| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "beit-large-patch16-224-finetuned-LungCancer-Classification-LC25000-AH-60-20-20/checkpoint-700", | |
| "epoch": 4.9733570159857905, | |
| "global_step": 700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 7.142857142857143e-07, | |
| "loss": 1.6004, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.4285714285714286e-06, | |
| "loss": 1.325, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.142857142857143e-06, | |
| "loss": 0.9127, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 0.7454, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.5714285714285714e-06, | |
| "loss": 0.5222, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.285714285714286e-06, | |
| "loss": 0.3041, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2369, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 0.1788, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.428571428571429e-06, | |
| "loss": 0.1364, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 0.1518, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.857142857142858e-06, | |
| "loss": 0.1596, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.571428571428573e-06, | |
| "loss": 0.1156, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.285714285714286e-06, | |
| "loss": 0.1384, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1503, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.0714285714285714e-05, | |
| "loss": 0.118, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.1428571428571429e-05, | |
| "loss": 0.142, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.2142857142857144e-05, | |
| "loss": 0.1192, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.2857142857142857e-05, | |
| "loss": 0.1385, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.357142857142857e-05, | |
| "loss": 0.1238, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.1065, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0875, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.5714285714285715e-05, | |
| "loss": 0.0809, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.642857142857143e-05, | |
| "loss": 0.0808, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.7142857142857145e-05, | |
| "loss": 0.0823, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 0.1061, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.8571428571428572e-05, | |
| "loss": 0.1104, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.928571428571429e-05, | |
| "loss": 0.0421, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1071, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.993, | |
| "eval_loss": 0.01808181218802929, | |
| "eval_runtime": 1679.5269, | |
| "eval_samples_per_second": 1.786, | |
| "eval_steps_per_second": 0.112, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 2.0714285714285718e-05, | |
| "loss": 0.0572, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.0842, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 2.214285714285714e-05, | |
| "loss": 0.0668, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 2.2857142857142858e-05, | |
| "loss": 0.046, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 2.357142857142857e-05, | |
| "loss": 0.0822, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.4285714285714288e-05, | |
| "loss": 0.0689, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.1075, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.5714285714285714e-05, | |
| "loss": 0.0331, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.642857142857143e-05, | |
| "loss": 0.0882, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.714285714285714e-05, | |
| "loss": 0.0772, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.785714285714286e-05, | |
| "loss": 0.1812, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.1212, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.9285714285714288e-05, | |
| "loss": 0.0471, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0938, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 3.071428571428572e-05, | |
| "loss": 0.0362, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 3.142857142857143e-05, | |
| "loss": 0.091, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 0.0912, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 3.285714285714286e-05, | |
| "loss": 0.0398, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 3.357142857142857e-05, | |
| "loss": 0.1107, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 3.428571428571429e-05, | |
| "loss": 0.1248, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0597, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.089, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.642857142857143e-05, | |
| "loss": 0.0735, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 3.7142857142857143e-05, | |
| "loss": 0.1365, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.785714285714286e-05, | |
| "loss": 0.1206, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.857142857142858e-05, | |
| "loss": 0.0985, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 3.928571428571429e-05, | |
| "loss": 0.0522, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 4e-05, | |
| "loss": 0.2317, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.983, | |
| "eval_loss": 0.047446358948946, | |
| "eval_runtime": 130.3008, | |
| "eval_samples_per_second": 23.024, | |
| "eval_steps_per_second": 1.443, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 4.0714285714285717e-05, | |
| "loss": 0.1193, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 4.1428571428571437e-05, | |
| "loss": 0.1147, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 4.214285714285714e-05, | |
| "loss": 0.1097, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 0.0535, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 4.3571428571428576e-05, | |
| "loss": 0.0363, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 4.428571428571428e-05, | |
| "loss": 0.0717, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.135, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 4.5714285714285716e-05, | |
| "loss": 0.0782, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 4.642857142857143e-05, | |
| "loss": 0.0318, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 4.714285714285714e-05, | |
| "loss": 0.1323, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 4.785714285714286e-05, | |
| "loss": 0.0224, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 4.8571428571428576e-05, | |
| "loss": 0.0766, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 4.928571428571429e-05, | |
| "loss": 0.055, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0659, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 4.928571428571429e-05, | |
| "loss": 0.0177, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.8571428571428576e-05, | |
| "loss": 0.0865, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.785714285714286e-05, | |
| "loss": 0.0588, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 4.714285714285714e-05, | |
| "loss": 0.1111, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 4.642857142857143e-05, | |
| "loss": 0.0298, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 4.5714285714285716e-05, | |
| "loss": 0.0682, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0502, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 4.428571428571428e-05, | |
| "loss": 0.0522, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 4.3571428571428576e-05, | |
| "loss": 0.089, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 0.0877, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 4.214285714285714e-05, | |
| "loss": 0.0557, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 4.1428571428571437e-05, | |
| "loss": 0.0448, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 4.0714285714285717e-05, | |
| "loss": 0.0283, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0454, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9926666666666667, | |
| "eval_loss": 0.017334768548607826, | |
| "eval_runtime": 129.9512, | |
| "eval_samples_per_second": 23.086, | |
| "eval_steps_per_second": 1.447, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.928571428571429e-05, | |
| "loss": 0.0947, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 3.857142857142858e-05, | |
| "loss": 0.0823, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 3.785714285714286e-05, | |
| "loss": 0.0826, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 3.7142857142857143e-05, | |
| "loss": 0.0438, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 3.642857142857143e-05, | |
| "loss": 0.0302, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.0235, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0544, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 3.428571428571429e-05, | |
| "loss": 0.0493, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 3.357142857142857e-05, | |
| "loss": 0.0836, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 3.285714285714286e-05, | |
| "loss": 0.0215, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 0.0257, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 3.142857142857143e-05, | |
| "loss": 0.0074, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 3.071428571428572e-05, | |
| "loss": 0.0548, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0118, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 2.9285714285714288e-05, | |
| "loss": 0.0219, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.0183, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 2.785714285714286e-05, | |
| "loss": 0.0076, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 2.714285714285714e-05, | |
| "loss": 0.0566, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 2.642857142857143e-05, | |
| "loss": 0.0416, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 2.5714285714285714e-05, | |
| "loss": 0.0093, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0252, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 2.4285714285714288e-05, | |
| "loss": 0.0375, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 2.357142857142857e-05, | |
| "loss": 0.0286, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 2.2857142857142858e-05, | |
| "loss": 0.0489, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 2.214285714285714e-05, | |
| "loss": 0.0116, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.0326, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 2.0714285714285718e-05, | |
| "loss": 0.0452, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0299, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.994, | |
| "eval_loss": 0.015278426930308342, | |
| "eval_runtime": 129.7962, | |
| "eval_samples_per_second": 23.113, | |
| "eval_steps_per_second": 1.448, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 1.928571428571429e-05, | |
| "loss": 0.0435, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 1.8571428571428572e-05, | |
| "loss": 0.04, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 0.026, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 1.7142857142857145e-05, | |
| "loss": 0.0144, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 1.642857142857143e-05, | |
| "loss": 0.0621, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 1.5714285714285715e-05, | |
| "loss": 0.0041, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0172, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.0023, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 1.357142857142857e-05, | |
| "loss": 0.0239, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 1.2857142857142857e-05, | |
| "loss": 0.0153, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 1.2142857142857144e-05, | |
| "loss": 0.0142, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 1.1428571428571429e-05, | |
| "loss": 0.0156, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 1.0714285714285714e-05, | |
| "loss": 0.0158, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0434, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 9.285714285714286e-06, | |
| "loss": 0.0107, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 8.571428571428573e-06, | |
| "loss": 0.0443, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 7.857142857142858e-06, | |
| "loss": 0.0151, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 0.0074, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 6.428571428571429e-06, | |
| "loss": 0.0024, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 0.0114, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0011, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 4.285714285714286e-06, | |
| "loss": 0.01, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 3.5714285714285714e-06, | |
| "loss": 0.0225, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 0.0255, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 2.142857142857143e-06, | |
| "loss": 0.0012, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 1.4285714285714286e-06, | |
| "loss": 0.0259, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 7.142857142857143e-07, | |
| "loss": 0.0208, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 0.0, | |
| "loss": 0.0055, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.00011626419291133061, | |
| "eval_runtime": 129.4487, | |
| "eval_samples_per_second": 23.175, | |
| "eval_steps_per_second": 1.452, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "step": 700, | |
| "total_flos": 1.2267729254916882e+19, | |
| "train_loss": 0.10130466574936041, | |
| "train_runtime": 12554.5867, | |
| "train_samples_per_second": 3.584, | |
| "train_steps_per_second": 0.056 | |
| } | |
| ], | |
| "max_steps": 700, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.2267729254916882e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |