End of training

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 2.96,
-    "eval_accuracy": 0.8710801393728222,
-    "eval_loss": 0.3399865925312042,
-    "eval_runtime": 4.1257,
-    "eval_samples_per_second": 69.563,
-    "eval_steps_per_second": 2.181,
+    "eval_accuracy": 0.8780487804878049,
+    "eval_loss": 0.28312796354293823,
+    "eval_runtime": 4.3945,
+    "eval_samples_per_second": 65.308,
+    "eval_steps_per_second": 2.048,
     "total_flos": 1.9045723068223488e+17,
-    "train_loss": 0.657797618707021,
-    "train_runtime": 145.8955,
-    "train_samples_per_second": 53.113,
-    "train_steps_per_second": 0.411
+    "train_loss": 0.6072771787643433,
+    "train_runtime": 158.0756,
+    "train_samples_per_second": 49.021,
+    "train_steps_per_second": 0.38
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.96,
-    "eval_accuracy": 0.8710801393728222,
-    "eval_loss": 0.3399865925312042,
-    "eval_runtime": 4.1257,
-    "eval_samples_per_second": 69.563,
-    "eval_steps_per_second": 2.181
+    "eval_accuracy": 0.8780487804878049,
+    "eval_loss": 0.28312796354293823,
+    "eval_runtime": 4.3945,
+    "eval_samples_per_second": 65.308,
+    "eval_steps_per_second": 2.048
 }

runs/Apr08_12-38-05_90600695b4f6/events.out.tfevents.1712580054.90600695b4f6.424.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e14f3394fbd7c7b40c82d174051a640760db2c4d6165a79685367a2098e96da
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.96,
     "total_flos": 1.9045723068223488e+17,
-    "train_loss": 0.657797618707021,
-    "train_runtime": 145.8955,
-    "train_samples_per_second": 53.113,
-    "train_steps_per_second": 0.411
+    "train_loss": 0.6072771787643433,
+    "train_runtime": 158.0756,
+    "train_samples_per_second": 49.021,
+    "train_steps_per_second": 0.38
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8710801393728222,
+  "best_metric": 0.8780487804878049,
   "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-60",
   "epoch": 2.962962962962963,
   "eval_steps": 500,
@@ -10,81 +10,81 @@
   "log_history": [
     {
       "epoch": 0.49,
-      "grad_norm": 9.358732223510742,
+      "grad_norm": 7.887508392333984,
       "learning_rate": 4.62962962962963e-05,
-      "loss": 1.259,
+      "loss": 1.1976,
       "step": 10
     },
     {
       "epoch": 0.99,
-      "grad_norm": 11.161949157714844,
+      "grad_norm": 9.747188568115234,
       "learning_rate": 3.7037037037037037e-05,
-      "loss": 0.8451,
+      "loss": 0.7533,
       "step": 20
     },
     {
       "epoch": 0.99,
-      "eval_accuracy": 0.7874564459930313,
-      "eval_loss": 0.5740640163421631,
-      "eval_runtime": 4.4336,
-      "eval_samples_per_second": 64.733,
-      "eval_steps_per_second": 2.03,
+      "eval_accuracy": 0.7770034843205574,
+      "eval_loss": 0.5473685264587402,
+      "eval_runtime": 4.0122,
+      "eval_samples_per_second": 71.531,
+      "eval_steps_per_second": 2.243,
       "step": 20
     },
     {
       "epoch": 1.48,
-      "grad_norm": 13.122177124023438,
+      "grad_norm": 18.254377365112305,
       "learning_rate": 2.777777777777778e-05,
-      "loss": 0.581,
+      "loss": 0.5298,
       "step": 30
     },
     {
       "epoch": 1.98,
-      "grad_norm": 10.2821044921875,
+      "grad_norm": 10.268461227416992,
       "learning_rate": 1.8518518518518518e-05,
-      "loss": 0.4621,
+      "loss": 0.4366,
       "step": 40
     },
     {
       "epoch": 1.98,
-      "eval_accuracy": 0.8048780487804879,
-      "eval_loss": 0.45788925886154175,
-      "eval_runtime": 4.1854,
-      "eval_samples_per_second": 68.572,
-      "eval_steps_per_second": 2.15,
+      "eval_accuracy": 0.8606271777003485,
+      "eval_loss": 0.3385283052921295,
+      "eval_runtime": 3.9279,
+      "eval_samples_per_second": 73.066,
+      "eval_steps_per_second": 2.291,
       "step": 40
     },
     {
       "epoch": 2.47,
-      "grad_norm": 12.540511131286621,
+      "grad_norm": 11.050724983215332,
       "learning_rate": 9.259259259259259e-06,
-      "loss": 0.4259,
+      "loss": 0.3945,
       "step": 50
     },
     {
       "epoch": 2.96,
-      "grad_norm": 6.045067310333252,
+      "grad_norm": 5.141947269439697,
       "learning_rate": 0.0,
-      "loss": 0.3736,
+      "loss": 0.3318,
       "step": 60
     },
     {
       "epoch": 2.96,
-      "eval_accuracy": 0.8710801393728222,
-      "eval_loss": 0.3399865925312042,
-      "eval_runtime": 4.397,
-      "eval_samples_per_second": 65.272,
-      "eval_steps_per_second": 2.047,
+      "eval_accuracy": 0.8780487804878049,
+      "eval_loss": 0.28312796354293823,
+      "eval_runtime": 5.5586,
+      "eval_samples_per_second": 51.632,
+      "eval_steps_per_second": 1.619,
       "step": 60
     },
     {
       "epoch": 2.96,
       "step": 60,
       "total_flos": 1.9045723068223488e+17,
-      "train_loss": 0.657797618707021,
-      "train_runtime": 145.8955,
-      "train_samples_per_second": 53.113,
-      "train_steps_per_second": 0.411
+      "train_loss": 0.6072771787643433,
+      "train_runtime": 158.0756,
+      "train_samples_per_second": 49.021,
+      "train_steps_per_second": 0.38
     }
   ],
   "logging_steps": 10,