Invalid JSON:Unexpected token 'N', ..."ad_norm": NaN,
"... is not valid JSON
| { | |
| "best_metric": 0.10166666666666667, | |
| "best_model_checkpoint": "resnet-18-finetuned-cifar10/checkpoint-273", | |
| "epoch": 2.9945155393053016, | |
| "eval_steps": 500, | |
| "global_step": 819, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0975609756097564e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2195121951219513e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8292682926829268e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4390243902439026e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.048780487804878e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6585365853658535e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.26829268292683e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.878048780487805e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.94572591587517e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.877883310719132e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.810040705563094e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.742198100407056e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.674355495251018e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.60651289009498e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5386702849389416e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.470827679782904e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.402985074626866e-05, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.335142469470828e-05, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.26729986431479e-05, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.199457259158752e-05, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.131614654002714e-05, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.063772048846676e-05, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.995929443690638e-05, | |
| "loss": 0.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9280868385345995e-05, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.860244233378562e-05, | |
| "loss": 0.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.792401628222524e-05, | |
| "loss": 0.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.724559023066486e-05, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.10166666666666667, | |
| "eval_loss": NaN, | |
| "eval_runtime": 135.8532, | |
| "eval_samples_per_second": 110.413, | |
| "eval_steps_per_second": 3.452, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.656716417910448e-05, | |
| "loss": 0.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.58887381275441e-05, | |
| "loss": 0.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.521031207598372e-05, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.453188602442334e-05, | |
| "loss": 0.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.385345997286296e-05, | |
| "loss": 0.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3175033921302575e-05, | |
| "loss": 0.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.24966078697422e-05, | |
| "loss": 0.0, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.181818181818182e-05, | |
| "loss": 0.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.113975576662144e-05, | |
| "loss": 0.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.046132971506106e-05, | |
| "loss": 0.0, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9782903663500678e-05, | |
| "loss": 0.0, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.91044776119403e-05, | |
| "loss": 0.0, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.842605156037992e-05, | |
| "loss": 0.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7747625508819542e-05, | |
| "loss": 0.0, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7069199457259158e-05, | |
| "loss": 0.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.639077340569878e-05, | |
| "loss": 0.0, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.57123473541384e-05, | |
| "loss": 0.0, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5033921302578023e-05, | |
| "loss": 0.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4355495251017642e-05, | |
| "loss": 0.0, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.367706919945726e-05, | |
| "loss": 0.0, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.299864314789688e-05, | |
| "loss": 0.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2320217096336503e-05, | |
| "loss": 0.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.164179104477612e-05, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0963364993215738e-05, | |
| "loss": 0.0, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.028493894165536e-05, | |
| "loss": 0.0, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.960651289009498e-05, | |
| "loss": 0.0, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.89280868385346e-05, | |
| "loss": 0.0, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.10166666666666667, | |
| "eval_loss": NaN, | |
| "eval_runtime": 132.0195, | |
| "eval_samples_per_second": 113.62, | |
| "eval_steps_per_second": 3.553, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.824966078697422e-05, | |
| "loss": 0.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.757123473541384e-05, | |
| "loss": 0.0, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.689280868385346e-05, | |
| "loss": 0.0, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6214382632293083e-05, | |
| "loss": 0.0, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.55359565807327e-05, | |
| "loss": 0.0, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.485753052917232e-05, | |
| "loss": 0.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.417910447761194e-05, | |
| "loss": 0.0, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3500678426051561e-05, | |
| "loss": 0.0, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.282225237449118e-05, | |
| "loss": 0.0, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2143826322930801e-05, | |
| "loss": 0.0, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1465400271370422e-05, | |
| "loss": 0.0, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0786974219810041e-05, | |
| "loss": 0.0, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.010854816824966e-05, | |
| "loss": 0.0, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.430122116689281e-06, | |
| "loss": 0.0, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.751696065128902e-06, | |
| "loss": 0.0, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.073270013568522e-06, | |
| "loss": 0.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.394843962008141e-06, | |
| "loss": 0.0, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.716417910447762e-06, | |
| "loss": 0.0, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.037991858887382e-06, | |
| "loss": 0.0, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.359565807327002e-06, | |
| "loss": 0.0, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.681139755766622e-06, | |
| "loss": 0.0, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.002713704206242e-06, | |
| "loss": 0.0, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.324287652645862e-06, | |
| "loss": 0.0, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.645861601085482e-06, | |
| "loss": 0.0, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.967435549525102e-06, | |
| "loss": 0.0, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.289009497964722e-06, | |
| "loss": 0.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.10583446404342e-07, | |
| "loss": 0.0, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.10166666666666667, | |
| "eval_loss": NaN, | |
| "eval_runtime": 130.8726, | |
| "eval_samples_per_second": 114.615, | |
| "eval_steps_per_second": 3.584, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "step": 819, | |
| "total_flos": 1.0585264325663785e+18, | |
| "train_loss": 0.0, | |
| "train_runtime": 811.0273, | |
| "train_samples_per_second": 129.465, | |
| "train_steps_per_second": 1.01 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 819, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1.0585264325663785e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |