| { | |
| "best_metric": 0.9428571428571428, | |
| "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-375", | |
| "epoch": 4.2, | |
| "global_step": 375, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.3157894736842106e-05, | |
| "loss": 2.3419, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 2.2624, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 3.9473684210526316e-05, | |
| "loss": 2.179, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.9703264094955494e-05, | |
| "loss": 2.1293, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.821958456973294e-05, | |
| "loss": 2.1553, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.673590504451038e-05, | |
| "loss": 1.8437, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.525222551928784e-05, | |
| "loss": 1.8376, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.5571428571428572, | |
| "eval_loss": 1.3921232223510742, | |
| "eval_runtime": 12.9943, | |
| "eval_samples_per_second": 5.387, | |
| "eval_steps_per_second": 1.385, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.3768545994065286e-05, | |
| "loss": 1.4008, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.228486646884273e-05, | |
| "loss": 1.1143, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.080118694362018e-05, | |
| "loss": 0.998, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.9317507418397627e-05, | |
| "loss": 0.8409, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.783382789317508e-05, | |
| "loss": 1.0214, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.635014836795252e-05, | |
| "loss": 0.9771, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.4866468842729974e-05, | |
| "loss": 0.9039, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.338278931750742e-05, | |
| "loss": 0.569, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_accuracy": 0.7714285714285715, | |
| "eval_loss": 0.6125089526176453, | |
| "eval_runtime": 12.3209, | |
| "eval_samples_per_second": 5.681, | |
| "eval_steps_per_second": 1.461, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 3.189910979228487e-05, | |
| "loss": 0.6987, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 3.0415430267062318e-05, | |
| "loss": 0.4678, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.8931750741839762e-05, | |
| "loss": 0.382, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.744807121661721e-05, | |
| "loss": 0.3473, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.5964391691394662e-05, | |
| "loss": 0.4796, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.4480712166172106e-05, | |
| "loss": 0.4357, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.2997032640949558e-05, | |
| "loss": 0.32, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_accuracy": 0.7857142857142857, | |
| "eval_loss": 0.48143571615219116, | |
| "eval_runtime": 12.6305, | |
| "eval_samples_per_second": 5.542, | |
| "eval_steps_per_second": 1.425, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 2.1513353115727002e-05, | |
| "loss": 0.3037, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 2.0029673590504454e-05, | |
| "loss": 0.4254, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.85459940652819e-05, | |
| "loss": 0.1861, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 1.706231454005935e-05, | |
| "loss": 0.3395, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 1.5578635014836794e-05, | |
| "loss": 0.3721, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 1.4094955489614246e-05, | |
| "loss": 0.0912, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 1.2611275964391692e-05, | |
| "loss": 0.1102, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 1.112759643916914e-05, | |
| "loss": 0.2384, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.31621307134628296, | |
| "eval_runtime": 12.1865, | |
| "eval_samples_per_second": 5.744, | |
| "eval_steps_per_second": 1.477, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 9.643916913946588e-06, | |
| "loss": 0.0773, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 8.160237388724036e-06, | |
| "loss": 0.1736, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 6.676557863501484e-06, | |
| "loss": 0.1724, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 5.192878338278932e-06, | |
| "loss": 0.0376, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 3.7091988130563796e-06, | |
| "loss": 0.1776, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 2.225519287833828e-06, | |
| "loss": 0.0882, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 7.41839762611276e-07, | |
| "loss": 0.0338, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "eval_accuracy": 0.9428571428571428, | |
| "eval_loss": 0.17980989813804626, | |
| "eval_runtime": 12.3133, | |
| "eval_samples_per_second": 5.685, | |
| "eval_steps_per_second": 1.462, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "step": 375, | |
| "total_flos": 1.86923023515648e+18, | |
| "train_loss": 0.7618915402094523, | |
| "train_runtime": 844.1562, | |
| "train_samples_per_second": 1.777, | |
| "train_steps_per_second": 0.444 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "eval_accuracy": 0.896774193548387, | |
| "eval_loss": 0.27069538831710815, | |
| "eval_runtime": 30.7865, | |
| "eval_samples_per_second": 5.035, | |
| "eval_steps_per_second": 1.267, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "eval_accuracy": 0.896774193548387, | |
| "eval_loss": 0.2612727880477905, | |
| "eval_runtime": 28.5494, | |
| "eval_samples_per_second": 5.429, | |
| "eval_steps_per_second": 1.366, | |
| "step": 375 | |
| } | |
| ], | |
| "max_steps": 375, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 1.86923023515648e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |