| { | |
| "best_metric": 0.10512479394674301, | |
| "best_model_checkpoint": "/home/projects/Project - Fundus Photo Glaucoma Detection (AI)//model_results/vit-base-gpu/checkpoint-200", | |
| "epoch": 5.0, | |
| "eval_steps": 100, | |
| "global_step": 285, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17543859649122806, | |
| "grad_norm": 1.762933373451233, | |
| "learning_rate": 9.649122807017545e-06, | |
| "loss": 0.5817, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "grad_norm": 1.567679762840271, | |
| "learning_rate": 9.298245614035088e-06, | |
| "loss": 0.4467, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 1.3810224533081055, | |
| "learning_rate": 8.947368421052632e-06, | |
| "loss": 0.3667, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 1.4549124240875244, | |
| "learning_rate": 8.596491228070176e-06, | |
| "loss": 0.2947, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8771929824561403, | |
| "grad_norm": 0.9504640102386475, | |
| "learning_rate": 8.24561403508772e-06, | |
| "loss": 0.2705, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 0.7635705471038818, | |
| "learning_rate": 7.894736842105265e-06, | |
| "loss": 0.1962, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.2280701754385965, | |
| "grad_norm": 0.7457385063171387, | |
| "learning_rate": 7.5438596491228074e-06, | |
| "loss": 0.1838, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.4035087719298245, | |
| "grad_norm": 0.7596029043197632, | |
| "learning_rate": 7.192982456140352e-06, | |
| "loss": 0.1583, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 1.0756629705429077, | |
| "learning_rate": 6.842105263157896e-06, | |
| "loss": 0.1294, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.7543859649122808, | |
| "grad_norm": 0.8500545024871826, | |
| "learning_rate": 6.491228070175439e-06, | |
| "loss": 0.1311, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.7543859649122808, | |
| "eval_accuracy": 0.9647577092511013, | |
| "eval_confusion_matrix": [ | |
| [ | |
| 58, | |
| 8 | |
| ], | |
| [ | |
| 0, | |
| 161 | |
| ] | |
| ], | |
| "eval_loss": 0.15690478682518005, | |
| "eval_runtime": 24.1707, | |
| "eval_samples_per_second": 9.392, | |
| "eval_steps_per_second": 0.331, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.9298245614035088, | |
| "grad_norm": 2.896561861038208, | |
| "learning_rate": 6.140350877192983e-06, | |
| "loss": 0.1334, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 0.3675668239593506, | |
| "learning_rate": 5.789473684210527e-06, | |
| "loss": 0.1151, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.280701754385965, | |
| "grad_norm": 0.46107763051986694, | |
| "learning_rate": 5.438596491228071e-06, | |
| "loss": 0.1217, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.456140350877193, | |
| "grad_norm": 0.46047243475914, | |
| "learning_rate": 5.087719298245615e-06, | |
| "loss": 0.0809, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 0.33362969756126404, | |
| "learning_rate": 4.736842105263158e-06, | |
| "loss": 0.0935, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.807017543859649, | |
| "grad_norm": 0.4287916421890259, | |
| "learning_rate": 4.385964912280702e-06, | |
| "loss": 0.0855, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.982456140350877, | |
| "grad_norm": 0.4844302237033844, | |
| "learning_rate": 4.035087719298246e-06, | |
| "loss": 0.0845, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.1578947368421053, | |
| "grad_norm": 0.3423462212085724, | |
| "learning_rate": 3.6842105263157896e-06, | |
| "loss": 0.0911, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.288198322057724, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.0855, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.5087719298245617, | |
| "grad_norm": 0.5208536982536316, | |
| "learning_rate": 2.9824561403508774e-06, | |
| "loss": 0.0929, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.5087719298245617, | |
| "eval_accuracy": 0.9823788546255506, | |
| "eval_confusion_matrix": [ | |
| [ | |
| 62, | |
| 4 | |
| ], | |
| [ | |
| 0, | |
| 161 | |
| ] | |
| ], | |
| "eval_loss": 0.10512479394674301, | |
| "eval_runtime": 24.0408, | |
| "eval_samples_per_second": 9.442, | |
| "eval_steps_per_second": 0.333, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.6842105263157894, | |
| "grad_norm": 0.3295786380767822, | |
| "learning_rate": 2.631578947368421e-06, | |
| "loss": 0.1019, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.8596491228070176, | |
| "grad_norm": 0.4086381196975708, | |
| "learning_rate": 2.280701754385965e-06, | |
| "loss": 0.069, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.035087719298246, | |
| "grad_norm": 0.7247630953788757, | |
| "learning_rate": 1.929824561403509e-06, | |
| "loss": 0.1078, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.2105263157894735, | |
| "grad_norm": 0.37916073203086853, | |
| "learning_rate": 1.5789473684210526e-06, | |
| "loss": 0.0757, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.385964912280702, | |
| "grad_norm": 0.26061660051345825, | |
| "learning_rate": 1.2280701754385965e-06, | |
| "loss": 0.0572, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.56140350877193, | |
| "grad_norm": 0.259589284658432, | |
| "learning_rate": 8.771929824561404e-07, | |
| "loss": 0.0545, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.7368421052631575, | |
| "grad_norm": 0.25950363278388977, | |
| "learning_rate": 5.263157894736843e-07, | |
| "loss": 0.0447, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.912280701754386, | |
| "grad_norm": 0.4733501970767975, | |
| "learning_rate": 1.7543859649122808e-07, | |
| "loss": 0.0958, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 285, | |
| "total_flos": 7.020774259082035e+17, | |
| "train_loss": 0.1542712652892397, | |
| "train_runtime": 2868.9315, | |
| "train_samples_per_second": 3.179, | |
| "train_steps_per_second": 0.099 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 285, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.020774259082035e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |