| { |
| "best_metric": 1.0, |
| "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/MY DATA/VideoMAE_LSA64_SR_24/checkpoint-1152", |
| "epoch": 8.033333333333333, |
| "eval_steps": 500, |
| "global_step": 2592, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.011574074074074073, |
| "grad_norm": 48.236595153808594, |
| "learning_rate": 5.497685185185186e-06, |
| "loss": 16.755, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.023148148148148147, |
| "grad_norm": 62.92658615112305, |
| "learning_rate": 1.1284722222222223e-05, |
| "loss": 14.399, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.03333333333333333, |
| "eval_accuracy": 0.6953125, |
| "eval_f1": 0.6468255702630703, |
| "eval_loss": 2.0813236236572266, |
| "eval_precision": 0.668625992063492, |
| "eval_recall": 0.6953125, |
| "eval_runtime": 341.0926, |
| "eval_samples_per_second": 0.751, |
| "eval_steps_per_second": 0.375, |
| "step": 288 |
| }, |
| { |
| "epoch": 1.0013888888888889, |
| "grad_norm": 54.11103820800781, |
| "learning_rate": 1.707175925925926e-05, |
| "loss": 10.15, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.012962962962963, |
| "grad_norm": 40.01463317871094, |
| "learning_rate": 2.2800925925925927e-05, |
| "loss": 5.3607, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.024537037037037, |
| "grad_norm": 18.988719940185547, |
| "learning_rate": 2.8587962962962966e-05, |
| "loss": 2.5013, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0333333333333334, |
| "eval_accuracy": 0.953125, |
| "eval_f1": 0.9517902236652236, |
| "eval_loss": 0.3334716558456421, |
| "eval_precision": 0.9672619047619048, |
| "eval_recall": 0.953125, |
| "eval_runtime": 339.4035, |
| "eval_samples_per_second": 0.754, |
| "eval_steps_per_second": 0.377, |
| "step": 576 |
| }, |
| { |
| "epoch": 2.0027777777777778, |
| "grad_norm": 20.131940841674805, |
| "learning_rate": 3.4375e-05, |
| "loss": 1.1186, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.0143518518518517, |
| "grad_norm": 10.411463737487793, |
| "learning_rate": 4.016203703703704e-05, |
| "loss": 0.4956, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.025925925925926, |
| "grad_norm": 0.8578620553016663, |
| "learning_rate": 4.594907407407408e-05, |
| "loss": 0.2412, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.033333333333333, |
| "eval_accuracy": 0.99609375, |
| "eval_f1": 0.996031746031746, |
| "eval_loss": 0.06003136187791824, |
| "eval_precision": 0.996875, |
| "eval_recall": 0.99609375, |
| "eval_runtime": 298.2338, |
| "eval_samples_per_second": 0.858, |
| "eval_steps_per_second": 0.429, |
| "step": 864 |
| }, |
| { |
| "epoch": 3.004166666666667, |
| "grad_norm": 16.9967041015625, |
| "learning_rate": 4.9807098765432105e-05, |
| "loss": 0.3369, |
| "step": 900 |
| }, |
| { |
| "epoch": 3.015740740740741, |
| "grad_norm": 16.173372268676758, |
| "learning_rate": 4.916409465020577e-05, |
| "loss": 0.1188, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.027314814814815, |
| "grad_norm": 0.1294809877872467, |
| "learning_rate": 4.852109053497942e-05, |
| "loss": 0.0331, |
| "step": 1100 |
| }, |
| { |
| "epoch": 3.033333333333333, |
| "eval_accuracy": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 0.003711148165166378, |
| "eval_precision": 1.0, |
| "eval_recall": 1.0, |
| "eval_runtime": 310.3185, |
| "eval_samples_per_second": 0.825, |
| "eval_steps_per_second": 0.412, |
| "step": 1152 |
| }, |
| { |
| "epoch": 4.0055555555555555, |
| "grad_norm": 69.08421325683594, |
| "learning_rate": 4.7878086419753086e-05, |
| "loss": 0.0941, |
| "step": 1200 |
| }, |
| { |
| "epoch": 4.01712962962963, |
| "grad_norm": 0.061350248754024506, |
| "learning_rate": 4.723508230452675e-05, |
| "loss": 0.0132, |
| "step": 1300 |
| }, |
| { |
| "epoch": 4.0287037037037035, |
| "grad_norm": 0.05384208261966705, |
| "learning_rate": 4.6592078189300416e-05, |
| "loss": 0.0739, |
| "step": 1400 |
| }, |
| { |
| "epoch": 4.033333333333333, |
| "eval_accuracy": 0.9921875, |
| "eval_f1": 0.9920634920634921, |
| "eval_loss": 0.00851808488368988, |
| "eval_precision": 0.99375, |
| "eval_recall": 0.9921875, |
| "eval_runtime": 294.4498, |
| "eval_samples_per_second": 0.869, |
| "eval_steps_per_second": 0.435, |
| "step": 1440 |
| }, |
| { |
| "epoch": 5.006944444444445, |
| "grad_norm": 1.5208560228347778, |
| "learning_rate": 4.594907407407408e-05, |
| "loss": 0.0279, |
| "step": 1500 |
| }, |
| { |
| "epoch": 5.018518518518518, |
| "grad_norm": 0.15581129491329193, |
| "learning_rate": 4.530606995884774e-05, |
| "loss": 0.0073, |
| "step": 1600 |
| }, |
| { |
| "epoch": 5.030092592592593, |
| "grad_norm": 0.018887920305132866, |
| "learning_rate": 4.46630658436214e-05, |
| "loss": 0.0022, |
| "step": 1700 |
| }, |
| { |
| "epoch": 5.033333333333333, |
| "eval_accuracy": 0.99609375, |
| "eval_f1": 0.996031746031746, |
| "eval_loss": 0.011190671473741531, |
| "eval_precision": 0.996875, |
| "eval_recall": 0.99609375, |
| "eval_runtime": 295.4223, |
| "eval_samples_per_second": 0.867, |
| "eval_steps_per_second": 0.433, |
| "step": 1728 |
| }, |
| { |
| "epoch": 6.008333333333334, |
| "grad_norm": 0.0411268025636673, |
| "learning_rate": 4.402006172839506e-05, |
| "loss": 0.0017, |
| "step": 1800 |
| }, |
| { |
| "epoch": 6.019907407407407, |
| "grad_norm": 0.009254544042050838, |
| "learning_rate": 4.337705761316873e-05, |
| "loss": 0.0013, |
| "step": 1900 |
| }, |
| { |
| "epoch": 6.031481481481482, |
| "grad_norm": 0.010603751055896282, |
| "learning_rate": 4.273405349794239e-05, |
| "loss": 0.0011, |
| "step": 2000 |
| }, |
| { |
| "epoch": 6.033333333333333, |
| "eval_accuracy": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 0.0007740329019725323, |
| "eval_precision": 1.0, |
| "eval_recall": 1.0, |
| "eval_runtime": 291.9009, |
| "eval_samples_per_second": 0.877, |
| "eval_steps_per_second": 0.439, |
| "step": 2016 |
| }, |
| { |
| "epoch": 7.009722222222222, |
| "grad_norm": 0.015449409373104572, |
| "learning_rate": 4.209104938271605e-05, |
| "loss": 0.0007, |
| "step": 2100 |
| }, |
| { |
| "epoch": 7.021296296296296, |
| "grad_norm": 0.010291109792888165, |
| "learning_rate": 4.1448045267489715e-05, |
| "loss": 0.0007, |
| "step": 2200 |
| }, |
| { |
| "epoch": 7.032870370370371, |
| "grad_norm": 0.008957922458648682, |
| "learning_rate": 4.080504115226338e-05, |
| "loss": 0.0006, |
| "step": 2300 |
| }, |
| { |
| "epoch": 7.033333333333333, |
| "eval_accuracy": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 0.00039501162245869637, |
| "eval_precision": 1.0, |
| "eval_recall": 1.0, |
| "eval_runtime": 279.4867, |
| "eval_samples_per_second": 0.916, |
| "eval_steps_per_second": 0.458, |
| "step": 2304 |
| }, |
| { |
| "epoch": 8.011111111111111, |
| "grad_norm": 0.009041463024914265, |
| "learning_rate": 4.016203703703704e-05, |
| "loss": 0.0607, |
| "step": 2400 |
| }, |
| { |
| "epoch": 8.022685185185185, |
| "grad_norm": 0.04054854065179825, |
| "learning_rate": 3.95190329218107e-05, |
| "loss": 0.001, |
| "step": 2500 |
| }, |
| { |
| "epoch": 8.033333333333333, |
| "eval_accuracy": 0.9921875, |
| "eval_f1": 0.9916666666666667, |
| "eval_loss": 0.015493648126721382, |
| "eval_precision": 0.9947916666666666, |
| "eval_recall": 0.9921875, |
| "eval_runtime": 273.5703, |
| "eval_samples_per_second": 0.936, |
| "eval_steps_per_second": 0.468, |
| "step": 2592 |
| }, |
| { |
| "epoch": 8.033333333333333, |
| "step": 2592, |
| "total_flos": 1.817493393869321e+19, |
| "train_loss": 1.998577486999609, |
| "train_runtime": 27613.8881, |
| "train_samples_per_second": 2.503, |
| "train_steps_per_second": 0.313 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 8640, |
| "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": 1.817493393869321e+19, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
