| { | |
| "best_metric": 0.7496974935177182, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-1218", | |
| "epoch": 2.994468346650277, | |
| "eval_steps": 500, | |
| "global_step": 1218, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.098360655737704e-06, | |
| "loss": 6.433, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.196721311475409e-06, | |
| "loss": 6.416, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.2295081967213116e-05, | |
| "loss": 6.3382, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.6393442622950818e-05, | |
| "loss": 6.1258, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.0491803278688525e-05, | |
| "loss": 5.8421, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.459016393442623e-05, | |
| "loss": 5.5024, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.8688524590163935e-05, | |
| "loss": 5.1467, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.2786885245901635e-05, | |
| "loss": 4.7367, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.6885245901639346e-05, | |
| "loss": 4.4434, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.098360655737705e-05, | |
| "loss": 4.2133, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.508196721311476e-05, | |
| "loss": 4.0056, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.918032786885246e-05, | |
| "loss": 4.0001, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.963503649635037e-05, | |
| "loss": 3.9115, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.9178832116788325e-05, | |
| "loss": 3.909, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.872262773722628e-05, | |
| "loss": 3.8147, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.8266423357664235e-05, | |
| "loss": 3.6984, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.7810218978102196e-05, | |
| "loss": 3.5625, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.7354014598540144e-05, | |
| "loss": 3.5524, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.6897810218978106e-05, | |
| "loss": 3.4258, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.644160583941606e-05, | |
| "loss": 3.4335, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.5985401459854016e-05, | |
| "loss": 3.4224, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.552919708029198e-05, | |
| "loss": 3.2971, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.5072992700729925e-05, | |
| "loss": 3.3419, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.461678832116789e-05, | |
| "loss": 3.22, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.416058394160584e-05, | |
| "loss": 3.2559, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.3704379562043796e-05, | |
| "loss": 3.2359, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 4.324817518248175e-05, | |
| "loss": 2.9756, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.279197080291971e-05, | |
| "loss": 2.9418, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.233576642335767e-05, | |
| "loss": 3.0601, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.187956204379562e-05, | |
| "loss": 3.0173, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.1423357664233584e-05, | |
| "loss": 2.9081, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.096715328467153e-05, | |
| "loss": 2.7525, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.0510948905109494e-05, | |
| "loss": 2.774, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.005474452554745e-05, | |
| "loss": 2.7805, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.95985401459854e-05, | |
| "loss": 2.6359, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.914233576642336e-05, | |
| "loss": 2.7126, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.868613138686132e-05, | |
| "loss": 2.5696, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.822992700729927e-05, | |
| "loss": 2.5396, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.777372262773723e-05, | |
| "loss": 2.5119, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.7317518248175184e-05, | |
| "loss": 2.5294, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5865168539325842, | |
| "eval_loss": 2.107146739959717, | |
| "eval_runtime": 28.2223, | |
| "eval_samples_per_second": 204.98, | |
| "eval_steps_per_second": 6.413, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.686131386861314e-05, | |
| "loss": 2.5622, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.64051094890511e-05, | |
| "loss": 2.4528, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.594890510948905e-05, | |
| "loss": 2.4302, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.549270072992701e-05, | |
| "loss": 2.3664, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.5036496350364965e-05, | |
| "loss": 2.3382, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.458029197080292e-05, | |
| "loss": 2.386, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.4124087591240875e-05, | |
| "loss": 2.3621, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.3667883211678836e-05, | |
| "loss": 2.3706, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.321167883211679e-05, | |
| "loss": 2.3005, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.2755474452554746e-05, | |
| "loss": 2.3632, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.229927007299271e-05, | |
| "loss": 2.2058, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.1843065693430655e-05, | |
| "loss": 2.231, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.138686131386862e-05, | |
| "loss": 2.3454, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.093065693430657e-05, | |
| "loss": 2.1551, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.0474452554744527e-05, | |
| "loss": 2.1461, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 3.0018248175182485e-05, | |
| "loss": 2.2473, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.9562043795620443e-05, | |
| "loss": 2.2178, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.9105839416058394e-05, | |
| "loss": 2.0885, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.8649635036496353e-05, | |
| "loss": 2.1198, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.8193430656934304e-05, | |
| "loss": 2.1566, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.7737226277372262e-05, | |
| "loss": 2.2305, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.728102189781022e-05, | |
| "loss": 2.0076, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.6824817518248175e-05, | |
| "loss": 1.9865, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.6368613138686133e-05, | |
| "loss": 2.151, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.591240875912409e-05, | |
| "loss": 2.0612, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.5456204379562043e-05, | |
| "loss": 2.0431, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.0422, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.4543795620437956e-05, | |
| "loss": 2.0565, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.4087591240875914e-05, | |
| "loss": 1.9515, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.363138686131387e-05, | |
| "loss": 2.1044, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.3175182481751824e-05, | |
| "loss": 1.9952, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.2718978102189782e-05, | |
| "loss": 2.0582, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.226277372262774e-05, | |
| "loss": 1.9372, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.1806569343065695e-05, | |
| "loss": 1.9758, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.135036496350365e-05, | |
| "loss": 1.9974, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.0894160583941608e-05, | |
| "loss": 1.9725, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2.0437956204379563e-05, | |
| "loss": 2.0613, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.9981751824817518e-05, | |
| "loss": 1.8908, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.9525547445255476e-05, | |
| "loss": 1.8355, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.906934306569343e-05, | |
| "loss": 1.8955, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.861313868613139e-05, | |
| "loss": 1.9362, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7218668971477961, | |
| "eval_loss": 1.4541077613830566, | |
| "eval_runtime": 27.9276, | |
| "eval_samples_per_second": 207.143, | |
| "eval_steps_per_second": 6.481, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.8156934306569344e-05, | |
| "loss": 1.8781, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.7700729927007302e-05, | |
| "loss": 1.9182, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.7244525547445257e-05, | |
| "loss": 1.8944, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.678832116788321e-05, | |
| "loss": 1.8667, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.633211678832117e-05, | |
| "loss": 1.879, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.5875912408759125e-05, | |
| "loss": 1.8376, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.541970802919708e-05, | |
| "loss": 1.8446, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.496350364963504e-05, | |
| "loss": 1.8271, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.4507299270072994e-05, | |
| "loss": 1.8052, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.4051094890510949e-05, | |
| "loss": 1.7987, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.3594890510948904e-05, | |
| "loss": 1.9407, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.3138686131386862e-05, | |
| "loss": 1.9835, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.2682481751824818e-05, | |
| "loss": 1.7249, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.2226277372262775e-05, | |
| "loss": 1.7717, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.177007299270073e-05, | |
| "loss": 1.7976, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.1313868613138686e-05, | |
| "loss": 1.7857, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 1.0857664233576643e-05, | |
| "loss": 1.8899, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 1.04014598540146e-05, | |
| "loss": 1.7449, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 9.945255474452556e-06, | |
| "loss": 1.7657, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 9.48905109489051e-06, | |
| "loss": 1.8645, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 9.032846715328467e-06, | |
| "loss": 1.8106, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 8.576642335766425e-06, | |
| "loss": 1.8082, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 8.12043795620438e-06, | |
| "loss": 1.5872, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.664233576642336e-06, | |
| "loss": 1.8594, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 7.208029197080292e-06, | |
| "loss": 1.7495, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.751824817518249e-06, | |
| "loss": 1.6744, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 6.295620437956205e-06, | |
| "loss": 1.6667, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 5.839416058394161e-06, | |
| "loss": 1.7831, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.3832116788321165e-06, | |
| "loss": 1.6088, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 4.927007299270074e-06, | |
| "loss": 1.6938, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.4708029197080295e-06, | |
| "loss": 1.794, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 4.014598540145985e-06, | |
| "loss": 1.8384, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.5583941605839416e-06, | |
| "loss": 1.6364, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.102189781021898e-06, | |
| "loss": 1.7934, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.6459854014598542e-06, | |
| "loss": 1.7715, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.1897810218978103e-06, | |
| "loss": 1.7242, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.7335766423357664e-06, | |
| "loss": 1.8898, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.2773722627737227e-06, | |
| "loss": 1.6993, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 8.211678832116789e-07, | |
| "loss": 1.8267, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.6496350364963505e-07, | |
| "loss": 1.8206, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.7496974935177182, | |
| "eval_loss": 1.28416907787323, | |
| "eval_runtime": 27.5596, | |
| "eval_samples_per_second": 209.909, | |
| "eval_steps_per_second": 6.568, | |
| "step": 1218 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "step": 1218, | |
| "total_flos": 3.942238865741697e+18, | |
| "train_loss": 2.564211890028028, | |
| "train_runtime": 1311.9838, | |
| "train_samples_per_second": 119.043, | |
| "train_steps_per_second": 0.928 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1218, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 3.942238865741697e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |