| { | |
| "best_metric": 0.8, | |
| "best_model_checkpoint": "videomae-base-ipm_first_videos/checkpoint-123", | |
| "epoch": 48.00606060606061, | |
| "global_step": 146, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.22857142857142856, | |
| "eval_loss": 1.7709606885910034, | |
| "eval_runtime": 56.0244, | |
| "eval_samples_per_second": 0.625, | |
| "eval_steps_per_second": 0.161, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_accuracy": 0.14285714285714285, | |
| "eval_loss": 1.7788584232330322, | |
| "eval_runtime": 54.8936, | |
| "eval_samples_per_second": 0.638, | |
| "eval_steps_per_second": 0.164, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_accuracy": 0.08571428571428572, | |
| "eval_loss": 1.7939355373382568, | |
| "eval_runtime": 57.093, | |
| "eval_samples_per_second": 0.613, | |
| "eval_steps_per_second": 0.158, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 1.7369, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "eval_accuracy": 0.11428571428571428, | |
| "eval_loss": 1.8259599208831787, | |
| "eval_runtime": 49.6198, | |
| "eval_samples_per_second": 0.705, | |
| "eval_steps_per_second": 0.181, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "eval_accuracy": 0.11428571428571428, | |
| "eval_loss": 1.8636661767959595, | |
| "eval_runtime": 47.6299, | |
| "eval_samples_per_second": 0.735, | |
| "eval_steps_per_second": 0.189, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "eval_accuracy": 0.11428571428571428, | |
| "eval_loss": 1.916202187538147, | |
| "eval_runtime": 54.478, | |
| "eval_samples_per_second": 0.642, | |
| "eval_steps_per_second": 0.165, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 3.0303030303030306e-05, | |
| "loss": 1.6934, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "eval_accuracy": 0.11428571428571428, | |
| "eval_loss": 1.979854702949524, | |
| "eval_runtime": 47.3817, | |
| "eval_samples_per_second": 0.739, | |
| "eval_steps_per_second": 0.19, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "eval_accuracy": 0.11428571428571428, | |
| "eval_loss": 2.032222270965576, | |
| "eval_runtime": 47.048, | |
| "eval_samples_per_second": 0.744, | |
| "eval_steps_per_second": 0.191, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "eval_accuracy": 0.11428571428571428, | |
| "eval_loss": 2.147186756134033, | |
| "eval_runtime": 56.4896, | |
| "eval_samples_per_second": 0.62, | |
| "eval_steps_per_second": 0.159, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 1.636, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "eval_accuracy": 0.11428571428571428, | |
| "eval_loss": 2.201059103012085, | |
| "eval_runtime": 47.193, | |
| "eval_samples_per_second": 0.742, | |
| "eval_steps_per_second": 0.191, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "eval_accuracy": 0.11428571428571428, | |
| "eval_loss": 2.3041186332702637, | |
| "eval_runtime": 49.6007, | |
| "eval_samples_per_second": 0.706, | |
| "eval_steps_per_second": 0.181, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "eval_accuracy": 0.11428571428571428, | |
| "eval_loss": 2.202650785446167, | |
| "eval_runtime": 51.3674, | |
| "eval_samples_per_second": 0.681, | |
| "eval_steps_per_second": 0.175, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "eval_accuracy": 0.11428571428571428, | |
| "eval_loss": 2.1011433601379395, | |
| "eval_runtime": 47.3736, | |
| "eval_samples_per_second": 0.739, | |
| "eval_steps_per_second": 0.19, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.882154882154882e-05, | |
| "loss": 1.6069, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "eval_accuracy": 0.11428571428571428, | |
| "eval_loss": 2.0470354557037354, | |
| "eval_runtime": 52.7055, | |
| "eval_samples_per_second": 0.664, | |
| "eval_steps_per_second": 0.171, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "eval_accuracy": 0.11428571428571428, | |
| "eval_loss": 1.9688891172409058, | |
| "eval_runtime": 46.2559, | |
| "eval_samples_per_second": 0.757, | |
| "eval_steps_per_second": 0.195, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "eval_accuracy": 0.11428571428571428, | |
| "eval_loss": 1.911560297012329, | |
| "eval_runtime": 55.4227, | |
| "eval_samples_per_second": 0.632, | |
| "eval_steps_per_second": 0.162, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 4.713804713804714e-05, | |
| "loss": 1.6509, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "eval_accuracy": 0.11428571428571428, | |
| "eval_loss": 1.9125531911849976, | |
| "eval_runtime": 55.4531, | |
| "eval_samples_per_second": 0.631, | |
| "eval_steps_per_second": 0.162, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "eval_accuracy": 0.11428571428571428, | |
| "eval_loss": 2.038973808288574, | |
| "eval_runtime": 47.6175, | |
| "eval_samples_per_second": 0.735, | |
| "eval_steps_per_second": 0.189, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "eval_accuracy": 0.11428571428571428, | |
| "eval_loss": 1.904532551765442, | |
| "eval_runtime": 47.9854, | |
| "eval_samples_per_second": 0.729, | |
| "eval_steps_per_second": 0.188, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 1.5023, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "eval_accuracy": 0.11428571428571428, | |
| "eval_loss": 1.796205759048462, | |
| "eval_runtime": 51.1635, | |
| "eval_samples_per_second": 0.684, | |
| "eval_steps_per_second": 0.176, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "eval_accuracy": 0.34285714285714286, | |
| "eval_loss": 1.618465542793274, | |
| "eval_runtime": 54.8541, | |
| "eval_samples_per_second": 0.638, | |
| "eval_steps_per_second": 0.164, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "eval_accuracy": 0.34285714285714286, | |
| "eval_loss": 1.4067193269729614, | |
| "eval_runtime": 56.983, | |
| "eval_samples_per_second": 0.614, | |
| "eval_steps_per_second": 0.158, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "eval_accuracy": 0.5142857142857142, | |
| "eval_loss": 1.342714548110962, | |
| "eval_runtime": 49.6455, | |
| "eval_samples_per_second": 0.705, | |
| "eval_steps_per_second": 0.181, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 4.3771043771043774e-05, | |
| "loss": 1.2231, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "eval_accuracy": 0.37142857142857144, | |
| "eval_loss": 1.199639081954956, | |
| "eval_runtime": 46.5204, | |
| "eval_samples_per_second": 0.752, | |
| "eval_steps_per_second": 0.193, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "eval_accuracy": 0.5428571428571428, | |
| "eval_loss": 1.067163348197937, | |
| "eval_runtime": 47.5503, | |
| "eval_samples_per_second": 0.736, | |
| "eval_steps_per_second": 0.189, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "eval_accuracy": 0.5142857142857142, | |
| "eval_loss": 1.1605939865112305, | |
| "eval_runtime": 46.8125, | |
| "eval_samples_per_second": 0.748, | |
| "eval_steps_per_second": 0.192, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 4.208754208754209e-05, | |
| "loss": 1.086, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "eval_accuracy": 0.5142857142857142, | |
| "eval_loss": 1.0507373809814453, | |
| "eval_runtime": 47.2904, | |
| "eval_samples_per_second": 0.74, | |
| "eval_steps_per_second": 0.19, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.8726997971534729, | |
| "eval_runtime": 47.448, | |
| "eval_samples_per_second": 0.738, | |
| "eval_steps_per_second": 0.19, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "eval_accuracy": 0.5714285714285714, | |
| "eval_loss": 1.1010727882385254, | |
| "eval_runtime": 46.68, | |
| "eval_samples_per_second": 0.75, | |
| "eval_steps_per_second": 0.193, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 4.0404040404040405e-05, | |
| "loss": 1.1221, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "eval_accuracy": 0.6285714285714286, | |
| "eval_loss": 1.070949673652649, | |
| "eval_runtime": 47.7392, | |
| "eval_samples_per_second": 0.733, | |
| "eval_steps_per_second": 0.189, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "eval_accuracy": 0.34285714285714286, | |
| "eval_loss": 1.2051596641540527, | |
| "eval_runtime": 52.6759, | |
| "eval_samples_per_second": 0.664, | |
| "eval_steps_per_second": 0.171, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "eval_accuracy": 0.3142857142857143, | |
| "eval_loss": 1.1637940406799316, | |
| "eval_runtime": 47.6299, | |
| "eval_samples_per_second": 0.735, | |
| "eval_steps_per_second": 0.189, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "eval_accuracy": 0.5714285714285714, | |
| "eval_loss": 1.0540904998779297, | |
| "eval_runtime": 47.2579, | |
| "eval_samples_per_second": 0.741, | |
| "eval_steps_per_second": 0.19, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 3.872053872053872e-05, | |
| "loss": 1.0483, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "eval_accuracy": 0.5428571428571428, | |
| "eval_loss": 0.9793229103088379, | |
| "eval_runtime": 48.2595, | |
| "eval_samples_per_second": 0.725, | |
| "eval_steps_per_second": 0.186, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.9788510203361511, | |
| "eval_runtime": 46.729, | |
| "eval_samples_per_second": 0.749, | |
| "eval_steps_per_second": 0.193, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "eval_accuracy": 0.6285714285714286, | |
| "eval_loss": 1.0231552124023438, | |
| "eval_runtime": 47.7551, | |
| "eval_samples_per_second": 0.733, | |
| "eval_steps_per_second": 0.188, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.8313, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 1.0134854316711426, | |
| "eval_runtime": 50.8022, | |
| "eval_samples_per_second": 0.689, | |
| "eval_steps_per_second": 0.177, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.9512158036231995, | |
| "eval_runtime": 47.6931, | |
| "eval_samples_per_second": 0.734, | |
| "eval_steps_per_second": 0.189, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "eval_accuracy": 0.7428571428571429, | |
| "eval_loss": 0.6964335441589355, | |
| "eval_runtime": 48.6009, | |
| "eval_samples_per_second": 0.72, | |
| "eval_steps_per_second": 0.185, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 3.535353535353535e-05, | |
| "loss": 0.9314, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 0.7565953135490417, | |
| "eval_runtime": 48.8407, | |
| "eval_samples_per_second": 0.717, | |
| "eval_steps_per_second": 0.184, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.6933528184890747, | |
| "eval_runtime": 46.6051, | |
| "eval_samples_per_second": 0.751, | |
| "eval_steps_per_second": 0.193, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "eval_accuracy": 0.7714285714285715, | |
| "eval_loss": 0.7758246064186096, | |
| "eval_runtime": 46.5497, | |
| "eval_samples_per_second": 0.752, | |
| "eval_steps_per_second": 0.193, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "eval_accuracy": 0.5714285714285714, | |
| "eval_loss": 0.8644936084747314, | |
| "eval_runtime": 47.6569, | |
| "eval_samples_per_second": 0.734, | |
| "eval_steps_per_second": 0.189, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 3.3670033670033675e-05, | |
| "loss": 0.9863, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "eval_accuracy": 0.7714285714285715, | |
| "eval_loss": 0.8204832673072815, | |
| "eval_runtime": 53.1222, | |
| "eval_samples_per_second": 0.659, | |
| "eval_steps_per_second": 0.169, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "eval_accuracy": 0.7714285714285715, | |
| "eval_loss": 0.7429643273353577, | |
| "eval_runtime": 47.3081, | |
| "eval_samples_per_second": 0.74, | |
| "eval_steps_per_second": 0.19, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.7228943705558777, | |
| "eval_runtime": 45.8699, | |
| "eval_samples_per_second": 0.763, | |
| "eval_steps_per_second": 0.196, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 3.198653198653199e-05, | |
| "loss": 0.6828, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.684984028339386, | |
| "eval_runtime": 52.7837, | |
| "eval_samples_per_second": 0.663, | |
| "eval_steps_per_second": 0.171, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "eval_accuracy": 0.7714285714285715, | |
| "eval_loss": 0.6505874395370483, | |
| "eval_runtime": 47.1631, | |
| "eval_samples_per_second": 0.742, | |
| "eval_steps_per_second": 0.191, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "eval_accuracy": 0.7894736842105263, | |
| "eval_loss": 0.6245588660240173, | |
| "eval_runtime": 50.9021, | |
| "eval_samples_per_second": 0.747, | |
| "eval_steps_per_second": 0.196, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.7047864198684692, | |
| "eval_runtime": 43.3232, | |
| "eval_samples_per_second": 0.739, | |
| "eval_steps_per_second": 0.185, | |
| "step": 146 | |
| } | |
| ], | |
| "max_steps": 330, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 6.579455730080809e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |