Training in progress, epoch 1

all_results.json

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 75.188,
     "eval_steps_per_second": 2.685,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.5572980443636576,
-    "train_runtime": 82.6981,
-    "train_samples_per_second": 32.322,
-    "train_steps_per_second": 0.254
+    "train_loss": 0.5421512808118548,
+    "train_runtime": 83.653,
+    "train_samples_per_second": 31.953,
+    "train_steps_per_second": 0.251
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ce3638422de66893b5ddbee0e9769addc70f696fc1a8ea87158feb57ccc6421
+oid sha256:05d6c994c95c13060ef164c0676730715155caaf35810a1b58a56e7729768970
 size 110394865

runs/Jul24_17-23-16_79617dc78cd9/events.out.tfevents.1690220620.79617dc78cd9.248.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f32390d2f73c11b445522147b09c2e881d0f3ab09deea140cf2fd7edead7f90d
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.5572980443636576,
-    "train_runtime": 82.6981,
-    "train_samples_per_second": 32.322,
-    "train_steps_per_second": 0.254
+    "train_loss": 0.5421512808118548,
+    "train_runtime": 83.653,
+    "train_samples_per_second": 31.953,
+    "train_steps_per_second": 0.251
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.8125,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-14",
+  "best_metric": 0.7767857142857143,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-7",
   "epoch": 3.0,
   "global_step": 21,
   "is_hyper_param_search": false,
@@ -9,51 +9,51 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7589285714285714,
-      "eval_loss": 0.5504956841468811,
-      "eval_runtime": 0.7654,
-      "eval_samples_per_second": 146.327,
-      "eval_steps_per_second": 5.226,
+      "eval_accuracy": 0.7767857142857143,
+      "eval_loss": 0.5114142298698425,
+      "eval_runtime": 0.7727,
+      "eval_samples_per_second": 144.952,
+      "eval_steps_per_second": 5.177,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.5762,
+      "loss": 0.5535,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8125,
-      "eval_loss": 0.5154673457145691,
-      "eval_runtime": 0.7892,
-      "eval_samples_per_second": 141.913,
-      "eval_steps_per_second": 5.068,
+      "eval_accuracy": 0.7589285714285714,
+      "eval_loss": 0.49566155672073364,
+      "eval_runtime": 0.7693,
+      "eval_samples_per_second": 145.578,
+      "eval_steps_per_second": 5.199,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.5422,
+      "loss": 0.5327,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7946428571428571,
-      "eval_loss": 0.5146691203117371,
-      "eval_runtime": 0.8083,
-      "eval_samples_per_second": 138.559,
-      "eval_steps_per_second": 4.949,
+      "eval_accuracy": 0.7678571428571429,
+      "eval_loss": 0.4878653883934021,
+      "eval_runtime": 0.8404,
+      "eval_samples_per_second": 133.268,
+      "eval_steps_per_second": 4.76,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.5572980443636576,
-      "train_runtime": 82.6981,
-      "train_samples_per_second": 32.322,
-      "train_steps_per_second": 0.254
+      "train_loss": 0.5421512808118548,
+      "train_runtime": 83.653,
+      "train_samples_per_second": 31.953,
+      "train_steps_per_second": 0.251
     }
   ],
   "max_steps": 21,