|
{ |
|
"best_metric": 0.992469545957918, |
|
"best_model_checkpoint": "swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-LungCancer-LC25000-AH-40-30-30-3/checkpoint-1309", |
|
"epoch": 6.990654205607477, |
|
"eval_steps": 500, |
|
"global_step": 1309, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 3.816793893129771e-06, |
|
"loss": 1.1292, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 7.633587786259541e-06, |
|
"loss": 0.9838, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.1450381679389314e-05, |
|
"loss": 0.689, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 1.5267175572519083e-05, |
|
"loss": 0.4829, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 1.9083969465648855e-05, |
|
"loss": 0.3431, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 2.2900763358778628e-05, |
|
"loss": 0.3189, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 2.6717557251908397e-05, |
|
"loss": 0.1807, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 3.0534351145038166e-05, |
|
"loss": 0.3006, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 3.435114503816794e-05, |
|
"loss": 0.3244, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 3.816793893129771e-05, |
|
"loss": 0.2128, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 4.198473282442748e-05, |
|
"loss": 0.2781, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 4.5801526717557256e-05, |
|
"loss": 0.181, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 4.9618320610687025e-05, |
|
"loss": 0.1957, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 5.3435114503816794e-05, |
|
"loss": 0.1996, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 5.725190839694656e-05, |
|
"loss": 0.1654, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 6.106870229007633e-05, |
|
"loss": 0.1993, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 6.488549618320611e-05, |
|
"loss": 0.1601, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 6.870229007633588e-05, |
|
"loss": 0.2335, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 7.251908396946565e-05, |
|
"loss": 0.1595, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 7.633587786259542e-05, |
|
"loss": 0.3264, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 8.015267175572518e-05, |
|
"loss": 0.261, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 8.396946564885496e-05, |
|
"loss": 0.1172, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 8.778625954198472e-05, |
|
"loss": 0.2057, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 9.160305343511451e-05, |
|
"loss": 0.4153, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 9.541984732824429e-05, |
|
"loss": 0.4453, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 9.923664122137405e-05, |
|
"loss": 0.2069, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 0.00010305343511450383, |
|
"loss": 0.1238, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 0.00010687022900763359, |
|
"loss": 0.3154, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 0.00011068702290076336, |
|
"loss": 0.2941, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 0.00011450381679389313, |
|
"loss": 0.3083, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 0.0001183206106870229, |
|
"loss": 0.3601, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 0.00012213740458015266, |
|
"loss": 0.3151, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 0.00012595419847328244, |
|
"loss": 0.284, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 0.00012977099236641222, |
|
"loss": 0.3097, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 0.000133587786259542, |
|
"loss": 0.2929, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.00013740458015267177, |
|
"loss": 0.1706, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 0.00014122137404580154, |
|
"loss": 0.2297, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.9231450719822812, |
|
"eval_loss": 0.3400990664958954, |
|
"eval_runtime": 2470.4126, |
|
"eval_samples_per_second": 1.828, |
|
"eval_steps_per_second": 0.229, |
|
"step": 187 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 0.0001450381679389313, |
|
"loss": 0.3795, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 0.00014885496183206107, |
|
"loss": 0.8246, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 0.00015267175572519084, |
|
"loss": 0.4403, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 0.00015648854961832062, |
|
"loss": 0.1943, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 0.00016030534351145037, |
|
"loss": 0.3229, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 0.00016412213740458014, |
|
"loss": 0.262, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 0.00016793893129770992, |
|
"loss": 0.2737, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 0.0001717557251908397, |
|
"loss": 0.1592, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 0.00017557251908396944, |
|
"loss": 0.253, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 0.00017938931297709925, |
|
"loss": 0.2214, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 0.00018320610687022902, |
|
"loss": 0.3303, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 0.0001870229007633588, |
|
"loss": 0.3262, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 0.00019083969465648857, |
|
"loss": 0.2077, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 0.00019465648854961832, |
|
"loss": 0.2725, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 0.0001984732824427481, |
|
"loss": 0.1802, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 0.00020229007633587788, |
|
"loss": 0.2252, |
|
"step": 265 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 0.00020610687022900765, |
|
"loss": 0.2548, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 0.0002099236641221374, |
|
"loss": 0.2303, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 0.00021374045801526718, |
|
"loss": 0.5035, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 0.00021755725190839695, |
|
"loss": 0.4469, |
|
"step": 285 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 0.00022137404580152673, |
|
"loss": 0.3752, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 0.00022519083969465648, |
|
"loss": 0.1244, |
|
"step": 295 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 0.00022900763358778625, |
|
"loss": 0.1889, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 0.00023282442748091603, |
|
"loss": 0.1583, |
|
"step": 305 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 0.0002366412213740458, |
|
"loss": 0.2542, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 0.00024045801526717558, |
|
"loss": 0.2861, |
|
"step": 315 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 0.00024427480916030533, |
|
"loss": 0.1671, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 0.00024809160305343513, |
|
"loss": 0.2157, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 0.0002519083969465649, |
|
"loss": 0.2092, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 0.00025572519083969463, |
|
"loss": 0.172, |
|
"step": 335 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 0.00025954198473282443, |
|
"loss": 0.4118, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 0.0002633587786259542, |
|
"loss": 0.2941, |
|
"step": 345 |
|
}, |
|
{ |
|
"epoch": 1.87, |
|
"learning_rate": 0.000267175572519084, |
|
"loss": 0.1484, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 0.00027099236641221373, |
|
"loss": 0.287, |
|
"step": 355 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 0.00027480916030534353, |
|
"loss": 0.279, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 0.0002786259541984733, |
|
"loss": 0.2117, |
|
"step": 365 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 0.0002824427480916031, |
|
"loss": 0.3255, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.9643410852713178, |
|
"eval_loss": 0.1010039672255516, |
|
"eval_runtime": 193.6164, |
|
"eval_samples_per_second": 23.319, |
|
"eval_steps_per_second": 2.918, |
|
"step": 374 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 0.0002862595419847328, |
|
"loss": 0.193, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 0.0002900763358778626, |
|
"loss": 0.3363, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 2.06, |
|
"learning_rate": 0.0002938931297709924, |
|
"loss": 0.2783, |
|
"step": 385 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 0.00029770992366412214, |
|
"loss": 0.1567, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 2.11, |
|
"learning_rate": 0.00030152671755725194, |
|
"loss": 0.3207, |
|
"step": 395 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 0.0003053435114503817, |
|
"loss": 0.2227, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 0.0003091603053435115, |
|
"loss": 0.2319, |
|
"step": 405 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 0.00031297709923664124, |
|
"loss": 0.2516, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 2.22, |
|
"learning_rate": 0.000316793893129771, |
|
"loss": 0.198, |
|
"step": 415 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 0.00032061068702290074, |
|
"loss": 0.3153, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 2.27, |
|
"learning_rate": 0.00032442748091603054, |
|
"loss": 0.3282, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 2.3, |
|
"learning_rate": 0.0003282442748091603, |
|
"loss": 0.305, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 0.0003320610687022901, |
|
"loss": 0.4627, |
|
"step": 435 |
|
}, |
|
{ |
|
"epoch": 2.35, |
|
"learning_rate": 0.00033587786259541984, |
|
"loss": 0.2607, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 2.38, |
|
"learning_rate": 0.00033969465648854964, |
|
"loss": 0.235, |
|
"step": 445 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 0.0003435114503816794, |
|
"loss": 0.2973, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 2.43, |
|
"learning_rate": 0.0003473282442748092, |
|
"loss": 0.3968, |
|
"step": 455 |
|
}, |
|
{ |
|
"epoch": 2.46, |
|
"learning_rate": 0.0003511450381679389, |
|
"loss": 0.2779, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"learning_rate": 0.0003549618320610687, |
|
"loss": 0.242, |
|
"step": 465 |
|
}, |
|
{ |
|
"epoch": 2.51, |
|
"learning_rate": 0.0003587786259541985, |
|
"loss": 0.1816, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 0.00036259541984732824, |
|
"loss": 0.2947, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 0.00036641221374045805, |
|
"loss": 0.2522, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 2.59, |
|
"learning_rate": 0.0003702290076335878, |
|
"loss": 0.4026, |
|
"step": 485 |
|
}, |
|
{ |
|
"epoch": 2.62, |
|
"learning_rate": 0.0003740458015267176, |
|
"loss": 0.3203, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"learning_rate": 0.00037786259541984735, |
|
"loss": 0.1702, |
|
"step": 495 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"learning_rate": 0.00038167938931297715, |
|
"loss": 0.2985, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.7, |
|
"learning_rate": 0.00038549618320610684, |
|
"loss": 0.3186, |
|
"step": 505 |
|
}, |
|
{ |
|
"epoch": 2.72, |
|
"learning_rate": 0.00038931297709923665, |
|
"loss": 0.1724, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"learning_rate": 0.0003931297709923664, |
|
"loss": 0.3203, |
|
"step": 515 |
|
}, |
|
{ |
|
"epoch": 2.78, |
|
"learning_rate": 0.0003969465648854962, |
|
"loss": 0.4068, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 2.8, |
|
"learning_rate": 0.00040076335877862595, |
|
"loss": 0.247, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 2.83, |
|
"learning_rate": 0.00040458015267175575, |
|
"loss": 0.2256, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 2.86, |
|
"learning_rate": 0.0004083969465648855, |
|
"loss": 0.2111, |
|
"step": 535 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 0.0004122137404580153, |
|
"loss": 0.2228, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 2.91, |
|
"learning_rate": 0.00041603053435114505, |
|
"loss": 0.1618, |
|
"step": 545 |
|
}, |
|
{ |
|
"epoch": 2.94, |
|
"learning_rate": 0.0004198473282442748, |
|
"loss": 0.1953, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 2.96, |
|
"learning_rate": 0.00042366412213740455, |
|
"loss": 0.4014, |
|
"step": 555 |
|
}, |
|
{ |
|
"epoch": 2.99, |
|
"learning_rate": 0.00042748091603053435, |
|
"loss": 0.4962, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9607973421926911, |
|
"eval_loss": 0.09668433666229248, |
|
"eval_runtime": 193.2648, |
|
"eval_samples_per_second": 23.362, |
|
"eval_steps_per_second": 2.923, |
|
"step": 561 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 0.00043129770992366415, |
|
"loss": 0.1603, |
|
"step": 565 |
|
}, |
|
{ |
|
"epoch": 3.04, |
|
"learning_rate": 0.0004351145038167939, |
|
"loss": 0.1989, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 3.07, |
|
"learning_rate": 0.0004389312977099237, |
|
"loss": 0.126, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 3.1, |
|
"learning_rate": 0.00044274809160305345, |
|
"loss": 0.4359, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 3.12, |
|
"learning_rate": 0.00044656488549618326, |
|
"loss": 0.2178, |
|
"step": 585 |
|
}, |
|
{ |
|
"epoch": 3.15, |
|
"learning_rate": 0.00045038167938931295, |
|
"loss": 0.2256, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 3.18, |
|
"learning_rate": 0.00045419847328244275, |
|
"loss": 0.2226, |
|
"step": 595 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"learning_rate": 0.0004580152671755725, |
|
"loss": 0.2424, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 3.23, |
|
"learning_rate": 0.0004618320610687023, |
|
"loss": 0.2644, |
|
"step": 605 |
|
}, |
|
{ |
|
"epoch": 3.26, |
|
"learning_rate": 0.00046564885496183206, |
|
"loss": 0.2048, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 3.28, |
|
"learning_rate": 0.00046946564885496186, |
|
"loss": 0.2766, |
|
"step": 615 |
|
}, |
|
{ |
|
"epoch": 3.31, |
|
"learning_rate": 0.0004732824427480916, |
|
"loss": 0.2327, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 3.34, |
|
"learning_rate": 0.0004770992366412214, |
|
"loss": 0.2662, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 3.36, |
|
"learning_rate": 0.00048091603053435116, |
|
"loss": 0.1448, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 3.39, |
|
"learning_rate": 0.0004847328244274809, |
|
"loss": 0.2287, |
|
"step": 635 |
|
}, |
|
{ |
|
"epoch": 3.42, |
|
"learning_rate": 0.0004885496183206107, |
|
"loss": 0.1811, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 3.44, |
|
"learning_rate": 0.0004923664122137404, |
|
"loss": 0.2301, |
|
"step": 645 |
|
}, |
|
{ |
|
"epoch": 3.47, |
|
"learning_rate": 0.0004961832061068703, |
|
"loss": 0.2068, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 3.5, |
|
"learning_rate": 0.0005, |
|
"loss": 0.1134, |
|
"step": 655 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"learning_rate": 0.000496177370030581, |
|
"loss": 0.215, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 3.55, |
|
"learning_rate": 0.0004923547400611621, |
|
"loss": 0.2762, |
|
"step": 665 |
|
}, |
|
{ |
|
"epoch": 3.58, |
|
"learning_rate": 0.0004885321100917432, |
|
"loss": 0.2555, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 3.6, |
|
"learning_rate": 0.00048470948012232416, |
|
"loss": 0.3345, |
|
"step": 675 |
|
}, |
|
{ |
|
"epoch": 3.63, |
|
"learning_rate": 0.00048088685015290524, |
|
"loss": 0.1561, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 3.66, |
|
"learning_rate": 0.00047706422018348627, |
|
"loss": 0.1449, |
|
"step": 685 |
|
}, |
|
{ |
|
"epoch": 3.68, |
|
"learning_rate": 0.00047324159021406724, |
|
"loss": 0.3557, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 3.71, |
|
"learning_rate": 0.0004694189602446483, |
|
"loss": 0.5036, |
|
"step": 695 |
|
}, |
|
{ |
|
"epoch": 3.74, |
|
"learning_rate": 0.00046559633027522934, |
|
"loss": 0.1832, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 3.77, |
|
"learning_rate": 0.00046177370030581037, |
|
"loss": 0.4736, |
|
"step": 705 |
|
}, |
|
{ |
|
"epoch": 3.79, |
|
"learning_rate": 0.00045795107033639145, |
|
"loss": 0.2116, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 3.82, |
|
"learning_rate": 0.0004541284403669725, |
|
"loss": 0.1522, |
|
"step": 715 |
|
}, |
|
{ |
|
"epoch": 3.85, |
|
"learning_rate": 0.00045030581039755355, |
|
"loss": 0.1374, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 3.87, |
|
"learning_rate": 0.0004464831804281346, |
|
"loss": 0.2018, |
|
"step": 725 |
|
}, |
|
{ |
|
"epoch": 3.9, |
|
"learning_rate": 0.0004426605504587156, |
|
"loss": 0.1472, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 3.93, |
|
"learning_rate": 0.0004388379204892967, |
|
"loss": 0.2752, |
|
"step": 735 |
|
}, |
|
{ |
|
"epoch": 3.95, |
|
"learning_rate": 0.0004350152905198777, |
|
"loss": 0.2655, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 3.98, |
|
"learning_rate": 0.00043119266055045873, |
|
"loss": 0.181, |
|
"step": 745 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.9295681063122924, |
|
"eval_loss": 0.16242608428001404, |
|
"eval_runtime": 193.174, |
|
"eval_samples_per_second": 23.373, |
|
"eval_steps_per_second": 2.925, |
|
"step": 749 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 0.00042737003058103976, |
|
"loss": 0.1413, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 4.03, |
|
"learning_rate": 0.0004235474006116208, |
|
"loss": 0.1415, |
|
"step": 755 |
|
}, |
|
{ |
|
"epoch": 4.06, |
|
"learning_rate": 0.0004197247706422018, |
|
"loss": 0.1483, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 4.09, |
|
"learning_rate": 0.0004159021406727829, |
|
"loss": 0.2537, |
|
"step": 765 |
|
}, |
|
{ |
|
"epoch": 4.11, |
|
"learning_rate": 0.0004120795107033639, |
|
"loss": 0.2672, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 4.14, |
|
"learning_rate": 0.00040825688073394494, |
|
"loss": 0.1963, |
|
"step": 775 |
|
}, |
|
{ |
|
"epoch": 4.17, |
|
"learning_rate": 0.000404434250764526, |
|
"loss": 0.1984, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 4.19, |
|
"learning_rate": 0.00040061162079510704, |
|
"loss": 0.171, |
|
"step": 785 |
|
}, |
|
{ |
|
"epoch": 4.22, |
|
"learning_rate": 0.00039678899082568807, |
|
"loss": 0.2535, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 4.25, |
|
"learning_rate": 0.00039296636085626915, |
|
"loss": 0.2084, |
|
"step": 795 |
|
}, |
|
{ |
|
"epoch": 4.27, |
|
"learning_rate": 0.00038914373088685017, |
|
"loss": 0.122, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 4.3, |
|
"learning_rate": 0.0003853211009174312, |
|
"loss": 0.1591, |
|
"step": 805 |
|
}, |
|
{ |
|
"epoch": 4.33, |
|
"learning_rate": 0.0003814984709480123, |
|
"loss": 0.2064, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 4.35, |
|
"learning_rate": 0.00037767584097859325, |
|
"loss": 0.1932, |
|
"step": 815 |
|
}, |
|
{ |
|
"epoch": 4.38, |
|
"learning_rate": 0.00037385321100917427, |
|
"loss": 0.1794, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 4.41, |
|
"learning_rate": 0.00037003058103975535, |
|
"loss": 0.1727, |
|
"step": 825 |
|
}, |
|
{ |
|
"epoch": 4.43, |
|
"learning_rate": 0.0003662079510703364, |
|
"loss": 0.0987, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 4.46, |
|
"learning_rate": 0.00036238532110091746, |
|
"loss": 0.1894, |
|
"step": 835 |
|
}, |
|
{ |
|
"epoch": 4.49, |
|
"learning_rate": 0.0003585626911314985, |
|
"loss": 0.1725, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 4.51, |
|
"learning_rate": 0.0003547400611620795, |
|
"loss": 0.1334, |
|
"step": 845 |
|
}, |
|
{ |
|
"epoch": 4.54, |
|
"learning_rate": 0.0003509174311926606, |
|
"loss": 0.1386, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 4.57, |
|
"learning_rate": 0.0003470948012232416, |
|
"loss": 0.2012, |
|
"step": 855 |
|
}, |
|
{ |
|
"epoch": 4.59, |
|
"learning_rate": 0.00034327217125382264, |
|
"loss": 0.4956, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 4.62, |
|
"learning_rate": 0.0003394495412844037, |
|
"loss": 0.16, |
|
"step": 865 |
|
}, |
|
{ |
|
"epoch": 4.65, |
|
"learning_rate": 0.00033562691131498474, |
|
"loss": 0.2497, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 4.67, |
|
"learning_rate": 0.00033180428134556576, |
|
"loss": 0.2201, |
|
"step": 875 |
|
}, |
|
{ |
|
"epoch": 4.7, |
|
"learning_rate": 0.0003279816513761468, |
|
"loss": 0.1424, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 4.73, |
|
"learning_rate": 0.0003241590214067278, |
|
"loss": 0.1505, |
|
"step": 885 |
|
}, |
|
{ |
|
"epoch": 4.75, |
|
"learning_rate": 0.00032033639143730884, |
|
"loss": 0.1896, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 4.78, |
|
"learning_rate": 0.0003165137614678899, |
|
"loss": 0.1165, |
|
"step": 895 |
|
}, |
|
{ |
|
"epoch": 4.81, |
|
"learning_rate": 0.00031269113149847094, |
|
"loss": 0.0779, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 4.83, |
|
"learning_rate": 0.00030886850152905197, |
|
"loss": 0.1667, |
|
"step": 905 |
|
}, |
|
{ |
|
"epoch": 4.86, |
|
"learning_rate": 0.00030504587155963305, |
|
"loss": 0.103, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 4.89, |
|
"learning_rate": 0.0003012232415902141, |
|
"loss": 0.2255, |
|
"step": 915 |
|
}, |
|
{ |
|
"epoch": 4.91, |
|
"learning_rate": 0.0002974006116207951, |
|
"loss": 0.2617, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 4.94, |
|
"learning_rate": 0.0002935779816513762, |
|
"loss": 0.2884, |
|
"step": 925 |
|
}, |
|
{ |
|
"epoch": 4.97, |
|
"learning_rate": 0.0002897553516819572, |
|
"loss": 0.1863, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 4.99, |
|
"learning_rate": 0.0002859327217125383, |
|
"loss": 0.2266, |
|
"step": 935 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.9614617940199336, |
|
"eval_loss": 0.09752781689167023, |
|
"eval_runtime": 193.4672, |
|
"eval_samples_per_second": 23.337, |
|
"eval_steps_per_second": 2.92, |
|
"step": 936 |
|
}, |
|
{ |
|
"epoch": 5.02, |
|
"learning_rate": 0.00028211009174311925, |
|
"loss": 0.1735, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 5.05, |
|
"learning_rate": 0.0002782874617737003, |
|
"loss": 0.1106, |
|
"step": 945 |
|
}, |
|
{ |
|
"epoch": 5.07, |
|
"learning_rate": 0.00027446483180428136, |
|
"loss": 0.1575, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 5.1, |
|
"learning_rate": 0.0002706422018348624, |
|
"loss": 0.1547, |
|
"step": 955 |
|
}, |
|
{ |
|
"epoch": 5.13, |
|
"learning_rate": 0.0002668195718654434, |
|
"loss": 0.1507, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 5.15, |
|
"learning_rate": 0.0002629969418960245, |
|
"loss": 0.1887, |
|
"step": 965 |
|
}, |
|
{ |
|
"epoch": 5.18, |
|
"learning_rate": 0.0002591743119266055, |
|
"loss": 0.1534, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 5.21, |
|
"learning_rate": 0.00025535168195718654, |
|
"loss": 0.0758, |
|
"step": 975 |
|
}, |
|
{ |
|
"epoch": 5.23, |
|
"learning_rate": 0.0002515290519877676, |
|
"loss": 0.0655, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 5.26, |
|
"learning_rate": 0.00024770642201834864, |
|
"loss": 0.1125, |
|
"step": 985 |
|
}, |
|
{ |
|
"epoch": 5.29, |
|
"learning_rate": 0.00024388379204892967, |
|
"loss": 0.1932, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 5.31, |
|
"learning_rate": 0.0002400611620795107, |
|
"loss": 0.1113, |
|
"step": 995 |
|
}, |
|
{ |
|
"epoch": 5.34, |
|
"learning_rate": 0.00023623853211009174, |
|
"loss": 0.0912, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 5.37, |
|
"learning_rate": 0.0002324159021406728, |
|
"loss": 0.1605, |
|
"step": 1005 |
|
}, |
|
{ |
|
"epoch": 5.39, |
|
"learning_rate": 0.00022859327217125385, |
|
"loss": 0.1793, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 5.42, |
|
"learning_rate": 0.00022477064220183487, |
|
"loss": 0.0705, |
|
"step": 1015 |
|
}, |
|
{ |
|
"epoch": 5.45, |
|
"learning_rate": 0.0002209480122324159, |
|
"loss": 0.0778, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 5.47, |
|
"learning_rate": 0.00021712538226299695, |
|
"loss": 0.1484, |
|
"step": 1025 |
|
}, |
|
{ |
|
"epoch": 5.5, |
|
"learning_rate": 0.00021330275229357798, |
|
"loss": 0.0914, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 5.53, |
|
"learning_rate": 0.00020948012232415903, |
|
"loss": 0.0886, |
|
"step": 1035 |
|
}, |
|
{ |
|
"epoch": 5.55, |
|
"learning_rate": 0.00020565749235474008, |
|
"loss": 0.1647, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 5.58, |
|
"learning_rate": 0.0002018348623853211, |
|
"loss": 0.0911, |
|
"step": 1045 |
|
}, |
|
{ |
|
"epoch": 5.61, |
|
"learning_rate": 0.00019801223241590213, |
|
"loss": 0.0603, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 5.63, |
|
"learning_rate": 0.00019418960244648318, |
|
"loss": 0.097, |
|
"step": 1055 |
|
}, |
|
{ |
|
"epoch": 5.66, |
|
"learning_rate": 0.0001903669724770642, |
|
"loss": 0.1378, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 5.69, |
|
"learning_rate": 0.00018654434250764526, |
|
"loss": 0.1187, |
|
"step": 1065 |
|
}, |
|
{ |
|
"epoch": 5.71, |
|
"learning_rate": 0.0001827217125382263, |
|
"loss": 0.1202, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 5.74, |
|
"learning_rate": 0.00017889908256880736, |
|
"loss": 0.1565, |
|
"step": 1075 |
|
}, |
|
{ |
|
"epoch": 5.77, |
|
"learning_rate": 0.00017507645259938836, |
|
"loss": 0.0996, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 5.79, |
|
"learning_rate": 0.00017125382262996941, |
|
"loss": 0.0821, |
|
"step": 1085 |
|
}, |
|
{ |
|
"epoch": 5.82, |
|
"learning_rate": 0.00016743119266055047, |
|
"loss": 0.084, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 5.85, |
|
"learning_rate": 0.0001636085626911315, |
|
"loss": 0.1211, |
|
"step": 1095 |
|
}, |
|
{ |
|
"epoch": 5.87, |
|
"learning_rate": 0.00015978593272171254, |
|
"loss": 0.1592, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 5.9, |
|
"learning_rate": 0.0001559633027522936, |
|
"loss": 0.1067, |
|
"step": 1105 |
|
}, |
|
{ |
|
"epoch": 5.93, |
|
"learning_rate": 0.00015214067278287462, |
|
"loss": 0.111, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 5.95, |
|
"learning_rate": 0.00014831804281345565, |
|
"loss": 0.0776, |
|
"step": 1115 |
|
}, |
|
{ |
|
"epoch": 5.98, |
|
"learning_rate": 0.0001444954128440367, |
|
"loss": 0.0981, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_accuracy": 0.9782945736434109, |
|
"eval_loss": 0.05765698477625847, |
|
"eval_runtime": 193.5485, |
|
"eval_samples_per_second": 23.327, |
|
"eval_steps_per_second": 2.919, |
|
"step": 1123 |
|
}, |
|
{ |
|
"epoch": 6.01, |
|
"learning_rate": 0.00014067278287461775, |
|
"loss": 0.1255, |
|
"step": 1125 |
|
}, |
|
{ |
|
"epoch": 6.03, |
|
"learning_rate": 0.00013685015290519878, |
|
"loss": 0.093, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 6.06, |
|
"learning_rate": 0.00013302752293577983, |
|
"loss": 0.1009, |
|
"step": 1135 |
|
}, |
|
{ |
|
"epoch": 6.09, |
|
"learning_rate": 0.00012920489296636088, |
|
"loss": 0.0498, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 6.11, |
|
"learning_rate": 0.00012538226299694188, |
|
"loss": 0.0594, |
|
"step": 1145 |
|
}, |
|
{ |
|
"epoch": 6.14, |
|
"learning_rate": 0.00012155963302752294, |
|
"loss": 0.0882, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 6.17, |
|
"learning_rate": 0.00011773700305810397, |
|
"loss": 0.3622, |
|
"step": 1155 |
|
}, |
|
{ |
|
"epoch": 6.19, |
|
"learning_rate": 0.00011391437308868502, |
|
"loss": 0.0536, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 6.22, |
|
"learning_rate": 0.00011009174311926606, |
|
"loss": 0.0691, |
|
"step": 1165 |
|
}, |
|
{ |
|
"epoch": 6.25, |
|
"learning_rate": 0.0001062691131498471, |
|
"loss": 0.0965, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 6.28, |
|
"learning_rate": 0.00010244648318042814, |
|
"loss": 0.0614, |
|
"step": 1175 |
|
}, |
|
{ |
|
"epoch": 6.3, |
|
"learning_rate": 9.862385321100918e-05, |
|
"loss": 0.041, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 6.33, |
|
"learning_rate": 9.480122324159021e-05, |
|
"loss": 0.0135, |
|
"step": 1185 |
|
}, |
|
{ |
|
"epoch": 6.36, |
|
"learning_rate": 9.097859327217125e-05, |
|
"loss": 0.0938, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 6.38, |
|
"learning_rate": 8.71559633027523e-05, |
|
"loss": 0.1184, |
|
"step": 1195 |
|
}, |
|
{ |
|
"epoch": 6.41, |
|
"learning_rate": 8.333333333333333e-05, |
|
"loss": 0.1004, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 6.44, |
|
"learning_rate": 7.951070336391437e-05, |
|
"loss": 0.0319, |
|
"step": 1205 |
|
}, |
|
{ |
|
"epoch": 6.46, |
|
"learning_rate": 7.568807339449542e-05, |
|
"loss": 0.1098, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 6.49, |
|
"learning_rate": 7.186544342507645e-05, |
|
"loss": 0.1152, |
|
"step": 1215 |
|
}, |
|
{ |
|
"epoch": 6.52, |
|
"learning_rate": 6.80428134556575e-05, |
|
"loss": 0.077, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 6.54, |
|
"learning_rate": 6.422018348623854e-05, |
|
"loss": 0.0487, |
|
"step": 1225 |
|
}, |
|
{ |
|
"epoch": 6.57, |
|
"learning_rate": 6.0397553516819576e-05, |
|
"loss": 0.0873, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 6.6, |
|
"learning_rate": 5.6574923547400615e-05, |
|
"loss": 0.0838, |
|
"step": 1235 |
|
}, |
|
{ |
|
"epoch": 6.62, |
|
"learning_rate": 5.275229357798165e-05, |
|
"loss": 0.0458, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 6.65, |
|
"learning_rate": 4.892966360856269e-05, |
|
"loss": 0.1171, |
|
"step": 1245 |
|
}, |
|
{ |
|
"epoch": 6.68, |
|
"learning_rate": 4.510703363914373e-05, |
|
"loss": 0.0412, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 6.7, |
|
"learning_rate": 4.1284403669724776e-05, |
|
"loss": 0.0484, |
|
"step": 1255 |
|
}, |
|
{ |
|
"epoch": 6.73, |
|
"learning_rate": 3.746177370030581e-05, |
|
"loss": 0.1255, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 6.76, |
|
"learning_rate": 3.3639143730886846e-05, |
|
"loss": 0.1212, |
|
"step": 1265 |
|
}, |
|
{ |
|
"epoch": 6.78, |
|
"learning_rate": 2.9816513761467892e-05, |
|
"loss": 0.0265, |
|
"step": 1270 |
|
}, |
|
{ |
|
"epoch": 6.81, |
|
"learning_rate": 2.599388379204893e-05, |
|
"loss": 0.0676, |
|
"step": 1275 |
|
}, |
|
{ |
|
"epoch": 6.84, |
|
"learning_rate": 2.217125382262997e-05, |
|
"loss": 0.0216, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 6.86, |
|
"learning_rate": 1.834862385321101e-05, |
|
"loss": 0.0113, |
|
"step": 1285 |
|
}, |
|
{ |
|
"epoch": 6.89, |
|
"learning_rate": 1.452599388379205e-05, |
|
"loss": 0.0254, |
|
"step": 1290 |
|
}, |
|
{ |
|
"epoch": 6.92, |
|
"learning_rate": 1.0703363914373088e-05, |
|
"loss": 0.0666, |
|
"step": 1295 |
|
}, |
|
{ |
|
"epoch": 6.94, |
|
"learning_rate": 6.880733944954129e-06, |
|
"loss": 0.0762, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 6.97, |
|
"learning_rate": 3.0581039755351682e-06, |
|
"loss": 0.0629, |
|
"step": 1305 |
|
}, |
|
{ |
|
"epoch": 6.99, |
|
"eval_accuracy": 0.992469545957918, |
|
"eval_loss": 0.0190800242125988, |
|
"eval_runtime": 193.283, |
|
"eval_samples_per_second": 23.36, |
|
"eval_steps_per_second": 2.923, |
|
"step": 1309 |
|
}, |
|
{ |
|
"epoch": 6.99, |
|
"step": 1309, |
|
"total_flos": 9.636137349860819e+18, |
|
"train_loss": 0.2139335812344817, |
|
"train_runtime": 11717.3663, |
|
"train_samples_per_second": 3.575, |
|
"train_steps_per_second": 0.112 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 1309, |
|
"num_train_epochs": 7, |
|
"save_steps": 500, |
|
"total_flos": 9.636137349860819e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|