| { | |
| "best_metric": 0.9911111111111112, | |
| "best_model_checkpoint": "/kaggle/working/swin-brain-modality-classification/checkpoint-48", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 48, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 9.655741691589355, | |
| "learning_rate": 1.5625e-05, | |
| "loss": 1.364, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8266666666666667, | |
| "eval_loss": 0.6507545113563538, | |
| "eval_runtime": 1.8483, | |
| "eval_samples_per_second": 121.736, | |
| "eval_steps_per_second": 4.328, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 6.807246685028076, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.7521, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.875, | |
| "grad_norm": 5.148420333862305, | |
| "learning_rate": 4.6875e-05, | |
| "loss": 0.2053, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9555555555555556, | |
| "eval_loss": 0.08017182350158691, | |
| "eval_runtime": 1.8504, | |
| "eval_samples_per_second": 121.592, | |
| "eval_steps_per_second": 4.323, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 9.427779197692871, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 0.0841, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9911111111111112, | |
| "eval_loss": 0.02681696228682995, | |
| "eval_runtime": 1.886, | |
| "eval_samples_per_second": 119.3, | |
| "eval_steps_per_second": 4.242, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 48, | |
| "total_flos": 1.5048656676458496e+17, | |
| "train_loss": 0.5111757349222898, | |
| "train_runtime": 85.6924, | |
| "train_samples_per_second": 470.987, | |
| "train_steps_per_second": 3.734 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 320, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "CustomEarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 1.5048656676458496e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |