| { | |
| "best_metric": 0.8958333333333334, | |
| "best_model_checkpoint": "convnext-tiny-224-klobasaniklobasa/checkpoint-288", | |
| "epoch": 10.0, | |
| "global_step": 480, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.608, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.6676, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.6403, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.7062, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.84375, | |
| "eval_loss": 0.7115556597709656, | |
| "eval_runtime": 3.3605, | |
| "eval_samples_per_second": 28.567, | |
| "eval_steps_per_second": 3.571, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.981481481481482e-05, | |
| "loss": 0.5469, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.5691, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 3.7962962962962964e-05, | |
| "loss": 0.5161, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 3.703703703703704e-05, | |
| "loss": 0.4157, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.6111111111111116e-05, | |
| "loss": 0.4831, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.5967997312545776, | |
| "eval_runtime": 3.6773, | |
| "eval_samples_per_second": 26.106, | |
| "eval_steps_per_second": 3.263, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.3808, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 3.425925925925926e-05, | |
| "loss": 0.3956, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.3992, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 3.2407407407407415e-05, | |
| "loss": 0.3256, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 3.148148148148149e-05, | |
| "loss": 0.2429, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8541666666666666, | |
| "eval_loss": 0.5383699536323547, | |
| "eval_runtime": 3.5584, | |
| "eval_samples_per_second": 26.979, | |
| "eval_steps_per_second": 3.372, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 3.0555555555555554e-05, | |
| "loss": 0.2586, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.3041, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 2.8703703703703706e-05, | |
| "loss": 0.2511, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.2165, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 2.6851851851851852e-05, | |
| "loss": 0.2292, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.84375, | |
| "eval_loss": 0.4995401203632355, | |
| "eval_runtime": 3.5701, | |
| "eval_samples_per_second": 26.89, | |
| "eval_steps_per_second": 3.361, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 2.5925925925925928e-05, | |
| "loss": 0.2336, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.1827, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 2.4074074074074077e-05, | |
| "loss": 0.1918, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.1316, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2.2222222222222227e-05, | |
| "loss": 0.1549, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8854166666666666, | |
| "eval_loss": 0.45076122879981995, | |
| "eval_runtime": 3.3498, | |
| "eval_samples_per_second": 28.658, | |
| "eval_steps_per_second": 3.582, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 2.12962962962963e-05, | |
| "loss": 0.0792, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 2.0370370370370372e-05, | |
| "loss": 0.1449, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.0869, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 1.851851851851852e-05, | |
| "loss": 0.1682, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8958333333333334, | |
| "eval_loss": 0.4400902986526489, | |
| "eval_runtime": 3.566, | |
| "eval_samples_per_second": 26.921, | |
| "eval_steps_per_second": 3.365, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 1.7592592592592595e-05, | |
| "loss": 0.1264, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.1211, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 1.5740740740740744e-05, | |
| "loss": 0.0649, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.1159, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.1736, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8958333333333334, | |
| "eval_loss": 0.4440065622329712, | |
| "eval_runtime": 3.5045, | |
| "eval_samples_per_second": 27.393, | |
| "eval_steps_per_second": 3.424, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 1.2962962962962964e-05, | |
| "loss": 0.0679, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 1.2037037037037039e-05, | |
| "loss": 0.0915, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 1.1111111111111113e-05, | |
| "loss": 0.1254, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 1.0185185185185186e-05, | |
| "loss": 0.0588, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 9.25925925925926e-06, | |
| "loss": 0.0633, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8958333333333334, | |
| "eval_loss": 0.44057992100715637, | |
| "eval_runtime": 3.5708, | |
| "eval_samples_per_second": 26.885, | |
| "eval_steps_per_second": 3.361, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.0512, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.129, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "learning_rate": 6.481481481481482e-06, | |
| "loss": 0.0776, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 0.0628, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 4.62962962962963e-06, | |
| "loss": 0.0689, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8958333333333334, | |
| "eval_loss": 0.4371330738067627, | |
| "eval_runtime": 3.3898, | |
| "eval_samples_per_second": 28.32, | |
| "eval_steps_per_second": 3.54, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.0947, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 2.7777777777777783e-06, | |
| "loss": 0.1003, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.0593, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 9.259259259259259e-07, | |
| "loss": 0.0722, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0558, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8958333333333334, | |
| "eval_loss": 0.43337997794151306, | |
| "eval_runtime": 4.6987, | |
| "eval_samples_per_second": 20.431, | |
| "eval_steps_per_second": 2.554, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 480, | |
| "total_flos": 9.499297468243968e+16, | |
| "train_loss": 0.23564616565903027, | |
| "train_runtime": 303.0343, | |
| "train_samples_per_second": 12.474, | |
| "train_steps_per_second": 1.584 | |
| } | |
| ], | |
| "max_steps": 480, | |
| "num_train_epochs": 10, | |
| "total_flos": 9.499297468243968e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |