| { |
| "best_metric": 0.6891891891891891, |
| "best_model_checkpoint": "videomae-base-finetuned-ASBD_Augm/checkpoint-970", |
| "epoch": 10.076190476190476, |
| "global_step": 1050, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.01, |
| "learning_rate": 4.7619047619047615e-06, |
| "loss": 1.3461, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 9.523809523809523e-06, |
| "loss": 1.3018, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 1.4285714285714285e-05, |
| "loss": 1.3349, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 1.9047619047619046e-05, |
| "loss": 1.1836, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 2.380952380952381e-05, |
| "loss": 1.2575, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 2.857142857142857e-05, |
| "loss": 1.218, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 1.2303, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 3.809523809523809e-05, |
| "loss": 1.2067, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 4.2857142857142856e-05, |
| "loss": 1.0908, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.09, |
| "eval_accuracy": 0.28378378378378377, |
| "eval_loss": 1.6047701835632324, |
| "eval_runtime": 61.5212, |
| "eval_samples_per_second": 1.203, |
| "eval_steps_per_second": 0.114, |
| "step": 97 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 4.761904761904762e-05, |
| "loss": 1.3374, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 4.973544973544973e-05, |
| "loss": 1.1298, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 4.9206349206349204e-05, |
| "loss": 1.1408, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 4.8677248677248676e-05, |
| "loss": 1.3557, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 4.814814814814815e-05, |
| "loss": 1.1369, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 4.761904761904762e-05, |
| "loss": 1.1117, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 4.708994708994709e-05, |
| "loss": 1.0359, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 4.656084656084656e-05, |
| "loss": 0.6933, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 4.603174603174603e-05, |
| "loss": 1.2343, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 4.55026455026455e-05, |
| "loss": 1.0824, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.09, |
| "eval_accuracy": 0.44594594594594594, |
| "eval_loss": 1.061498761177063, |
| "eval_runtime": 47.0858, |
| "eval_samples_per_second": 1.572, |
| "eval_steps_per_second": 0.149, |
| "step": 194 |
| }, |
| { |
| "epoch": 2.01, |
| "learning_rate": 4.4973544973544974e-05, |
| "loss": 0.7294, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.02, |
| "learning_rate": 4.4444444444444447e-05, |
| "loss": 0.8392, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.02, |
| "learning_rate": 4.391534391534391e-05, |
| "loss": 0.5406, |
| "step": 220 |
| }, |
| { |
| "epoch": 2.03, |
| "learning_rate": 4.3386243386243384e-05, |
| "loss": 1.0679, |
| "step": 230 |
| }, |
| { |
| "epoch": 2.04, |
| "learning_rate": 4.2857142857142856e-05, |
| "loss": 0.6298, |
| "step": 240 |
| }, |
| { |
| "epoch": 2.05, |
| "learning_rate": 4.232804232804233e-05, |
| "loss": 0.4648, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.06, |
| "learning_rate": 4.17989417989418e-05, |
| "loss": 0.3894, |
| "step": 260 |
| }, |
| { |
| "epoch": 2.07, |
| "learning_rate": 4.126984126984127e-05, |
| "loss": 0.8449, |
| "step": 270 |
| }, |
| { |
| "epoch": 2.08, |
| "learning_rate": 4.074074074074074e-05, |
| "loss": 0.6964, |
| "step": 280 |
| }, |
| { |
| "epoch": 2.09, |
| "learning_rate": 4.021164021164021e-05, |
| "loss": 0.4003, |
| "step": 290 |
| }, |
| { |
| "epoch": 2.09, |
| "eval_accuracy": 0.6081081081081081, |
| "eval_loss": 1.4701193571090698, |
| "eval_runtime": 46.5535, |
| "eval_samples_per_second": 1.59, |
| "eval_steps_per_second": 0.15, |
| "step": 291 |
| }, |
| { |
| "epoch": 3.01, |
| "learning_rate": 3.968253968253968e-05, |
| "loss": 0.1506, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.02, |
| "learning_rate": 3.9153439153439155e-05, |
| "loss": 0.4478, |
| "step": 310 |
| }, |
| { |
| "epoch": 3.03, |
| "learning_rate": 3.862433862433863e-05, |
| "loss": 0.3388, |
| "step": 320 |
| }, |
| { |
| "epoch": 3.04, |
| "learning_rate": 3.809523809523809e-05, |
| "loss": 0.6625, |
| "step": 330 |
| }, |
| { |
| "epoch": 3.05, |
| "learning_rate": 3.7566137566137564e-05, |
| "loss": 0.4928, |
| "step": 340 |
| }, |
| { |
| "epoch": 3.06, |
| "learning_rate": 3.7037037037037037e-05, |
| "loss": 0.351, |
| "step": 350 |
| }, |
| { |
| "epoch": 3.07, |
| "learning_rate": 3.650793650793651e-05, |
| "loss": 0.5165, |
| "step": 360 |
| }, |
| { |
| "epoch": 3.08, |
| "learning_rate": 3.597883597883598e-05, |
| "loss": 0.3648, |
| "step": 370 |
| }, |
| { |
| "epoch": 3.08, |
| "learning_rate": 3.5449735449735446e-05, |
| "loss": 0.4568, |
| "step": 380 |
| }, |
| { |
| "epoch": 3.09, |
| "eval_accuracy": 0.4594594594594595, |
| "eval_loss": 2.2164571285247803, |
| "eval_runtime": 46.6006, |
| "eval_samples_per_second": 1.588, |
| "eval_steps_per_second": 0.15, |
| "step": 388 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 3.492063492063492e-05, |
| "loss": 0.3497, |
| "step": 390 |
| }, |
| { |
| "epoch": 4.01, |
| "learning_rate": 3.439153439153439e-05, |
| "loss": 0.1095, |
| "step": 400 |
| }, |
| { |
| "epoch": 4.02, |
| "learning_rate": 3.386243386243386e-05, |
| "loss": 0.335, |
| "step": 410 |
| }, |
| { |
| "epoch": 4.03, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.0922, |
| "step": 420 |
| }, |
| { |
| "epoch": 4.04, |
| "learning_rate": 3.280423280423281e-05, |
| "loss": 0.1991, |
| "step": 430 |
| }, |
| { |
| "epoch": 4.05, |
| "learning_rate": 3.227513227513227e-05, |
| "loss": 0.2725, |
| "step": 440 |
| }, |
| { |
| "epoch": 4.06, |
| "learning_rate": 3.1746031746031745e-05, |
| "loss": 0.4291, |
| "step": 450 |
| }, |
| { |
| "epoch": 4.07, |
| "learning_rate": 3.121693121693122e-05, |
| "loss": 0.2107, |
| "step": 460 |
| }, |
| { |
| "epoch": 4.08, |
| "learning_rate": 3.068783068783069e-05, |
| "loss": 0.1437, |
| "step": 470 |
| }, |
| { |
| "epoch": 4.09, |
| "learning_rate": 3.0158730158730158e-05, |
| "loss": 0.133, |
| "step": 480 |
| }, |
| { |
| "epoch": 4.09, |
| "eval_accuracy": 0.5135135135135135, |
| "eval_loss": 2.0912959575653076, |
| "eval_runtime": 46.9991, |
| "eval_samples_per_second": 1.574, |
| "eval_steps_per_second": 0.149, |
| "step": 485 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 2.962962962962963e-05, |
| "loss": 0.0873, |
| "step": 490 |
| }, |
| { |
| "epoch": 5.01, |
| "learning_rate": 2.91005291005291e-05, |
| "loss": 0.0897, |
| "step": 500 |
| }, |
| { |
| "epoch": 5.02, |
| "learning_rate": 2.857142857142857e-05, |
| "loss": 0.1943, |
| "step": 510 |
| }, |
| { |
| "epoch": 5.03, |
| "learning_rate": 2.8042328042328043e-05, |
| "loss": 0.1542, |
| "step": 520 |
| }, |
| { |
| "epoch": 5.04, |
| "learning_rate": 2.7513227513227512e-05, |
| "loss": 0.0933, |
| "step": 530 |
| }, |
| { |
| "epoch": 5.05, |
| "learning_rate": 2.6984126984126984e-05, |
| "loss": 0.0253, |
| "step": 540 |
| }, |
| { |
| "epoch": 5.06, |
| "learning_rate": 2.6455026455026456e-05, |
| "loss": 0.0376, |
| "step": 550 |
| }, |
| { |
| "epoch": 5.07, |
| "learning_rate": 2.5925925925925925e-05, |
| "loss": 0.0712, |
| "step": 560 |
| }, |
| { |
| "epoch": 5.08, |
| "learning_rate": 2.5396825396825397e-05, |
| "loss": 0.1212, |
| "step": 570 |
| }, |
| { |
| "epoch": 5.09, |
| "learning_rate": 2.4867724867724866e-05, |
| "loss": 0.07, |
| "step": 580 |
| }, |
| { |
| "epoch": 5.09, |
| "eval_accuracy": 0.6081081081081081, |
| "eval_loss": 1.7234810590744019, |
| "eval_runtime": 46.9353, |
| "eval_samples_per_second": 1.577, |
| "eval_steps_per_second": 0.149, |
| "step": 582 |
| }, |
| { |
| "epoch": 6.01, |
| "learning_rate": 2.4338624338624338e-05, |
| "loss": 0.0253, |
| "step": 590 |
| }, |
| { |
| "epoch": 6.02, |
| "learning_rate": 2.380952380952381e-05, |
| "loss": 0.0142, |
| "step": 600 |
| }, |
| { |
| "epoch": 6.03, |
| "learning_rate": 2.328042328042328e-05, |
| "loss": 0.0532, |
| "step": 610 |
| }, |
| { |
| "epoch": 6.04, |
| "learning_rate": 2.275132275132275e-05, |
| "loss": 0.0553, |
| "step": 620 |
| }, |
| { |
| "epoch": 6.05, |
| "learning_rate": 2.2222222222222223e-05, |
| "loss": 0.015, |
| "step": 630 |
| }, |
| { |
| "epoch": 6.06, |
| "learning_rate": 2.1693121693121692e-05, |
| "loss": 0.0711, |
| "step": 640 |
| }, |
| { |
| "epoch": 6.06, |
| "learning_rate": 2.1164021164021164e-05, |
| "loss": 0.0506, |
| "step": 650 |
| }, |
| { |
| "epoch": 6.07, |
| "learning_rate": 2.0634920634920636e-05, |
| "loss": 0.0902, |
| "step": 660 |
| }, |
| { |
| "epoch": 6.08, |
| "learning_rate": 2.0105820105820105e-05, |
| "loss": 0.018, |
| "step": 670 |
| }, |
| { |
| "epoch": 6.09, |
| "eval_accuracy": 0.6621621621621622, |
| "eval_loss": 1.897469162940979, |
| "eval_runtime": 46.8915, |
| "eval_samples_per_second": 1.578, |
| "eval_steps_per_second": 0.149, |
| "step": 679 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 1.9576719576719577e-05, |
| "loss": 0.003, |
| "step": 680 |
| }, |
| { |
| "epoch": 7.01, |
| "learning_rate": 1.9047619047619046e-05, |
| "loss": 0.0468, |
| "step": 690 |
| }, |
| { |
| "epoch": 7.02, |
| "learning_rate": 1.8518518518518518e-05, |
| "loss": 0.0035, |
| "step": 700 |
| }, |
| { |
| "epoch": 7.03, |
| "learning_rate": 1.798941798941799e-05, |
| "loss": 0.0029, |
| "step": 710 |
| }, |
| { |
| "epoch": 7.04, |
| "learning_rate": 1.746031746031746e-05, |
| "loss": 0.007, |
| "step": 720 |
| }, |
| { |
| "epoch": 7.05, |
| "learning_rate": 1.693121693121693e-05, |
| "loss": 0.0313, |
| "step": 730 |
| }, |
| { |
| "epoch": 7.06, |
| "learning_rate": 1.6402116402116404e-05, |
| "loss": 0.0197, |
| "step": 740 |
| }, |
| { |
| "epoch": 7.07, |
| "learning_rate": 1.5873015873015872e-05, |
| "loss": 0.0126, |
| "step": 750 |
| }, |
| { |
| "epoch": 7.08, |
| "learning_rate": 1.5343915343915344e-05, |
| "loss": 0.052, |
| "step": 760 |
| }, |
| { |
| "epoch": 7.09, |
| "learning_rate": 1.4814814814814815e-05, |
| "loss": 0.0162, |
| "step": 770 |
| }, |
| { |
| "epoch": 7.09, |
| "eval_accuracy": 0.6621621621621622, |
| "eval_loss": 2.0285696983337402, |
| "eval_runtime": 47.3561, |
| "eval_samples_per_second": 1.563, |
| "eval_steps_per_second": 0.148, |
| "step": 776 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 1.4285714285714285e-05, |
| "loss": 0.0802, |
| "step": 780 |
| }, |
| { |
| "epoch": 8.01, |
| "learning_rate": 1.3756613756613756e-05, |
| "loss": 0.0081, |
| "step": 790 |
| }, |
| { |
| "epoch": 8.02, |
| "learning_rate": 1.3227513227513228e-05, |
| "loss": 0.002, |
| "step": 800 |
| }, |
| { |
| "epoch": 8.03, |
| "learning_rate": 1.2698412698412699e-05, |
| "loss": 0.0015, |
| "step": 810 |
| }, |
| { |
| "epoch": 8.04, |
| "learning_rate": 1.2169312169312169e-05, |
| "loss": 0.0053, |
| "step": 820 |
| }, |
| { |
| "epoch": 8.05, |
| "learning_rate": 1.164021164021164e-05, |
| "loss": 0.0014, |
| "step": 830 |
| }, |
| { |
| "epoch": 8.06, |
| "learning_rate": 1.1111111111111112e-05, |
| "loss": 0.0024, |
| "step": 840 |
| }, |
| { |
| "epoch": 8.07, |
| "learning_rate": 1.0582010582010582e-05, |
| "loss": 0.0562, |
| "step": 850 |
| }, |
| { |
| "epoch": 8.08, |
| "learning_rate": 1.0052910052910053e-05, |
| "loss": 0.0012, |
| "step": 860 |
| }, |
| { |
| "epoch": 8.09, |
| "learning_rate": 9.523809523809523e-06, |
| "loss": 0.0019, |
| "step": 870 |
| }, |
| { |
| "epoch": 8.09, |
| "eval_accuracy": 0.6486486486486487, |
| "eval_loss": 2.069594621658325, |
| "eval_runtime": 46.5861, |
| "eval_samples_per_second": 1.588, |
| "eval_steps_per_second": 0.15, |
| "step": 873 |
| }, |
| { |
| "epoch": 9.01, |
| "learning_rate": 8.994708994708995e-06, |
| "loss": 0.0015, |
| "step": 880 |
| }, |
| { |
| "epoch": 9.02, |
| "learning_rate": 8.465608465608466e-06, |
| "loss": 0.001, |
| "step": 890 |
| }, |
| { |
| "epoch": 9.03, |
| "learning_rate": 7.936507936507936e-06, |
| "loss": 0.0014, |
| "step": 900 |
| }, |
| { |
| "epoch": 9.04, |
| "learning_rate": 7.4074074074074075e-06, |
| "loss": 0.0581, |
| "step": 910 |
| }, |
| { |
| "epoch": 9.04, |
| "learning_rate": 6.878306878306878e-06, |
| "loss": 0.0394, |
| "step": 920 |
| }, |
| { |
| "epoch": 9.05, |
| "learning_rate": 6.349206349206349e-06, |
| "loss": 0.0022, |
| "step": 930 |
| }, |
| { |
| "epoch": 9.06, |
| "learning_rate": 5.82010582010582e-06, |
| "loss": 0.0013, |
| "step": 940 |
| }, |
| { |
| "epoch": 9.07, |
| "learning_rate": 5.291005291005291e-06, |
| "loss": 0.0012, |
| "step": 950 |
| }, |
| { |
| "epoch": 9.08, |
| "learning_rate": 4.7619047619047615e-06, |
| "loss": 0.033, |
| "step": 960 |
| }, |
| { |
| "epoch": 9.09, |
| "learning_rate": 4.232804232804233e-06, |
| "loss": 0.0012, |
| "step": 970 |
| }, |
| { |
| "epoch": 9.09, |
| "eval_accuracy": 0.6891891891891891, |
| "eval_loss": 1.875375747680664, |
| "eval_runtime": 47.0229, |
| "eval_samples_per_second": 1.574, |
| "eval_steps_per_second": 0.149, |
| "step": 970 |
| }, |
| { |
| "epoch": 10.01, |
| "learning_rate": 3.7037037037037037e-06, |
| "loss": 0.0026, |
| "step": 980 |
| }, |
| { |
| "epoch": 10.02, |
| "learning_rate": 3.1746031746031746e-06, |
| "loss": 0.0013, |
| "step": 990 |
| }, |
| { |
| "epoch": 10.03, |
| "learning_rate": 2.6455026455026455e-06, |
| "loss": 0.001, |
| "step": 1000 |
| }, |
| { |
| "epoch": 10.04, |
| "learning_rate": 2.1164021164021164e-06, |
| "loss": 0.0011, |
| "step": 1010 |
| }, |
| { |
| "epoch": 10.05, |
| "learning_rate": 1.5873015873015873e-06, |
| "loss": 0.0414, |
| "step": 1020 |
| }, |
| { |
| "epoch": 10.06, |
| "learning_rate": 1.0582010582010582e-06, |
| "loss": 0.0012, |
| "step": 1030 |
| }, |
| { |
| "epoch": 10.07, |
| "learning_rate": 5.291005291005291e-07, |
| "loss": 0.0012, |
| "step": 1040 |
| }, |
| { |
| "epoch": 10.08, |
| "learning_rate": 0.0, |
| "loss": 0.0042, |
| "step": 1050 |
| }, |
| { |
| "epoch": 10.08, |
| "eval_accuracy": 0.6756756756756757, |
| "eval_loss": 1.889765739440918, |
| "eval_runtime": 46.8481, |
| "eval_samples_per_second": 1.58, |
| "eval_steps_per_second": 0.149, |
| "step": 1050 |
| }, |
| { |
| "epoch": 10.08, |
| "step": 1050, |
| "total_flos": 1.5638389523605094e+19, |
| "train_loss": 0.352122999012825, |
| "train_runtime": 5976.124, |
| "train_samples_per_second": 2.108, |
| "train_steps_per_second": 0.176 |
| }, |
| { |
| "epoch": 10.08, |
| "eval_accuracy": 0.6891891891891891, |
| "eval_loss": 1.875375747680664, |
| "eval_runtime": 46.8722, |
| "eval_samples_per_second": 1.579, |
| "eval_steps_per_second": 0.149, |
| "step": 1050 |
| }, |
| { |
| "epoch": 10.08, |
| "eval_accuracy": 0.7647058823529411, |
| "eval_loss": 1.007310390472412, |
| "eval_runtime": 35.9583, |
| "eval_samples_per_second": 1.891, |
| "eval_steps_per_second": 0.167, |
| "step": 1050 |
| } |
| ], |
| "max_steps": 1050, |
| "num_train_epochs": 9223372036854775807, |
| "total_flos": 1.5638389523605094e+19, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
