| { | |
| "best_metric": 0.7875, | |
| "best_model_checkpoint": "videomae-base-finetuned-gesturePhasev2/checkpoint-95", | |
| "epoch": 4.125, | |
| "eval_steps": 500, | |
| "global_step": 237, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.026595744680851064, | |
| "grad_norm": 9.288494110107422, | |
| "learning_rate": 6.578947368421053e-07, | |
| "loss": 1.4443, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05319148936170213, | |
| "grad_norm": 10.334871292114258, | |
| "learning_rate": 1.3157894736842106e-06, | |
| "loss": 1.418, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0797872340425532, | |
| "grad_norm": 7.731433391571045, | |
| "learning_rate": 1.973684210526316e-06, | |
| "loss": 1.3362, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10638297872340426, | |
| "grad_norm": 10.242834091186523, | |
| "learning_rate": 2.631578947368421e-06, | |
| "loss": 1.1665, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "eval_accuracy": 0.775, | |
| "eval_loss": 1.0642327070236206, | |
| "eval_runtime": 15.1556, | |
| "eval_samples_per_second": 10.557, | |
| "eval_steps_per_second": 1.32, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0066489361702127, | |
| "grad_norm": 5.333619594573975, | |
| "learning_rate": 3.289473684210527e-06, | |
| "loss": 1.0034, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0332446808510638, | |
| "grad_norm": 4.666859149932861, | |
| "learning_rate": 3.947368421052632e-06, | |
| "loss": 0.8562, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.059840425531915, | |
| "grad_norm": 4.381842136383057, | |
| "learning_rate": 4.605263157894737e-06, | |
| "loss": 0.7196, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.086436170212766, | |
| "grad_norm": 4.5117340087890625, | |
| "learning_rate": 4.997807075247147e-06, | |
| "loss": 0.7522, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.113031914893617, | |
| "grad_norm": 3.7782816886901855, | |
| "learning_rate": 4.973180832407471e-06, | |
| "loss": 0.7316, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.1263297872340425, | |
| "eval_accuracy": 0.7875, | |
| "eval_loss": 0.7825992703437805, | |
| "eval_runtime": 11.6767, | |
| "eval_samples_per_second": 13.703, | |
| "eval_steps_per_second": 1.713, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 2.0132978723404253, | |
| "grad_norm": 3.1058461666107178, | |
| "learning_rate": 4.921457902821578e-06, | |
| "loss": 0.785, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.0398936170212765, | |
| "grad_norm": 3.0555734634399414, | |
| "learning_rate": 4.84320497372973e-06, | |
| "loss": 0.7795, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.0664893617021276, | |
| "grad_norm": 3.8933866024017334, | |
| "learning_rate": 4.7392794005985324e-06, | |
| "loss": 0.774, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0930851063829787, | |
| "grad_norm": 4.3550591468811035, | |
| "learning_rate": 4.610819813755038e-06, | |
| "loss": 0.7218, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.11968085106383, | |
| "grad_norm": 4.537750720977783, | |
| "learning_rate": 4.4592336433146e-06, | |
| "loss": 0.7259, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.125, | |
| "eval_accuracy": 0.7875, | |
| "eval_loss": 0.8042387962341309, | |
| "eval_runtime": 10.5863, | |
| "eval_samples_per_second": 15.114, | |
| "eval_steps_per_second": 1.889, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 3.0199468085106385, | |
| "grad_norm": 3.3319995403289795, | |
| "learning_rate": 4.286181699082008e-06, | |
| "loss": 0.6222, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.046542553191489, | |
| "grad_norm": 4.209911823272705, | |
| "learning_rate": 4.093559974371725e-06, | |
| "loss": 0.7533, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.0731382978723403, | |
| "grad_norm": 2.9892210960388184, | |
| "learning_rate": 3.88347887310836e-06, | |
| "loss": 0.8408, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.0997340425531914, | |
| "grad_norm": 4.7717814445495605, | |
| "learning_rate": 3.658240087799655e-06, | |
| "loss": 0.7287, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.1263297872340425, | |
| "grad_norm": 5.496540546417236, | |
| "learning_rate": 3.4203113817116955e-06, | |
| "loss": 0.6643, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.1263297872340425, | |
| "eval_accuracy": 0.7875, | |
| "eval_loss": 0.8022773861885071, | |
| "eval_runtime": 10.4825, | |
| "eval_samples_per_second": 15.264, | |
| "eval_steps_per_second": 1.908, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.026595744680851, | |
| "grad_norm": 3.0813848972320557, | |
| "learning_rate": 3.1722995515381644e-06, | |
| "loss": 0.6386, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.053191489361702, | |
| "grad_norm": 3.0726428031921387, | |
| "learning_rate": 2.9169218667902562e-06, | |
| "loss": 0.6708, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 4.079787234042553, | |
| "grad_norm": 5.47495174407959, | |
| "learning_rate": 2.6569762988232838e-06, | |
| "loss": 0.8216, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.1063829787234045, | |
| "grad_norm": 3.801624059677124, | |
| "learning_rate": 2.3953108656770018e-06, | |
| "loss": 0.761, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.125, | |
| "eval_accuracy": 0.7875, | |
| "eval_loss": 0.8077355623245239, | |
| "eval_runtime": 16.5222, | |
| "eval_samples_per_second": 9.684, | |
| "eval_steps_per_second": 1.21, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 4.125, | |
| "step": 237, | |
| "total_flos": 4.691516857081528e+18, | |
| "train_loss": 0.8600665486814604, | |
| "train_runtime": 867.0351, | |
| "train_samples_per_second": 6.939, | |
| "train_steps_per_second": 0.434 | |
| }, | |
| { | |
| "epoch": 4.125, | |
| "eval_accuracy": 0.7633136094674556, | |
| "eval_loss": 0.8172227144241333, | |
| "eval_runtime": 60.5871, | |
| "eval_samples_per_second": 2.789, | |
| "eval_steps_per_second": 0.363, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 4.125, | |
| "eval_accuracy": 0.7633136094674556, | |
| "eval_loss": 0.8172227144241333, | |
| "eval_runtime": 11.0103, | |
| "eval_samples_per_second": 15.349, | |
| "eval_steps_per_second": 1.998, | |
| "step": 237 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 376, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.691516857081528e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |