| { | |
| "best_metric": 0.6666666666666666, | |
| "best_model_checkpoint": "videomae-base-finetuned-ucf1012bovi-subset/checkpoint-144", | |
| "epoch": 7.1, | |
| "global_step": 280, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 0.7036, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.6919, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.960317460317461e-05, | |
| "loss": 0.7118, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.5714285714285714, | |
| "eval_loss": 0.6813519597053528, | |
| "eval_runtime": 17.1635, | |
| "eval_samples_per_second": 1.224, | |
| "eval_steps_per_second": 0.175, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 0.7934, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.563492063492064e-05, | |
| "loss": 0.7599, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 4.3650793650793655e-05, | |
| "loss": 0.6935, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.8238, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_accuracy": 0.5714285714285714, | |
| "eval_loss": 0.6640704274177551, | |
| "eval_runtime": 17.0264, | |
| "eval_samples_per_second": 1.233, | |
| "eval_steps_per_second": 0.176, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 0.6964, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 3.76984126984127e-05, | |
| "loss": 0.6997, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.6892, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_accuracy": 0.47619047619047616, | |
| "eval_loss": 0.6934835910797119, | |
| "eval_runtime": 16.5245, | |
| "eval_samples_per_second": 1.271, | |
| "eval_steps_per_second": 0.182, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.3730158730158734e-05, | |
| "loss": 0.7053, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 0.6779, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 2.9761904761904762e-05, | |
| "loss": 0.6888, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.7013, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.6818560361862183, | |
| "eval_runtime": 17.5029, | |
| "eval_samples_per_second": 1.2, | |
| "eval_steps_per_second": 0.171, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 2.5793650793650796e-05, | |
| "loss": 0.7085, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 0.6941, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 2.1825396825396827e-05, | |
| "loss": 0.6897, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 1.984126984126984e-05, | |
| "loss": 0.6871, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "eval_accuracy": 0.5714285714285714, | |
| "eval_loss": 0.6750560998916626, | |
| "eval_runtime": 18.5719, | |
| "eval_samples_per_second": 1.131, | |
| "eval_steps_per_second": 0.162, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 0.6712, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 0.6929, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.7159, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "eval_accuracy": 0.5238095238095238, | |
| "eval_loss": 0.6854279041290283, | |
| "eval_runtime": 18.2412, | |
| "eval_samples_per_second": 1.151, | |
| "eval_steps_per_second": 0.164, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 1.1904761904761905e-05, | |
| "loss": 0.6867, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 9.92063492063492e-06, | |
| "loss": 0.6832, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 0.6992, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 5.9523809523809525e-06, | |
| "loss": 0.6884, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.6735024452209473, | |
| "eval_runtime": 17.7454, | |
| "eval_samples_per_second": 1.183, | |
| "eval_steps_per_second": 0.169, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 3.968253968253968e-06, | |
| "loss": 0.6854, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 1.984126984126984e-06, | |
| "loss": 0.6846, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 0.0, | |
| "loss": 0.6905, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "eval_accuracy": 0.6190476190476191, | |
| "eval_loss": 0.6739117503166199, | |
| "eval_runtime": 16.357, | |
| "eval_samples_per_second": 1.284, | |
| "eval_steps_per_second": 0.183, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "step": 280, | |
| "total_flos": 2.783708292879876e+18, | |
| "train_loss": 0.7040540405682155, | |
| "train_runtime": 2623.4719, | |
| "train_samples_per_second": 0.854, | |
| "train_steps_per_second": 0.107 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.6818560361862183, | |
| "eval_runtime": 16.5475, | |
| "eval_samples_per_second": 1.269, | |
| "eval_steps_per_second": 0.181, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.681856095790863, | |
| "eval_runtime": 18.2305, | |
| "eval_samples_per_second": 1.152, | |
| "eval_steps_per_second": 0.165, | |
| "step": 280 | |
| } | |
| ], | |
| "max_steps": 280, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 2.783708292879876e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |