| { | |
| "best_metric": 0.007897687144577503, | |
| "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-barkley\\checkpoint-266", | |
| "epoch": 9.0, | |
| "eval_steps": 500, | |
| "global_step": 342, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "train_accuracy": 0.31167763157894735 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 12.05273151397705, | |
| "learning_rate": 1.3523651731772227e-06, | |
| "loss": 1.5547, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.472770236299648, | |
| "eval_error_rate": 0.527229763700352, | |
| "eval_f1": 0.4239844424393964, | |
| "eval_loss": 1.4018361568450928, | |
| "eval_precision": 0.568315238272393, | |
| "eval_recall": 0.45394736842105265, | |
| "eval_runtime": 77.2729, | |
| "eval_samples_per_second": 1.967, | |
| "eval_steps_per_second": 0.065, | |
| "eval_top1_accuracy": 0.45394736842105265, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "train_accuracy": 0.6059941520467836 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": Infinity, | |
| "learning_rate": 2.945896675096576e-06, | |
| "loss": 1.1732, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8077275012569132, | |
| "eval_error_rate": 0.19227249874308683, | |
| "eval_f1": 0.798546834840623, | |
| "eval_loss": 0.9193388223648071, | |
| "eval_precision": 0.8095493933458997, | |
| "eval_recall": 0.7960526315789473, | |
| "eval_runtime": 74.7172, | |
| "eval_samples_per_second": 2.034, | |
| "eval_steps_per_second": 0.067, | |
| "eval_top1_accuracy": 0.7960526315789473, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "train_accuracy": 0.8654970760233918 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 9.15374755859375, | |
| "learning_rate": 5.472913419787674e-06, | |
| "loss": 0.6764, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9483207642031172, | |
| "eval_error_rate": 0.05167923579688283, | |
| "eval_f1": 0.9470289415786431, | |
| "eval_loss": 0.36436742544174194, | |
| "eval_precision": 0.9488354259225403, | |
| "eval_recall": 0.9473684210526315, | |
| "eval_runtime": 76.1752, | |
| "eval_samples_per_second": 1.995, | |
| "eval_steps_per_second": 0.066, | |
| "eval_top1_accuracy": 0.9473684210526315, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "train_accuracy": 0.9649122807017544 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 8.670642852783203, | |
| "learning_rate": 8.59766441885347e-06, | |
| "loss": 0.2566, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9944444444444445, | |
| "eval_error_rate": 0.005555555555555536, | |
| "eval_f1": 0.99343678755752, | |
| "eval_loss": 0.08713744580745697, | |
| "eval_precision": 0.9936647173489279, | |
| "eval_recall": 0.993421052631579, | |
| "eval_runtime": 72.4529, | |
| "eval_samples_per_second": 2.098, | |
| "eval_steps_per_second": 0.069, | |
| "eval_top1_accuracy": 0.993421052631579, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "train_accuracy": 0.9839181286549707 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 8.482632637023926, | |
| "learning_rate": 1.1941067495001943e-05, | |
| "loss": 0.1014, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.981111111111111, | |
| "eval_error_rate": 0.018888888888888955, | |
| "eval_f1": 0.980233547031901, | |
| "eval_loss": 0.05328463390469551, | |
| "eval_precision": 0.9808624413887572, | |
| "eval_recall": 0.9802631578947368, | |
| "eval_runtime": 73.3921, | |
| "eval_samples_per_second": 2.071, | |
| "eval_steps_per_second": 0.068, | |
| "eval_top1_accuracy": 0.9802631578947368, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "train_accuracy": 0.9897660818713451 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.8424493670463562, | |
| "learning_rate": 1.50975144835985e-05, | |
| "loss": 0.0538, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 1.0, | |
| "eval_error_rate": 0.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.020772233605384827, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 74.2604, | |
| "eval_samples_per_second": 2.047, | |
| "eval_steps_per_second": 0.067, | |
| "eval_top1_accuracy": 1.0, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "train_accuracy": 0.9941520467836257 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.9595191478729248, | |
| "learning_rate": 1.7684077977850795e-05, | |
| "loss": 0.0304, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 1.0, | |
| "eval_error_rate": 0.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.007897687144577503, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 69.1824, | |
| "eval_samples_per_second": 2.197, | |
| "eval_steps_per_second": 0.072, | |
| "eval_top1_accuracy": 1.0, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "train_accuracy": 0.9861111111111112 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 2.93084454536438, | |
| "learning_rate": 1.9386966536009276e-05, | |
| "loss": 0.0571, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 1.0, | |
| "eval_error_rate": 0.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.008802073076367378, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 59.208, | |
| "eval_samples_per_second": 2.567, | |
| "eval_steps_per_second": 0.084, | |
| "eval_top1_accuracy": 1.0, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "train_accuracy": 0.9817251461988304 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.27030402421951294, | |
| "learning_rate": 1.9998370404079306e-05, | |
| "loss": 0.0608, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9933333333333334, | |
| "eval_error_rate": 0.006666666666666599, | |
| "eval_f1": 0.9934103601236665, | |
| "eval_loss": 0.022643933072686195, | |
| "eval_precision": 0.9935988620199147, | |
| "eval_recall": 0.993421052631579, | |
| "eval_runtime": 54.0581, | |
| "eval_samples_per_second": 2.812, | |
| "eval_steps_per_second": 0.092, | |
| "eval_top1_accuracy": 0.993421052631579, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "step": 342, | |
| "total_flos": 8.477326613832008e+17, | |
| "train_loss": 0.4405021691880031, | |
| "train_runtime": 8765.8937, | |
| "train_samples_per_second": 4.162, | |
| "train_steps_per_second": 0.13 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1140, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 8.477326613832008e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |