| { | |
| "best_metric": 0.15928371250629425, | |
| "best_model_checkpoint": "./Remote-Sensing-Classification-image-classification/checkpoint-500", | |
| "epoch": 4.0, | |
| "eval_steps": 100, | |
| "global_step": 560, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019642857142857144, | |
| "loss": 1.7404, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019285714285714286, | |
| "loss": 1.2945, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001892857142857143, | |
| "loss": 0.9461, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00018571428571428572, | |
| "loss": 0.6914, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00018214285714285714, | |
| "loss": 0.5938, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0001785714285714286, | |
| "loss": 0.5389, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.000175, | |
| "loss": 0.522, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00017142857142857143, | |
| "loss": 0.5365, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00016785714285714288, | |
| "loss": 0.4732, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00016428571428571428, | |
| "loss": 0.3922, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_accuracy": 0.8821428571428571, | |
| "eval_loss": 0.4226740300655365, | |
| "eval_runtime": 9.2568, | |
| "eval_samples_per_second": 60.496, | |
| "eval_steps_per_second": 7.562, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00016071428571428573, | |
| "loss": 0.3948, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00015714285714285716, | |
| "loss": 0.5197, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0001535714285714286, | |
| "loss": 0.2765, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.3043, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00014642857142857141, | |
| "loss": 0.136, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 0.2342, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0001392857142857143, | |
| "loss": 0.2023, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00013571428571428572, | |
| "loss": 0.2333, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00013214285714285715, | |
| "loss": 0.1803, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00012857142857142858, | |
| "loss": 0.2986, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_accuracy": 0.9089285714285714, | |
| "eval_loss": 0.31418919563293457, | |
| "eval_runtime": 13.8936, | |
| "eval_samples_per_second": 40.306, | |
| "eval_steps_per_second": 5.038, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.000125, | |
| "loss": 0.1593, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00012142857142857143, | |
| "loss": 0.1688, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00011785714285714287, | |
| "loss": 0.1953, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00011428571428571428, | |
| "loss": 0.1932, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00011071428571428572, | |
| "loss": 0.1448, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00010714285714285715, | |
| "loss": 0.2531, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00010357142857142859, | |
| "loss": 0.1877, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1615, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.642857142857143e-05, | |
| "loss": 0.1966, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 9.285714285714286e-05, | |
| "loss": 0.1109, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_accuracy": 0.9517857142857142, | |
| "eval_loss": 0.20564210414886475, | |
| "eval_runtime": 15.261, | |
| "eval_samples_per_second": 36.695, | |
| "eval_steps_per_second": 4.587, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 8.92857142857143e-05, | |
| "loss": 0.0765, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 0.0653, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 8.214285714285714e-05, | |
| "loss": 0.03, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 7.857142857142858e-05, | |
| "loss": 0.0783, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0706, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 0.0635, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 6.785714285714286e-05, | |
| "loss": 0.0281, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 6.428571428571429e-05, | |
| "loss": 0.0636, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 6.0714285714285715e-05, | |
| "loss": 0.043, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 0.0864, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy": 0.9375, | |
| "eval_loss": 0.2472143918275833, | |
| "eval_runtime": 8.8207, | |
| "eval_samples_per_second": 63.487, | |
| "eval_steps_per_second": 7.936, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 5.3571428571428575e-05, | |
| "loss": 0.1104, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0393, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 4.642857142857143e-05, | |
| "loss": 0.0235, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 0.0191, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 3.928571428571429e-05, | |
| "loss": 0.0236, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.0448, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 0.0401, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.0186, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0197, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.0397, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "eval_accuracy": 0.9589285714285715, | |
| "eval_loss": 0.15928371250629425, | |
| "eval_runtime": 9.0766, | |
| "eval_samples_per_second": 61.697, | |
| "eval_steps_per_second": 7.712, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 0.0291, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.0182, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1.0714285714285714e-05, | |
| "loss": 0.0452, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 0.0173, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 3.5714285714285714e-06, | |
| "loss": 0.0165, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0166, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 560, | |
| "total_flos": 6.943593421681459e+17, | |
| "train_loss": 0.23941477111407689, | |
| "train_runtime": 355.1929, | |
| "train_samples_per_second": 25.226, | |
| "train_steps_per_second": 1.577 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 560, | |
| "num_train_epochs": 4, | |
| "save_steps": 100, | |
| "total_flos": 6.943593421681459e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |