Training in progress, epoch 1

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 8.923548605812163e+17,
-    "train_loss": 0.05896045783503104,
-    "train_runtime": 1057.571,
-    "train_samples_per_second": 33.947,
-    "train_steps_per_second": 1.061
+    "train_loss": 0.16757579408121193,
+    "train_runtime": 1092.7636,
+    "train_samples_per_second": 32.853,
+    "train_steps_per_second": 1.027
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2278af5d7e9cc96d8b90c6a57eb22124b549d954a25aa734e22dd71427a08116
+oid sha256:b39052865a3f0a2e07a3df4e530ebfc570f2220d939c3079f28e88359531126d
 size 110342832

runs/Dec07_00-13-26_7d2ff79f697a/events.out.tfevents.1701909244.7d2ff79f697a.235.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd02f1865783672f5617db2ca9ea70d382090fd52f13abecbd0cf686a11ade6b
+size 10845

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 8.923548605812163e+17,
-    "train_loss": 0.05896045783503104,
-    "train_runtime": 1057.571,
-    "train_samples_per_second": 33.947,
-    "train_steps_per_second": 1.061
+    "train_loss": 0.16757579408121193,
+    "train_runtime": 1092.7636,
+    "train_samples_per_second": 32.853,
+    "train_steps_per_second": 1.027
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.9963235294117647,
+  "best_metric": 0.983957219251337,
   "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-748",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -11,710 +11,710 @@
     {
       "epoch": 0.03,
       "learning_rate": 4.424778761061947e-06,
-      "loss": 0.0861,
+      "loss": 0.7114,
       "step": 10
     },
     {
       "epoch": 0.05,
       "learning_rate": 8.849557522123894e-06,
-      "loss": 0.0536,
+      "loss": 0.6818,
       "step": 20
     },
     {
       "epoch": 0.08,
       "learning_rate": 1.3274336283185843e-05,
-      "loss": 0.0764,
+      "loss": 0.5928,
       "step": 30
     },
     {
       "epoch": 0.11,
       "learning_rate": 1.7699115044247787e-05,
-      "loss": 0.0808,
+      "loss": 0.5168,
       "step": 40
     },
     {
       "epoch": 0.13,
       "learning_rate": 2.2123893805309738e-05,
-      "loss": 0.1042,
+      "loss": 0.4569,
       "step": 50
     },
     {
       "epoch": 0.16,
       "learning_rate": 2.6548672566371686e-05,
-      "loss": 0.0486,
+      "loss": 0.4175,
       "step": 60
     },
     {
       "epoch": 0.19,
       "learning_rate": 3.097345132743363e-05,
-      "loss": 0.0229,
+      "loss": 0.3775,
       "step": 70
     },
     {
       "epoch": 0.21,
       "learning_rate": 3.5398230088495574e-05,
-      "loss": 0.0433,
+      "loss": 0.3782,
       "step": 80
     },
     {
       "epoch": 0.24,
       "learning_rate": 3.982300884955752e-05,
-      "loss": 0.0444,
+      "loss": 0.3482,
       "step": 90
     },
     {
       "epoch": 0.27,
       "learning_rate": 4.4247787610619477e-05,
-      "loss": 0.0873,
+      "loss": 0.3127,
       "step": 100
     },
     {
       "epoch": 0.29,
       "learning_rate": 4.867256637168142e-05,
-      "loss": 0.0857,
+      "loss": 0.3227,
       "step": 110
     },
     {
       "epoch": 0.32,
       "learning_rate": 4.9653121902874134e-05,
-      "loss": 0.0505,
+      "loss": 0.2943,
       "step": 120
     },
     {
       "epoch": 0.35,
       "learning_rate": 4.9157581764122896e-05,
-      "loss": 0.1017,
+      "loss": 0.2172,
       "step": 130
     },
     {
       "epoch": 0.37,
       "learning_rate": 4.866204162537166e-05,
-      "loss": 0.0413,
+      "loss": 0.2294,
       "step": 140
     },
     {
       "epoch": 0.4,
       "learning_rate": 4.816650148662042e-05,
-      "loss": 0.0603,
+      "loss": 0.3111,
       "step": 150
     },
     {
       "epoch": 0.43,
       "learning_rate": 4.767096134786918e-05,
-      "loss": 0.0831,
+      "loss": 0.1876,
       "step": 160
     },
     {
       "epoch": 0.45,
       "learning_rate": 4.717542120911794e-05,
-      "loss": 0.1536,
+      "loss": 0.2117,
       "step": 170
     },
     {
       "epoch": 0.48,
       "learning_rate": 4.66798810703667e-05,
-      "loss": 0.0868,
+      "loss": 0.1996,
       "step": 180
     },
     {
       "epoch": 0.51,
       "learning_rate": 4.618434093161546e-05,
-      "loss": 0.0617,
+      "loss": 0.202,
       "step": 190
     },
     {
       "epoch": 0.53,
       "learning_rate": 4.568880079286422e-05,
-      "loss": 0.0848,
+      "loss": 0.2251,
       "step": 200
     },
     {
       "epoch": 0.56,
       "learning_rate": 4.5193260654112984e-05,
-      "loss": 0.0583,
+      "loss": 0.1994,
       "step": 210
     },
     {
       "epoch": 0.59,
       "learning_rate": 4.4697720515361746e-05,
-      "loss": 0.0419,
+      "loss": 0.214,
       "step": 220
     },
     {
       "epoch": 0.61,
       "learning_rate": 4.420218037661051e-05,
-      "loss": 0.1151,
+      "loss": 0.2265,
       "step": 230
     },
     {
       "epoch": 0.64,
       "learning_rate": 4.370664023785927e-05,
-      "loss": 0.1199,
+      "loss": 0.2537,
       "step": 240
     },
     {
       "epoch": 0.67,
       "learning_rate": 4.321110009910803e-05,
-      "loss": 0.0718,
+      "loss": 0.2283,
       "step": 250
     },
     {
       "epoch": 0.7,
       "learning_rate": 4.27155599603568e-05,
-      "loss": 0.0671,
+      "loss": 0.2179,
       "step": 260
     },
     {
       "epoch": 0.72,
       "learning_rate": 4.222001982160555e-05,
-      "loss": 0.0757,
+      "loss": 0.1785,
       "step": 270
     },
     {
       "epoch": 0.75,
       "learning_rate": 4.172447968285431e-05,
-      "loss": 0.0758,
+      "loss": 0.1959,
       "step": 280
     },
     {
       "epoch": 0.78,
       "learning_rate": 4.122893954410307e-05,
-      "loss": 0.055,
+      "loss": 0.1733,
       "step": 290
     },
     {
       "epoch": 0.8,
       "learning_rate": 4.0733399405351834e-05,
-      "loss": 0.0817,
+      "loss": 0.1866,
       "step": 300
     },
     {
       "epoch": 0.83,
       "learning_rate": 4.0237859266600596e-05,
-      "loss": 0.0693,
+      "loss": 0.1919,
       "step": 310
     },
     {
       "epoch": 0.86,
       "learning_rate": 3.9742319127849357e-05,
-      "loss": 0.0529,
+      "loss": 0.1769,
       "step": 320
     },
     {
       "epoch": 0.88,
       "learning_rate": 3.924677898909812e-05,
-      "loss": 0.0701,
+      "loss": 0.1724,
       "step": 330
     },
     {
       "epoch": 0.91,
       "learning_rate": 3.8751238850346886e-05,
-      "loss": 0.0963,
+      "loss": 0.2367,
       "step": 340
     },
     {
       "epoch": 0.94,
       "learning_rate": 3.825569871159564e-05,
-      "loss": 0.1127,
+      "loss": 0.1933,
       "step": 350
     },
     {
       "epoch": 0.96,
       "learning_rate": 3.77601585728444e-05,
-      "loss": 0.0827,
+      "loss": 0.1371,
       "step": 360
     },
     {
       "epoch": 0.99,
       "learning_rate": 3.726461843409316e-05,
-      "loss": 0.0732,
+      "loss": 0.1221,
       "step": 370
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.991644385026738,
-      "eval_loss": 0.020979605615139008,
-      "eval_runtime": 59.8783,
-      "eval_samples_per_second": 49.968,
-      "eval_steps_per_second": 6.246,
+      "eval_accuracy": 0.9752673796791443,
+      "eval_loss": 0.06625619530677795,
+      "eval_runtime": 56.0823,
+      "eval_samples_per_second": 53.35,
+      "eval_steps_per_second": 6.669,
       "step": 374
     },
     {
       "epoch": 1.02,
       "learning_rate": 3.676907829534192e-05,
-      "loss": 0.0599,
+      "loss": 0.1682,
       "step": 380
     },
     {
       "epoch": 1.04,
       "learning_rate": 3.6273538156590684e-05,
-      "loss": 0.0632,
+      "loss": 0.1149,
       "step": 390
     },
     {
       "epoch": 1.07,
       "learning_rate": 3.5777998017839445e-05,
-      "loss": 0.106,
+      "loss": 0.1326,
       "step": 400
     },
     {
       "epoch": 1.1,
       "learning_rate": 3.5282457879088207e-05,
-      "loss": 0.0528,
+      "loss": 0.1628,
       "step": 410
     },
     {
       "epoch": 1.12,
       "learning_rate": 3.4786917740336974e-05,
-      "loss": 0.0566,
+      "loss": 0.1162,
       "step": 420
     },
     {
       "epoch": 1.15,
       "learning_rate": 3.429137760158573e-05,
-      "loss": 0.0372,
+      "loss": 0.1211,
       "step": 430
     },
     {
       "epoch": 1.18,
       "learning_rate": 3.379583746283449e-05,
-      "loss": 0.0968,
+      "loss": 0.1569,
       "step": 440
     },
     {
       "epoch": 1.2,
       "learning_rate": 3.330029732408325e-05,
-      "loss": 0.057,
+      "loss": 0.1748,
       "step": 450
     },
     {
       "epoch": 1.23,
       "learning_rate": 3.280475718533201e-05,
-      "loss": 0.0906,
+      "loss": 0.149,
       "step": 460
     },
     {
       "epoch": 1.26,
       "learning_rate": 3.230921704658077e-05,
-      "loss": 0.0554,
+      "loss": 0.1389,
       "step": 470
     },
     {
       "epoch": 1.28,
       "learning_rate": 3.1813676907829534e-05,
-      "loss": 0.0909,
+      "loss": 0.1382,
       "step": 480
     },
     {
       "epoch": 1.31,
       "learning_rate": 3.13181367690783e-05,
-      "loss": 0.0922,
+      "loss": 0.1472,
       "step": 490
     },
     {
       "epoch": 1.34,
       "learning_rate": 3.0822596630327057e-05,
-      "loss": 0.0531,
+      "loss": 0.1334,
       "step": 500
     },
     {
       "epoch": 1.36,
       "learning_rate": 3.0327056491575818e-05,
-      "loss": 0.0898,
+      "loss": 0.1479,
       "step": 510
     },
     {
       "epoch": 1.39,
       "learning_rate": 2.983151635282458e-05,
-      "loss": 0.0726,
+      "loss": 0.1615,
       "step": 520
     },
     {
       "epoch": 1.42,
       "learning_rate": 2.933597621407334e-05,
-      "loss": 0.0388,
+      "loss": 0.1835,
       "step": 530
     },
     {
       "epoch": 1.44,
       "learning_rate": 2.88404360753221e-05,
-      "loss": 0.0597,
+      "loss": 0.1199,
       "step": 540
     },
     {
       "epoch": 1.47,
       "learning_rate": 2.8344895936570865e-05,
-      "loss": 0.0383,
+      "loss": 0.1561,
       "step": 550
     },
     {
       "epoch": 1.5,
       "learning_rate": 2.7849355797819627e-05,
-      "loss": 0.0206,
+      "loss": 0.1284,
       "step": 560
     },
     {
       "epoch": 1.52,
       "learning_rate": 2.7353815659068388e-05,
-      "loss": 0.1202,
+      "loss": 0.0988,
       "step": 570
     },
     {
       "epoch": 1.55,
       "learning_rate": 2.6858275520317145e-05,
-      "loss": 0.0324,
+      "loss": 0.1238,
       "step": 580
     },
     {
       "epoch": 1.58,
       "learning_rate": 2.6362735381565906e-05,
-      "loss": 0.0584,
+      "loss": 0.0941,
       "step": 590
     },
     {
       "epoch": 1.6,
       "learning_rate": 2.5867195242814668e-05,
-      "loss": 0.0279,
+      "loss": 0.1076,
       "step": 600
     },
     {
       "epoch": 1.63,
       "learning_rate": 2.537165510406343e-05,
-      "loss": 0.0693,
+      "loss": 0.1121,
       "step": 610
     },
     {
       "epoch": 1.66,
       "learning_rate": 2.4876114965312193e-05,
-      "loss": 0.0915,
+      "loss": 0.1547,
       "step": 620
     },
     {
       "epoch": 1.68,
       "learning_rate": 2.4380574826560954e-05,
-      "loss": 0.0657,
+      "loss": 0.1167,
       "step": 630
     },
     {
       "epoch": 1.71,
       "learning_rate": 2.3885034687809712e-05,
-      "loss": 0.0722,
+      "loss": 0.1006,
       "step": 640
     },
     {
       "epoch": 1.74,
       "learning_rate": 2.3389494549058473e-05,
-      "loss": 0.0589,
+      "loss": 0.1313,
       "step": 650
     },
     {
       "epoch": 1.76,
       "learning_rate": 2.2893954410307238e-05,
-      "loss": 0.0867,
+      "loss": 0.0762,
       "step": 660
     },
     {
       "epoch": 1.79,
       "learning_rate": 2.2398414271556e-05,
-      "loss": 0.0537,
+      "loss": 0.1407,
       "step": 670
     },
     {
       "epoch": 1.82,
       "learning_rate": 2.1902874132804756e-05,
-      "loss": 0.0116,
+      "loss": 0.1033,
       "step": 680
     },
     {
       "epoch": 1.84,
       "learning_rate": 2.1407333994053518e-05,
-      "loss": 0.0745,
+      "loss": 0.1404,
       "step": 690
     },
     {
       "epoch": 1.87,
       "learning_rate": 2.0911793855302282e-05,
-      "loss": 0.0159,
+      "loss": 0.1184,
       "step": 700
     },
     {
       "epoch": 1.9,
       "learning_rate": 2.0416253716551043e-05,
-      "loss": 0.0503,
+      "loss": 0.1018,
       "step": 710
     },
     {
       "epoch": 1.93,
       "learning_rate": 1.99207135777998e-05,
-      "loss": 0.0401,
+      "loss": 0.113,
       "step": 720
     },
     {
       "epoch": 1.95,
       "learning_rate": 1.9425173439048562e-05,
-      "loss": 0.0603,
+      "loss": 0.1662,
       "step": 730
     },
     {
       "epoch": 1.98,
       "learning_rate": 1.8929633300297326e-05,
-      "loss": 0.0341,
+      "loss": 0.1151,
       "step": 740
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.9963235294117647,
-      "eval_loss": 0.015195885673165321,
-      "eval_runtime": 60.4503,
-      "eval_samples_per_second": 49.495,
-      "eval_steps_per_second": 6.187,
+      "eval_accuracy": 0.983957219251337,
+      "eval_loss": 0.048957787454128265,
+      "eval_runtime": 52.6013,
+      "eval_samples_per_second": 56.881,
+      "eval_steps_per_second": 7.11,
       "step": 748
     },
     {
       "epoch": 2.01,
       "learning_rate": 1.8434093161546088e-05,
-      "loss": 0.0331,
+      "loss": 0.0981,
       "step": 750
     },
     {
       "epoch": 2.03,
       "learning_rate": 1.7938553022794845e-05,
-      "loss": 0.0399,
+      "loss": 0.0992,
       "step": 760
     },
     {
       "epoch": 2.06,
       "learning_rate": 1.7443012884043606e-05,
-      "loss": 0.0357,
+      "loss": 0.0729,
       "step": 770
     },
     {
       "epoch": 2.09,
       "learning_rate": 1.694747274529237e-05,
-      "loss": 0.05,
+      "loss": 0.0915,
       "step": 780
     },
     {
       "epoch": 2.11,
       "learning_rate": 1.6451932606541132e-05,
-      "loss": 0.0313,
+      "loss": 0.1058,
       "step": 790
     },
     {
       "epoch": 2.14,
       "learning_rate": 1.595639246778989e-05,
-      "loss": 0.0375,
+      "loss": 0.1003,
       "step": 800
     },
     {
       "epoch": 2.17,
       "learning_rate": 1.5460852329038654e-05,
-      "loss": 0.0313,
+      "loss": 0.1309,
       "step": 810
     },
     {
       "epoch": 2.19,
       "learning_rate": 1.4965312190287414e-05,
-      "loss": 0.0856,
+      "loss": 0.0556,
       "step": 820
     },
     {
       "epoch": 2.22,
       "learning_rate": 1.4469772051536176e-05,
-      "loss": 0.057,
+      "loss": 0.0863,
       "step": 830
     },
     {
       "epoch": 2.25,
       "learning_rate": 1.3974231912784936e-05,
-      "loss": 0.0818,
+      "loss": 0.1457,
       "step": 840
     },
     {
       "epoch": 2.27,
       "learning_rate": 1.3478691774033697e-05,
-      "loss": 0.0225,
+      "loss": 0.132,
       "step": 850
     },
     {
       "epoch": 2.3,
       "learning_rate": 1.298315163528246e-05,
-      "loss": 0.0786,
+      "loss": 0.1432,
       "step": 860
     },
     {
       "epoch": 2.33,
       "learning_rate": 1.2487611496531219e-05,
-      "loss": 0.0494,
+      "loss": 0.1289,
       "step": 870
     },
     {
       "epoch": 2.35,
       "learning_rate": 1.1992071357779982e-05,
-      "loss": 0.056,
+      "loss": 0.1004,
       "step": 880
     },
     {
       "epoch": 2.38,
       "learning_rate": 1.1496531219028741e-05,
-      "loss": 0.0081,
+      "loss": 0.0939,
       "step": 890
     },
     {
       "epoch": 2.41,
       "learning_rate": 1.1000991080277504e-05,
-      "loss": 0.053,
+      "loss": 0.088,
       "step": 900
     },
     {
       "epoch": 2.43,
       "learning_rate": 1.0505450941526264e-05,
-      "loss": 0.0412,
+      "loss": 0.083,
       "step": 910
     },
     {
       "epoch": 2.46,
       "learning_rate": 1.0009910802775026e-05,
-      "loss": 0.068,
+      "loss": 0.0839,
       "step": 920
     },
     {
       "epoch": 2.49,
       "learning_rate": 9.514370664023786e-06,
-      "loss": 0.0263,
+      "loss": 0.1182,
       "step": 930
     },
     {
       "epoch": 2.51,
       "learning_rate": 9.018830525272549e-06,
-      "loss": 0.0143,
+      "loss": 0.0785,
       "step": 940
     },
     {
       "epoch": 2.54,
       "learning_rate": 8.523290386521308e-06,
-      "loss": 0.0736,
+      "loss": 0.0703,
       "step": 950
     },
     {
       "epoch": 2.57,
       "learning_rate": 8.02775024777007e-06,
-      "loss": 0.0758,
+      "loss": 0.0554,
       "step": 960
     },
     {
       "epoch": 2.59,
       "learning_rate": 7.532210109018831e-06,
-      "loss": 0.0179,
+      "loss": 0.0977,
       "step": 970
     },
     {
       "epoch": 2.62,
       "learning_rate": 7.036669970267593e-06,
-      "loss": 0.0445,
+      "loss": 0.101,
       "step": 980
     },
     {
       "epoch": 2.65,
       "learning_rate": 6.541129831516353e-06,
-      "loss": 0.0311,
+      "loss": 0.0778,
       "step": 990
     },
     {
       "epoch": 2.67,
       "learning_rate": 6.045589692765114e-06,
-      "loss": 0.0425,
+      "loss": 0.1057,
       "step": 1000
     },
     {
       "epoch": 2.7,
       "learning_rate": 5.5500495540138754e-06,
-      "loss": 0.0294,
+      "loss": 0.0531,
       "step": 1010
     },
     {
       "epoch": 2.73,
       "learning_rate": 5.0545094152626366e-06,
-      "loss": 0.0408,
+      "loss": 0.0602,
       "step": 1020
     },
     {
       "epoch": 2.75,
       "learning_rate": 4.558969276511398e-06,
-      "loss": 0.0337,
+      "loss": 0.0801,
       "step": 1030
     },
     {
       "epoch": 2.78,
       "learning_rate": 4.063429137760159e-06,
-      "loss": 0.0358,
+      "loss": 0.0557,
       "step": 1040
     },
     {
       "epoch": 2.81,
       "learning_rate": 3.56788899900892e-06,
-      "loss": 0.0556,
+      "loss": 0.0741,
       "step": 1050
     },
     {
       "epoch": 2.83,
       "learning_rate": 3.072348860257681e-06,
-      "loss": 0.0275,
+      "loss": 0.0799,
       "step": 1060
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.576808721506442e-06,
-      "loss": 0.0237,
+      "loss": 0.0545,
       "step": 1070
     },
     {
       "epoch": 2.89,
       "learning_rate": 2.081268582755203e-06,
-      "loss": 0.0547,
+      "loss": 0.0553,
       "step": 1080
     },
     {
       "epoch": 2.91,
       "learning_rate": 1.5857284440039643e-06,
-      "loss": 0.0195,
+      "loss": 0.0841,
       "step": 1090
     },
     {
       "epoch": 2.94,
       "learning_rate": 1.0901883052527254e-06,
-      "loss": 0.0119,
+      "loss": 0.0917,
       "step": 1100
     },
     {
       "epoch": 2.97,
       "learning_rate": 5.946481665014866e-07,
-      "loss": 0.0161,
+      "loss": 0.0778,
       "step": 1110
     },
     {
       "epoch": 2.99,
       "learning_rate": 9.910802775024777e-08,
-      "loss": 0.0489,
+      "loss": 0.0997,
       "step": 1120
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.9953208556149733,
-      "eval_loss": 0.016200048848986626,
-      "eval_runtime": 59.147,
-      "eval_samples_per_second": 50.586,
-      "eval_steps_per_second": 6.323,
+      "eval_accuracy": 0.983957219251337,
+      "eval_loss": 0.04800822585821152,
+      "eval_runtime": 53.1175,
+      "eval_samples_per_second": 56.328,
+      "eval_steps_per_second": 7.041,
       "step": 1122
     },
     {
       "epoch": 3.0,
       "step": 1122,
       "total_flos": 8.923548605812163e+17,
-      "train_loss": 0.05896045783503104,
-      "train_runtime": 1057.571,
-      "train_samples_per_second": 33.947,
-      "train_steps_per_second": 1.061
+      "train_loss": 0.16757579408121193,
+      "train_runtime": 1092.7636,
+      "train_samples_per_second": 32.853,
+      "train_steps_per_second": 1.027
     }
   ],
   "logging_steps": 10,