 0.7350614070892334, | |
| "learning_rate": 8.006482982171798e-05, | |
| "loss": 0.4039, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.6559766763848397, | |
| "grad_norm": 0.8046320676803589, | |
| "learning_rate": 7.682333873581848e-05, | |
| "loss": 0.5529, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.6705539358600583, | |
| "grad_norm": 4.921350479125977, | |
| "learning_rate": 7.358184764991896e-05, | |
| "loss": 0.5457, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.685131195335277, | |
| "grad_norm": 4.605738162994385, | |
| "learning_rate": 7.034035656401945e-05, | |
| "loss": 0.5231, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.6997084548104956, | |
| "grad_norm": 0.7577686905860901, | |
| "learning_rate": 6.709886547811994e-05, | |
| "loss": 0.1105, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 5.336033821105957, | |
| "learning_rate": 6.385737439222043e-05, | |
| "loss": 0.518, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.7288629737609329, | |
| "grad_norm": 5.111513614654541, | |
| "learning_rate": 6.061588330632091e-05, | |
| "loss": 0.8384, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7434402332361516, | |
| "grad_norm": 4.68665885925293, | |
| "learning_rate": 5.7374392220421394e-05, | |
| "loss": 0.5242, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.7580174927113703, | |
| "grad_norm": 1.1149446964263916, | |
| "learning_rate": 5.4132901134521884e-05, | |
| "loss": 0.257, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.7725947521865889, | |
| "grad_norm": 0.9691628813743591, | |
| "learning_rate": 5.089141004862237e-05, | |
| "loss": 0.2541, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.7871720116618076, | |
| "grad_norm": 0.6562572121620178, | |
| "learning_rate": 4.764991896272286e-05, | |
| "loss": 0.292, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.8017492711370262, | |
| "grad_norm": 0.4979492127895355, | |
| "learning_rate": 4.440842787682334e-05, | |
| "loss": 0.1124, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 5.363987445831299, | |
| "learning_rate": 4.1166936790923824e-05, | |
| "loss": 1.0071, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.8309037900874635, | |
| "grad_norm": 5.133065700531006, | |
| "learning_rate": 3.7925445705024314e-05, | |
| "loss": 0.4884, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.8454810495626822, | |
| "grad_norm": 0.6133359670639038, | |
| "learning_rate": 3.46839546191248e-05, | |
| "loss": 0.2977, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.8600583090379009, | |
| "grad_norm": 5.183351039886475, | |
| "learning_rate": 3.144246353322529e-05, | |
| "loss": 0.2104, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.8746355685131195, | |
| "grad_norm": 0.5160303115844727, | |
| "learning_rate": 2.820097244732577e-05, | |
| "loss": 0.3086, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8892128279883382, | |
| "grad_norm": 5.336419105529785, | |
| "learning_rate": 2.4959481361426257e-05, | |
| "loss": 0.4723, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.9037900874635568, | |
| "grad_norm": 0.4093821048736572, | |
| "learning_rate": 2.1717990275526743e-05, | |
| "loss": 0.3188, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.9183673469387755, | |
| "grad_norm": 0.4140465259552002, | |
| "learning_rate": 1.847649918962723e-05, | |
| "loss": 0.2983, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.9329446064139941, | |
| "grad_norm": 10.93191909790039, | |
| "learning_rate": 1.5235008103727717e-05, | |
| "loss": 0.9125, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.9475218658892128, | |
| "grad_norm": 5.311867713928223, | |
| "learning_rate": 1.1993517017828202e-05, | |
| "loss": 0.4714, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.9620991253644315, | |
| "grad_norm": 0.53305584192276, | |
| "learning_rate": 8.752025931928688e-06, | |
| "loss": 0.2829, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.9766763848396501, | |
| "grad_norm": 5.311007022857666, | |
| "learning_rate": 5.510534846029174e-06, | |
| "loss": 0.786, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.9912536443148688, | |
| "grad_norm": 0.5248007774353027, | |
| "learning_rate": 2.2690437601296597e-06, | |
| "loss": 0.6467, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9082969432314411, | |
| "eval_loss": 0.3608160614967346, | |
| "eval_runtime": 396.3874, | |
| "eval_samples_per_second": 1.733, | |
| "eval_steps_per_second": 0.434, | |
| "step": 686 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 686, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "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 | |
| } | |