| { | |
| "best_metric": 0.7872340425531915, | |
| "best_model_checkpoint": "videomae-base-finetuned-movienet-take2-finetuned-movienet-take3/checkpoint-186", | |
| "epoch": 3.024662162162162, | |
| "global_step": 631, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5.630630630630631e-07, | |
| "loss": 0.0705, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.1261261261261262e-06, | |
| "loss": 0.0143, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.6891891891891894e-06, | |
| "loss": 0.0012, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.2522522522522524e-06, | |
| "loss": 0.0015, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.8153153153153154e-06, | |
| "loss": 0.0009, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.3783783783783788e-06, | |
| "loss": 0.0009, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.941441441441441e-06, | |
| "loss": 0.1339, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.504504504504505e-06, | |
| "loss": 0.0011, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.067567567567568e-06, | |
| "loss": 0.001, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.630630630630631e-06, | |
| "loss": 0.0009, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 6.193693693693694e-06, | |
| "loss": 0.0862, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 6.7567567567567575e-06, | |
| "loss": 0.0115, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 7.31981981981982e-06, | |
| "loss": 0.001, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 7.882882882882883e-06, | |
| "loss": 0.0009, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.445945945945946e-06, | |
| "loss": 0.0234, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.00900900900901e-06, | |
| "loss": 0.0018, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.572072072072071e-06, | |
| "loss": 0.0547, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.0135135135135136e-05, | |
| "loss": 0.0017, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.7872340425531915, | |
| "eval_loss": 1.2727888822555542, | |
| "eval_runtime": 128.4612, | |
| "eval_samples_per_second": 1.463, | |
| "eval_steps_per_second": 0.187, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.06981981981982e-05, | |
| "loss": 0.0011, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.1261261261261261e-05, | |
| "loss": 0.0017, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.1824324324324325e-05, | |
| "loss": 0.0013, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.2387387387387388e-05, | |
| "loss": 0.0026, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.2950450450450452e-05, | |
| "loss": 0.0007, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.3513513513513515e-05, | |
| "loss": 0.0007, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.4076576576576578e-05, | |
| "loss": 0.0009, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.463963963963964e-05, | |
| "loss": 0.0008, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.5202702702702704e-05, | |
| "loss": 0.0006, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.5765765765765765e-05, | |
| "loss": 0.0041, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1.632882882882883e-05, | |
| "loss": 0.0008, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1.6891891891891892e-05, | |
| "loss": 0.0721, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1.7454954954954956e-05, | |
| "loss": 0.042, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.801801801801802e-05, | |
| "loss": 0.0018, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.8581081081081082e-05, | |
| "loss": 0.003, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.9144144144144142e-05, | |
| "loss": 0.0814, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.970720720720721e-05, | |
| "loss": 0.0007, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 2.0270270270270273e-05, | |
| "loss": 0.0018, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.1183, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_accuracy": 0.7712765957446809, | |
| "eval_loss": 1.4289134740829468, | |
| "eval_runtime": 144.8537, | |
| "eval_samples_per_second": 1.298, | |
| "eval_steps_per_second": 0.166, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.13963963963964e-05, | |
| "loss": 0.1161, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.195945945945946e-05, | |
| "loss": 0.0151, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.2522522522522523e-05, | |
| "loss": 0.0024, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.3085585585585586e-05, | |
| "loss": 0.0209, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.364864864864865e-05, | |
| "loss": 0.0009, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.4211711711711713e-05, | |
| "loss": 0.0926, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.4774774774774777e-05, | |
| "loss": 0.1813, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.533783783783784e-05, | |
| "loss": 0.2054, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.5900900900900903e-05, | |
| "loss": 0.0592, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.6463963963963967e-05, | |
| "loss": 0.11, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.702702702702703e-05, | |
| "loss": 0.1377, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.7590090090090094e-05, | |
| "loss": 0.0748, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.8153153153153157e-05, | |
| "loss": 0.0015, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.8716216216216217e-05, | |
| "loss": 0.0219, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.927927927927928e-05, | |
| "loss": 0.0791, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.9842342342342344e-05, | |
| "loss": 0.1388, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 3.0405405405405407e-05, | |
| "loss": 0.1931, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 3.096846846846847e-05, | |
| "loss": 0.066, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_accuracy": 0.7819148936170213, | |
| "eval_loss": 1.345596432685852, | |
| "eval_runtime": 129.9233, | |
| "eval_samples_per_second": 1.447, | |
| "eval_steps_per_second": 0.185, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.153153153153153e-05, | |
| "loss": 0.4016, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.20945945945946e-05, | |
| "loss": 0.0978, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.265765765765766e-05, | |
| "loss": 0.3239, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.3220720720720724e-05, | |
| "loss": 0.2957, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.3783783783783784e-05, | |
| "loss": 0.3396, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.4346846846846844e-05, | |
| "loss": 0.085, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.490990990990991e-05, | |
| "loss": 0.0595, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.547297297297297e-05, | |
| "loss": 0.4123, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_accuracy": 0.7395833333333334, | |
| "eval_loss": 1.4086805582046509, | |
| "eval_runtime": 166.2862, | |
| "eval_samples_per_second": 1.155, | |
| "eval_steps_per_second": 0.144, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_accuracy": 0.7395833333333334, | |
| "eval_loss": 1.4086805582046509, | |
| "eval_runtime": 167.2166, | |
| "eval_samples_per_second": 1.148, | |
| "eval_steps_per_second": 0.144, | |
| "step": 631 | |
| } | |
| ], | |
| "max_steps": 2960, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 6.25416549666177e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |