{ "best_metric": 0.65, "best_model_checkpoint": "swinv2-base-patch4-window8-256-isic217/checkpoint-178", "epoch": 9.887640449438202, "eval_steps": 500, "global_step": 220, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.9887640449438202, "grad_norm": 12.935554504394531, "learning_rate": 5e-05, "loss": 2.1681, "step": 22 }, { "epoch": 0.9887640449438202, "eval_accuracy": 0.25, "eval_loss": 2.0018374919891357, "eval_runtime": 2.9002, "eval_samples_per_second": 6.896, "eval_steps_per_second": 3.448, "step": 22 }, { "epoch": 1.9775280898876404, "grad_norm": 12.57723331451416, "learning_rate": 4.4444444444444447e-05, "loss": 1.9254, "step": 44 }, { "epoch": 1.9775280898876404, "eval_accuracy": 0.35, "eval_loss": 1.765319585800171, "eval_runtime": 2.8633, "eval_samples_per_second": 6.985, "eval_steps_per_second": 3.493, "step": 44 }, { "epoch": 2.966292134831461, "grad_norm": 18.157392501831055, "learning_rate": 3.888888888888889e-05, "loss": 1.6706, "step": 66 }, { "epoch": 2.966292134831461, "eval_accuracy": 0.6, "eval_loss": 1.664868712425232, "eval_runtime": 2.8974, "eval_samples_per_second": 6.903, "eval_steps_per_second": 3.451, "step": 66 }, { "epoch": 4.0, "grad_norm": 22.54041290283203, "learning_rate": 3.308080808080809e-05, "loss": 1.2834, "step": 89 }, { "epoch": 4.0, "eval_accuracy": 0.5, "eval_loss": 1.557893991470337, "eval_runtime": 2.9133, "eval_samples_per_second": 6.865, "eval_steps_per_second": 3.432, "step": 89 }, { "epoch": 4.98876404494382, "grad_norm": 24.279077529907227, "learning_rate": 2.7525252525252528e-05, "loss": 1.2039, "step": 111 }, { "epoch": 4.98876404494382, "eval_accuracy": 0.55, "eval_loss": 1.4086878299713135, "eval_runtime": 2.9062, "eval_samples_per_second": 6.882, "eval_steps_per_second": 3.441, "step": 111 }, { "epoch": 5.97752808988764, "grad_norm": 26.200206756591797, "learning_rate": 2.1969696969696972e-05, "loss": 0.9395, "step": 133 }, { "epoch": 5.97752808988764, "eval_accuracy": 0.5, "eval_loss": 1.3115328550338745, "eval_runtime": 2.9002, "eval_samples_per_second": 6.896, "eval_steps_per_second": 3.448, "step": 133 }, { "epoch": 6.966292134831461, "grad_norm": 24.642183303833008, "learning_rate": 1.6414141414141416e-05, "loss": 0.7532, "step": 155 }, { "epoch": 6.966292134831461, "eval_accuracy": 0.6, "eval_loss": 1.3599040508270264, "eval_runtime": 2.9052, "eval_samples_per_second": 6.884, "eval_steps_per_second": 3.442, "step": 155 }, { "epoch": 8.0, "grad_norm": 20.47603416442871, "learning_rate": 1.0606060606060607e-05, "loss": 0.6573, "step": 178 }, { "epoch": 8.0, "eval_accuracy": 0.65, "eval_loss": 1.158837914466858, "eval_runtime": 2.8838, "eval_samples_per_second": 6.935, "eval_steps_per_second": 3.468, "step": 178 }, { "epoch": 8.98876404494382, "grad_norm": 29.59978485107422, "learning_rate": 5.050505050505051e-06, "loss": 0.6663, "step": 200 }, { "epoch": 8.98876404494382, "eval_accuracy": 0.6, "eval_loss": 1.207406759262085, "eval_runtime": 2.8796, "eval_samples_per_second": 6.945, "eval_steps_per_second": 3.473, "step": 200 }, { "epoch": 9.887640449438202, "grad_norm": 12.570259094238281, "learning_rate": 0.0, "loss": 0.4686, "step": 220 }, { "epoch": 9.887640449438202, "eval_accuracy": 0.6, "eval_loss": 1.228463888168335, "eval_runtime": 2.9115, "eval_samples_per_second": 6.869, "eval_steps_per_second": 3.435, "step": 220 }, { "epoch": 9.887640449438202, "step": 220, "total_flos": 1.8042639737683968e+17, "train_loss": 1.1781822247938676, "train_runtime": 376.1356, "train_samples_per_second": 4.732, "train_steps_per_second": 0.585 } ], "logging_steps": 500, "max_steps": 220, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.8042639737683968e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }