| { |
| "best_metric": 1.0, |
| "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/MY DATA/VideoMAE_LSA64SR_8_kineticsFinetuned/checkpoint-864", |
| "epoch": 7.049956597222222, |
| "eval_steps": 500, |
| "global_step": 2304, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.017361111111111112, |
| "grad_norm": 30.59429931640625, |
| "learning_rate": 8.59375e-06, |
| "loss": 16.5865, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.034722222222222224, |
| "grad_norm": 58.47425079345703, |
| "learning_rate": 1.71875e-05, |
| "loss": 14.4931, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.05, |
| "eval_accuracy": 0.76171875, |
| "eval_f1": 0.7337064844877345, |
| "eval_loss": 2.1667022705078125, |
| "eval_precision": 0.7967904491341992, |
| "eval_recall": 0.76171875, |
| "eval_runtime": 358.4399, |
| "eval_samples_per_second": 0.714, |
| "eval_steps_per_second": 0.357, |
| "step": 288 |
| }, |
| { |
| "epoch": 1.0020399305555556, |
| "grad_norm": 56.96902084350586, |
| "learning_rate": 2.578125e-05, |
| "loss": 10.1888, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.0194010416666666, |
| "grad_norm": 40.733245849609375, |
| "learning_rate": 3.446180555555556e-05, |
| "loss": 5.571, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.0367621527777777, |
| "grad_norm": 22.693687438964844, |
| "learning_rate": 4.3142361111111114e-05, |
| "loss": 2.5661, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0499565972222222, |
| "eval_accuracy": 0.98046875, |
| "eval_f1": 0.9751984126984128, |
| "eval_loss": 0.2914118766784668, |
| "eval_precision": 0.9734375, |
| "eval_recall": 0.98046875, |
| "eval_runtime": 373.8944, |
| "eval_samples_per_second": 0.685, |
| "eval_steps_per_second": 0.342, |
| "step": 576 |
| }, |
| { |
| "epoch": 2.004123263888889, |
| "grad_norm": 14.30058479309082, |
| "learning_rate": 4.979745370370371e-05, |
| "loss": 1.2886, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.021484375, |
| "grad_norm": 3.734978199005127, |
| "learning_rate": 4.88329475308642e-05, |
| "loss": 0.467, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.038845486111111, |
| "grad_norm": 5.726315498352051, |
| "learning_rate": 4.7868441358024695e-05, |
| "loss": 0.27, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.0499565972222222, |
| "eval_accuracy": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 0.016510166227817535, |
| "eval_precision": 1.0, |
| "eval_recall": 1.0, |
| "eval_runtime": 360.6612, |
| "eval_samples_per_second": 0.71, |
| "eval_steps_per_second": 0.355, |
| "step": 864 |
| }, |
| { |
| "epoch": 3.006206597222222, |
| "grad_norm": 0.7236186265945435, |
| "learning_rate": 4.6903935185185186e-05, |
| "loss": 0.1411, |
| "step": 900 |
| }, |
| { |
| "epoch": 3.023567708333333, |
| "grad_norm": 0.646736741065979, |
| "learning_rate": 4.5939429012345683e-05, |
| "loss": 0.0818, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.0409288194444444, |
| "grad_norm": 0.1304841786623001, |
| "learning_rate": 4.4974922839506174e-05, |
| "loss": 0.0167, |
| "step": 1100 |
| }, |
| { |
| "epoch": 3.0499565972222222, |
| "eval_accuracy": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 0.0026155859231948853, |
| "eval_precision": 1.0, |
| "eval_recall": 1.0, |
| "eval_runtime": 366.9721, |
| "eval_samples_per_second": 0.698, |
| "eval_steps_per_second": 0.349, |
| "step": 1152 |
| }, |
| { |
| "epoch": 4.008289930555556, |
| "grad_norm": 0.15498673915863037, |
| "learning_rate": 4.401041666666667e-05, |
| "loss": 0.1066, |
| "step": 1200 |
| }, |
| { |
| "epoch": 4.025651041666666, |
| "grad_norm": 0.08085419237613678, |
| "learning_rate": 4.304591049382716e-05, |
| "loss": 0.0249, |
| "step": 1300 |
| }, |
| { |
| "epoch": 4.043012152777778, |
| "grad_norm": 0.07580918073654175, |
| "learning_rate": 4.208140432098765e-05, |
| "loss": 0.037, |
| "step": 1400 |
| }, |
| { |
| "epoch": 4.049956597222222, |
| "eval_accuracy": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 0.0018264222890138626, |
| "eval_precision": 1.0, |
| "eval_recall": 1.0, |
| "eval_runtime": 367.3729, |
| "eval_samples_per_second": 0.697, |
| "eval_steps_per_second": 0.348, |
| "step": 1440 |
| }, |
| { |
| "epoch": 5.010373263888889, |
| "grad_norm": 0.05828005447983742, |
| "learning_rate": 4.111689814814815e-05, |
| "loss": 0.0138, |
| "step": 1500 |
| }, |
| { |
| "epoch": 5.027734375, |
| "grad_norm": 0.024922983720898628, |
| "learning_rate": 4.015239197530865e-05, |
| "loss": 0.004, |
| "step": 1600 |
| }, |
| { |
| "epoch": 5.045095486111111, |
| "grad_norm": 0.028165679425001144, |
| "learning_rate": 3.918788580246914e-05, |
| "loss": 0.045, |
| "step": 1700 |
| }, |
| { |
| "epoch": 5.049956597222222, |
| "eval_accuracy": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 0.0008003702387213707, |
| "eval_precision": 1.0, |
| "eval_recall": 1.0, |
| "eval_runtime": 358.6553, |
| "eval_samples_per_second": 0.714, |
| "eval_steps_per_second": 0.357, |
| "step": 1728 |
| }, |
| { |
| "epoch": 6.012456597222222, |
| "grad_norm": 0.04725846275687218, |
| "learning_rate": 3.822337962962963e-05, |
| "loss": 0.0031, |
| "step": 1800 |
| }, |
| { |
| "epoch": 6.029817708333334, |
| "grad_norm": 0.02346525527536869, |
| "learning_rate": 3.7258873456790126e-05, |
| "loss": 0.0416, |
| "step": 1900 |
| }, |
| { |
| "epoch": 6.0471788194444445, |
| "grad_norm": 0.024501143023371696, |
| "learning_rate": 3.629436728395062e-05, |
| "loss": 0.006, |
| "step": 2000 |
| }, |
| { |
| "epoch": 6.049956597222222, |
| "eval_accuracy": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 0.0006333552300930023, |
| "eval_precision": 1.0, |
| "eval_recall": 1.0, |
| "eval_runtime": 370.0624, |
| "eval_samples_per_second": 0.692, |
| "eval_steps_per_second": 0.346, |
| "step": 2016 |
| }, |
| { |
| "epoch": 7.014539930555555, |
| "grad_norm": 0.05547843500971794, |
| "learning_rate": 3.5329861111111114e-05, |
| "loss": 0.0019, |
| "step": 2100 |
| }, |
| { |
| "epoch": 7.031901041666667, |
| "grad_norm": 0.020581351593136787, |
| "learning_rate": 3.4365354938271605e-05, |
| "loss": 0.0019, |
| "step": 2200 |
| }, |
| { |
| "epoch": 7.049262152777778, |
| "grad_norm": 0.016313279047608376, |
| "learning_rate": 3.34008487654321e-05, |
| "loss": 0.0022, |
| "step": 2300 |
| }, |
| { |
| "epoch": 7.049956597222222, |
| "eval_accuracy": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 0.0004577161744236946, |
| "eval_precision": 1.0, |
| "eval_recall": 1.0, |
| "eval_runtime": 371.0878, |
| "eval_samples_per_second": 0.69, |
| "eval_steps_per_second": 0.345, |
| "step": 2304 |
| }, |
| { |
| "epoch": 7.049956597222222, |
| "step": 2304, |
| "total_flos": 2.2981408544274776e+19, |
| "train_loss": 2.2551603910720184, |
| "train_runtime": 29576.2328, |
| "train_samples_per_second": 1.558, |
| "train_steps_per_second": 0.195 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 5760, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 5 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.2981408544274776e+19, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
