| { | |
| "best_metric": 0.4006434977054596, | |
| "best_model_checkpoint": "food_beverages_japan_image_detection/checkpoint-2340", | |
| "epoch": 39.0, | |
| "eval_steps": 500, | |
| "global_step": 2340, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6215644820295984, | |
| "eval_loss": 0.6740179657936096, | |
| "eval_runtime": 8.3101, | |
| "eval_samples_per_second": 56.919, | |
| "eval_steps_per_second": 7.22, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7019027484143763, | |
| "eval_loss": 0.6518784165382385, | |
| "eval_runtime": 8.3128, | |
| "eval_samples_per_second": 56.9, | |
| "eval_steps_per_second": 7.218, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7315010570824524, | |
| "eval_loss": 0.6313825249671936, | |
| "eval_runtime": 8.4056, | |
| "eval_samples_per_second": 56.272, | |
| "eval_steps_per_second": 7.138, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7378435517970402, | |
| "eval_loss": 0.6076480150222778, | |
| "eval_runtime": 8.3695, | |
| "eval_samples_per_second": 56.515, | |
| "eval_steps_per_second": 7.169, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7505285412262156, | |
| "eval_loss": 0.5873068571090698, | |
| "eval_runtime": 8.3314, | |
| "eval_samples_per_second": 56.773, | |
| "eval_steps_per_second": 7.202, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7758985200845666, | |
| "eval_loss": 0.5679311752319336, | |
| "eval_runtime": 8.239, | |
| "eval_samples_per_second": 57.41, | |
| "eval_steps_per_second": 7.282, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7780126849894292, | |
| "eval_loss": 0.5512701869010925, | |
| "eval_runtime": 7.9131, | |
| "eval_samples_per_second": 59.775, | |
| "eval_steps_per_second": 7.582, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7801268498942917, | |
| "eval_loss": 0.5363279581069946, | |
| "eval_runtime": 7.9214, | |
| "eval_samples_per_second": 59.712, | |
| "eval_steps_per_second": 7.574, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 4.042553191489362e-06, | |
| "loss": 0.5935, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7843551797040169, | |
| "eval_loss": 0.5246909260749817, | |
| "eval_runtime": 7.9484, | |
| "eval_samples_per_second": 59.509, | |
| "eval_steps_per_second": 7.549, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7906976744186046, | |
| "eval_loss": 0.5121592283248901, | |
| "eval_runtime": 7.9961, | |
| "eval_samples_per_second": 59.154, | |
| "eval_steps_per_second": 7.504, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7991543340380549, | |
| "eval_loss": 0.4976297616958618, | |
| "eval_runtime": 7.9409, | |
| "eval_samples_per_second": 59.565, | |
| "eval_steps_per_second": 7.556, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8054968287526427, | |
| "eval_loss": 0.48714011907577515, | |
| "eval_runtime": 7.9777, | |
| "eval_samples_per_second": 59.29, | |
| "eval_steps_per_second": 7.521, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8033826638477801, | |
| "eval_loss": 0.47856396436691284, | |
| "eval_runtime": 8.0373, | |
| "eval_samples_per_second": 58.85, | |
| "eval_steps_per_second": 7.465, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8054968287526427, | |
| "eval_loss": 0.4685792028903961, | |
| "eval_runtime": 8.0022, | |
| "eval_samples_per_second": 59.109, | |
| "eval_steps_per_second": 7.498, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.8076109936575053, | |
| "eval_loss": 0.4633488357067108, | |
| "eval_runtime": 7.897, | |
| "eval_samples_per_second": 59.896, | |
| "eval_steps_per_second": 7.598, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8097251585623678, | |
| "eval_loss": 0.4541207253932953, | |
| "eval_runtime": 7.9062, | |
| "eval_samples_per_second": 59.826, | |
| "eval_steps_per_second": 7.589, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 2.978723404255319e-06, | |
| "loss": 0.3919, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.8181818181818182, | |
| "eval_loss": 0.44693174958229065, | |
| "eval_runtime": 7.9465, | |
| "eval_samples_per_second": 59.523, | |
| "eval_steps_per_second": 7.551, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8202959830866807, | |
| "eval_loss": 0.4403076171875, | |
| "eval_runtime": 7.9729, | |
| "eval_samples_per_second": 59.326, | |
| "eval_steps_per_second": 7.526, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8181818181818182, | |
| "eval_loss": 0.43559935688972473, | |
| "eval_runtime": 7.8143, | |
| "eval_samples_per_second": 60.53, | |
| "eval_steps_per_second": 7.678, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8245243128964059, | |
| "eval_loss": 0.43019139766693115, | |
| "eval_runtime": 7.7993, | |
| "eval_samples_per_second": 60.646, | |
| "eval_steps_per_second": 7.693, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.8202959830866807, | |
| "eval_loss": 0.42576563358306885, | |
| "eval_runtime": 7.7862, | |
| "eval_samples_per_second": 60.749, | |
| "eval_steps_per_second": 7.706, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.8245243128964059, | |
| "eval_loss": 0.4226011633872986, | |
| "eval_runtime": 7.8089, | |
| "eval_samples_per_second": 60.572, | |
| "eval_steps_per_second": 7.684, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.8266384778012685, | |
| "eval_loss": 0.4196974039077759, | |
| "eval_runtime": 7.7453, | |
| "eval_samples_per_second": 61.069, | |
| "eval_steps_per_second": 7.747, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8308668076109936, | |
| "eval_loss": 0.4153010845184326, | |
| "eval_runtime": 7.7967, | |
| "eval_samples_per_second": 60.667, | |
| "eval_steps_per_second": 7.696, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 1.9148936170212767e-06, | |
| "loss": 0.2598, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.8245243128964059, | |
| "eval_loss": 0.41346848011016846, | |
| "eval_runtime": 8.0165, | |
| "eval_samples_per_second": 59.003, | |
| "eval_steps_per_second": 7.485, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.828752642706131, | |
| "eval_loss": 0.41087058186531067, | |
| "eval_runtime": 8.2057, | |
| "eval_samples_per_second": 57.643, | |
| "eval_steps_per_second": 7.312, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.8350951374207188, | |
| "eval_loss": 0.410675048828125, | |
| "eval_runtime": 8.1905, | |
| "eval_samples_per_second": 57.75, | |
| "eval_steps_per_second": 7.326, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8372093023255814, | |
| "eval_loss": 0.4087086319923401, | |
| "eval_runtime": 8.1633, | |
| "eval_samples_per_second": 57.942, | |
| "eval_steps_per_second": 7.35, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.8266384778012685, | |
| "eval_loss": 0.41004815697669983, | |
| "eval_runtime": 8.2033, | |
| "eval_samples_per_second": 57.66, | |
| "eval_steps_per_second": 7.314, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.8372093023255814, | |
| "eval_loss": 0.40502193570137024, | |
| "eval_runtime": 8.171, | |
| "eval_samples_per_second": 57.888, | |
| "eval_steps_per_second": 7.343, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.828752642706131, | |
| "eval_loss": 0.40703651309013367, | |
| "eval_runtime": 8.1556, | |
| "eval_samples_per_second": 57.997, | |
| "eval_steps_per_second": 7.357, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8350951374207188, | |
| "eval_loss": 0.40481287240982056, | |
| "eval_runtime": 8.1436, | |
| "eval_samples_per_second": 58.083, | |
| "eval_steps_per_second": 7.368, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.8329809725158562, | |
| "eval_loss": 0.4047437608242035, | |
| "eval_runtime": 8.1259, | |
| "eval_samples_per_second": 58.209, | |
| "eval_steps_per_second": 7.384, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 8.510638297872341e-07, | |
| "loss": 0.1847, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.8329809725158562, | |
| "eval_loss": 0.4028582274913788, | |
| "eval_runtime": 8.1842, | |
| "eval_samples_per_second": 57.795, | |
| "eval_steps_per_second": 7.331, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.8329809725158562, | |
| "eval_loss": 0.4015713930130005, | |
| "eval_runtime": 8.1082, | |
| "eval_samples_per_second": 58.336, | |
| "eval_steps_per_second": 7.4, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.8329809725158562, | |
| "eval_loss": 0.4017912745475769, | |
| "eval_runtime": 8.0144, | |
| "eval_samples_per_second": 59.019, | |
| "eval_steps_per_second": 7.487, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.8372093023255814, | |
| "eval_loss": 0.401458203792572, | |
| "eval_runtime": 7.7426, | |
| "eval_samples_per_second": 61.091, | |
| "eval_steps_per_second": 7.749, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.8372093023255814, | |
| "eval_loss": 0.40120792388916016, | |
| "eval_runtime": 7.812, | |
| "eval_samples_per_second": 60.548, | |
| "eval_steps_per_second": 7.68, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.8372093023255814, | |
| "eval_loss": 0.4006434977054596, | |
| "eval_runtime": 7.8268, | |
| "eval_samples_per_second": 60.433, | |
| "eval_steps_per_second": 7.666, | |
| "step": 2340 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2400, | |
| "num_train_epochs": 40, | |
| "save_steps": 500, | |
| "total_flos": 5.714956742086545e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |