Training in progress, epoch 0

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 2.67,
-    "eval_accuracy": 0.9354838709677419,
-    "eval_loss": 0.4233046770095825,
-    "eval_runtime": 7.2507,
-    "eval_samples_per_second": 4.275,
-    "eval_steps_per_second": 0.138,
-    "train_loss": 0.6217495600382487,
-    "train_runtime": 537.472,
-    "train_samples_per_second": 1.546,
-    "train_steps_per_second": 0.011
+    "epoch": 2.4,
+    "eval_accuracy": 0.7647058823529411,
+    "eval_loss": 0.6287894248962402,
+    "eval_runtime": 4.763,
+    "eval_samples_per_second": 7.138,
+    "eval_steps_per_second": 0.42,
+    "train_loss": 0.5813180605570475,
+    "train_runtime": 509.1656,
+    "train_samples_per_second": 1.768,
+    "train_steps_per_second": 0.012
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.67,
-    "eval_accuracy": 0.9354838709677419,
-    "eval_loss": 0.4233046770095825,
-    "eval_runtime": 7.2507,
-    "eval_samples_per_second": 4.275,
-    "eval_steps_per_second": 0.138
+    "epoch": 2.4,
+    "eval_accuracy": 0.7647058823529411,
+    "eval_loss": 0.6287894248962402,
+    "eval_runtime": 4.763,
+    "eval_samples_per_second": 7.138,
+    "eval_steps_per_second": 0.42
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d571184e95699417def29f618c976798ca294ab3e6169b7990ef740c94d9b66
+oid sha256:dbb4aef35d30f2fb7cb64543119c9521ca0c8b90c7957716ef7bd2896a1d1c77
 size 195966545

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 2.67,
-    "train_loss": 0.6217495600382487,
-    "train_runtime": 537.472,
-    "train_samples_per_second": 1.546,
-    "train_steps_per_second": 0.011
+    "epoch": 2.4,
+    "train_loss": 0.5813180605570475,
+    "train_runtime": 509.1656,
+    "train_samples_per_second": 1.768,
+    "train_steps_per_second": 0.012
 }

trainer_state.json

@@ -1,52 +1,52 @@
 {
-  "best_metric": 0.9354838709677419,
-  "best_model_checkpoint": "swin-small-patch4-window7-224-finetuned-eurosat\\checkpoint-6",
-  "epoch": 2.6666666666666665,
+  "best_metric": 0.7647058823529411,
+  "best_model_checkpoint": "swin-small-patch4-window7-224-finetuned-eurosat\\checkpoint-2",
+  "epoch": 2.4,
   "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.89,
-      "eval_accuracy": 0.8387096774193549,
-      "eval_loss": 0.568583071231842,
-      "eval_runtime": 5.9962,
-      "eval_samples_per_second": 5.17,
-      "eval_steps_per_second": 0.167,
+      "epoch": 0.8,
+      "eval_accuracy": 0.7647058823529411,
+      "eval_loss": 0.6287894248962402,
+      "eval_runtime": 7.0042,
+      "eval_samples_per_second": 4.854,
+      "eval_steps_per_second": 0.286,
       "step": 2
     },
     {
-      "epoch": 1.78,
-      "eval_accuracy": 0.9032258064516129,
-      "eval_loss": 0.46046480536460876,
-      "eval_runtime": 7.0675,
-      "eval_samples_per_second": 4.386,
-      "eval_steps_per_second": 0.141,
-      "step": 4
+      "epoch": 2.0,
+      "eval_accuracy": 0.7647058823529411,
+      "eval_loss": 0.4928305149078369,
+      "eval_runtime": 10.0214,
+      "eval_samples_per_second": 3.393,
+      "eval_steps_per_second": 0.2,
+      "step": 5
     },
     {
-      "epoch": 2.67,
-      "eval_accuracy": 0.9354838709677419,
-      "eval_loss": 0.4233046770095825,
-      "eval_runtime": 8.5993,
-      "eval_samples_per_second": 3.605,
-      "eval_steps_per_second": 0.116,
+      "epoch": 2.4,
+      "eval_accuracy": 0.7352941176470589,
+      "eval_loss": 0.4771716296672821,
+      "eval_runtime": 6.8122,
+      "eval_samples_per_second": 4.991,
+      "eval_steps_per_second": 0.294,
       "step": 6
     },
     {
-      "epoch": 2.67,
+      "epoch": 2.4,
       "step": 6,
-      "total_flos": 3.290578972847309e+16,
-      "train_loss": 0.6217495600382487,
-      "train_runtime": 537.472,
-      "train_samples_per_second": 1.546,
-      "train_steps_per_second": 0.011
+      "total_flos": 3.2111816249769984e+16,
+      "train_loss": 0.5813180605570475,
+      "train_runtime": 509.1656,
+      "train_samples_per_second": 1.768,
+      "train_steps_per_second": 0.012
     }
   ],
   "max_steps": 6,
   "num_train_epochs": 3,
-  "total_flos": 3.290578972847309e+16,
+  "total_flos": 3.2111816249769984e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee35d9247f42f044e54a751d98db02724811fdac2164d9e80eb42b81f0daff64
+oid sha256:0f7ea70f4751923a4a82084d22753753f18b00638f9d1e86ccdc937ca0206990
 size 4027