Training in progress, epoch 1

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 2.9745162019373875e+17,
-    "train_loss": 0.24205425238226824,
-    "train_runtime": 396.8396,
-    "train_samples_per_second": 30.156,
-    "train_steps_per_second": 0.942
+    "train_loss": 0.14610644119149224,
+    "train_runtime": 378.7606,
+    "train_samples_per_second": 31.595,
+    "train_steps_per_second": 0.987
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:028941190e7ba5cd87f9c8ffc02db2fad17e5639943eb9e3e4d947073ef1093b
+oid sha256:37f4fedba0c5a8e5394ee600c12157837b081b63c4a57597ac489088fbe39dbe
 size 110342832

runs/Dec08_00-28-28_fdad06de1630/events.out.tfevents.1701996366.fdad06de1630.603.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5be6f7a32ff8fabb7fad5eb2e2cf36daeeea07ad4154905bb83dc5b54d73338
+size 11302

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 2.9745162019373875e+17,
-    "train_loss": 0.24205425238226824,
-    "train_runtime": 396.8396,
-    "train_samples_per_second": 30.156,
-    "train_steps_per_second": 0.942
+    "train_loss": 0.14610644119149224,
+    "train_runtime": 378.7606,
+    "train_samples_per_second": 31.595,
+    "train_steps_per_second": 0.987
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.9669117647058824,
+  "best_metric": 0.9709224598930482,
   "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": 0.6739,
+      "loss": 0.1577,
       "step": 10
     },
     {
       "epoch": 0.05,
       "learning_rate": 2.6315789473684212e-05,
-      "loss": 0.5529,
+      "loss": 0.1531,
       "step": 20
     },
     {
       "epoch": 0.08,
       "learning_rate": 3.9473684210526316e-05,
-      "loss": 0.414,
+      "loss": 0.17,
       "step": 30
     },
     {
       "epoch": 0.11,
       "learning_rate": 4.9702380952380955e-05,
-      "loss": 0.3019,
+      "loss": 0.1579,
       "step": 40
     },
     {
       "epoch": 0.13,
       "learning_rate": 4.8214285714285716e-05,
-      "loss": 0.3307,
+      "loss": 0.1519,
       "step": 50
     },
     {
       "epoch": 0.16,
       "learning_rate": 4.672619047619048e-05,
-      "loss": 0.3032,
+      "loss": 0.1473,
       "step": 60
     },
     {
       "epoch": 0.19,
       "learning_rate": 4.523809523809524e-05,
-      "loss": 0.3082,
+      "loss": 0.1744,
       "step": 70
     },
     {
       "epoch": 0.21,
       "learning_rate": 4.375e-05,
-      "loss": 0.3066,
+      "loss": 0.2375,
       "step": 80
     },
     {
       "epoch": 0.24,
       "learning_rate": 4.226190476190476e-05,
-      "loss": 0.2905,
+      "loss": 0.2237,
       "step": 90
     },
     {
       "epoch": 0.27,
       "learning_rate": 4.077380952380952e-05,
-      "loss": 0.2479,
+      "loss": 0.1836,
       "step": 100
     },
     {
       "epoch": 0.29,
       "learning_rate": 3.928571428571429e-05,
-      "loss": 0.2469,
+      "loss": 0.1407,
       "step": 110
     },
     {
       "epoch": 0.32,
       "learning_rate": 3.779761904761905e-05,
-      "loss": 0.273,
+      "loss": 0.2213,
       "step": 120
     },
     {
       "epoch": 0.35,
       "learning_rate": 3.630952380952381e-05,
-      "loss": 0.3014,
+      "loss": 0.179,
       "step": 130
     },
     {
       "epoch": 0.37,
       "learning_rate": 3.4821428571428574e-05,
-      "loss": 0.211,
+      "loss": 0.1025,
       "step": 140
     },
     {
       "epoch": 0.4,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.1831,
+      "loss": 0.1499,
       "step": 150
     },
     {
       "epoch": 0.43,
       "learning_rate": 3.1845238095238096e-05,
-      "loss": 0.2286,
+      "loss": 0.1136,
       "step": 160
     },
     {
       "epoch": 0.45,
       "learning_rate": 3.0357142857142857e-05,
-      "loss": 0.231,
+      "loss": 0.153,
       "step": 170
     },
     {
       "epoch": 0.48,
       "learning_rate": 2.886904761904762e-05,
-      "loss": 0.2197,
+      "loss": 0.1628,
       "step": 180
     },
     {
       "epoch": 0.51,
       "learning_rate": 2.7380952380952383e-05,
-      "loss": 0.2137,
+      "loss": 0.1349,
       "step": 190
     },
     {
       "epoch": 0.53,
       "learning_rate": 2.5892857142857148e-05,
-      "loss": 0.1982,
+      "loss": 0.1389,
       "step": 200
     },
     {
       "epoch": 0.56,
       "learning_rate": 2.4404761904761906e-05,
-      "loss": 0.2188,
+      "loss": 0.1291,
       "step": 210
     },
     {
       "epoch": 0.59,
       "learning_rate": 2.2916666666666667e-05,
-      "loss": 0.1693,
+      "loss": 0.1247,
       "step": 220
     },
     {
       "epoch": 0.61,
       "learning_rate": 2.1428571428571428e-05,
-      "loss": 0.2192,
+      "loss": 0.1108,
       "step": 230
     },
     {
       "epoch": 0.64,
       "learning_rate": 1.9940476190476193e-05,
-      "loss": 0.2273,
+      "loss": 0.1494,
       "step": 240
     },
     {
       "epoch": 0.67,
       "learning_rate": 1.8452380952380954e-05,
-      "loss": 0.1556,
+      "loss": 0.134,
       "step": 250
     },
     {
       "epoch": 0.7,
       "learning_rate": 1.6964285714285715e-05,
-      "loss": 0.1847,
+      "loss": 0.1322,
       "step": 260
     },
     {
       "epoch": 0.72,
       "learning_rate": 1.5476190476190476e-05,
-      "loss": 0.1663,
+      "loss": 0.0959,
       "step": 270
     },
     {
       "epoch": 0.75,
       "learning_rate": 1.398809523809524e-05,
-      "loss": 0.1862,
+      "loss": 0.1577,
       "step": 280
     },
     {
       "epoch": 0.78,
       "learning_rate": 1.25e-05,
-      "loss": 0.2096,
+      "loss": 0.1316,
       "step": 290
     },
     {
       "epoch": 0.8,
       "learning_rate": 1.1011904761904762e-05,
-      "loss": 0.1796,
+      "loss": 0.1051,
       "step": 300
     },
     {
       "epoch": 0.83,
       "learning_rate": 9.523809523809523e-06,
-      "loss": 0.1547,
+      "loss": 0.1481,
       "step": 310
     },
     {
       "epoch": 0.86,
       "learning_rate": 8.035714285714286e-06,
-      "loss": 0.1206,
+      "loss": 0.1244,
       "step": 320
     },
     {
       "epoch": 0.88,
       "learning_rate": 6.547619047619048e-06,
-      "loss": 0.1614,
+      "loss": 0.1447,
       "step": 330
     },
     {
       "epoch": 0.91,
       "learning_rate": 5.05952380952381e-06,
-      "loss": 0.2026,
+      "loss": 0.1068,
       "step": 340
     },
     {
       "epoch": 0.94,
       "learning_rate": 3.5714285714285714e-06,
-      "loss": 0.1345,
+      "loss": 0.1264,
       "step": 350
     },
     {
       "epoch": 0.96,
       "learning_rate": 2.0833333333333334e-06,
-      "loss": 0.147,
+      "loss": 0.1303,
       "step": 360
     },
     {
       "epoch": 0.99,
       "learning_rate": 5.952380952380952e-07,
-      "loss": 0.1483,
+      "loss": 0.139,
       "step": 370
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.9669117647058824,
+      "eval_accuracy": 0.9709224598930482,
       "eval_confusion_matrix": [
         [
-          1471,
-          41
+          1490,
+          22
         ],
         [
-          58,
-          1422
+          65,
+          1415
         ]
       ],
-      "eval_loss": 0.08614899963140488,
-      "eval_precision": 0.9669680640397452,
-      "eval_recall": 0.9669117647058824,
-      "eval_runtime": 64.8752,
-      "eval_samples_per_second": 46.119,
-      "eval_steps_per_second": 5.765,
+      "eval_loss": 0.07573658227920532,
+      "eval_precision": 0.9713031790497177,
+      "eval_recall": 0.9709224598930482,
+      "eval_runtime": 65.4358,
+      "eval_samples_per_second": 45.724,
+      "eval_steps_per_second": 5.716,
       "step": 374
     },
     {
       "epoch": 1.0,
       "step": 374,
       "total_flos": 2.9745162019373875e+17,
-      "train_loss": 0.24205425238226824,
-      "train_runtime": 396.8396,
-      "train_samples_per_second": 30.156,
-      "train_steps_per_second": 0.942
+      "train_loss": 0.14610644119149224,
+      "train_runtime": 378.7606,
+      "train_samples_per_second": 31.595,
+      "train_steps_per_second": 0.987
     }
   ],
   "logging_steps": 10,