| { | |
| "best_metric": 0.5189873417721519, | |
| "best_model_checkpoint": "swin-finetuned-food101\\checkpoint-111", | |
| "epoch": 4.954954954954955, | |
| "eval_steps": 500, | |
| "global_step": 275, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0005882352941176471, | |
| "loss": 0.6928, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0009883720930232557, | |
| "loss": 0.7119, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0009496124031007753, | |
| "loss": 0.701, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0009108527131782945, | |
| "loss": 0.6967, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0008720930232558139, | |
| "loss": 0.7016, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.4810126582278481, | |
| "eval_auc": 0.47442875481386393, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.7054013609886169, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 7.2267, | |
| "eval_samples_per_second": 54.658, | |
| "eval_steps_per_second": 6.919, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0008333333333333334, | |
| "loss": 0.7091, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0007945736434108527, | |
| "loss": 0.6942, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0007558139534883722, | |
| "loss": 0.703, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0007170542635658915, | |
| "loss": 0.6974, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0006782945736434108, | |
| "loss": 0.6947, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0006395348837209303, | |
| "loss": 0.6894, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5189873417721519, | |
| "eval_auc": 0.4473812580231065, | |
| "eval_f1": 0.6833333333333332, | |
| "eval_loss": 0.6947762370109558, | |
| "eval_precision": 0.5189873417721519, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 6.9385, | |
| "eval_samples_per_second": 56.928, | |
| "eval_steps_per_second": 7.206, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.0006007751937984496, | |
| "loss": 0.6918, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.000562015503875969, | |
| "loss": 0.6962, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 0.0005232558139534884, | |
| "loss": 0.6935, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.00048449612403100775, | |
| "loss": 0.6913, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.00044573643410852714, | |
| "loss": 0.6905, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.5189873417721519, | |
| "eval_auc": 0.6049550706033376, | |
| "eval_f1": 0.6833333333333332, | |
| "eval_loss": 0.6924389600753784, | |
| "eval_precision": 0.5189873417721519, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 6.8681, | |
| "eval_samples_per_second": 57.512, | |
| "eval_steps_per_second": 7.28, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.00040697674418604653, | |
| "loss": 0.6962, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 0.00036821705426356586, | |
| "loss": 0.695, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 0.00032945736434108526, | |
| "loss": 0.693, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 0.00029069767441860465, | |
| "loss": 0.6939, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 0.00025193798449612404, | |
| "loss": 0.6882, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 0.0002131782945736434, | |
| "loss": 0.6956, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5189873417721519, | |
| "eval_auc": 0.38290115532734276, | |
| "eval_f1": 0.6833333333333332, | |
| "eval_loss": 0.6925024390220642, | |
| "eval_precision": 0.5189873417721519, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 6.9643, | |
| "eval_samples_per_second": 56.718, | |
| "eval_steps_per_second": 7.179, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.0001744186046511628, | |
| "loss": 0.6877, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 0.00013565891472868216, | |
| "loss": 0.6963, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 9.689922480620156e-05, | |
| "loss": 0.6979, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 5.8139534883720933e-05, | |
| "loss": 0.6926, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 1.937984496124031e-05, | |
| "loss": 0.6909, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "eval_accuracy": 0.5189873417721519, | |
| "eval_auc": 0.3773170731707318, | |
| "eval_f1": 0.6833333333333332, | |
| "eval_loss": 0.6924667954444885, | |
| "eval_precision": 0.5189873417721519, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 6.8651, | |
| "eval_samples_per_second": 57.537, | |
| "eval_steps_per_second": 7.283, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "step": 275, | |
| "total_flos": 3.4409368031831654e+17, | |
| "train_loss": 0.6955731582641601, | |
| "train_runtime": 190.8065, | |
| "train_samples_per_second": 23.217, | |
| "train_steps_per_second": 1.441 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 275, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 3.4409368031831654e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |