| { | |
| "best_metric": 0.9005493521690369, | |
| "best_model_checkpoint": "butterfly_moth_species_detection/checkpoint-6800", | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 6800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7451268848841486, | |
| "eval_loss": 4.074434757232666, | |
| "eval_runtime": 27.623, | |
| "eval_samples_per_second": 98.432, | |
| "eval_steps_per_second": 24.617, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 9.333333333333334e-06, | |
| "loss": 4.214, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8528870908422214, | |
| "eval_loss": 3.4827189445495605, | |
| "eval_runtime": 26.6308, | |
| "eval_samples_per_second": 102.1, | |
| "eval_steps_per_second": 25.534, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 8.592592592592593e-06, | |
| "loss": 3.3464, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8830452372195661, | |
| "eval_loss": 3.0303194522857666, | |
| "eval_runtime": 26.4726, | |
| "eval_samples_per_second": 102.71, | |
| "eval_steps_per_second": 25.687, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.900331004045605, | |
| "eval_loss": 2.6731619834899902, | |
| "eval_runtime": 26.0171, | |
| "eval_samples_per_second": 104.508, | |
| "eval_steps_per_second": 26.137, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 7.851851851851853e-06, | |
| "loss": 2.7283, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9128356013240162, | |
| "eval_loss": 2.3697543144226074, | |
| "eval_runtime": 26.2379, | |
| "eval_samples_per_second": 103.629, | |
| "eval_steps_per_second": 25.917, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 7.111111111111112e-06, | |
| "loss": 2.2616, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9194556822361162, | |
| "eval_loss": 2.1162424087524414, | |
| "eval_runtime": 26.3215, | |
| "eval_samples_per_second": 103.3, | |
| "eval_steps_per_second": 25.834, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9238690695108496, | |
| "eval_loss": 1.9014132022857666, | |
| "eval_runtime": 26.1807, | |
| "eval_samples_per_second": 103.855, | |
| "eval_steps_per_second": 25.973, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 6.370370370370371e-06, | |
| "loss": 1.9012, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9257079808753218, | |
| "eval_loss": 1.7136589288711548, | |
| "eval_runtime": 26.3325, | |
| "eval_samples_per_second": 103.256, | |
| "eval_steps_per_second": 25.824, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 5.62962962962963e-06, | |
| "loss": 1.6095, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.930856932695844, | |
| "eval_loss": 1.5556321144104004, | |
| "eval_runtime": 26.241, | |
| "eval_samples_per_second": 103.616, | |
| "eval_steps_per_second": 25.914, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9312247149687385, | |
| "eval_loss": 1.4216381311416626, | |
| "eval_runtime": 26.197, | |
| "eval_samples_per_second": 103.791, | |
| "eval_steps_per_second": 25.957, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 10.29, | |
| "learning_rate": 4.888888888888889e-06, | |
| "loss": 1.3796, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9363736667892607, | |
| "eval_loss": 1.3075575828552246, | |
| "eval_runtime": 26.5047, | |
| "eval_samples_per_second": 102.586, | |
| "eval_steps_per_second": 25.656, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 4.1481481481481485e-06, | |
| "loss": 1.1947, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9367414490621552, | |
| "eval_loss": 1.2107630968093872, | |
| "eval_runtime": 26.2341, | |
| "eval_samples_per_second": 103.644, | |
| "eval_steps_per_second": 25.92, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9407870540639941, | |
| "eval_loss": 1.1325198411941528, | |
| "eval_runtime": 26.2572, | |
| "eval_samples_per_second": 103.553, | |
| "eval_steps_per_second": 25.898, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 3.4074074074074077e-06, | |
| "loss": 1.0567, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9396837072453108, | |
| "eval_loss": 1.0684376955032349, | |
| "eval_runtime": 26.3289, | |
| "eval_samples_per_second": 103.27, | |
| "eval_steps_per_second": 25.827, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 0.9542, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9411548363368886, | |
| "eval_loss": 1.013007402420044, | |
| "eval_runtime": 26.9467, | |
| "eval_samples_per_second": 100.903, | |
| "eval_steps_per_second": 25.235, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9433615299742553, | |
| "eval_loss": 0.9716300368309021, | |
| "eval_runtime": 26.7453, | |
| "eval_samples_per_second": 101.663, | |
| "eval_steps_per_second": 25.425, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 16.18, | |
| "learning_rate": 1.925925925925926e-06, | |
| "loss": 0.8704, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.9418904008826775, | |
| "eval_loss": 0.9403185248374939, | |
| "eval_runtime": 26.5078, | |
| "eval_samples_per_second": 102.573, | |
| "eval_steps_per_second": 25.653, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 17.65, | |
| "learning_rate": 1.1851851851851854e-06, | |
| "loss": 0.816, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9418904008826775, | |
| "eval_loss": 0.9185165762901306, | |
| "eval_runtime": 26.3963, | |
| "eval_samples_per_second": 103.007, | |
| "eval_steps_per_second": 25.761, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.9418904008826775, | |
| "eval_loss": 0.9051674604415894, | |
| "eval_runtime": 26.4947, | |
| "eval_samples_per_second": 102.624, | |
| "eval_steps_per_second": 25.666, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 19.12, | |
| "learning_rate": 4.444444444444445e-07, | |
| "loss": 0.7842, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9422581831555719, | |
| "eval_loss": 0.9005493521690369, | |
| "eval_runtime": 26.4957, | |
| "eval_samples_per_second": 102.62, | |
| "eval_steps_per_second": 25.665, | |
| "step": 6800 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6800, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "total_flos": 1.686931178010624e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |