Training in progress, epoch 1

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 2.9745162019373875e+17,
-    "train_loss": 0.11409819707832235,
-    "train_runtime": 378.4423,
-    "train_samples_per_second": 31.622,
-    "train_steps_per_second": 0.988
+    "train_loss": 0.10583112962583807,
+    "train_runtime": 376.6309,
+    "train_samples_per_second": 31.774,
+    "train_steps_per_second": 0.993
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfaf57e5bbcf3068ceca549268163dc1d733c46ab4835bc56b25218c0dd7c191
+oid sha256:8517df5400c55e76fd3d5850ed01ed01099a54dae530e965d2b39edca8fc0172
 size 110342832

runs/Dec08_00-28-28_fdad06de1630/events.out.tfevents.1701997135.fdad06de1630.603.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba587f22baefc44109e390c88eef78375d08c9131ae439cddbde73fefc87bdde
+size 11302

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 2.9745162019373875e+17,
-    "train_loss": 0.11409819707832235,
-    "train_runtime": 378.4423,
-    "train_samples_per_second": 31.622,
-    "train_steps_per_second": 0.988
+    "train_loss": 0.10583112962583807,
+    "train_runtime": 376.6309,
+    "train_samples_per_second": 31.774,
+    "train_steps_per_second": 0.993
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.972927807486631,
+  "best_metric": 0.9756016042780749,
   "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-374",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -11,254 +11,254 @@
     {
       "epoch": 0.03,
       "learning_rate": 1.3157894736842106e-05,
-      "loss": 0.1001,
+      "loss": 0.0949,
       "step": 10
     },
     {
       "epoch": 0.05,
       "learning_rate": 2.6315789473684212e-05,
-      "loss": 0.0982,
+      "loss": 0.0881,
       "step": 20
     },
     {
       "epoch": 0.08,
       "learning_rate": 3.9473684210526316e-05,
-      "loss": 0.1169,
+      "loss": 0.1858,
       "step": 30
     },
     {
       "epoch": 0.11,
       "learning_rate": 4.9702380952380955e-05,
-      "loss": 0.0633,
+      "loss": 0.1089,
       "step": 40
     },
     {
       "epoch": 0.13,
       "learning_rate": 4.8214285714285716e-05,
-      "loss": 0.1774,
+      "loss": 0.145,
       "step": 50
     },
     {
       "epoch": 0.16,
       "learning_rate": 4.672619047619048e-05,
-      "loss": 0.2385,
+      "loss": 0.1805,
       "step": 60
     },
     {
       "epoch": 0.19,
       "learning_rate": 4.523809523809524e-05,
-      "loss": 0.145,
+      "loss": 0.1132,
       "step": 70
     },
     {
       "epoch": 0.21,
       "learning_rate": 4.375e-05,
-      "loss": 0.1312,
+      "loss": 0.0904,
       "step": 80
     },
     {
       "epoch": 0.24,
       "learning_rate": 4.226190476190476e-05,
-      "loss": 0.1137,
+      "loss": 0.1453,
       "step": 90
     },
     {
       "epoch": 0.27,
       "learning_rate": 4.077380952380952e-05,
-      "loss": 0.1199,
+      "loss": 0.1422,
       "step": 100
     },
     {
       "epoch": 0.29,
       "learning_rate": 3.928571428571429e-05,
-      "loss": 0.1165,
+      "loss": 0.0741,
       "step": 110
     },
     {
       "epoch": 0.32,
       "learning_rate": 3.779761904761905e-05,
-      "loss": 0.131,
+      "loss": 0.1438,
       "step": 120
     },
     {
       "epoch": 0.35,
       "learning_rate": 3.630952380952381e-05,
-      "loss": 0.1121,
+      "loss": 0.1043,
       "step": 130
     },
     {
       "epoch": 0.37,
       "learning_rate": 3.4821428571428574e-05,
-      "loss": 0.1271,
+      "loss": 0.1097,
       "step": 140
     },
     {
       "epoch": 0.4,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.1162,
+      "loss": 0.11,
       "step": 150
     },
     {
       "epoch": 0.43,
       "learning_rate": 3.1845238095238096e-05,
-      "loss": 0.2048,
+      "loss": 0.134,
       "step": 160
     },
     {
       "epoch": 0.45,
       "learning_rate": 3.0357142857142857e-05,
-      "loss": 0.1286,
+      "loss": 0.1498,
       "step": 170
     },
     {
       "epoch": 0.48,
       "learning_rate": 2.886904761904762e-05,
-      "loss": 0.0717,
+      "loss": 0.1092,
       "step": 180
     },
     {
       "epoch": 0.51,
       "learning_rate": 2.7380952380952383e-05,
-      "loss": 0.119,
+      "loss": 0.0992,
       "step": 190
     },
     {
       "epoch": 0.53,
       "learning_rate": 2.5892857142857148e-05,
-      "loss": 0.172,
+      "loss": 0.1108,
       "step": 200
     },
     {
       "epoch": 0.56,
       "learning_rate": 2.4404761904761906e-05,
-      "loss": 0.0658,
+      "loss": 0.0904,
       "step": 210
     },
     {
       "epoch": 0.59,
       "learning_rate": 2.2916666666666667e-05,
-      "loss": 0.1289,
+      "loss": 0.0838,
       "step": 220
     },
     {
       "epoch": 0.61,
       "learning_rate": 2.1428571428571428e-05,
-      "loss": 0.0854,
+      "loss": 0.0689,
       "step": 230
     },
     {
       "epoch": 0.64,
       "learning_rate": 1.9940476190476193e-05,
-      "loss": 0.0916,
+      "loss": 0.0948,
       "step": 240
     },
     {
       "epoch": 0.67,
       "learning_rate": 1.8452380952380954e-05,
-      "loss": 0.1156,
+      "loss": 0.1015,
       "step": 250
     },
     {
       "epoch": 0.7,
       "learning_rate": 1.6964285714285715e-05,
-      "loss": 0.1183,
+      "loss": 0.1242,
       "step": 260
     },
     {
       "epoch": 0.72,
       "learning_rate": 1.5476190476190476e-05,
-      "loss": 0.0888,
+      "loss": 0.0954,
       "step": 270
     },
     {
       "epoch": 0.75,
       "learning_rate": 1.398809523809524e-05,
-      "loss": 0.0805,
+      "loss": 0.093,
       "step": 280
     },
     {
       "epoch": 0.78,
       "learning_rate": 1.25e-05,
-      "loss": 0.1425,
+      "loss": 0.1057,
       "step": 290
     },
     {
       "epoch": 0.8,
       "learning_rate": 1.1011904761904762e-05,
-      "loss": 0.0935,
+      "loss": 0.109,
       "step": 300
     },
     {
       "epoch": 0.83,
       "learning_rate": 9.523809523809523e-06,
-      "loss": 0.0671,
+      "loss": 0.039,
       "step": 310
     },
     {
       "epoch": 0.86,
       "learning_rate": 8.035714285714286e-06,
-      "loss": 0.0833,
+      "loss": 0.1241,
       "step": 320
     },
     {
       "epoch": 0.88,
       "learning_rate": 6.547619047619048e-06,
-      "loss": 0.0716,
+      "loss": 0.1037,
       "step": 330
     },
     {
       "epoch": 0.91,
       "learning_rate": 5.05952380952381e-06,
-      "loss": 0.0732,
+      "loss": 0.071,
       "step": 340
     },
     {
       "epoch": 0.94,
       "learning_rate": 3.5714285714285714e-06,
-      "loss": 0.1044,
+      "loss": 0.0445,
       "step": 350
     },
     {
       "epoch": 0.96,
       "learning_rate": 2.0833333333333334e-06,
-      "loss": 0.114,
+      "loss": 0.0835,
       "step": 360
     },
     {
       "epoch": 0.99,
       "learning_rate": 5.952380952380952e-07,
-      "loss": 0.0978,
+      "loss": 0.0637,
       "step": 370
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.972927807486631,
+      "eval_accuracy": 0.9756016042780749,
       "eval_confusion_matrix": [
         [
-          1495,
-          17
+          1501,
+          11
         ],
         [
-          64,
-          1416
+          62,
+          1418
         ]
       ],
-      "eval_loss": 0.06770511716604233,
-      "eval_precision": 0.9733863203281101,
-      "eval_recall": 0.972927807486631,
-      "eval_runtime": 64.6261,
-      "eval_samples_per_second": 46.297,
-      "eval_steps_per_second": 5.787,
+      "eval_loss": 0.05807357281446457,
+      "eval_precision": 0.9761465409105035,
+      "eval_recall": 0.9756016042780749,
+      "eval_runtime": 65.979,
+      "eval_samples_per_second": 45.348,
+      "eval_steps_per_second": 5.668,
       "step": 374
     },
     {
       "epoch": 1.0,
       "step": 374,
       "total_flos": 2.9745162019373875e+17,
-      "train_loss": 0.11409819707832235,
-      "train_runtime": 378.4423,
-      "train_samples_per_second": 31.622,
-      "train_steps_per_second": 0.988
+      "train_loss": 0.10583112962583807,
+      "train_runtime": 376.6309,
+      "train_samples_per_second": 31.774,
+      "train_steps_per_second": 0.993
     }
   ],
   "logging_steps": 10,